CN114755515B - Fault diagnosis and early warning method for key equipment of energy storage power station based on data mining - Google Patents
Fault diagnosis and early warning method for key equipment of energy storage power station based on data miningInfo
- Publication number
- CN114755515B CN114755515B CN202210331092.6A CN202210331092A CN114755515B CN 114755515 B CN114755515 B CN 114755515B CN 202210331092 A CN202210331092 A CN 202210331092A CN 114755515 B CN114755515 B CN 114755515B
- Authority
- CN
- China
- Prior art keywords
- early warning
- fault
- energy storage
- data
- storage power
- 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
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B19/00—Alarms responsive to two or more different undesired or abnormal conditions, e.g. burglary and fire, abnormal temperature and abnormal rate of flow
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for AC mains or AC distribution networks
- H02J3/001—Methods to deal with contingencies, e.g. abnormalities, faults or failures
- H02J3/0012—Contingency detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Fuzzy Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
本发明公开一种基于数据挖掘的储能电站关键设备故障诊断预警方法，本方法采用K‑近邻互信息和Apriori关联规则算法实现储能电站关键设备的故障诊断预警，与传统告警策略相比，该方法能够深入挖掘储能电站关键设备各运行参数与故障信息之间的隐性关联，有效缩短故障诊断时间，给出的维护建议简单高效，为运维人员提供精细化指导。与其他智能算法诊断预警策略相比，该方法针对储能电站关键设备参数种类繁多、耦合性强且历史数据体量巨大等问题，结合工程经验，采用K‑近邻互信息算法筛选故障主要影响因素，能够降低人为筛选工作量及误差，提高执行效率。
The present invention discloses a method for fault diagnosis and early warning of key equipment of energy storage power stations based on data mining. This method uses K-nearest neighbor mutual information and Apriori association rule algorithm to realize fault diagnosis and early warning of key equipment of energy storage power stations. Compared with traditional alarm strategies, this method can deeply mine the implicit association between various operating parameters of key equipment of energy storage power stations and fault information, effectively shorten the fault diagnosis time, and provide simple and efficient maintenance suggestions, providing refined guidance for operation and maintenance personnel. Compared with other intelligent algorithm diagnosis and early warning strategies, this method targets the problems of a wide variety of parameters of key equipment of energy storage power stations, strong coupling, and huge volume of historical data, and combines engineering experience to use K-nearest neighbor mutual information algorithm to screen the main influencing factors of faults, which can reduce the workload and error of manual screening and improve execution efficiency.
Description
Technical Field
The invention relates to the field of fault diagnosis of energy storage equipment, in particular to a fault diagnosis and early warning method for key equipment of an energy storage power station based on data mining.
Background
In order to better realize the aims of double carbon and constructing a novel power system taking new energy as a main body, the renewable energy sources such as photovoltaic, wind power and the like are mainly used for replacing emission reduction in the future. But the new energy power generation has the characteristics of poor intermittence, randomness and schedulability, the large-scale new energy power generation grid connection provides a serious test for an electric power system, the existing flexible resources are gradually weak to support the electric power grid to accept the fluctuation energy source with such high proportion, and the stored energy is used as a higher-quality flexible resource, so that the new energy output can be effectively smoothed, and auxiliary services such as frequency modulation and peak shaving can be provided.
The existing energy storage system mostly adopts a lithium battery, and due to the characteristics of the lithium battery, the improper use can cause the safety problem of equipment. Energy storage safety is often interacted by a plurality of factors, so that the battery is abused and is in thermal runaway, and finally accidents occur. The method can be divided into a plurality of aspects such as battery body faults, running environment defects, shortage of an integrated management system of the energy storage system and the like. In the aspect of shortage of an integrated management system of an energy storage system, a Battery Management System (BMS), an energy storage converter (PCS) and an Energy Management System (EMS) are incomplete or not timely shared, the PCS and the battery are improperly configured and coordinated, the PCS has abnormal faults after the PCS are cleared, and the problems of system management such as collision between a measuring device and the management system occur, so that the faults can not be timely and effectively managed and controlled, and finally evolve into accidents.
The key equipment of the energy storage power station comprises a battery body, a battery management system BMS, an energy storage converter PCS and the like, and has the advantages of multiple equipment types, large quantity, high energy density of the energy storage battery, potential safety hazard and lower efficiency of the original operation and maintenance mode of the energy storage power station. The existing critical equipment fault diagnosis early warning method can only provide abnormal state warning, has low response speed, can only reflect the current abnormal state information of the equipment, cannot analyze the root fault reasons of the equipment reflected after the abnormal state, is difficult to meet the field refined operation and maintenance requirements of the power station, and even causes energy storage safety accidents.
Disclosure of Invention
The invention aims to solve the problems that the existing energy storage power station key equipment fault diagnosis method is low in response speed and cannot analyze the equipment root fault reasons reflected by abnormal states, and the power station field refined operation and maintenance requirements are difficult to meet, and provides an energy storage power station key equipment fault diagnosis early warning method based on data mining.
In order to solve the technical problems, the technical scheme includes that the fault diagnosis early warning method for the energy storage power station key equipment based on data mining comprises the following steps of S01, establishing a diagnosis early warning rule base according to historical data, establishing a response operation and maintenance suggestion base aiming at various rules, S02, collecting and processing abnormal signals in a period of time, performing fuzzy matching with the rule base, sending out fault diagnosis early warning information if matching is successful, otherwise, only giving out warning on the abnormal state, and S03, if the system sends out diagnosis early warning information, giving out corresponding operation and maintenance suggestions according to different fault types deduced in the step S02.
Further, the step S01 of establishing a diagnosis fault rule base and an operation and maintenance suggestion base comprises the steps of initially screening influence parameters which possibly cause equipment faults from operation and maintenance parameters of an original energy storage power station according to engineering experience, then selecting corresponding influence parameter data in a complete period from a historical database and preprocessing, S12 of analyzing the correlation between the initially screened influence parameters and the faults according to the historical data to determine parameters with the correlation meeting requirements as main influence factors, S13 of discretizing the historical data of the main influence factors according to set thresholds, and establishing an equipment fault diagnosis early warning rule base by adopting a data mining algorithm, S14 of formulating operation and maintenance suggestions according to fault types corresponding to different rules in the rule base and establishing the operation and maintenance suggestion base.
Further, the correlation between a certain parameter and a fault is analyzed by adopting a K-neighbor mutual information algorithm, and the specific method is that a correlation threshold value theta is firstly set, then mutual information MI between a certain parameter and the fault is calculated by utilizing the K-neighbor mutual information algorithm, the correlation threshold value theta and the mutual information MI are compared, if MI is smaller than theta, the parameter is abandoned, and otherwise the parameter is recorded.
Further, a group of influence parameters related to faults are determined by adopting an Apriori association rule algorithm, so that a device fault diagnosis early warning rule base is established; b, scanning history data of the discretized main influence factors, finding out all items meeting the minimum support degree, namely a frequent 1 item set, c, based on the frequent 1 item set, scanning history data of the discretized main influence factors, finding out a frequent 2 item set, cycling the process until no new frequent k+1 item set exists, wherein k is the category number of the main influence factors, d, calculating whether confidence between the item sets meets the condition that the confidence is not less than the minimum confidence, and determining strong association.
Further, in the process of generating frequent k+1 item sets by frequent k item sets, a connection step and a pruning step are adopted to improve efficiency, the connection step is used for finding out frequent k+1 item set L k+1, the frequent k item sets in L k are connected to generate candidate sets C k+1, in order to ensure that the generated item sets are irrelevant, if and only if the previous k-1 items after 2 frequent k item sets are ordered are identical, the pruning step is used for finding out item sets with C k+1 meeting the minimum support, the support of each item set is calculated by directly scanning historical data of main influence factors after discretization, and when C k+1 is larger than a set threshold value, C k+1 is compressed by adopting priori knowledge.
Further, the step S02 includes the steps of collecting real-time data of parameters screened in the step S01, recording signal data if abnormal signals appear, the step S22 includes the steps of counting abnormal signals appearing in a period of time after the first data are collected in the step S21, recording the data of the abnormal signals, the step S23 includes the steps of carrying out discretization processing on the data recorded in the step S21 and the step S22 according to a set threshold value, carrying out fuzzy matching on the processed real-time data of the parameters and a diagnosis and early warning rule base, and the step S24 includes the steps of sending diagnosis and early warning information aiming at different fault types and levels if the matching is successful, otherwise, carrying out warning on the abnormal state only through vibration.
Further, the step S03 comprises 2 steps, specifically, if the step S02 is successfully matched, the diagnosis early warning information is sent out, meanwhile, corresponding operation and maintenance suggestions are accurately matched in an operation and maintenance library according to different fault types, and the matched operation and maintenance suggestions in the step S31 are pushed through a picture in the step S32.
The method has the beneficial effects that the K-neighbor mutual information and the Apriori association rule algorithm are adopted to realize fault diagnosis early warning of the key equipment of the energy storage power station, and compared with the traditional warning strategy, the method can deeply mine the hidden association between each operation parameter of the key equipment of the energy storage power station and the fault information, effectively shortens the fault diagnosis time, provides simple and efficient maintenance suggestions, and provides fine guidance for operation and maintenance personnel. Compared with other intelligent algorithm diagnosis early warning strategies, the method aims at the problems of various key equipment parameters of the energy storage power station, strong coupling, huge volume of historical data and the like, combines engineering experience, adopts a K-nearest neighbor mutual information algorithm to screen main influencing factors of faults, can reduce manual screening workload and errors, and improves execution efficiency. Meanwhile, the expert database built by the method supports functions of rule expansion, modification, deletion and the like, and can provide support for new operation and maintenance requirements of the energy storage power station in the later period.
The method has the advantages that through monitoring the operation state of key equipment of the energy storage power station in real time, when faults are about to occur or occur, a plurality of collected early warning or alarming signals are subjected to fuzzy matching with a rule base within a certain time range, potential hazards possibly existing in the operation process of the system are analyzed, the abnormality or the fault type of the energy storage system is timely and accurately judged, abnormal working condition limitation, fault protection and audible and visual alarm are automatically implemented, and corresponding operation and maintenance suggestions are given.
Drawings
FIG. 1 is an overall flow chart of the present invention;
FIG. 2 is a flow chart for screening the main influencing factors of faults by using K-neighbor mutual information;
FIG. 3 is a flow chart of data mining using the Apriori algorithm;
FIG. 4 is a diagram of a partial fault and corresponding operation and maintenance proposal;
FIG. 5 is a diagram of a rule base trigger mechanism and a specific trigger path according to the present invention.
Detailed Description
The invention will be further described with reference to the drawings and the specific examples.
Example 1
When the power grid fails, the EMS can receive action event sequence records of power grid switches and relay protection devices sent by different RTUs, substation automation systems and other systems, and the events are arranged in time sequence and then stored in a historical database as historical information. According to different key equipment of the energy storage power station, the method can be mainly divided into PCS diagnosis early warning and battery system diagnosis early warning.
(1) PCS diagnosis early warning
Diagnosis and early warning are carried out according to the PCS running state and real-time data, and operations such as shutdown maintenance, connector fastening, fault module replacement, overhaul and the like are carried out on the PCS. The main fault types include the following:
a) Ac voltage is too high and too low
B) The alternating frequency is too high and too low
C) The DC voltage is too high and too low
D) Overload, overheat and short-circuit of converter
E) Overheat of radiator
F) Island of converter
G) DSP failure
(2) Battery system diagnosis and early warning
When the battery system operates, if the voltage, current, temperature and other analog quantities of the battery exceed the safety protection limit value, the on-site fault isolation can be implemented, the battery pack with the problem is taken out of operation, and meanwhile, protection information is reported. The main fault types are as follows:
a) Overvoltage of battery
B) Under-voltage of battery
C) Over-temperature of battery
D) Low temperature battery
E) Battery overcurrent
F) SOC out-of-limit
As shown in fig. 1, a fault diagnosis and early warning method for key equipment of an energy storage power station based on data mining mainly comprises the following specific implementation steps:
1. And establishing and maintaining two libraries, namely establishing a diagnosis early warning rule library according to historical data, and establishing a corresponding operation and maintenance suggestion library aiming at various rules. The rule base and the operation and maintenance base can be maintained in the background of supplementation, deletion, modification and the like according to the requirements of different application scenes;
2. processing an abnormal signal in a period of time, performing fuzzy matching with a rule base, and sending out fault diagnosis early warning information if the matching is successful, otherwise, only alarming for the abnormal state;
3. and (4) pushing operation and maintenance suggestions, namely if the system sends diagnosis early warning information, giving out corresponding operation and maintenance suggestions according to the fault type pushed out in the step (2), as shown in fig. 4.
According to the specific embodiment of the present invention, the above-mentioned step 1 "two-library" establishment and maintenance process includes four steps, specifically as follows:
(1) And preliminarily screening influence parameters which cause the faults of the energy storage power station equipment from a large number of operation and maintenance parameters according to engineering experience. Selecting data in a complete period from a historical database and preprocessing, wherein the preprocessing comprises the processing of abnormal values and vacant values;
(2) Analyzing the correlation between the preliminarily screened parameters and the faults according to the historical data, and determining the parameters with the correlation meeting the requirements as main influencing factors;
(3) Discretizing the historical data of the parameters according to a set threshold value, and establishing a rule base by adopting a data mining algorithm. The rule base can be expanded subsequently as required;
(4) And formulating operation and maintenance suggestions according to fault types corresponding to different rules in the rule base, and establishing an operation and maintenance suggestion base. The operation and maintenance library can be expanded subsequently as required.
The correlation analysis method in the step 2 is a K-neighbor mutual information algorithm, and the data mining algorithm for establishing the rule base is an Apriori association rule algorithm.
Mutual information (Mutual information, MI) is a method for measuring the degree of interdependence of two random variables, and is based on the concept of entropy in information theory. The larger the mutual information of the two random variables, the stronger the correlation. The main influence factors of the faults are selected according to mutual information, the influence of multivariable coupling on equipment faults is not considered, and the defects of high-dimensional operation amount, low precision and the like exist. The K-neighbor mutual information method can avoid directly calculating probability density and has good evaluation effect on complex nonlinear relations.
The definition of the mutual information shows that the smaller the mutual information MI (X, Y) is, the smaller the shared information amount of the sequence X and the sequence Y is, and the smaller the sequence correlation is, whereas the larger the mutual information MI (X, Y) is, the more the shared information amount of the sequence X and the sequence Y is, and the larger the sequence correlation is. Therefore, the main influencing factors of the key equipment faults of the energy storage power station can be determined according to the MI.
As shown in FIG. 2, the process of screening the main influencing factors of the faults by using the K-neighbor mutual information method comprises the steps of firstly setting a correlation threshold value theta, then calculating mutual information MI between a certain fault and the fault by using a K-neighbor mutual information algorithm, comparing the correlation threshold value theta with the mutual information MI, and discarding the parameter if MI is smaller than theta, otherwise recording the parameter. If a plurality of main influencing factors are calculated, repeating the process, and calculating the correlation between other factors and faults.
Further explanation of steps (1) and (2) is made in accordance with the description of the K-nearest neighbor mutual information algorithm above:
The key equipment of the energy storage power station comprises a battery body, a BMS, a PCS and the like, the equipment parameters are various, the coupling is strong, the volume of historical data is huge, and the main influencing factors causing faults are difficult to determine. Therefore, the invention combines engineering experience to preliminarily screen out influence parameters which cause equipment faults from a plurality of operation and maintenance parameters such as current, voltage, frequency, temperature, pressure and the like. And selecting data in a complete period from the historical database for preprocessing, including processing of abnormal values and vacant values. A correlation threshold is then set, i.e. above which the parameter is considered to be sufficiently strongly correlated with the fault to be the main cause of the fault occurrence. And finally, analyzing the correlation between the preliminarily screened parameters and the equipment faults by adopting a K-nearest neighbor mutual information algorithm according to historical data, and determining 3-5 parameters exceeding a correlation threshold as final parameters for establishing a rule base.
The association rules may find internal association mechanisms between 2 or more variables and predict event occurrence by analyzing the established association mechanisms. When key equipment such as PCS (personal communication System) and the like breaks down, fault related information is recorded in an EMS system log and stored in a historical database, and correlation rules can be applied to extract dependence and correlation between fault types and fault phenomena by analyzing historical data so as to obtain mode characteristics of various faults and guide diagnosis and early warning processes.
The correlation analysis results are typically measured using two key indicators of support and confidence. Taking the item set X and the item set Y as examples, the support S refers to the probability that the item sets X and Y occur simultaneously, and the confidence C refers to the probability that the item set Y occurs when the item set X occurs. Where an item set is a collection of items, an item set containing k items is referred to as a k item set, e.g., the collection { A, B, C } is a 3 item set.
In general, a term set satisfying the support degree not less than the minimum support degree is referred to as a frequent term set, while a rule satisfying the support degree not less than the minimum support degree and the confidence degree not less than the minimum confidence degree is referred to as a strong rule, in which the minimum support degree s_min and the minimum confidence degree c_min are used to define thresholds of the support degree and the confidence degree.
The mining of the association rule in this embodiment is to obtain mode features of various faults, that is, a group of signals corresponding to the faults, as shown in fig. 3, that is, a specific flow is as follows:
a. Setting a minimum support degree and a minimum confidence degree, b, scanning historical data of the discretized main influence factors, finding out all items meeting the minimum support degree, namely a frequent 1 item set, c, based on the frequent 1 item set, scanning the historical data of the discretized main influence factors, finding out a frequent 2 item set, cycling the process until no new frequent k+1 item set exists, k is the category number of the main influence factors, d, calculating whether the confidence degree among the item sets meets the condition that the confidence degree is not less than the minimum confidence degree, and determining strong association.
The method is characterized in that the whole database is required to be completely scanned every time a new item set is searched, the execution efficiency is low, a connection step and a pruning step are adopted in the process of generating frequent k+1 item sets by frequent k item sets, the connection step is used for finding out frequent k+1 item set L k+1, connecting frequent k item sets in L k to generate candidate set C k+1, in order to ensure that the generated item sets are irrelevant, if and only if the first k-1 items after 2 frequent k item sets are ordered are identical, the pruning step is used for finding out item sets with the minimum support degree of C k+1, the support degree of each item set is calculated by directly scanning historical data of main influence factors after discretization, and when C k+1 is larger than a set threshold value, the prior knowledge is adopted for compressing C k+1.
Because the association rule algorithm can only process Boolean data, and the values of parameters such as current, voltage, temperature and the like of key equipment of the energy storage power station are continuous, the historical data of the parameters screened in the step (2) are required to be discretized according to a set threshold value. Taking the current as an example, i.e. when the current exceeds a set threshold, it is noted "1", otherwise it is noted "0". And then, establishing a diagnosis early warning rule base by combining a confidence coefficient formula through a connection step and a pruning step by using discretized data and adopting an Apriori association rule algorithm.
According to the specific embodiment of the invention, the equipment fault diagnosis and early warning process in the step 2 comprises 4 steps, and the specific steps are as follows:
(1) Acquiring real-time data of the parameters screened in the step 1, and recording the signal data if abnormal signals occur;
(2) Counting abnormal signals occurring in a period of time from the time when the first data is acquired in the step (1) and recording the data of the abnormal signals;
(3) Discretizing the data recorded in the steps (1) and (2) according to a set threshold value, and carrying out fuzzy matching on the processed parameter real-time data and a diagnosis early warning rule base;
(4) If the matching is successful, different diagnosis early warning information such as sound, light, vibration, pushing pictures and the like shown in fig. 5 is sent out aiming at different fault types and levels, otherwise, the abnormal state is only warned through vibration.
According to a specific embodiment of the present invention, the operation and maintenance suggestion pushing process in the step 3 includes 2 steps, which are specifically as follows:
(1) If the step 2 is successful in matching, sending diagnosis early warning information, and simultaneously, accurately matching corresponding operation and maintenance suggestions in an operation and maintenance library according to different fault types;
(2) Pushing the matched operation and maintenance suggestions in the step (1) through a picture.
According to the specific embodiment of the invention, taking the battery module fault as an example, the whole flow of the method is further explained:
And analyzing collected historical operation data of signals such as battery current and voltage, battery compartment temperature and pressure, fire protection out-of-limit of a battery system and the like through a K neighbor mutual information algorithm by combining engineering experience to obtain parameters such as battery cell voltage, battery compartment temperature, fire protection of the battery system and the like and larger faults MI of the battery module. Discretizing the parameters according to a set threshold value, wherein the result after the discretization treatment is that the overvoltage of the battery monomer is recorded as 1, the overtemperature of a battery compartment is recorded as 1, the fire-fighting out-of-limit alarm of a battery system is recorded as 1, and the fault of a battery module is recorded as 1. And determining { battery cell overvoltage, battery temperature overhigh, battery system fire alarm } > battery module fault strong association rule according to the Apriori association rule algorithm.
When the energy storage power station operates, when one of the parameters { battery cell overvoltage, battery temperature is too high and battery system fire alarm } acquired in real time appears, the system starts timing and automatically carries out fuzzy matching with the rule base. If two other abnormal signals occur within 30 seconds, triggering a rule base under the action of the combined alarm signal, adopting the modes of sound, light, vibration, pushing pictures and the like for early warning, pushing information such as maintenance suggestions and the like, and providing references for operation and maintenance overhaulers.
The foregoing has outlined the principles and embodiments of the present invention in order that the detailed description of the invention may be better understood, and in order that the present invention may be better understood. Various other modifications and variations which do not depart from the gist of the invention may be made by those skilled in the art in light of the present disclosure and are intended to be within the scope of the invention.
Claims (4)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210331092.6A CN114755515B (en) | 2022-03-31 | 2022-03-31 | Fault diagnosis and early warning method for key equipment of energy storage power station based on data mining |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210331092.6A CN114755515B (en) | 2022-03-31 | 2022-03-31 | Fault diagnosis and early warning method for key equipment of energy storage power station based on data mining |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114755515A CN114755515A (en) | 2022-07-15 |
| CN114755515B true CN114755515B (en) | 2025-07-25 |
Family
ID=82329355
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210331092.6A Active CN114755515B (en) | 2022-03-31 | 2022-03-31 | Fault diagnosis and early warning method for key equipment of energy storage power station based on data mining |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114755515B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115497267A (en) * | 2022-09-06 | 2022-12-20 | 江西小手软件技术有限公司 | Equipment early warning platform based on time sequence association rule |
| CN115755837B (en) * | 2022-11-08 | 2025-05-06 | 广西电网有限责任公司电力科学研究院 | A method and system for predicting equipment defects |
| CN115825756B (en) * | 2023-02-16 | 2023-05-16 | 中国华能集团清洁能源技术研究院有限公司 | Distributed energy storage power station fault multi-level diagnosis method and system |
| CN116304031B (en) * | 2023-02-23 | 2025-09-26 | 浙江浙能数字科技有限公司 | A method for early warning diagnosis of generator sets based on association rule mining |
| CN116415149A (en) * | 2023-03-20 | 2023-07-11 | 安徽交泰智能技术有限公司 | A Multi-data Fusion Predictive Fault Diagnosis Method |
| CN116720324B (en) * | 2023-05-15 | 2024-11-15 | 中铁第四勘察设计院集团有限公司 | Fault early warning method and system for key equipment in traction substation based on prediction model |
| CN116577673B (en) * | 2023-07-12 | 2023-09-12 | 深圳先进储能材料国家工程研究中心有限公司 | Distributed neural network-based energy storage power station fault diagnosis method and system |
| CN117475590A (en) * | 2023-09-28 | 2024-01-30 | 杨联富 | Security visual alarm system for power transmission and transformation project |
| CN117787880B (en) * | 2023-11-13 | 2024-09-13 | 深圳赛瀚德技术有限公司 | Industrial digital management system and method based on cloud edge cooperation |
| CN118364407B (en) * | 2024-04-30 | 2024-10-01 | 山东文登抽水蓄能有限公司 | Intelligent switching station fault diagnosis system and method for pumped storage power station |
| CN118499316B (en) * | 2024-05-23 | 2024-12-24 | 江苏澳瑞思液压润滑设备有限公司 | A hydraulic station status monitoring method and system based on cloud data |
| CN119991350B (en) * | 2025-04-16 | 2025-08-01 | 新能瑞驰（北京）能源技术有限公司 | Distributed energy storage safety supervision method and system based on big data and cloud platform |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103871003A (en) * | 2014-03-31 | 2014-06-18 | 国家电网公司 | Power distribution network fault diagnosis method utilizing historical fault data |
| CN108549995A (en) * | 2018-04-24 | 2018-09-18 | 江苏电力信息技术有限公司 | A method of distribution public affairs time variant voltage exception Analysis of Policy Making is realized by data mining |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3629514B2 (en) * | 2000-05-24 | 2005-03-16 | インターナショナル・ビジネス・マシーンズ・コーポレーション | Region calculation method, spatial data mining device, map information display device, spatial data mining system, and storage medium |
| US8983940B2 (en) * | 2011-09-02 | 2015-03-17 | Adobe Systems Incorporated | K-nearest neighbor re-ranking |
| CN103559655B (en) * | 2013-11-15 | 2016-05-25 | 哈尔滨工业大学 | The Forecasting Methodology of the novel feeder line load of microgrid based on data mining |
| CN103630244B (en) * | 2013-12-18 | 2016-03-09 | 重庆大学 | Power system device method for diagnosing faults and system |
| CN104750861B (en) * | 2015-04-16 | 2019-05-21 | 中国电力科学研究院 | A kind of energy-accumulating power station mass data cleaning method and system |
| US20160364648A1 (en) * | 2015-06-09 | 2016-12-15 | Florida Power And Light Company | Outage prevention in an electric power distribution grid using smart meter messaging |
| CN105260618B (en) * | 2015-11-04 | 2017-11-28 | 华北电力大学 | A kind of energy-storage system typical curve method for digging based on cloud model |
| CN108830745B (en) * | 2018-06-29 | 2022-04-12 | 国网上海市电力公司 | Grid cascading fault diagnosis, early warning and evaluation system based on monitoring information |
| CN113761025B (en) * | 2021-08-30 | 2022-08-05 | 上海电气国轩新能源科技有限公司 | Method, system, equipment and medium for detecting data abnormity of battery of energy storage power station |
| CN114037099A (en) * | 2021-11-10 | 2022-02-11 | 江苏慧智能源工程技术创新研究院有限公司 | Intelligent energy storage power station operation and maintenance system based on industrial park |
-
2022
- 2022-03-31 CN CN202210331092.6A patent/CN114755515B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103871003A (en) * | 2014-03-31 | 2014-06-18 | 国家电网公司 | Power distribution network fault diagnosis method utilizing historical fault data |
| CN108549995A (en) * | 2018-04-24 | 2018-09-18 | 江苏电力信息技术有限公司 | A method of distribution public affairs time variant voltage exception Analysis of Policy Making is realized by data mining |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114755515A (en) | 2022-07-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114755515B (en) | Fault diagnosis and early warning method for key equipment of energy storage power station based on data mining | |
| CN111650921A (en) | A method and system for fault diagnosis of smart grid regulation and control system equipment | |
| WO2024146353A1 (en) | Active safety three-level prevention and control system and method for battery energy storage power station | |
| CN118690247A (en) | A Transformer Fault Prediction Method | |
| CN109948808A (en) | Database construction method, fault diagnosis method and system for substation equipment fault case database | |
| CN101833324B (en) | Intelligent fault diagnosis system in tread extrusion process and diagnosis method thereof | |
| CN113776591A (en) | Data recording and fault analyzing device and method for locomotive auxiliary control unit | |
| CN116644291A (en) | Energy storage battery multi-risk type early warning method based on cloud edge cooperation | |
| CN117169751A (en) | Energy storage power station fault monitoring management system and method based on machine learning | |
| CN114814603A (en) | Intelligent fault positioning method and system for energy storage power station | |
| CN112801313A (en) | Fully mechanized mining face fault judgment method based on big data technology | |
| CN117200449B (en) | Multi-dimensional algorithm analysis-based power grid monitoring management method and system | |
| CN114202304A (en) | A method and system for intelligent monitoring and processing of power grid faults | |
| WO2024098986A1 (en) | Relay protection apparatus defect detection method and system based on intelligent oscillograph | |
| CN119211000A (en) | A power communication network fault prediction and diagnosis system | |
| CN119355533A (en) | A battery fault diagnosis method based on multi-dimensional feature fusion | |
| CN117807155A (en) | Method, equipment and storage medium for generating multi-dimensional early warning prompt information | |
| CN119561125A (en) | Energy storage power station management system based on big data analysis | |
| CN118884257A (en) | A Fault Diagnosis Method for Energy Storage Grid Connected with Distributed Generation | |
| CN117805511A (en) | Energy storage power station abnormality identification system and method | |
| CN116996430A (en) | Product monitoring service system based on NCE network manager | |
| CN116070140A (en) | A system and method for monitoring the safe operation status of a power distribution substation | |
| CN114297253A (en) | A method and system for data mining of power secondary equipment defects | |
| Li et al. | Research on PHM Technology for Special Vehicle Weapon Control System | |
| CN119108970B (en) | Intelligent short-circuit optimization system, method and device based on reverse electromotive force |
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 |