CN117703346A - Liquid supply skid fault analysis method, device, equipment and storage medium - Google Patents
Liquid supply skid fault analysis method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117703346A CN117703346A CN202311776691.XA CN202311776691A CN117703346A CN 117703346 A CN117703346 A CN 117703346A CN 202311776691 A CN202311776691 A CN 202311776691A CN 117703346 A CN117703346 A CN 117703346A
- Authority
- CN
- China
- Prior art keywords
- liquid supply
- module
- data
- sledge
- monitoring data
- 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.)
- Pending
Links
Classifications
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B47/00—Survey of boreholes or wells
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B41/00—Equipment or details not covered by groups E21B15/00 - E21B40/00
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mining & Mineral Resources (AREA)
- Geology (AREA)
- Theoretical Computer Science (AREA)
- Geochemistry & Mineralogy (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- Fluid Mechanics (AREA)
- Environmental & Geological Engineering (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Geometry (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Marine Sciences & Fisheries (AREA)
- Animal Husbandry (AREA)
- Agronomy & Crop Science (AREA)
- Geophysics (AREA)
- Measurement Of Levels Of Liquids Or Fluent Solid Materials (AREA)
Abstract
The invention discloses a liquid supply skid fault analysis method, a device, equipment and a storage medium, and relates to the field of data processing, wherein the method comprises the following steps: performing operation monitoring on each module of the target liquid supply sledge to obtain original monitoring data corresponding to each module, performing feature extraction on the original monitoring data to obtain data feature values corresponding to each original monitoring data, comparing each data feature value with a monitoring threshold value corresponding to each module, determining operation state information of each module based on a comparison result, performing fault analysis on the target liquid supply sledge based on the operation state information, and performing early warning based on a fault analysis result; according to the invention, the monitoring data characteristic values of the modules in the target liquid supply sledge are compared with the monitoring threshold values, and the fault analysis is carried out according to the running state information of the modules, so that the faults of the liquid supply sledge can be timely and accurately detected, the timeliness of detection is ensured, the fault early warning is carried out timely, and the potential safety hazard caused by untimely fault detection is avoided.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a method, an apparatus, a device, and a storage medium for analyzing a failure of a liquid supply sledge.
Background
Along with the continuous development of petroleum exploitation technology and the continuous increase of environmental awareness, the requirements on the fracturing pump are higher and higher, the traditional mechanical fracturing and hydraulic fracturing are both powered by a diesel engine, and the equipment has high energy consumption, high noise and serious environmental pollution, so that the electrically driven fracturing pump with the advantages of low use cost, low noise, environmental protection and the like becomes the development trend of the fracturing pump. The liquid supply sledge is used as important component equipment in the fracturing process and is widely applied to the petroleum and natural gas production increasing construction process. The traditional liquid supply sledge mostly adopts a post maintenance and regular maintenance mode, so that the running condition of the liquid supply sledge cannot be effectively monitored at present, the fault detection timeliness is poor, the faults existing in the liquid supply sledge cannot be timely and accurately detected, and therefore, the liquid supply sledge has a large potential safety hazard in the use process.
The foregoing is provided merely for the purpose of facilitating understanding of the technical solutions of the present invention and is not intended to represent an admission that the foregoing is prior art.
Disclosure of Invention
The invention mainly aims to provide a liquid supply skid fault analysis method, device, equipment and storage medium, and aims to solve the technical problems that the operation condition of a liquid supply skid cannot be effectively monitored, the fault detection timeliness is poor, and the faults of the liquid supply skid cannot be timely and accurately detected in the prior art.
In order to achieve the above object, the present invention provides a method for analyzing faults of a liquid supply sledge, the method comprising the following steps:
performing operation monitoring on each module of the target liquid supply sledge to obtain original monitoring data corresponding to each module;
extracting the characteristics of the original monitoring data to obtain data characteristic values corresponding to the original monitoring data;
comparing each data characteristic value with a monitoring threshold value corresponding to each module;
determining running state information of each module based on the comparison result, and performing fault analysis on the target liquid supply sledge based on the running state information;
and carrying out early warning based on the fault analysis result of the target liquid supply sledge.
Optionally, the determining the operation state information of each module based on the comparison result, and performing fault analysis on the target liquid supply sledge based on the operation state information includes:
determining a difference value between the data characteristic value and the monitoring threshold value based on the comparison result;
judging whether the difference value is within a preset error range or not;
if the difference value is not in the preset error range, inputting the difference value into a pre-built operation analysis model to obtain operation state information of each module, and carrying out fault analysis on the target liquid supply sledge based on the operation state information, wherein the operation analysis model is built based on expert data and historical fault data of the target liquid supply sledge;
if the difference value is within a preset error range, determining difference value fluctuation trend information based on the operation monitoring result of the target liquid supply sledge, inputting the difference value fluctuation trend information into the operation analysis model to obtain operation trend information of each module, and performing fault analysis on the target liquid supply sledge based on the operation trend information.
Optionally, before the difference is input to the pre-constructed operation analysis model, the method further includes:
acquiring historical fault data and expert data of a target liquid supply sledge;
constructing a training set based on the historical fault data and expert data;
and training the original model based on the training set to obtain an operation analysis model.
Optionally, the feature extracting the original monitoring data to obtain a data feature value corresponding to each original monitoring data includes:
carrying out aggregation treatment on the original monitoring data corresponding to each module to obtain the aggregated original monitoring data;
and carrying out feature extraction on the aggregated original monitoring data based on a pre-constructed feature library to obtain data feature values corresponding to the original monitoring data.
Optionally, the aggregating the raw monitoring data corresponding to each module to obtain aggregated raw monitoring data includes:
extracting signal characteristics of original monitoring data corresponding to each module to obtain signal characteristic information;
and carrying out aggregation processing on the original monitoring data corresponding to each module based on the signal characteristic information to obtain the aggregated original monitoring data.
Optionally, the raw monitoring data comprises image monitoring data; the liquid supply sledge fault analysis method comprises the following steps:
extracting image features of the image monitoring data to obtain image feature vectors corresponding to the modules;
acquiring initial feature vectors corresponding to the modules based on a pre-constructed image feature library;
comparing the image feature vector with the initial feature vector to obtain image feature difference information;
and performing fault analysis on the target liquid supply sledge based on the image characteristic difference information.
Optionally, before comparing each data characteristic value with the monitoring threshold value corresponding to each module, the method further includes:
acquiring a factory initial threshold value of a target liquid supply sledge and historical operation information of the target liquid supply sledge;
determining a current performance parameter of the target liquid supply skid based on the historical operating information;
collecting the service environment information of the target liquid supply sledge;
and correcting the initial threshold value of the factory based on the current performance parameter and the using environment information to obtain a monitoring threshold value.
In addition, in order to achieve the above object, the present invention also provides a liquid supply skid fault analysis device, including:
the data monitoring module is used for performing operation monitoring on each module of the target liquid supply sledge to obtain original monitoring data corresponding to each module;
the feature extraction module is used for carrying out feature extraction on the original monitoring data to obtain data feature values corresponding to the original monitoring data;
the threshold value comparison module is used for comparing each data characteristic value with a monitoring threshold value corresponding to each module;
the fault analysis module is used for determining the running state information of each module based on the comparison result and carrying out fault analysis on the target liquid supply sledge based on the running state information;
and the fault early warning module is used for carrying out early warning based on the fault analysis result of the target liquid supply sledge.
In addition, to achieve the above object, the present invention also proposes a liquid supply skid failure analysis apparatus, including: a memory, a processor, and a fluid supply skid failure analysis program stored on the memory and executable on the processor, the fluid supply skid failure analysis program configured to implement the steps of the fluid supply skid failure analysis method as described above.
In addition, in order to achieve the above object, the present invention also proposes a storage medium having stored thereon a liquid supply skid failure analysis program which, when executed by a processor, implements the steps of the liquid supply skid failure analysis method as described above.
According to the invention, through operation monitoring of each module of a target liquid supply sledge, original monitoring data corresponding to each module is obtained, feature extraction is carried out on the original monitoring data, data feature values corresponding to the original monitoring data are obtained, the data feature values are compared with monitoring threshold values corresponding to the modules, operation state information of the modules is determined based on the comparison result, fault analysis is carried out on the target liquid supply sledge based on the operation state information, and early warning is carried out based on the fault analysis result of the target liquid supply sledge; according to the invention, the monitoring data of each module of the target liquid supply sledge is subjected to feature extraction, and each data feature value is compared with the monitoring threshold value corresponding to each module, so that the running state information of each module is determined, and therefore, whether the target liquid supply sledge has a fault or not is accurately analyzed, the fault of the liquid supply sledge is timely and accurately detected, the timeliness of fault detection is ensured, the timely fault early warning is realized, and the potential safety hazard caused by untimely fault detection is avoided.
Drawings
FIG. 1 is a schematic diagram of a fluid supply skid failure analysis apparatus for a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a first embodiment of a method for analyzing a liquid supply skid fault according to the present invention;
FIG. 3 is a flow chart illustrating a second embodiment of a method for analyzing a liquid supply skid fault according to the present invention;
FIG. 4 is a schematic diagram illustrating a feature extraction of a second embodiment of a method for analyzing a liquid supply skid fault according to the present invention;
FIG. 5 is a flow chart illustrating a third embodiment of a method for analyzing a liquid supply skid fault according to the present invention;
FIG. 6 is a block diagram illustrating a first embodiment of a fluid supply skid failure analysis apparatus according to the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a liquid supply skid fault analysis device in a hardware operation environment according to an embodiment of the present invention.
As shown in fig. 1, the liquid supply skid fault analysis apparatus may include: a processor 1001, such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (Wi-Fi) interface). The Memory 1005 may be a high-speed random access Memory (Random Access Memory, RAM) or a stable nonvolatile Memory (NVM), such as a disk Memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
Those skilled in the art will appreciate that the configuration shown in FIG. 1 is not limiting of the fluid supply skid fault analysis apparatus and may include more or fewer components than shown, or may combine certain components, or may be a different arrangement of components.
As shown in fig. 1, an operating system, a network communication module, a user interface module, and a fluid supply skid failure analysis program may be included in the memory 1005 as one type of storage medium.
In the liquid supply skid fault analysis device shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the liquid supply skid fault analysis device of the present invention may be disposed in the liquid supply skid fault analysis device, where the liquid supply skid fault analysis device invokes a liquid supply skid fault analysis program stored in the memory 1005 through the processor 1001, and executes the liquid supply skid fault analysis method provided by the embodiment of the present invention.
An embodiment of the invention provides a method for analyzing a failure of a liquid supply sled, and referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of the method for analyzing a failure of a liquid supply sled.
In this embodiment, the method for analyzing the failure of the liquid supply sledge includes the following steps:
step S10: and performing operation monitoring on each module of the target liquid supply sledge to obtain original monitoring data corresponding to each module.
It should be understood that the main body of the method of this embodiment may be a fluid supply skid fault analysis device with data processing, network communication and program running functions, such as a computer, or other devices or apparatuses capable of implementing the same or similar functions, where the fluid supply skid fault analysis device (hereinafter referred to as a fault analysis device) is described as an example.
It should be noted that, in this embodiment, the sensor may be preset at the corresponding position of each module, so as to accurately monitor the operation state information of each module, for example, the flow sensor may be used to monitor the real-time flow of the target liquid supply sled, the pressure sensor may be used to monitor the pressure of the target liquid supply sled, the voltage and current sensor may be used to monitor the real-time voltage and current of the target liquid supply sled, and the image sensor may be used to monitor the image of the target liquid supply sled, so as to determine whether the target liquid supply sled has liquid leakage or deformation.
It can be appreciated that the fault analysis device can obtain various state parameters of the target liquid supply sledge by configuring the relevant state monitoring sensor to monitor the electric, mechanical and fluid states of the target liquid supply sledge in real time.
Step S20: and extracting the characteristics of the original monitoring data to obtain data characteristic values corresponding to the original monitoring data.
It should be noted that, since the collected original monitoring data may include multiple types of monitoring data, for example, the original monitoring data may include electrical signal monitoring data, flow signal monitoring data, image signal monitoring data, and pressure signal monitoring data, feature extraction needs to be performed on each monitoring data to obtain data feature values corresponding to each monitoring data, so that failure analysis efficiency is improved.
In a specific implementation, the fault analysis device can perform signal unified processing on multiple types of monitoring data, and as the multiple types of monitoring data may be different types of signals, various types of monitoring data are subjected to signal unified processing, and various types of signals are uniformly converted into the same type of signals, so that the data and the signals are conveniently processed, and the processing efficiency and the analysis efficiency are improved.
Step S30: and comparing each data characteristic value with a monitoring threshold value corresponding to each module.
It should be noted that the monitoring threshold may be a preset normal data threshold, for example, if the data characteristic value corresponding to the pressure signal exceeds the monitoring threshold corresponding to the pressure signal, it is determined that the pressure of the target liquid supply sledge is abnormal, and a pressure fault exists.
It is understood that the monitoring threshold may be a preset threshold, and each module corresponds to a different threshold, for example, the pressure module corresponds to a pressure monitoring threshold, the flow module corresponds to a flow monitoring threshold, and so on.
In a specific implementation, the monitoring threshold may be a device threshold set by a factory, or may be a threshold obtained after the fault analysis device recalibrates based on historical data of the target liquid supply sledge.
Further, in order to accurately set the monitoring threshold, before the step S30, the method further includes:
acquiring a factory initial threshold value of a target liquid supply sledge and historical operation information of the target liquid supply sledge;
determining a current performance parameter of the target liquid supply skid based on the historical operating information;
collecting the service environment information of the target liquid supply sledge;
and correcting the initial threshold value of the factory based on the current performance parameter and the using environment information to obtain a monitoring threshold value.
It will be appreciated that the monitoring threshold may be a factory set threshold of the target fluid supply skid, or may be a threshold obtained after correction of the factory set threshold, so that the usage environment and the usage time of the fluid supply skid may cause a difference between thresholds of the same type of fluid supply skid, and thus in some embodiments, the factory threshold needs to be adjusted and corrected in combination with the influence of the device depreciation performance caused by the usage environment and the device usage time of the fluid supply skid.
In a specific implementation, the fault analysis device may obtain the monitoring threshold corresponding to each type of signal, for example, obtain the pressure monitoring threshold corresponding to the pressure signal, obtain the flow monitoring threshold corresponding to the flow signal, obtain the motor/pump monitoring threshold corresponding to the motor/pump signal, obtain the current/voltage monitoring threshold corresponding to the current/voltage signal, and so on.
Step S40: and determining the running state information of each module based on the comparison result, and performing fault analysis on the target liquid supply sledge based on the running state information.
It can be understood that the fault analysis device can judge whether each module has a fault currently based on the comparison result, and if the fault exists, the fault module is positioned; if no fault exists, predicting the operation trend of each module based on the comparison result, judging whether each module has faults at future time based on the operation trend, and if so, analyzing the fault reason based on the predicted operation trend.
Further, in order to accurately determine whether the target liquid supply skid has a fault, the step S40 may include:
step S41: determining a difference value between the data characteristic value and the monitoring threshold value based on the comparison result;
step S42: judging whether the difference value is within a preset error range or not;
step S43: if the difference value is not in the preset error range, inputting the difference value into a pre-constructed operation analysis model to obtain operation state information of each module, and performing fault analysis on the target liquid supply sledge based on the operation state information;
step S44: if the difference value is within a preset error range, determining difference value fluctuation trend information based on the operation monitoring result of the target liquid supply sledge, inputting the difference value fluctuation trend information into the operation analysis model to obtain operation trend information of each module, and performing fault analysis on the target liquid supply sledge based on the operation trend information.
It should be noted that the difference fluctuation trend information may be a fluctuation trend of a real-time difference between the data characteristic value and the monitoring threshold value over a continuous monitoring period (for example, 3 minutes), for example, the difference is 0.2 in the first second, 0.1 in the second, 0.5 in the third second, and so on. The operation analysis model is constructed based on expert data and historical fault data of the target liquid supply sledge, and the fault analysis equipment can perform module operation analysis by inputting the difference value and/or the fluctuation trend information of the difference value into the operation analysis model so as to obtain operation state information and/or operation trend information of each module.
It should be understood that the fault analysis device may record the difference between the data characteristic value and the monitoring threshold value in a preset monitoring period, and construct a difference fluctuation analysis chart and/or a difference fluctuation data table based on the difference recording result in the preset monitoring period, in combination with a time sequence, so as to analyze the difference fluctuation trend information, predict the future operation trend of the target liquid supply skid based on the difference fluctuation trend information analysis result, and determine whether the target liquid supply skid will fail in the future.
It can be appreciated that the fault analysis device may determine whether a fault exists in each module of the target liquid supply skid based on the comparison result, if the difference between the data characteristic value and the monitoring threshold exceeds a preset error range, it is determined that a fault exists, for example, the difference between the data characteristic value of the pressure signal and the pressure monitoring threshold exceeds a normal pressure error range, and it is determined that an abnormality exists in the pressure of the target liquid supply skid.
If the difference value between the data characteristic value and the monitoring threshold value is in a normal range, determining a real-time difference value based on a real-time monitoring result of the target liquid supply sledge, predicting the operation trend of the target liquid supply sledge based on the real-time difference value, obtaining trend information, determining the operation state information of each module based on the trend information, and performing fault analysis on the target liquid supply sledge based on the operation state information.
Further, in order to accurately analyze the fault, before the step S43, the method further includes:
acquiring historical fault data and expert data of a target liquid supply sledge;
constructing a training set based on the historical fault data and expert data;
and training the original model based on the training set to obtain an operation analysis model.
It should be noted that the historical fault data may be device operation log data and external record data recorded when the target liquid supply sledge and/or the liquid supply sledge of the same model have failed in the past. The expert data may be based on fault analysis log data of the standard fluid supply sledge and/or the fluid supply sledge of the same model when the fluid supply sledge has failed in the past.
It will be appreciated that the fault analysis apparatus prepares the input data by pre-processing the historical fault data and expert data, for example, performing pre-processing steps such as data cleaning, feature selection, feature scaling, data balancing, etc. on the training set; and constructing a training set based on the preprocessed historical fault data and expert data, and training the initial deep learning model based on the training set to obtain an operation analysis model.
Step S50: and carrying out early warning based on the fault analysis result of the target liquid supply sledge.
It should be noted that, whether the operation state of each module is abnormal is determined based on the result of the fault analysis, if so, the target liquid supply sledge is determined to have a fault risk, and fault early warning is performed based on the result of the fault analysis, for example, warning, alarm, fault information and the like are popped up on the HMI interface, so that the user can more intuitively understand the state of the device.
According to the method, through operation monitoring of each module of a target liquid supply sledge, original monitoring data corresponding to each module are obtained, feature extraction is conducted on the original monitoring data, data feature values corresponding to the original monitoring data are obtained, the data feature values are compared with monitoring threshold values corresponding to the modules, operation state information of the modules is determined based on the comparison result, fault analysis is conducted on the target liquid supply sledge based on the operation state information, and early warning is conducted based on fault analysis results of the target liquid supply sledge; according to the invention, the monitoring data of each module of the target liquid supply sledge is subjected to feature extraction, and each data feature value is compared with the monitoring threshold value corresponding to each module, so that the running state information of each module is determined, and therefore, whether the target liquid supply sledge has a fault or not is accurately analyzed, the fault of the liquid supply sledge is timely and accurately detected, the timeliness of fault detection is ensured, the timely fault early warning is realized, and the potential safety hazard caused by untimely fault detection is avoided.
Referring to fig. 3, fig. 3 is a flow chart of a second embodiment of a method for analyzing a failure of a liquid supply sled according to the present invention.
Based on the first embodiment, in this embodiment, the step S20 includes:
step S21: carrying out aggregation treatment on the original monitoring data corresponding to each module to obtain the aggregated original monitoring data;
step S22: and carrying out feature extraction on the aggregated original monitoring data based on a pre-constructed feature library to obtain data feature values corresponding to the original monitoring data.
It should be noted that, because the fault analysis device monitors each module, the collected signal types have differences, such as flow signals, pressure signals, electric signals, etc., in order to improve the fault analysis efficiency, in this embodiment, in order to improve the fault analysis efficiency, the collected original monitoring data may be aggregated in advance, and different types of signals are converted into the same type of signal data, so that the monitoring data of each type of signals are processed through a preset communication protocol.
It can be understood that referring to fig. 4, fig. 4 is a schematic diagram of feature extraction, the fault analysis device monitors the operation of the target liquid supply sledge through a flow sensor, a pressure sensor, a motor/pump frequency converter, a voltage/current sensor and an image sensor, collects flow signals, pressure signals, motor/pump signals, voltage/current signals and image signals, extracts features of each signal based on a pre-constructed feature library, and shares the extracted feature values to corresponding feature libraries respectively to perform data sharing and updating on the feature libraries.
Further, in order to improve the feature extraction efficiency, the step S21 may include:
step S211: extracting signal characteristics of original monitoring data corresponding to each module to obtain signal characteristic information;
step S212: and carrying out aggregation processing on the original monitoring data corresponding to each module based on the signal characteristic information to obtain the aggregated original monitoring data.
It should be noted that, the fault analysis device may perform noise reduction processing on the original monitoring data to clean repeated data, invalid data, noise data and the like of the original monitoring data, obtain high-quality candidate data, perform signal feature extraction on the candidate data to obtain signal feature information, and perform aggregation processing on the original monitoring data corresponding to each module based on the signal feature information to obtain aggregated original monitoring data, so as to uniformly convert the candidate data into signal data of the same type, thereby improving processing efficiency and fault analysis efficiency.
According to the method, the raw monitoring data corresponding to each module are subjected to aggregation processing to obtain the aggregated raw monitoring data, and feature extraction is performed on the aggregated raw monitoring data based on a pre-constructed feature library to obtain a data feature value corresponding to each raw monitoring data; according to the method, the device and the system, the original monitoring data are aggregated, so that the monitoring data of different types of signals are unified, the signals of different types are converted into the signals of the same type, the aggregated original monitoring data are subjected to feature extraction based on the pre-constructed feature library, and the data feature value corresponding to each piece of original monitoring data is obtained, so that the feature extraction efficiency is improved.
Referring to fig. 5, fig. 5 is a schematic flow chart of a third embodiment of a method for analyzing a failure of a liquid supply sled according to the present invention.
Based on the first embodiment, in this embodiment, the original monitoring data includes image monitoring data, and the method for analyzing the failure of the liquid supply sledge includes:
step S50: extracting image features of the image monitoring data to obtain image feature vectors corresponding to the modules;
step S60: acquiring initial feature vectors corresponding to the modules based on a pre-constructed image feature library;
step S70: comparing the image feature vector with the initial feature vector to obtain image feature difference information;
step S80: and performing fault analysis on the target liquid supply sledge based on the image characteristic difference information.
It should be noted that, the initial feature vector may be a normal feature vector extracted from an image of a normal state of each module. The image feature library can be constructed by carrying out image acquisition and image feature extraction on the liquid supply sledge in the factory state in advance and based on the extracted image feature vector in the factory state. The image feature difference information may be difference information between the current image feature and the normal image feature of the monitored target liquid supply sledge, and based on the image feature difference information, whether each module of the target liquid supply sledge has a fault or not may be accurately judged, for example, whether the monitored collected liquid supply sledge image has an abnormality such as a shadow or not may be accurately identified based on the image feature vector.
It can be understood that the fault analysis device in this embodiment may perform image feature extraction on the image monitoring data after preprocessing by performing preprocessing on the image monitoring data, and accurately identify whether an abnormality exists in the monitored image of the target liquid supply skid by using the extracted image feature vector and the initial feature vector, and if the abnormality exists, locate the fault based on the image feature difference information.
In a specific implementation, the fault analysis device may perform rasterization processing on a monitored image corresponding to the image monitored data to obtain a plurality of target grids, perform feature extraction on the plurality of target grids respectively to obtain target grid feature vectors corresponding to each target grid, extract an initial image in a pre-constructed image feature library, perform raster processing on the initial image to obtain a plurality of initial grids, perform feature extraction on the plurality of initial grids respectively to obtain an initial grid feature vector, and compare the target grid feature vector with the initial grid feature vector based on pixel coordinates of each target grid and pixel coordinates of each initial grid to obtain feature difference information between each target grid and each initial grid.
According to the embodiment, image feature extraction is carried out on the image monitoring data to obtain image feature vectors corresponding to the modules, initial feature vectors corresponding to the modules are obtained based on a pre-constructed image feature library, the image feature vectors are compared with the initial feature vectors to obtain image feature difference information, and fault analysis is carried out on the target liquid supply sledge based on the image feature difference information; because the image monitoring is carried out on the target liquid supply sledge, the image feature extraction is carried out on the collected image monitoring data, and the image feature vector is compared with the initial feature vector in the image feature library, so that the image feature difference information is obtained, whether the target liquid supply sledge has faults or not is accurately judged based on the image feature difference information, and therefore the fault analysis efficiency and the timeliness of the fault analysis are improved.
In addition, the embodiment of the invention also provides a storage medium, wherein the storage medium is stored with a liquid supply sledge fault analysis program, and the liquid supply sledge fault analysis program realizes the steps of the liquid supply sledge fault analysis method when being executed by a processor.
Because the storage medium adopts all the technical solutions of all the embodiments, at least all the beneficial effects brought by the technical solutions of the embodiments are not described in detail herein.
Referring to fig. 6, fig. 6 is a block diagram illustrating a first embodiment of a fluid supply skid failure analysis apparatus according to the present invention.
As shown in fig. 6, the device for analyzing a liquid supply skid fault according to the embodiment of the present invention includes:
the data monitoring module 10 is used for performing operation monitoring on each module of the target liquid supply sledge to obtain original monitoring data corresponding to each module;
the feature extraction module 20 is configured to perform feature extraction on the original monitoring data, so as to obtain a data feature value corresponding to each original monitoring data;
a threshold comparison module 30, configured to compare each of the data feature values with a monitoring threshold corresponding to each of the modules;
the fault analysis module 40 is configured to determine operation state information of each module based on the comparison result, and perform fault analysis on the target liquid supply sledge based on the operation state information;
and the fault early warning module 50 is used for carrying out early warning based on the fault analysis result of the target liquid supply sledge.
Further, the fault analysis module 40 is further configured to determine a difference between the data characteristic value and the monitoring threshold value based on the comparison result; judging whether the difference value is within a preset error range or not; if the difference value is not in the preset error range, inputting the difference value into a pre-constructed operation analysis model to obtain operation state information of each module, and performing fault analysis on the target liquid supply sledge based on the operation state information; if the difference value is within a preset error range, determining difference value fluctuation trend information based on the operation monitoring result of the target liquid supply sledge, inputting the difference value fluctuation trend information into the operation analysis model to obtain operation trend information of each module, and performing fault analysis on the target liquid supply sledge based on the operation trend information.
Further, the liquid supply sledge fault analysis device further includes:
the model building module 60 is configured to obtain historical fault data and expert data of the target liquid supply sledge; constructing a training set based on the historical fault data and expert data; and training the original model based on the training set to obtain an operation analysis model.
Further, the feature extraction module 20 is further configured to aggregate the original monitoring data corresponding to each module, so as to obtain the aggregated original monitoring data; and carrying out feature extraction on the aggregated original monitoring data based on a pre-constructed feature library to obtain data feature values corresponding to the original monitoring data.
Further, the feature extraction module 20 is further configured to perform noise reduction processing on the original monitoring data corresponding to each module, so as to obtain candidate data corresponding to each module; extracting signal characteristics of original monitoring data corresponding to each module to obtain signal characteristic information; and carrying out aggregation processing on the original monitoring data corresponding to each module based on the signal characteristic information to obtain the aggregated original monitoring data.
Further, the raw monitoring data includes image monitoring data; the liquid supply sledge fault analysis device further comprises:
the image monitoring module 70 is configured to perform image feature extraction on the image monitoring data to obtain image feature vectors corresponding to each module; acquiring initial feature vectors corresponding to the modules based on a pre-constructed image feature library; comparing the image feature vector with the initial feature vector to obtain image feature difference information; and performing fault analysis on the target liquid supply sledge based on the image characteristic difference information.
Further, the liquid supply sledge fault analysis device further includes:
the threshold correction module 80 is configured to obtain a factory initial threshold of a target liquid supply sledge and historical operation information of the target liquid supply sledge; determining a current performance parameter of the target liquid supply skid based on the historical operating information; collecting the service environment information of the target liquid supply sledge; and correcting the initial threshold value of the factory based on the current performance parameter and the using environment information to obtain a monitoring threshold value.
According to the method, through operation monitoring of each module of a target liquid supply sledge, original monitoring data corresponding to each module are obtained, feature extraction is conducted on the original monitoring data, data feature values corresponding to the original monitoring data are obtained, the data feature values are compared with monitoring threshold values corresponding to the modules, operation state information of the modules is determined based on the comparison result, fault analysis is conducted on the target liquid supply sledge based on the operation state information, and early warning is conducted based on fault analysis results of the target liquid supply sledge; according to the invention, the monitoring data of each module of the target liquid supply sledge is subjected to feature extraction, and each data feature value is compared with the monitoring threshold value corresponding to each module, so that the running state information of each module is determined, and therefore, whether the target liquid supply sledge has a fault or not is accurately analyzed, the fault of the liquid supply sledge is timely and accurately detected, the timeliness of fault detection is ensured, the timely fault early warning is realized, and the potential safety hazard caused by untimely fault detection is avoided.
It should be understood that the foregoing is illustrative only and is not limiting, and that in specific applications, those skilled in the art may set the invention as desired, and the invention is not limited thereto.
It should be noted that the above-described working procedure is merely illustrative, and does not limit the scope of the present invention, and in practical application, a person skilled in the art may select part or all of them according to actual needs to achieve the purpose of the embodiment, which is not limited herein.
In addition, technical details not described in detail in the present embodiment may refer to the method for analyzing a failure of the liquid supply sledge provided in any embodiment of the present invention, which is not described herein.
Furthermore, it should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. Read Only Memory)/RAM, magnetic disk, optical disk) and including several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (10)
1. The liquid supply sledge fault analysis method is characterized by comprising the following steps:
performing operation monitoring on each module of the target liquid supply sledge to obtain original monitoring data corresponding to each module;
extracting the characteristics of the original monitoring data to obtain data characteristic values corresponding to the original monitoring data;
comparing each data characteristic value with a monitoring threshold value corresponding to each module;
determining running state information of each module based on the comparison result, and performing fault analysis on the target liquid supply sledge based on the running state information;
and carrying out early warning based on the fault analysis result of the target liquid supply sledge.
2. The fluid supply skid fault analysis method of claim 1, wherein determining operational status information for each of the modules based on the comparison results and performing fault analysis on the target fluid supply skid based on the operational status information comprises:
determining a difference value between the data characteristic value and the monitoring threshold value based on the comparison result;
judging whether the difference value is within a preset error range or not;
if the difference value is not in the preset error range, inputting the difference value into a pre-built operation analysis model to obtain operation state information of each module, and carrying out fault analysis on the target liquid supply sledge based on the operation state information, wherein the operation analysis model is built based on expert data and historical fault data of the target liquid supply sledge;
if the difference value is within a preset error range, determining difference value fluctuation trend information based on the operation monitoring result of the target liquid supply sledge, inputting the difference value fluctuation trend information into the operation analysis model to obtain operation trend information of each module, and performing fault analysis on the target liquid supply sledge based on the operation trend information.
3. The fluid supply skid fault analysis method of claim 2, wherein said inputting said difference value into a pre-constructed operational analysis model further comprises:
acquiring historical fault data and expert data of a target liquid supply sledge;
constructing a training set based on the historical fault data and expert data;
and training the original model based on the training set to obtain an operation analysis model.
4. The method of claim 1, wherein the performing feature extraction on the raw monitoring data to obtain data feature values corresponding to the raw monitoring data comprises:
carrying out aggregation treatment on the original monitoring data corresponding to each module to obtain the aggregated original monitoring data;
and carrying out feature extraction on the aggregated original monitoring data based on a pre-constructed feature library to obtain data feature values corresponding to the original monitoring data.
5. The method of claim 4, wherein the aggregating the raw monitoring data corresponding to each module to obtain aggregated raw monitoring data comprises:
extracting signal characteristics of original monitoring data corresponding to each module to obtain signal characteristic information;
and carrying out aggregation processing on the original monitoring data corresponding to each module based on the signal characteristic information to obtain the aggregated original monitoring data.
6. The fluid supply skid fault analysis method of claim 1, wherein the raw monitoring data comprises image monitoring data; the liquid supply sledge fault analysis method comprises the following steps:
extracting image features of the image monitoring data to obtain image feature vectors corresponding to the modules;
acquiring initial feature vectors corresponding to the modules based on a pre-constructed image feature library;
comparing the image feature vector with the initial feature vector to obtain image feature difference information;
and performing fault analysis on the target liquid supply sledge based on the image characteristic difference information.
7. The fluid supply skid fault analysis method of claim 1, wherein before comparing each of the data characteristic values with the monitoring threshold value corresponding to each of the modules, further comprising:
acquiring a factory initial threshold value of a target liquid supply sledge and historical operation information of the target liquid supply sledge;
determining a current performance parameter of the target liquid supply skid based on the historical operating information;
collecting the service environment information of the target liquid supply sledge;
and correcting the initial threshold value of the factory based on the current performance parameter and the using environment information to obtain a monitoring threshold value.
8. A liquid supply skid fault analysis device, characterized in that the liquid supply skid fault analysis device comprises:
the data monitoring module is used for performing operation monitoring on each module of the target liquid supply sledge to obtain original monitoring data corresponding to each module;
the feature extraction module is used for carrying out feature extraction on the original monitoring data to obtain data feature values corresponding to the original monitoring data;
the threshold value comparison module is used for comparing each data characteristic value with a monitoring threshold value corresponding to each module;
the fault analysis module is used for determining the running state information of each module based on the comparison result and carrying out fault analysis on the target liquid supply sledge based on the running state information;
and the fault early warning module is used for carrying out early warning based on the fault analysis result of the target liquid supply sledge.
9. A fluid supply skid failure analysis apparatus, the fluid supply skid failure analysis apparatus comprising: a memory, a processor, and a fluid supply skid failure analysis program stored on the memory and executable on the processor, the fluid supply skid failure analysis program configured to implement the fluid supply skid failure analysis method of any one of claims 1 to 7.
10. A storage medium, wherein a liquid supply skid failure analysis program is stored on the storage medium, and when executed by a processor, the liquid supply skid failure analysis program implements the liquid supply skid failure analysis method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311776691.XA CN117703346A (en) | 2023-12-21 | 2023-12-21 | Liquid supply skid fault analysis method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311776691.XA CN117703346A (en) | 2023-12-21 | 2023-12-21 | Liquid supply skid fault analysis method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117703346A true CN117703346A (en) | 2024-03-15 |
Family
ID=90160509
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311776691.XA Pending CN117703346A (en) | 2023-12-21 | 2023-12-21 | Liquid supply skid fault analysis method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117703346A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118815433A (en) * | 2024-09-20 | 2024-10-22 | 克拉玛依国勘石油技术有限公司 | A troubleshooting method, system, equipment, medium and product for profile control construction |
-
2023
- 2023-12-21 CN CN202311776691.XA patent/CN117703346A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118815433A (en) * | 2024-09-20 | 2024-10-22 | 克拉玛依国勘石油技术有限公司 | A troubleshooting method, system, equipment, medium and product for profile control construction |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12184669B2 (en) | Systems and methods for malicious attack detection in phasor measurement unit data | |
| CN117074852A (en) | Power distribution network electric energy monitoring and early warning management method and system | |
| CN118035814A (en) | Equipment status fault early warning method and system based on digital twin field data analysis | |
| CN113570473B (en) | Equipment fault monitoring method, device, computer equipment and storage medium | |
| CN114996258B (en) | A method for fault diagnosis of overhead line based on data warehouse | |
| CN118035906A (en) | Main equipment fault diagnosis method and device based on spatiotemporal graph convolutional neural network | |
| CN118484356A (en) | A server status monitoring method and system based on RPA | |
| CN111934903A (en) | Docker container fault intelligent prediction method based on time sequence evolution genes | |
| CN114666117A (en) | Network security situation measuring and predicting method for power internet | |
| CN117703346A (en) | Liquid supply skid fault analysis method, device, equipment and storage medium | |
| CN118199958A (en) | A distributed photovoltaic terminal malicious attack detection method based on dual-domain features | |
| CN113705840A (en) | Equipment predictive maintenance method and device, computer equipment and storage medium | |
| CN116933108A (en) | Substation equipment operation state monitoring method, system, equipment and storage medium | |
| CN116754857A (en) | Fault detection methods and devices for power systems, power systems | |
| CN120449042A (en) | A method and system for analyzing power distribution system faults | |
| CN118193954B (en) | A method and system for detecting abnormal data in distribution network based on edge computing | |
| CN119511869A (en) | An intelligent monitoring and adjustment method, system and device based on digital twin technology | |
| CN118827331A (en) | Automated operation and maintenance method, device, equipment and storage medium | |
| CN115169650B (en) | Equipment health prediction method for big data analysis | |
| CN118408593A (en) | Remote diagnosis method, device and storage medium for electric power equipment | |
| CN118298523A (en) | Inspection task generating device, method and equipment based on abnormal conditions | |
| CN119066991B (en) | A CLCC converter fault location and analysis method, system and device | |
| CN117455124B (en) | Enterprise environmental protection equipment monitoring methods, systems, media and electronic equipment | |
| Tang et al. | Research on Transformer Temperature Warning Algorithm Based on Support Vector Machine | |
| CN118519818B (en) | Deep recursion network-based big data computer system fault detection method |
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 |