[go: up one dir, main page]

CN118914732B - A method for detecting faults of power equipment in a power distribution system - Google Patents

A method for detecting faults of power equipment in a power distribution system Download PDF

Info

Publication number
CN118914732B
CN118914732B CN202411407883.8A CN202411407883A CN118914732B CN 118914732 B CN118914732 B CN 118914732B CN 202411407883 A CN202411407883 A CN 202411407883A CN 118914732 B CN118914732 B CN 118914732B
Authority
CN
China
Prior art keywords
power
area
electric quantity
degree
time period
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202411407883.8A
Other languages
Chinese (zh)
Other versions
CN118914732A (en
Inventor
谢宗辉
蔡培东
崔健
沈金龙
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangsu Shangrong Electric Technology Co ltd
Original Assignee
Jiangsu Shangrong Electric Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jiangsu Shangrong Electric Technology Co ltd filed Critical Jiangsu Shangrong Electric Technology Co ltd
Priority to CN202411407883.8A priority Critical patent/CN118914732B/en
Publication of CN118914732A publication Critical patent/CN118914732A/en
Application granted granted Critical
Publication of CN118914732B publication Critical patent/CN118914732B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • HELECTRICITY
    • H02GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02JCIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00Circuit arrangements for AC mains or AC distribution networks
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01RMEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/23Clustering techniques

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Power Engineering (AREA)
  • Supply And Distribution Of Alternating Current (AREA)

Abstract

The invention relates to the technical field of electric quantity testing, in particular to a fault detection method for power equipment of a power transformation and distribution system. The method comprises the steps of obtaining electric quantity data, obtaining normal descending degree according to the change condition of the electric quantity data in a descending time period of an electric quantity descending region and the distribution condition of abnormal electric quantity data and the overall change trend of the electric quantity data of the electric quantity descending region, screening a first suspected fault region, obtaining the descending degree of a user according to the user change of the first suspected fault region, screening a second suspected fault region, obtaining electric quantity regulation degree according to the electric quantity demand difference and the electric quantity distribution difference between the second suspected fault region and each other region, screening a fault region, and detecting faults of electric equipment of the fault region. According to the invention, the fault area is accurately obtained, so that the area with the power equipment fault is accurately determined, the fault detection efficiency of the power equipment is improved, and a large amount of manpower and material resources are saved.

Description

Power equipment fault detection method for power transformation and distribution system
Technical Field
The invention relates to the technical field of electric quantity testing, in particular to a fault detection method for power equipment of a power transformation and distribution system.
Background
In a power transformation and distribution system, power equipment is used for converting and distributing electric energy, and normal and stable operation of the power equipment is critical to the reliability and stability of power supply of the power transformation and distribution system. The most critical power equipment for power conversion and transmission in a power transformation and distribution system is called a power transformer. Therefore, the power transformer needs to be detected in time, faults of the power transformer are found in time and maintained, and stable and reliable operation of the power transformation and distribution system is ensured.
In the prior art, the electric quantity data of each area is directly analyzed by a server, and when the electric quantity data is reduced, the power transformer in the corresponding area is prompted to be suspected to be faulty, so that the power transformer in the corresponding area is timely subjected to fault detection and maintenance. However, in practical situations, the reasons for the decrease and change of the electric quantity data are many, for example, the situations of high energy consumption unit or active power outage maintenance of high energy consumption equipment, great use of self-contained power sources such as solar panels by users, reduction of electric quantity users in areas, electric quantity regulation and control among areas and the like all cause the decrease of the electric quantity data in the areas, so that the fault detection of the electric power equipment in different areas is inaccurate, and a great amount of manpower and material resources are wasted.
Disclosure of Invention
In order to solve the technical problem of inaccurate fault detection of power equipment in an area, the invention aims to provide a power equipment fault detection method of a power transformation and distribution system, and the adopted technical scheme is as follows:
The embodiment of the invention provides a power equipment fault detection method of a power transformation and distribution system, which comprises the following steps:
Acquiring electric quantity data of each area at each moment in the current time period;
Acquiring a descending time period of each electric quantity descending region at the current moment, and acquiring the normal descending degree of each electric quantity descending region according to the change condition of electric quantity data and the distribution condition of abnormal electric quantity data in the descending time period of each electric quantity descending region and the overall change trend of the electric quantity data of each electric quantity descending region in the current time period;
obtaining the user descending degree of each first suspected fault region according to the difference of the number of users between the descending time period and the current time period of other parts of the non-descending time period of each first suspected fault region;
acquiring the electric quantity regulation degree of each second suspected fault region according to the electric quantity demand difference and the electric quantity distribution difference between each second suspected fault region and each other region at the current moment;
and performing fault detection on the power equipment in the fault area.
Further, the method for obtaining the normal decline degree comprises the following steps:
For any electric quantity reduction region, fitting electric quantity data in the current time period of the electric quantity reduction region into a curve according to time sequence, and taking the curve as an electric quantity data curve of the electric quantity reduction region;
Decomposing the electric quantity data curve through an STL decomposition algorithm to obtain a trend curve and a season curve of the electric quantity reduction region;
acquiring the slope of a fitting straight line corresponding to the trend curve as the overall change value of the electric quantity reduction area;
taking a seasonal curve corresponding to the descending time period of the electric quantity descending region as a reference seasonal curve of the electric quantity descending region;
acquiring the seasonal decline degree of the electric quantity decline area according to the change condition of the reference seasonal curve;
Acquiring abnormal electric quantity data in a descending time period of the electric quantity descending region through a local outlier factor detection algorithm, and acquiring abnormal sporadic degree of the electric quantity descending region according to the distribution condition of the abnormal electric quantity data;
and obtaining the normal descending degree of the electric quantity descending region according to the integral change value, the seasonal descending degree and the abnormal sporadic degree of the electric quantity descending region, wherein the integral change value and the normal descending degree are in a negative correlation, and the seasonal descending degree and the abnormal sporadic degree are in a positive correlation with the normal descending degree.
Further, the method for acquiring the season decline degree comprises the following steps:
for any electric quantity reduction region, taking the accumulated result of the corresponding time periods of all reduction parts in the reference seasonal curve of the electric quantity reduction region as a first time period;
Taking the accumulated result of the corresponding time periods of all ascending parts in the reference seasonal curve of the electric quantity descending area as a second time period;
Acquiring the data descending rate of each descending part in the reference seasonal curve of the electric quantity descending area as the first rate of the corresponding descending part;
acquiring the data rising rate of each rising part in the reference seasonal curve of the electric quantity falling area as a second rate of the corresponding rising part;
And obtaining the seasonal decrease degree of the electric quantity decrease area according to the difference between the first time period and the second time period and the difference between the average value of the first rate and the average value of the second rate, wherein the difference between the first time period and the second time period and the difference between the average value of the first rate and the average value of the second rate are in positive correlation with the seasonal decrease degree.
Further, the method for obtaining the anomaly contingency degree comprises the following steps:
For any electric quantity reduction region, clustering abnormal electric quantity data in the reduction time period of the electric quantity reduction region by using a DBSCAN density clustering algorithm to obtain a cluster;
acquiring the quantity of abnormal electric quantity data in each cluster as a first quantity;
Taking the difference between the maximum first quantity and the mean value of the first quantity as a first characteristic difference;
Acquiring the quantity of all abnormal electric quantity data in the descending time period of the electric quantity descending area as a second quantity;
And acquiring the abnormal sporadic degree of the electric quantity reduction region according to the difference between the number of the clusters and the second number and the first characteristic difference, wherein the difference between the number of the clusters and the second number and the abnormal sporadic degree are positive correlation, and the first characteristic difference and the abnormal sporadic degree are negative correlation.
Further, the method for acquiring the first suspected fault area comprises the following steps:
and when the normal descending degree does not meet the preset normal descending degree range, the corresponding electric quantity descending region is a first suspected fault region.
Further, the method for acquiring the user descent degree comprises the following steps:
For any first suspected fault area, acquiring the number of users at each moment in a descending time period of the first suspected fault area as the first number of users;
Acquiring the number of users at each moment in the current time period of other parts of the non-descent time period of the first suspected fault region as a second number of users;
And obtaining the user descending degree of the first suspected fault area according to the difference between the average value of the second user number and the average value of the first user number, wherein the difference between the average value of the second user number and the average value of the first user number and the user descending degree are in positive correlation.
Further, the method for acquiring the second suspected fault area comprises the following steps:
And when the user descending degree does not meet the preset user descending degree range, the corresponding first suspected fault area is a second suspected fault area.
Further, the method for obtaining the electric quantity regulation degree comprises the following steps:
Acquiring electric quantity demand data and electric quantity distribution data of each area at the current moment;
For any second suspected fault area, acquiring the average value of the electric quantity demand data and the average value of the electric quantity distribution data of all other areas except the second suspected fault area, and sequentially taking the average value and the average value as reference electric quantity demand data and reference electric quantity distribution data;
Taking the difference between the reference electric quantity demand data and the electric quantity demand data of the second suspected fault area as a first difference;
Taking the difference between the reference electric quantity distribution data and the electric quantity distribution data of the second suspected fault area as a second difference;
And acquiring the electric quantity regulation degree of the second suspected fault area according to the first difference and the second difference, wherein the first difference and the second difference are in positive correlation with the electric quantity regulation degree.
Further, the fault region obtaining method comprises the following steps:
when the electric quantity regulation degree does not meet the preset electric quantity regulation degree range, the corresponding second suspected fault area is the fault area at the current moment.
Further, the method for acquiring the electric quantity reduction region and the reduction time period comprises the following steps:
taking a time period formed by the last preset number of continuous moments of each region in the current time period as a reference time period of each region;
For any region, when all electric quantity data in the reference time period of the region are smaller than a preset electric quantity data threshold value of the region, the region is an electric quantity reduction region at the current moment;
For any electric quantity reduction region, taking the moment corresponding to the electric quantity data which is more than or equal to the preset electric quantity data threshold value of the region and is closest to the current moment in the current time period of the electric quantity reduction region as the target moment;
the time period formed by the next time of the target time and the current time is taken as the falling time period of the electric quantity falling area.
The invention has the following beneficial effects:
In order to obtain the fault area, and then according to the change condition of electric quantity data and the distribution condition of abnormal electric quantity data in the descending time period of each electric quantity descending area and the overall change trend of the electric quantity data in the current time period of each electric quantity descending area, the normal descending degree of each electric quantity descending area is obtained, the possible degree of the electric quantity data of each electric quantity descending area which is normal at the current time is reflected, the normally descending electric quantity descending area at the current time is accurately removed, the suspected fault area is primarily identified, and then the first suspected fault area is screened out based on the normal descending degree, thereby being beneficial to accurately and efficiently identifying the fault area in the follow-up, and further according to the difference of the number of users between the descending time period of each first suspected fault area and the current time period of other parts of the non-descending time period, the normal descending degree of each first suspected fault area is accurately reflected, the possible degree of the electric quantity data of each electric quantity descending area which is normal at the current time is reflected, the suspected fault area is accurately removed, and the suspected fault area is further accurately identified based on the second suspected fault area which is more accurately obtained based on the difference between the second suspected fault area and the second fault area which is more accurately identified, the possibility that the electric quantity of each second suspected fault area is regulated and controlled is accurately reflected, the second suspected fault area with electric quantity data reduced due to electric quantity regulation factors at the current moment is accurately removed, the fault area at the current moment is accurately screened out based on the electric quantity regulation degree, further, fault detection is carried out on electric equipment in the fault area, faults of the electric equipment are accurately and efficiently detected, a large amount of manpower and material resources are saved, meanwhile, timely maintenance on the faults of the electric equipment is facilitated, and the reliability and stability of power supply of a power transformation and distribution system are ensured.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a fault detection method for power equipment of a power transformation and distribution system according to an embodiment of the present invention;
FIG. 2 is a flowchart of a method for obtaining a normal descent level according to an embodiment of the present invention;
FIG. 3 is a flowchart of a method for obtaining a season degradation level according to an embodiment of the present invention;
Fig. 4 is a block diagram of a fault detection system for power equipment of a power transformation and distribution system according to an embodiment of the present invention;
fig. 5 is a schematic diagram of a computer device according to an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description is given below of a power equipment fault detection method of a power transformation and distribution system according to the invention, which is specific implementation, structure, characteristics and effects thereof, with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The invention provides a specific scheme of a power equipment fault detection method of a power transformation and distribution system, which is specifically described below with reference to the accompanying drawings.
Example 1:
The embodiment has the specific scene that the power equipment which is most critical in electric energy conversion and transmission in the power transformation and distribution system belongs to a power transformer. The safe operation of a power transformation and distribution system is a first defense line for avoiding grid accidents, and a power transformer is one of the most critical power equipment in the defense line. In order to timely and accurately detect faults of the power transformers in each area, the embodiment firstly obtains the power reduction area in which the faults of the power transformers are likely to exist according to the change condition of the power data in each area in the current time period, then analyzes the change condition of the power data in the power reduction time period of each power reduction area, eliminates the power reduction area in which the current power data normally falls, screens out the first suspected fault area in which the faults of the power transformers are likely to exist, further analyzes the change of the quantity of power users in each first suspected fault area, eliminates the first suspected fault area in which the power data fall due to the reduction of the power users, further screens out the second suspected fault area in which the faults of the power transformers are likely to exist, further analyzes the power regulation conditions of each second suspected fault area and other areas in the current time period, determines the second suspected fault area in which the power data fall due to the power regulation factors in the current time period, and finally detects and maintains the power transformers in the fault area, so that the fault detection efficiency of the power transformers is improved, and the manpower and material resources are greatly saved.
The invention provides a fault detection method for power equipment of a power transformation and distribution system, referring to fig. 1, which shows a schematic flow chart of the fault detection method for the power equipment of the power transformation and distribution system, according to one embodiment of the invention, the method comprises the following steps:
and S1, acquiring electric quantity data of each area at each moment in the current time period.
Specifically, each user in each area controlled by a power transformation and distribution system corresponds to an intelligent ammeter, and the electric quantity data of each user in each area at each moment can be obtained through the intelligent ammeter. In an actual situation, each intelligent ammeter stores the electric quantity data in a specified time period and transmits the electric quantity data to a server in the power transformation and distribution system, and the embodiment timely detects faults of the power transformer in each area by acquiring and analyzing the electric quantity data in the server in real time. The present embodiment sets the specified period of time to 1 hour, and the practitioner can set the duration of the specified period of time according to the actual situation, which is not limited herein. In order to improve the efficiency of analyzing the change of the electric quantity data of each area, the embodiment adds up the electric quantity data of all users in each area at the same time as the electric quantity data of the corresponding area at the same time, so as to obtain the electric quantity data of each area at each time. It should be noted that, the areas appearing in this embodiment are all areas controlled by the same power transformation and distribution system.
In order to analyze whether the power transformer in each area has a fault in real time, the embodiment acquires the electric quantity data of each area at each moment in the current time period in the server of the power transformation and distribution system, analyzes the electric quantity data of each area in the current time period, and further accurately analyzes whether the power transformer in each area has a fault at the current time. In this embodiment, the current time period is set to 3 years, the terminal time of the current time period is necessarily the current time, the time interval between two adjacent times in the current time period is set to 24 hours, and the size of the time interval between the current time period and two adjacent times can be set by an implementer according to the actual situation, which is not limited herein.
Step S2, acquiring a descending time period of each electric quantity descending region at the current moment, acquiring the normal descending degree of each electric quantity descending region according to the change condition of electric quantity data and the distribution condition of abnormal electric quantity data in the descending time period of each electric quantity descending region and the overall change trend of the electric quantity data of each electric quantity descending region in the current time period, and screening out a first suspected fault region based on the normal descending degree.
As known, when a power transformer in a certain area fails, the power data in the area must be reduced, and the reduction of the power data must be a continuous process, so this embodiment uses a time period formed by the last preset number of consecutive moments of each area in the current time period as a reference time period of each area, where the terminal moment of the reference time period is the current moment, the preset number is set to 10, and an implementer can set the magnitude of the preset number according to the actual situation, which is not limited herein. When the electric quantity data in the reference time period of a certain area is smaller, the area is more likely to be in a descending stage in the reference time period, and the area is indirectly indicated to be the area with the possibility of the power transformer fault. Therefore, the preset power data threshold of each area is set in this embodiment, and for any area, when all the power data in the reference time period of the area is smaller than the preset power data threshold of the area, the area is the power-down area where the power transformer may fail at the current time. So far, each electric quantity reduction area at the current moment is acquired.
Preferably, in some possible implementation manners of the embodiment, the method for acquiring the preset electric quantity data threshold includes, for any area, acquiring the average value of all electric quantity data of the area in the current time period as a reference value of the area, and taking the product of the first preset constant and the reference value as the preset electric quantity data threshold of the area, where the first preset constant is greater than 0 and less than 1, the first preset constant is set to 0.8, and an implementer can set the magnitude of the first preset constant according to actual conditions, and the implementation is not limited. So far, the preset electric quantity data threshold value of each area is obtained.
In order to accurately analyze the descending condition of the electric quantity data of each electric quantity descending region at the current time, the embodiment obtains the descending time period of each electric quantity descending region at the current time according to the changing condition of the electric quantity data of each electric quantity descending region. In some possible implementation manners of the embodiment, the method for acquiring the falling time period includes taking, as a target time, a time corresponding to electric quantity data which is more than or equal to a preset electric quantity data threshold value of the area and is closest to the current time in a current time period of any electric quantity falling area, and taking a time period formed by a next time of the target time and the current time as the falling time period of the electric quantity falling area. The electric quantity data in the descending time period of each electric quantity descending area are smaller than the preset electric quantity data threshold value of the corresponding electric quantity descending area. Up to this point, the falling period of each power-down region is acquired.
In practical situations, the electric quantity data of each area is reduced due to the influence of seasonal variation or other normal factors, for example, the electric quantity data of each area is relatively hot in summer, users in each area almost use an air conditioner, the weather in spring is relatively suitable, and the air conditioner is not needed, so that the electric quantity data of each area in spring is reduced compared with the electric quantity data of each area in summer. In order to determine whether the electric quantity data in the falling time period of each electric quantity falling region is the normally changed electric quantity data, the embodiment first analyzes the change condition of the electric quantity data in the falling time period of each electric quantity falling region, and when the falling part of the electric quantity data in the falling time period of a certain electric quantity falling region is more than the rising part and the falling speed of the electric quantity data is faster, the more likely the electric quantity data in the falling time period of the electric quantity falling region belongs to the normally changed electric quantity data, the less likely the electric quantity falling region is the power transformer fault region.
Since the distribution comparison set of the abnormal electric quantity data generated by the faults of the power transformer is known, and the distribution of the abnormal electric quantity data generated by other accidental accidents such as electric quantity data entry errors is more discrete, the embodiment firstly obtains the abnormal electric quantity data in the falling time period of each electric quantity falling area through the local outlier factor detection algorithm, further analyzes the distribution situation of the abnormal electric quantity data in the falling time period of each electric quantity falling area, and when the distribution of the abnormal electric quantity data in the falling time period of a certain electric quantity falling area is more discrete, the electric quantity falling area is more unlikely to be the fault area of the power transformer. The local outlier factor detection algorithm is a known technology, and will not be described in detail.
In practical situations, when the overall change trend of the electric quantity data of a certain electric quantity reduction area is downward, the electric quantity data of the electric quantity reduction area at the current moment is more likely to be the normally changed electric quantity data, and the electric quantity reduction area is less likely to be the power transformer fault area.
Therefore, in this embodiment, the normal descending degree of each electric quantity descending area is obtained according to the change condition of the electric quantity data and the distribution condition of the abnormal electric quantity data in the descending time period of each electric quantity descending area, and the overall change trend of the electric quantity data in the current time period of each electric quantity descending area. The greater the normal drop degree, the more normal the change of the electric quantity data in the drop period of the corresponding electric quantity drop region, the less likely the corresponding electric quantity drop region is a power transformer fault region. And then the first suspected fault area which possibly has the power transformer fault is primarily screened out according to the normal descending degree, and the detection efficiency of the fault area is improved.
In order to accurately analyze the change and overall change trend of the electric quantity data of each electric quantity reduction region, the embodiment respectively fits the electric quantity data of the current time period of each electric quantity reduction region into a curve according to time sequence to be used as the electric quantity data curve of each electric quantity reduction region, and decomposes each electric quantity data curve through an STL (STANDARD TEMPLATE Library) decomposition algorithm to obtain the trend curve and the season curve of each electric quantity reduction region. And analyzing the overall change trend of the electric quantity data of each electric quantity reduction region through a trend curve, and analyzing the change condition of the electric quantity data of each electric quantity reduction region through a seasonal curve. The curve fitting method and the STL (STANDARD TEMPLATE Library) decomposition algorithm are both known techniques, and will not be described in detail.
In some possible implementations of the present embodiment, referring to fig. 2, a flowchart of a method for obtaining a normal descent level according to an embodiment of the present invention is shown, where the method includes the following steps:
step S201, obtaining the whole change value.
Since the trend curve of each electric quantity reduction region can reflect the overall change condition of the electric quantity data of each electric quantity reduction region, in this embodiment, the trend curve of each electric quantity reduction region is fitted into a straight line, the slope of each straight line is obtained as the overall change value of each electric quantity reduction region, the smaller the overall change value is, the overall change trend of the electric quantity data of the corresponding electric quantity reduction region is indicated to be a reduction trend, and the more likely that the electric quantity data in the reduction time period of the corresponding electric quantity reduction region is the normally changed electric quantity data is indirectly indicated, and the less likely that the corresponding electric quantity reduction region is the power transformer fault region is.
And S202, acquiring the season decline degree.
In order to further analyze whether the electric quantity data in the descending time period of each electric quantity descending region is the electric quantity data which normally descends, the embodiment uses a part of seasonal curves corresponding to the descending time period of each electric quantity descending region as the reference seasonal curves of each electric quantity descending region, the change condition of the electric quantity data in the descending time period of each electric quantity descending region can be accurately analyzed through the reference seasonal curves, when the reference seasonal curves of a certain electric quantity descending region have more time periods in which the data descends, and when the data descending speed comparison block is used, the more likely electric quantity data in the descending time period of the electric quantity descending region are the electric quantity data which normally descend. Further, in this embodiment, the seasonal decrease degree of each electric quantity decrease area is obtained according to the change condition of the reference seasonal curve of each electric quantity decrease area. The greater the season drop degree, the more likely the electric quantity data in the drop time period of the corresponding electric quantity drop region is the electric quantity data which is normally dropped, and the more unlikely the corresponding electric quantity drop region is the power transformer fault region is indirectly indicated.
In some possible implementations of the present embodiment, referring to fig. 3, a flowchart of a method for obtaining a seasonal decline degree according to an embodiment of the present invention is shown, where the method includes the following steps:
Step S202-1, for any power-down area, the accumulated result of the corresponding time periods of all the down parts in the reference season curve of the power-down area is taken as a first time period.
The larger the first period is, the more the normal change of the electric quantity data tends to be reduced in the falling period of the electric quantity falling area, which means that the more likely the electric quantity data in the falling period of the electric quantity falling area is the normally changed electric quantity data, the less likely the electric quantity falling area is the power transformer fault area.
Step S202-2, the accumulated result of the corresponding time periods of all ascending parts in the reference season curve of the electric quantity descending region is used as a second time period.
The smaller the second period, the more the change of the power data in the falling period of the power-down area tends to be reduced, which means that the power data in the falling period of the power-down area is more likely to be the power data which is normally reduced.
Step S202-3, acquiring the data descending rate of each descending part in the reference season curve of the electric quantity descending region as the first rate of the corresponding descending part.
The greater the first rate, the more pronounced the data drop corresponding to the drop portion. The first rate obtaining method comprises the steps of obtaining a difference value between a maximum value and a minimum value of any descending part of a reference seasonal curve to be used as a first value, and taking a ratio of the first value to a time period duration corresponding to the descending part as the first rate of the descending part.
Step S202-4, the data rising rate of each rising part in the reference season curve of the electric quantity falling area is obtained as a second rate of the corresponding rising part.
The larger the second rate, the more pronounced the data rise corresponding to the rising portion. The second rate obtaining method is the same as the first rate obtaining method, and will not be described in detail.
And S202-5, acquiring the seasonal decrease degree of the electric quantity decrease area according to the difference between the first time period and the second time period and the difference between the average value of the first rate and the average value of the second rate, wherein the difference between the first time period and the second time period and the difference between the average value of the first rate and the average value of the second rate are in positive correlation with the seasonal decrease degree.
When the difference between the first time period and the second time period is larger, the electric quantity data in the falling time period of the electric quantity falling area tends to change downwards, which means that the electric quantity data in the falling time period of the electric quantity falling area is more likely to change downwards normally. In order to further determine whether the electric quantity data in the falling time period of the electric quantity falling area is the electric quantity data which normally falls, the obvious change condition of the electric quantity data in the falling time period of the electric quantity falling area is further analyzed, when the first speed is larger than the second speed, the more obvious the falling change of the electric quantity data in the falling time period of the electric quantity falling area is indicated, and the more probable the falling time period of the electric quantity falling area is the time period which normally changes is indirectly indicated. And obtaining the seasonal decrease degree of the electric quantity decrease area according to the difference value between the first time period and the second time period and the difference value between the average value of the first rate and the average value of the second rate, wherein the difference value between the first time period and the second time period and the difference value between the average value of the first rate and the average value of the second rate are in positive correlation with the seasonal decrease degree.
In order to accurately represent the normal degree of the electric quantity data in the descending time period of the electric quantity descending region, the embodiment specifically quantifies the seasonal descending degree into a seasonal descending degree value, and the larger the seasonal descending degree value is, the more likely the electric quantity data in the descending time period of the electric quantity descending region is to be the electric quantity data of the normal descending, and the more unlikely the electric quantity descending region is to be the power transformer fault region. The calculation formula of the season decline degree value is as follows: In the formula (I), in the formula (II), A season drop degree value of the a-th electric quantity drop area; A first period of time that is the a-th power-down region; a second period of time which is the a-th power-down region; A mean value of the first rate of the a-th power reduction region; is the average of the second rate for the a-th power down region. The larger andThe larger, i.eThe larger the electricity quantity data in the falling time period of the a-th electricity quantity falling area is, the more likely the electricity quantity data is to be the normally falling electricity quantity data, and the less likely the a-th electricity quantity falling area is to be the power failure area. And obtaining the season drop degree value of each electric quantity drop area.
And step S203, obtaining the anomaly contingency degree.
It is known that when the distribution of abnormal power data in a falling period of a certain power-down region is more discrete, the abnormal power data in the falling period of the power-down region is less likely to be generated by a power transformer fault, and the power-down region is more unlikely to be a power transformer fault region. Therefore, the embodiment obtains the abnormal sporadic degree of each electric quantity reduction region according to the distribution condition of the abnormal electric quantity data in the reduction time period of each electric quantity reduction region, and the larger the abnormal sporadic degree is, the less likely the corresponding electric quantity reduction region is a power transformer fault region.
Preferably, in some possible implementation manners of the embodiment, the method for acquiring the abnormal contingency degree is that, for any electric quantity reduction region, abnormal electric quantity data in a reduction time period of the electric quantity reduction region is clustered through a DBSCAN density clustering algorithm to obtain clusters, and when the clusters are scattered and the abnormal electric quantity data in each cluster are smaller, the abnormal electric quantity data in the reduction time period of the electric quantity reduction region is more likely to be caused by accidental accidents, the abnormal electric quantity data in the reduction time period of the electric quantity reduction region is less likely to be caused by power transformer faults, and the electric quantity reduction region is less likely to be caused by power transformer faults. The DBSCAN density clustering algorithm is a well-known technique, and will not be described in detail. In order to accurately analyze the distribution situation of the abnormal electric quantity data in the descending time period of the electric quantity descending region, the quantity of the abnormal electric quantity data in each cluster is obtained to be used as a first quantity, the difference value of the mean value of the largest first quantity and the first quantity is used as a first characteristic difference, the first characteristic difference is a certain nonnegative quantity, the smaller the first characteristic difference is, the more consistent the distribution of the abnormal electric quantity data in the cluster is indicated, the quantity of the abnormal electric quantity data in the descending time period of the electric quantity descending region is further obtained to be used as a second quantity, and the more discrete the distribution of the abnormal electric quantity data in the descending time period of the electric quantity descending region is indicated on the premise that the smaller the first characteristic difference is when the quantity of the cluster is equal to the second quantity. The abnormal sporadic degree of the electric quantity reduction area is obtained according to the difference between the number of the clusters and the second number and the first characteristic difference, wherein the difference between the number of the clusters and the second number and the abnormal sporadic degree are positive correlation, and the first characteristic difference and the abnormal sporadic degree are negative correlation.
In order to accurately represent the degree that abnormal electric quantity data in the falling time period of the electric quantity falling area is generated by accidental conditions, in this embodiment, the abnormal accidental degree is specifically quantified to be an abnormal accidental degree value, and the greater the abnormal accidental degree value is, the more likely the abnormal electric quantity data in the falling time period of the electric quantity falling area is caused by accidental conditions, and the more unlikely the electric quantity falling area is a power transformer fault area is indirectly described. The calculation formula of the abnormal sporadic degree value is as follows: In the formula (I), in the formula (II), The abnormal sporadic degree value of the a-th electric quantity reduction area; the number of clusters in the falling period of the a-th electric quantity falling area; a second number of power down regions a; a first number that is the greatest during the fall time period of the a-th power down region; the average value of the first quantity in the falling time period of the a-th electric quantity falling area is exp which is an exponential function based on a natural constant; Is the first characteristic difference. The larger the size of the container,The smaller the abnormal power data distribution in the falling period of the a-th power-down area, the more discrete the abnormal power data distribution in the falling period of the a-th power-down area, the more likely the abnormal power data in the falling period of the a-th power-down area is caused by accidental accidents,The larger the a-th power reduction zone is, the less likely the power transformer fault zone is. And obtaining the abnormal sporadic degree value of each electric quantity reduction area.
Step S204, obtaining the normal descent degree.
The smaller the overall change value is, the overall change trend of the electric quantity data of the corresponding electric quantity decreasing area is indicated to belong to decrease, the more likely to be the electric quantity data of normal change in the decreasing time period of the corresponding electric quantity decreasing area is indirectly indicated, the less likely to be the electric quantity data of the power transformer fault area is indicated to be the corresponding electric quantity decreasing area, the greater the season decreasing degree is, the less likely to be the electric quantity data of normal decrease in the decreasing time period of the corresponding electric quantity decreasing area is indicated to be the electric quantity data of normal decrease, the greater the abnormality contingency degree is, the more likely to be the accidental accident in the decreasing time period of the corresponding electric quantity decreasing area is indicated to be the electric quantity data of accidental occurrence, and the less likely to be the electric quantity transformer fault area is indicated to be the corresponding electric quantity decreasing area. Therefore, the embodiment obtains the normal descending degree of each electric quantity descending region according to the integral change value, the seasonal descending degree and the abnormal sporadic degree of each electric quantity descending region, wherein the integral change value and the normal descending degree are in a negative correlation, and the seasonal descending degree and the abnormal sporadic degree are in a positive correlation with the normal descending degree. The greater the normal drop degree, the more likely the power data in the drop period corresponding to the power drop region is the power data of the normal drop, and the less likely the corresponding power drop region is the power transformer fault region.
In order to accurately represent the normal degree of the electric quantity data in the descending time period of each electric quantity descending region, the embodiment specifically quantifies the normal descending degree into a normal descending degree value, and the larger the normal descending degree value is, the more likely the electric quantity data in the descending time period of the corresponding electric quantity descending region is the electric quantity data of the normal descending. Wherein, the calculation formula of the normal decline degree value is: In the formula (I), in the formula (II), The normal drop degree value of the a-th electric quantity drop area; a season drop degree value of the a-th electric quantity drop area; the abnormal sporadic degree value of the a-th electric quantity reduction area; the overall change value of the a-th electric quantity reduction area; is a second preset constant, greater than 0, and norm is a normalization function. Wherein, the value range of the normal decline degree value is 0 to 1.
The present embodiment will beSetting 1, avoiding denominator as 0, and setting by the practitioner according to actual conditionsIs not limited herein. And obtaining the normal descending degree value of each electric quantity descending area.
Since it is known that the larger the normal drop level value is, the less likely the corresponding power drop area is a power transformer fault area, and thus, the preset normal drop level threshold value is set to 0.8 according to the embodiment, and the operator can set the magnitude of the preset normal drop level threshold value according to the actual situation, which is not limited herein. When the normal descent level value is smaller than or equal to the preset normal descent level value threshold, the electric quantity data in the descent time period of the corresponding electric quantity descent area is the electric quantity data of normal change, the corresponding electric quantity descent area is not necessarily the power transformer fault area, and when the normal descent level value is smaller than or equal to the preset normal descent level value threshold, the corresponding electric quantity descent area is possibly the power transformer fault area, so that the electric quantity descent area corresponding to the normal descent level value smaller than or equal to the preset normal descent level value threshold is used as the first suspected fault area. And continuing to analyze the first suspected fault area, so that the efficiency of acquiring the fault area is improved.
And step S3, obtaining the user descending degree of each first suspected fault area according to the difference of the number of users between the descending time period of each first suspected fault area and the current time period of other parts of the non-descending time period, and screening out a second suspected fault area based on the user descending degree.
Specifically, in an actual situation, when a user in a certain area decreases, the electric quantity data of the area also decreases, so that in this embodiment, the change situation of the number of users in each first suspected fault area is analyzed, and an area where a power transformer fault actually exists at the current moment is further obtained. The user quantity at each moment in each area can be directly obtained in the power transformation and distribution system. When the user in the descending time period of a certain first suspected fault area is less than the user in the current time period of other parts of the non-descending time period, the more likely that the electric quantity data in the descending time period of the first suspected fault area is the normally-changed electric quantity data is indicated, and then the user descending degree of each first suspected fault area is obtained according to the user quantity difference between the descending time period of each first suspected fault area and the current time period of other parts of the non-descending time period, and the greater the user descending degree is, the more unlikely that the corresponding first suspected fault area is the power transformer fault area.
Preferably, in some possible implementation manners of the embodiment, the method for acquiring the user descending degree includes, for any one first suspected fault area, acquiring the number of users at each moment in a descending time period of the first suspected fault area as a first user number, acquiring the number of users at each moment in other part of the descending time period of the first suspected fault area, which are all second user numbers, as a second user number, for representing the number of users in the descending time period of the first suspected fault area and the number of users in the other part of the descending time period of the non-descending time period, acquiring a mean value of the first user number to represent the number of users in the descending time period of the first suspected fault area, and acquiring a mean value of the second user number to represent the number of users in the other part of the descending time period of the first suspected fault area, wherein the difference value of the mean value of the second user number and the mean value of the first user number is positive correlation degree.
In order to accurately represent the descending condition of the user in the descending time period of each first suspected fault area, in this embodiment, the descending degree of the user is specifically quantized into a descending degree value of the user, and the larger the descending degree value of the user is, the less likely the corresponding first suspected fault area is a fault area of the power transformer. The calculation formula of the user descent degree value is as follows: In the formula (I), in the formula (II), A user descent level value for the b first suspected fault region; a mean value of all second user numbers in the b first suspected fault area; The average value of the number of all first users in the b first suspected fault area is defined as a normalization function. Wherein, the value range of the user decline degree value is 0 to 1. So far, the user descent degree value of each first suspected fault area is obtained.
The greater the user degradation value is known, the less likely the corresponding first suspected fault region is a power transformer fault region. Therefore, in this embodiment, the preset user drop level threshold is set to 0.8, and the operator can set the magnitude of the preset user drop level threshold according to the actual situation, which is not limited herein. When the user descending degree value is larger than a preset user descending degree value threshold, the corresponding first suspected fault area is not necessarily the power transformer fault area, when the user descending degree value is smaller than or equal to the preset user descending degree value threshold, the corresponding first suspected fault area is possibly the power transformer fault area, and therefore the first suspected fault area corresponding to the user descending degree value smaller than or equal to the preset user descending degree value threshold is used as the second suspected fault area. And then, continuously analyzing the second suspected fault area, and improving the efficiency of acquiring the real power transformer fault area.
And S4, acquiring the electric quantity regulation degree of each second suspected fault area according to the electric quantity demand difference and the electric quantity distribution difference between each second suspected fault area and each other area at the current moment, and screening out the fault area at the current moment based on the electric quantity regulation degree.
Specifically, in the actual situation, some areas temporarily need more electricity consumption, so that in order to meet the demands of the areas, the power transformation and distribution system needs to regulate and control the electricity consumption of other areas, which can lead to the situation that the electricity consumption data of other areas is reduced. In order to determine whether a drop time period occurs in each second suspected fault area due to electric quantity regulation at the current time, in this embodiment, first, electric quantity demand data and electric quantity distribution data of each area at the current time are directly obtained through a power transformation and distribution system, when both the electric quantity demand data and the electric quantity distribution data of a certain second suspected fault area are smaller, the more likely that the electric quantity data in the drop time period of the second suspected fault area is generated due to electric quantity regulation between the areas, and the less likely that the second suspected fault area is a fault area of a power transformer. Therefore, according to the power demand difference and the power distribution difference between each second suspected fault area and each other area at the current time, the power regulation degree of each second suspected fault area is obtained, and the larger the power regulation degree is, the less likely the corresponding second suspected fault area is to be the power transformer fault area. And then accurately screening out a fault area at the current moment based on the electric quantity regulation degree.
Preferably, in some possible implementation manners of the embodiment, the electric quantity regulation and control degree obtaining method includes, for any one second suspected fault area, obtaining an average value of electric quantity demand data and an average value of electric quantity distribution data of all other areas except the second suspected fault area, sequentially using the average value and the average value of the electric quantity demand data as reference electric quantity demand data and reference electric quantity distribution data, using a difference value between the reference electric quantity demand data and the electric quantity demand data of the second suspected fault area as a first difference, using a difference value between the reference electric quantity distribution data and the electric quantity distribution data of the second suspected fault area as a second difference, using a difference value between the first difference and the second difference as a positive correlation, and using a difference value between the first difference and the second difference as a positive correlation, wherein the possibility that the second suspected fault area is regulated and controlled by a variable power distribution system at the current moment is greater. In order to accurately represent the possibility that each second suspected fault region is regulated by the power transformation and distribution system, in this embodiment, the electric quantity regulation degree is specifically quantized into an electric quantity regulation degree value, and the larger the electric quantity regulation degree value is, the more likely the electric quantity data corresponding to the falling time period of the second suspected fault region is generated by electric quantity regulation between regions, and the less likely the corresponding second suspected fault region is a fault region of the power transformer. The calculation formula of the electric quantity regulation degree value is as follows: In the formula (I), in the formula (II), The electric quantity regulation degree value of the d second suspected fault area is the electric quantity regulation degree value of the d second suspected fault area; is the reference electricity demand data; The electric quantity demand data of the d second suspected fault area is obtained; distributing data for the reference electric quantity; Distributing data for the electric quantity of the d second suspected fault area; is the first difference; the first difference and norm is the normalization function. Wherein, the value range of the electric quantity regulation degree value is 0 to 1. So far, the electric quantity regulation degree value of each second suspected fault area is obtained.
The greater the known electric quantity regulation degree value is, the less likely the corresponding second suspected fault region is to be the power transformer fault region, so the preset electric quantity regulation degree value threshold value is set to be 0.8 in this embodiment, and the magnitude of the preset electric quantity regulation degree value threshold value can be set by an implementer according to the actual situation, which is not limited herein. When the electric quantity regulation degree value is smaller than or equal to the preset electric quantity regulation degree value threshold, the corresponding second suspected fault area is a power transformer fault area, namely a fault area, so that the area where the power transformer fault exists is accurately determined.
And S5, performing fault detection on the power equipment in the fault area.
The power transformer in the fault area at the current moment is directly subjected to fault detection through a monitoring system or field investigation, so that the efficiency of power transformer fault detection is improved, the fault of the power transformer can be found in time, and a large amount of manpower and material resources are saved. Meanwhile, stable and reliable operation of the power transformation and distribution system is ensured in time.
In summary, the embodiment acquires electric quantity data, acquires normal descending degree according to the change condition of the electric quantity data and the distribution condition of abnormal electric quantity data in the descending time period of the electric quantity descending region and the overall change trend of the electric quantity data of the electric quantity descending region, and then screens out a first suspected fault region, acquires user descending degree according to the user change of the first suspected fault region, and then screens out a second suspected fault region, acquires electric quantity regulation degree according to the electric quantity demand difference and the electric quantity distribution difference between the second suspected fault region and each other region, and then screens out fault regions, and performs fault detection on electric equipment of the fault region. According to the invention, the fault area is accurately obtained, so that the area with the power equipment fault is accurately determined, the fault detection efficiency of the power equipment is improved, and a large amount of manpower and material resources are saved.
Example 2:
The invention also provides a fault detection system for power equipment of a power transformation and distribution system, referring to fig. 4, which shows a structure diagram of the fault detection system for power equipment of the power transformation and distribution system, provided by an embodiment of the invention, the system comprises an acquisition module 10, a first suspected fault area acquisition module 20, a second suspected fault area acquisition module 30, a fault area acquisition module 40 and a processing module 50.
And the acquisition module 10 is used for acquiring the electric quantity data of each area at each moment in the current time period.
The first suspected fault area obtaining module 20 is configured to obtain a falling time period of each electric quantity falling area at the current time, obtain a normal falling degree of each electric quantity falling area according to a change condition of electric quantity data and a distribution condition of abnormal electric quantity data in the falling time period of each electric quantity falling area and an overall change trend of the electric quantity data of each electric quantity falling area in the current time period, and screen out the first suspected fault area based on the normal falling degree.
The second suspected fault region obtaining module 30 is configured to obtain a user descent degree of each first suspected fault region according to a difference in the number of users between the descent time period of each first suspected fault region and the current time period of other parts of the non-descent time period, and screen out the second suspected fault region based on the user descent degree.
The fault region obtaining module 40 is configured to obtain a power regulation degree of each second suspected fault region according to a power demand difference and a power distribution difference between each second suspected fault region and each other region at the current time, and screen the fault region at the current time based on the power regulation degree.
And the processing module 50 is used for performing fault detection on the power equipment in the fault area.
It should be noted that, in the system provided in the above embodiment, only the division of the above functional modules is used as an example, in practical application, the above functional allocation may be performed by different functional modules according to needs, that is, the internal structure of the computer device is divided into different functional modules to perform all or part of the functions described above. In addition, the fault detection system of the power transformation and distribution system and the fault detection method embodiment of the power transformation and distribution system provided by the above embodiments belong to the same conception, and detailed implementation processes of the fault detection system and the fault detection method embodiment of the power transformation and distribution system are detailed in the method embodiment, and are not described herein again.
Example 3:
The application also provides a power equipment fault detection device of the power transformation and distribution system, which comprises a memory and a processor, wherein executable program codes are stored in the memory, and the processor is used for calling and executing the executable program codes to execute the power equipment fault detection method of the power transformation and distribution system provided by the embodiment of the application. The device can be a chip, a component or a module, the chip can comprise a processor and a memory which are connected, wherein the memory is used for storing instructions, and when the processor calls and executes the instructions, the chip can be made to execute the fault detection method for the power equipment of the power transformation and distribution system.
In addition, referring to fig. 5, the embodiment of the present application further protects a computer device, where the computer device includes a memory 401, a processor 402, and a computer program 403 stored in the memory 401 and running on the processor 402, where the processor 402 executes the computer program 403, so that the computer device can execute any one of the power transformation and distribution system power device fault detection methods described above.
Example 4:
The present embodiment also provides a computer readable storage medium, in which computer program code is stored, which when run on a computer, causes the computer to execute the above-mentioned related method steps to implement a power equipment fault detection method for a power transformation and distribution system provided in the above-mentioned embodiment.
Example 5:
the present embodiment also provides a computer program product, which when run on a computer, causes the computer to perform the above related steps, so as to implement a power equipment fault detection method of a power transformation and distribution system provided by the above embodiment.
The apparatus, the computer readable storage medium, the computer program product, or the chip provided in this embodiment are used to execute the corresponding method provided above, and therefore, the advantages achieved by the apparatus, the computer readable storage medium, the computer program product, or the chip can refer to the advantages of the corresponding method provided above, which are not described herein.
It should be noted that the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.

Claims (10)

1.一种变配电系统电力设备故障检测方法,其特征在于,该方法包括以下步骤:1. A method for detecting faults of power equipment in a power transformation and distribution system, characterized in that the method comprises the following steps: 获取当前时间段内每个区域每个时刻的电量数据;Get the power data of each area at each moment in the current time period; 获取当前时刻的每个电量下降区域的下降时间段,根据每个电量下降区域的下降时间段内电量数据的变化情况和异常电量数据的分布情况、以及每个电量下降区域在当前时间段内电量数据的整体变化趋势,获取每个电量下降区域的正常下降程度;基于正常下降程度筛选出第一疑似故障区域;Obtain the decline time period of each power decline area at the current moment, and obtain the normal decline degree of each power decline area according to the change of power data and the distribution of abnormal power data in the decline time period of each power decline area, as well as the overall change trend of power data in each power decline area in the current time period; and screen out the first suspected fault area based on the normal decline degree; 根据每个第一疑似故障区域的下降时间段与非下降时间段的其他部分当前时间段之间的用户数量差异,获取每个第一疑似故障区域的用户下降程度;基于用户下降程度筛选出第二疑似故障区域;According to the difference in the number of users between the falling time period of each first suspected fault area and the current time period of other parts of the non-falling time period, the degree of user decline of each first suspected fault area is obtained; and the second suspected fault area is screened out based on the degree of user decline; 根据当前时刻下每个第二疑似故障区域与其他每个区域之间的电量需求差异和电量分配差异,获取每个第二疑似故障区域的电量调控程度;基于电量调控程度筛选出当前时刻的故障区域;According to the power demand difference and power distribution difference between each second suspected fault area and each other area at the current moment, the power control degree of each second suspected fault area is obtained; and the fault area at the current moment is screened out based on the power control degree; 对故障区域的电力设备进行故障检测。Perform fault detection on the electrical equipment in the fault area. 2.如权利要求1所述的一种变配电系统电力设备故障检测方法,其特征在于,所述正常下降程度的获取方法为:2. A method for detecting faults of power equipment in a power transformation and distribution system according to claim 1, characterized in that the method for obtaining the normal decline degree is: 对于任一个电量下降区域,将该电量下降区域的当前时间段内的电量数据根据时间顺序拟合为一条曲线,作为该电量下降区域的电量数据曲线;For any area where the power is decreasing, the power data in the current time period of the area where the power is decreasing is fitted into a curve according to the time sequence as the power data curve of the area where the power is decreasing; 通过STL分解算法对电量数据曲线进行分解,获取该电量下降区域的趋势曲线和季节曲线;Decompose the power data curve using the STL decomposition algorithm to obtain the trend curve and seasonal curve of the power decline area; 获取趋势曲线所对应拟合直线的斜率,作为该电量下降区域的整体变化值;Obtain the slope of the fitted straight line corresponding to the trend curve as the overall change value of the power reduction area; 将该电量下降区域的下降时间段所对应的季节曲线,作为该电量下降区域的参考季节曲线;The seasonal curve corresponding to the decreasing time period of the power decreasing area is used as the reference seasonal curve of the power decreasing area; 根据参考季节曲线的变化情况,获取该电量下降区域的季节下降程度;According to the changes of the reference seasonal curve, the seasonal decrease degree of the power decrease area is obtained; 通过局部离群因子检测算法获取该电量下降区域的下降时间段内的异常电量数据,根据异常电量数据的分布情况,获取该电量下降区域的异常偶发程度;The abnormal power data in the falling time period of the power drop area is obtained by using the local outlier factor detection algorithm, and the abnormal sporadic degree of the power drop area is obtained according to the distribution of the abnormal power data; 根据该电量下降区域的整体变化值、季节下降程度和异常偶发程度,获取该电量下降区域的正常下降程度;其中,整体变化值与正常下降程度为负相关关系,季节下降程度和异常偶发程度均与正常下降程度为正相关关系。According to the overall change value, seasonal decline degree and abnormal occasional degree of the power decline area, the normal decline degree of the power decline area is obtained; among which, the overall change value is negatively correlated with the normal decline degree, and the seasonal decline degree and the abnormal occasional degree are positively correlated with the normal decline degree. 3.如权利要求2所述的一种变配电系统电力设备故障检测方法,其特征在于,所述季节下降程度的获取方法为:3. A method for detecting faults of power equipment in a power transformation and distribution system according to claim 2, characterized in that the method for obtaining the seasonal decline degree is: 对于任一个电量下降区域,将该电量下降区域的参考季节曲线中所有下降部分对应时间段的累加结果,作为第一时间段;For any area where the power consumption decreases, the accumulated result of the time periods corresponding to all the decreasing parts in the reference seasonal curve of the area where the power consumption decreases is taken as the first time period; 将该电量下降区域的参考季节曲线中所有上升部分对应时间段的累加结果,作为第二时间段;The accumulated result of the time periods corresponding to all the rising parts in the reference seasonal curve of the area where the power consumption decreases is taken as the second time period; 获取该电量下降区域的参考季节曲线中每个下降部分的数据下降速率,作为对应下降部分的第一速率;Obtaining a data drop rate of each drop portion in the reference seasonal curve of the power drop area as a first rate of the corresponding drop portion; 获取该电量下降区域的参考季节曲线中每个上升部分的数据上升速率,作为对应上升部分的第二速率;Obtaining a data rising rate of each rising portion in the reference seasonal curve of the power reduction area as a second rate of the corresponding rising portion; 根据第一时间段与第二时间段的差异,以及第一速率的均值与第二速率的均值的差异,获取该电量下降区域的季节下降程度;其中,第一时间段与第二时间段的差异、以及第一速率的均值与第二速率的均值的差异均和季节下降程度为正相关关系。According to the difference between the first time period and the second time period, and the difference between the mean of the first rate and the mean of the second rate, the seasonal decline degree of the power decline area is obtained; wherein, the difference between the first time period and the second time period, and the difference between the mean of the first rate and the mean of the second rate are positively correlated with the seasonal decline degree. 4.如权利要求2所述的一种变配电系统电力设备故障检测方法,其特征在于,所述异常偶发程度的获取方法为:4. A method for detecting faults of power equipment in a power transformation and distribution system according to claim 2, characterized in that the method for obtaining the degree of abnormal sporadic occurrence is: 对于任一个电量下降区域,通过DBSCAN密度聚类算法将该电量下降区域的下降时间段内的异常电量数据进行聚类,获得聚类簇;For any area where the power is decreasing, the abnormal power data in the decreasing time period of the area is clustered by using the DBSCAN density clustering algorithm to obtain a cluster cluster; 获取每个聚类簇内异常电量数据的数量,均作为第一数量;Obtain the number of abnormal power data in each cluster as the first number; 将最大的第一数量与第一数量的均值的差异,作为第一特征差异;The difference between the largest first quantity and the mean of the first quantity is taken as the first characteristic difference; 获取该电量下降区域的下降时间段内所有异常电量数据的数量,作为第二数量;Acquire the quantity of all abnormal power data in the power reduction time period of the power reduction area as the second quantity; 根据聚类簇的数量与第二数量的差异、以及第一特征差异,获取该电量下降区域的异常偶发程度;其中,聚类簇的数量与第二数量的差异和异常偶发程度为正相关关系,第一特征差异和异常偶发程度为负相关关系。According to the difference between the number of clusters and the second number, and the first characteristic difference, the abnormality and contingency degree of the power drop area is obtained; wherein, the difference between the number of clusters and the second number and the abnormality and contingency degree are positively correlated, and the first characteristic difference and the abnormality and contingency degree are negatively correlated. 5.如权利要求1所述的一种变配电系统电力设备故障检测方法,其特征在于,所述第一疑似故障区域的获取方法为:5. A method for detecting faults in power equipment of a power transformation and distribution system according to claim 1, characterized in that the method for obtaining the first suspected fault area is: 当正常下降程度不满足预设的正常下降程度范围时,对应电量下降区域为第一疑似故障区域。When the normal decrease degree does not meet the preset normal decrease degree range, the corresponding power decrease area is the first suspected fault area. 6.如权利要求1所述的一种变配电系统电力设备故障检测方法,其特征在于,所述用户下降程度的获取方法为:6. A method for detecting faults of power equipment in a power transformation and distribution system according to claim 1, characterized in that the method for obtaining the degree of user decline is: 对于任一个第一疑似故障区域,获取该第一疑似故障区域的下降时间段内每个时刻的用户数量,均作为第一用户数量;For any first suspected fault area, the number of users at each moment in the falling time period of the first suspected fault area is obtained as the first number of users; 获取该第一疑似故障区域的非下降时间段的其他部分当前时间段内每个时刻的用户数量,均作为第二用户数量;Obtain the number of users at each moment in the other parts of the current time period of the non-falling time period of the first suspected fault area, and use them as the second number of users; 根据第二用户数量的均值与第一用户数量的均值的差异,获取该第一疑似故障区域的用户下降程度;其中,第二用户数量的均值与第一用户数量的均值的差异和用户下降程度为正相关关系。According to the difference between the mean of the second number of users and the mean of the first number of users, the degree of user decline in the first suspected fault area is obtained; wherein the difference between the mean of the second number of users and the mean of the first number of users and the degree of user decline are positively correlated. 7.如权利要求1所述的一种变配电系统电力设备故障检测方法,其特征在于,所述第二疑似故障区域的获取方法为:7. A method for detecting faults in power equipment in a power transformation and distribution system according to claim 1, wherein the method for obtaining the second suspected fault area is: 当用户下降程度不满足预设的用户下降程度范围时,对应第一疑似故障区域为第二疑似故障区域。When the user's descent degree does not satisfy a preset user's descent degree range, the first suspected fault area corresponds to the second suspected fault area. 8.如权利要求1所述的一种变配电系统电力设备故障检测方法,其特征在于,所述电量调控程度的获取方法为:8. A method for detecting faults of power equipment in a power transformation and distribution system according to claim 1, characterized in that the method for obtaining the degree of power control is: 获取当前时刻下每个区域的电量需求数据和电量分配数据;Obtain the power demand data and power distribution data of each area at the current moment; 对于任一个第二疑似故障区域,获取除该第二疑似故障区域外其他所有区域的电量需求数据的均值和电量分配数据的均值,依次作为参考电量需求数据和参考电量分配数据;For any second suspected fault area, obtain the mean value of the power demand data and the mean value of the power allocation data of all other areas except the second suspected fault area, and use them as reference power demand data and reference power allocation data respectively; 将参考电量需求数据与该第二疑似故障区域的电量需求数据的差异,作为第一差异;taking a difference between the reference power demand data and the power demand data of the second suspected fault area as a first difference; 将参考电量分配数据与该第二疑似故障区域的电量分配数据的差异,作为第二差异;taking a difference between the reference power distribution data and the power distribution data of the second suspected fault area as a second difference; 根据第一差异和第二差异,获取该第二疑似故障区域的电量调控程度;其中,第一差异和第二差异均与电量调控程度为正相关关系。According to the first difference and the second difference, the power control degree of the second suspected fault area is obtained; wherein the first difference and the second difference are both positively correlated with the power control degree. 9.如权利要求1所述的一种变配电系统电力设备故障检测方法,其特征在于,所述故障区域的获取方法为:9. A method for detecting faults of power equipment in a power transformation and distribution system according to claim 1, characterized in that the method for obtaining the fault area is: 当电量调控程度不满足预设的电量调控程度范围时,对应第二疑似故障区域为当前时刻的故障区域。When the power control degree does not satisfy the preset power control degree range, the corresponding second suspected fault area is the fault area at the current moment. 10.如权利要求1所述的一种变配电系统电力设备故障检测方法,其特征在于,所述电量下降区域和下降时间段的获取方法为:10. A method for detecting faults of power equipment in a power transformation and distribution system according to claim 1, characterized in that the method for obtaining the power reduction area and the reduction time period is: 将当前时间段内每个区域最后的预设数量个连续的时刻所构成的时间段,作为每个区域的参考时间段;The time period consisting of the last preset number of consecutive moments in each area within the current time period is used as the reference time period for each area; 对于任一个区域,当该区域的参考时间段内所有电量数据均小于该区域的预设电量数据阈值时,该区域为当前时刻的电量下降区域;For any area, when all power data in the reference time period of the area are less than the preset power data threshold of the area, the area is a power reduction area at the current moment; 对于任一个电量下降区域,将该电量下降区域的当前时间段内距离当前时刻最近的大于或者等于该区域的预设电量数据阈值的电量数据所对应的时刻,作为目标时刻;For any area where the power is decreasing, the time corresponding to the power data which is closest to the current time and is greater than or equal to the preset power data threshold of the area within the current time period of the area where the power is decreasing is taken as the target time; 将目标时刻的下一时刻与当前时刻所构成的时间段,作为该电量下降区域的下降时间段。The time period formed by the next moment of the target moment and the current moment is used as the decreasing time period of the power decreasing area.
CN202411407883.8A 2024-10-10 2024-10-10 A method for detecting faults of power equipment in a power distribution system Active CN118914732B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202411407883.8A CN118914732B (en) 2024-10-10 2024-10-10 A method for detecting faults of power equipment in a power distribution system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202411407883.8A CN118914732B (en) 2024-10-10 2024-10-10 A method for detecting faults of power equipment in a power distribution system

Publications (2)

Publication Number Publication Date
CN118914732A CN118914732A (en) 2024-11-08
CN118914732B true CN118914732B (en) 2024-12-06

Family

ID=93296370

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202411407883.8A Active CN118914732B (en) 2024-10-10 2024-10-10 A method for detecting faults of power equipment in a power distribution system

Country Status (1)

Country Link
CN (1) CN118914732B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110634080A (en) * 2018-06-25 2019-12-31 中兴通讯股份有限公司 Abnormal power consumption detection method, device, equipment and computer-readable storage medium
CN112307435A (en) * 2020-10-30 2021-02-02 三峡大学 A method for screening abnormal electricity consumption based on fuzzy clustering and trend judgment

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6075997B2 (en) * 2012-08-27 2017-02-08 株式会社日立製作所 Fault diagnosis method for solar power generation system
CN115774652B (en) * 2023-02-13 2023-04-21 浪潮通用软件有限公司 Cluster control equipment health monitoring method, equipment and medium based on clustering algorithm
CN116151129A (en) * 2023-04-18 2023-05-23 石家庄科林电气股份有限公司 Power dispatching system fault diagnosis method based on extreme learning machine
CN116861312A (en) * 2023-07-06 2023-10-10 国网黑龙江省电力有限公司营销服务中心 Residual error network-based fault diagnosis method for electric power metering equipment
CN116595426B (en) * 2023-07-17 2023-09-26 济南大陆机电股份有限公司 An intelligent collection and management system for industrial Internet of Things data
CN116879662B (en) * 2023-09-06 2023-12-08 山东华尚电气有限公司 Transformer fault detection method based on data analysis
CN117057517B (en) * 2023-10-12 2024-01-12 国网吉林省电力有限公司长春供电公司 Efficient power data processing method and system based on digital twins
CN118294756A (en) * 2024-04-02 2024-07-05 黑河学院 Intelligent basic data association method and system
CN118362820B (en) * 2024-06-20 2024-08-23 国网甘肃省电力公司电力科学研究院 A method and system for intelligent diagnosis of energy storage equipment fault status

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110634080A (en) * 2018-06-25 2019-12-31 中兴通讯股份有限公司 Abnormal power consumption detection method, device, equipment and computer-readable storage medium
CN112307435A (en) * 2020-10-30 2021-02-02 三峡大学 A method for screening abnormal electricity consumption based on fuzzy clustering and trend judgment

Also Published As

Publication number Publication date
CN118914732A (en) 2024-11-08

Similar Documents

Publication Publication Date Title
CN119134354B (en) Intelligent dispatching system of district power supply electric network
CN111812427A (en) A method and system for evaluating the state of health of a power electronic device
CN109507535B (en) Method and device for predicting operation stage and operation life of transformer substation grounding grid
CN117118063A (en) New energy monitoring method and system based on cloud edge fusion
CN116154875A (en) Photovoltaic power station active power optimization distribution method based on TCN and error function
CN118914732B (en) A method for detecting faults of power equipment in a power distribution system
CN112782495A (en) String abnormity identification method for photovoltaic power station
CN114281846B (en) A new energy power generation prediction method based on machine learning
CN113934967B (en) Intelligent storage sample-checking feedback supervision system for coal samples
CN113379005A (en) Intelligent energy management system and method for power grid power equipment
CN107909096A (en) A kind of fault of converter early warning criterion implementation method based on two points of K mean clusters
CN118214367B (en) Intelligent monitoring method for photovoltaic diode state
CN119994972A (en) Dynamic optimization control system of energy storage cluster based on edge computing
CN103617454A (en) Wind power plant power forecast method according to numerical weather forecasts
CN113850017A (en) System-level fault analysis system and method based on power flow change map
CN119651555A (en) A control method for intelligent photovoltaic power generation system
CN117878958A (en) Night reactive compensation analysis method and system for water-light complementary photovoltaic power station
CN115967126A (en) Online analysis method for new energy cluster output outward-sending risk under natural disasters
CN120450145B (en) Energy-carbon management optimization method and system for source network charge storage and virtual power plant linkage
CN114362148B (en) Emergency control method and device for coping with transient uncertainty of new energy
CN119029902B (en) A method for identifying typical wind and solar power output scenarios considering comprehensive characteristics of sources and loads
CN118861557B (en) A 5G communication power supply health management method and device
CN119645624B (en) Performance management system and method based on artificial intelligent chip
CN120104432B (en) Intelligent operation and maintenance management method, system and storage medium based on data center
CN119671548B (en) Power grid data blood-margin management system

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant