CN117674407A - Power grid equipment fault early warning method, device, equipment and storage medium - Google Patents
Power grid equipment fault early warning method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117674407A CN117674407A CN202311482179.4A CN202311482179A CN117674407A CN 117674407 A CN117674407 A CN 117674407A CN 202311482179 A CN202311482179 A CN 202311482179A CN 117674407 A CN117674407 A CN 117674407A
- Authority
- CN
- China
- Prior art keywords
- distribution network
- fault
- power distribution
- data
- network equipment
- 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
- 238000000034 method Methods 0.000 title claims abstract description 51
- 230000007613 environmental effect Effects 0.000 claims abstract description 28
- 238000012544 monitoring process Methods 0.000 claims abstract description 25
- 238000012098 association analyses Methods 0.000 claims abstract description 14
- 238000012549 training Methods 0.000 claims description 91
- 238000012360 testing method Methods 0.000 claims description 50
- 230000002159 abnormal effect Effects 0.000 claims description 19
- 230000008859 change Effects 0.000 claims description 18
- 238000003062 neural network model Methods 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 8
- 238000005457 optimization Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 abstract description 8
- 238000012423 maintenance Methods 0.000 description 21
- 238000007726 management method Methods 0.000 description 12
- 230000000903 blocking effect Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 5
- 238000009423 ventilation Methods 0.000 description 5
- 230000005856 abnormality Effects 0.000 description 4
- 238000010276 construction Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000001681 protective effect Effects 0.000 description 4
- 238000000638 solvent extraction Methods 0.000 description 4
- 206010000117 Abnormal behaviour Diseases 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 3
- 230000008030 elimination Effects 0.000 description 3
- 238000003379 elimination reaction Methods 0.000 description 3
- 238000003672 processing method Methods 0.000 description 3
- 241000196324 Embryophyta Species 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000016507 interphase Effects 0.000 description 2
- 238000007670 refining Methods 0.000 description 2
- 238000013024 troubleshooting Methods 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000013021 overheating Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to the technical field of power system automation, and discloses a power grid equipment fault early warning method, a device, equipment and a storage medium, wherein the method comprises the following steps: monitoring power distribution network equipment to obtain operation condition data of the power distribution network equipment and environmental image data within a certain range; carrying out association analysis on the current influence weight to obtain the current influence weight; inputting the data into a preset running state prediction model to obtain a predicted fault type and a predicted fluctuation value; and when the predicted fluctuation value reaches the corresponding deviation value, performing fault early warning on the power distribution network equipment. Because the power distribution network equipment is monitored in real time, the operation condition data and the environment image data obtained by monitoring are subjected to fault prediction based on the preset operation state prediction model, and fault early warning is carried out when the predicted fluctuation value reaches the deviation value. The situation that equipment faults are difficult to discover by means of manual experience is avoided, potential problems of power distribution network equipment can be effectively discovered in time, and then the equipment fault processing efficiency is improved.
Description
Technical Field
The present invention relates to the field of power system automation technologies, and in particular, to a method, an apparatus, a device, and a storage medium for early warning of a power grid device fault.
Background
In order to improve the running safety and economy of the power distribution network, and assist operation and maintenance personnel of the power distribution network to carry out correct analysis and decision, power distribution network equipment is required to be monitored, and various states of the power distribution network equipment are comprehensively mastered, wherein the fault discovery of the power distribution network equipment is closely related to the running state, the health state and the environmental state of the equipment. To accurately judge and analyze various states of power distribution network equipment, comprehensive information such as power distribution system information, equipment information, environment information and the like is required. And early warning and defect elimination are carried out when the equipment fails.
However, the power grid monitoring signal quantity of the power system is very large, the signal correlation among the monitoring signals and between stations is weak, the power grid equipment fault event analysis and automatic identification technology is imperfect, the operation and maintenance capacity is limited by relying on the traditional operation and maintenance overhaul mode mainly taking manpower as a main part, and the operation and maintenance work requirements of the power grid which are rapidly increased are difficult to meet. Meanwhile, the traditional operation and maintenance overhaul mode is difficult to realize the optimal allocation of resources, the allocation randomness of the operation and detection resources is large, and the operation and detection efficiency is restricted. At present, equipment faults and abnormal events are judged only by means of manual experience, so that equipment faults or abnormal conditions are difficult to timely and effectively find, the timeliness of operation and maintenance work is difficult to guarantee, and the equipment fault processing efficiency is low.
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 power grid equipment fault early warning method, device, equipment and storage medium, and aims to solve the technical problem that equipment fault processing efficiency is low because equipment faults or abnormal conditions are difficult to timely and effectively find by means of manual experience in the prior art.
In order to achieve the above purpose, the present invention provides a power grid equipment fault early warning method, which comprises the following steps:
monitoring power distribution network equipment to obtain operation condition data of the power distribution network equipment and environment image data within a certain range of the power distribution network equipment;
performing association analysis on the operation condition data and the environment image data to obtain current influence weight between the power distribution network equipment and the environment image data;
inputting the operation condition data, the environment image data and the current influence weight into a preset operation state prediction model to obtain a predicted fault type and a predicted fluctuation value;
judging whether the predicted fluctuation value reaches a corresponding deviation value according to the predicted fault type;
And when the predicted fluctuation value reaches a corresponding deviation value, performing fault early warning on the power distribution network equipment according to the operation condition data and the environment image data.
Optionally, before the monitoring the power distribution network device to obtain the operation condition data of the power distribution network device and the environmental image data within a certain range of the power distribution network device, the method further includes:
performing feature extraction on historical operation state data of power distribution network equipment to obtain fault feature data of the power distribution network equipment;
dividing the fault characteristic data and the historical operating state data into a training data set and a test data set;
training the initial neural network model according to the training data set to obtain a training model;
and carrying out parameter optimization on the training model based on the test data set to obtain a preset running state prediction model of the power distribution network equipment.
Optionally, the feature extraction of the historical operation state data of the power distribution network device, after obtaining the fault feature data of the power distribution network device, further includes:
constructing a fault characteristic database corresponding to the power distribution network equipment according to the fault characteristic data and the historical running state data;
Constructing a fault rule comparison library corresponding to the power distribution network equipment based on the fault characteristic data and the operation management rule data of the power distribution network equipment;
correspondingly, the training the initial neural network model according to the training data set to obtain a training model comprises the following steps:
and training the initial neural network model according to the training data set, the fault characteristic database and the fault rule comparison library to obtain a training model.
Optionally, the performing parameter optimization on the training model based on the test data set to obtain a preset running state prediction model of the power distribution network device includes:
inputting the test data set into the training model to obtain a test output result;
judging whether the test output result reaches a preset accuracy rate or not;
and when the test output result does not reach the preset accuracy, updating the bias coefficient of the training model until the test output result reaches the preset accuracy, and taking the training model corresponding to the preset accuracy as a preset running state prediction model of the power distribution network equipment.
Optionally, when the predicted fluctuation value reaches a corresponding deviation value, performing fault early warning on the power distribution network device according to the operation condition data and the environmental image data, including:
Under the condition that the predicted fluctuation value reaches a corresponding deviation value, collecting load operation data and load operation indexes of the power distribution network transformer;
determining the execution form of the power distribution network transformer according to the load operation data;
judging whether the execution form belongs to a preset fault change form according to the load operation index;
and when the execution form belongs to the fault change form, carrying out fault early warning on the power distribution network equipment based on the load operation data.
Optionally, when the execution mode belongs to the fault change mode, performing fault early warning on the power distribution network equipment based on the load operation data, including:
when the execution form belongs to the fault change form, acquiring a line load rate and an electric medium number of a line where the power distribution network equipment is located;
performing problem positioning on the power distribution network equipment according to the line load rate, the electrical betweenness and the load operation data to obtain a fault position corresponding to the power distribution network equipment;
and carrying out fault early warning on the power distribution network equipment based on the fault position.
Optionally, the determining whether the predicted fluctuation value reaches a corresponding deviation value according to the predicted fault type includes:
When the predicted fluctuation value is within a first preset deviation value, judging that the power distribution network equipment is in a normal running state;
when the predicted fluctuation value reaches a second preset deviation value, judging that the power distribution network equipment is in an abnormal running state;
when the predicted fluctuation value reaches a third preset deviation value, judging that the power distribution network equipment is in a fault running state;
correspondingly, when the predicted fluctuation value reaches a corresponding deviation value, performing fault early warning on the power distribution network equipment according to the operation condition data and the environment image data, including:
and when the predicted fluctuation value reaches the second preset deviation value or the third preset deviation value, performing fault early warning on the power distribution network equipment according to the operation condition data and the environment image data.
In addition, in order to achieve the above purpose, the present invention also provides a power grid equipment fault early warning device, which comprises:
the data monitoring module is used for monitoring the power distribution network equipment and obtaining the operation condition data of the power distribution network equipment and the environmental image data within a certain range of the power distribution network equipment;
the association analysis module is used for carrying out association analysis on the operation condition data and the environment image data to obtain the current influence weight between the power distribution network equipment and the environment image data;
The model prediction module is used for inputting the operation condition data, the environment image data and the current influence weight into a preset operation state prediction model to obtain a prediction fault type and a prediction fluctuation value;
the deviation judging module is used for judging whether the predicted fluctuation value reaches a corresponding deviation value according to the predicted fault type;
and the fault early warning module is used for carrying out fault early warning on the power distribution network equipment according to the operation condition data and the environment image data when the predicted fluctuation value reaches the corresponding deviation value.
In addition, in order to achieve the above purpose, the present invention also provides a power grid equipment fault early warning device, the device includes: the system comprises a memory, a processor and a grid equipment fault early warning program stored on the memory and capable of running on the processor, wherein the grid equipment fault early warning program is configured to realize the steps of the grid equipment fault early warning method.
In addition, in order to achieve the above objective, the present invention further provides a storage medium, on which a power grid equipment fault early warning program is stored, which when executed by a processor, implements the steps of the power grid equipment fault early warning method as described above.
According to the invention, through monitoring the power distribution network equipment, the operation condition data of the power distribution network equipment and the environmental image data within a certain range of the power distribution network equipment are obtained; performing association analysis on the operation condition data and the environment image data to obtain current influence weight between the power distribution network equipment and the environment image data; inputting the operation condition data, the environment image data and the current influence weight into a preset operation state prediction model to obtain a predicted fault type and a predicted fluctuation value; finally, judging whether the predicted fluctuation value reaches a corresponding deviation value according to the predicted fault type; and when the predicted fluctuation value reaches a corresponding deviation value, performing fault early warning on the power distribution network equipment according to the operation condition data and the environment image data. Because the power distribution network equipment is monitored in real time, the operation condition data and the environment image data obtained by monitoring are subjected to fault prediction based on the preset operation state prediction model, and fault early warning is carried out when the predicted fluctuation value reaches the deviation value. The situation that equipment faults are difficult to discover in time by means of manual experience is avoided, potential problems of power distribution network equipment can be discovered effectively in time, and then equipment fault processing efficiency is improved.
Drawings
FIG. 1 is a schematic structural diagram of a power grid equipment fault early warning device in 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 power grid equipment fault early warning method according to the present invention;
FIG. 3 is a schematic flow chart of a second embodiment of a power grid equipment fault early warning method according to the present invention;
FIG. 4 is a schematic flow chart of a third embodiment of a power grid equipment fault early warning method according to the present invention;
fig. 5 is a block diagram of a first embodiment of a power grid equipment fault early warning device 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 power grid equipment fault early warning device in a hardware operation environment according to an embodiment of the present invention.
As shown in fig. 1, the power grid equipment fault early warning device 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.
It will be appreciated by those skilled in the art that the structure shown in fig. 1 does not constitute a limitation of the grid plant fault warning device, and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components.
As shown in fig. 1, an operating system, a network communication module, a user interface module, and a grid device fault warning program may be included in the memory 1005 as one storage medium.
In the power grid equipment fault early warning 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 power grid equipment fault early-warning device can be arranged in the power grid equipment fault early-warning device, and the power grid equipment fault early-warning device calls the power grid equipment fault early-warning program stored in the memory 1005 through the processor 1001 and executes the power grid equipment fault early-warning method provided by the embodiment of the invention.
The embodiment of the invention provides a power grid equipment fault early warning method, and referring to fig. 2, fig. 2 is a flow chart of a first embodiment of the power grid equipment fault early warning method.
In this embodiment, the power grid equipment fault early warning method includes the following steps:
step S10: and monitoring the power distribution network equipment to obtain the operation condition data of the power distribution network equipment and the environment image data within a certain range of the power distribution network equipment.
It should be noted that, the execution body of the method of the embodiment may be an electronic device having the functions of device monitoring, data prediction and fault early warning, for example, the above-mentioned power grid device fault early warning device, which is not limited in this embodiment. The present embodiment and the following embodiments will be specifically described herein with reference to the foregoing power grid equipment failure warning device (abbreviated as warning device).
It is understood that a distribution network device is a device used in a power system for distributing electrical power energy to different customers or devices, such as transformers, circuit breakers, switching devices, distribution boards, power metering devices, etc. Can be used to transfer electrical energy from a power source (e.g., a power plant or substation) to various end users, buildings, factories, or equipment to help ensure safe, reliable, and efficient power supply.
It should be understood that the operating condition data are information and parameters related to the operating state and performance of various electrical devices in the power distribution network, such as voltage and current data, temperature data, load data, switch state data, electrical energy metering data, and the like. The operating condition data can be used for monitoring the normal operation and potential problems of the power distribution system.
It is understood that the environmental image data is acquired image or video data related to the surrounding environment of the power distribution network device, including visual information of the location of the device, the surrounding environment, and potential problems, such as buildings, roads, vegetation and other geographic features surrounding the device, the presence or absence of obstructions, ventilation conditions, protective measures, and the like. The fault elimination of the power distribution network equipment can be further improved through the environment image data.
In a specific implementation, the early warning device can monitor the power distribution network device in real time to obtain the operation condition data of the power distribution network device and the environmental image data within a certain range of the power distribution network device, such as voltage and current data, temperature data, load data, switch state data, electric energy metering data and the like, for example, whether shielding objects, ventilation conditions, protective measures and the like exist or not, so that the fault elimination of the power distribution network device is further improved through the environmental image data.
Step S20: and performing association analysis on the operation condition data and the environment image data to obtain the current influence weight between the power distribution network equipment and the environment image data.
It should be noted that the current impact weight is the extent to which the operation and performance of the power distribution network equipment are affected by the environment.
It can be understood that the distribution network equipment faults can be classified into symmetrical faults, asymmetrical faults, interphase faults and grounding faults. The reasons for the failure of the distribution network equipment can include equipment insulation failure, aging, lightning strike, wind blowing, misoperation, birds and beasts, and the like. For example, if the environmental image data shows that there is a lot of weeds and vegetation around the device, this may affect the ventilation of the device and thus the temperature of the device. Accordingly, this situation may increase the risk of overheating the device. In this case, the impact weight of the ambient image data is high, since it is directly related to the safe operation of the device. Therefore, the environment image data can be associated with the operation of the power distribution network equipment, and the accuracy of equipment fault monitoring is further improved.
Step S30: and inputting the operation condition data, the environment image data and the current influence weight into a preset operation state prediction model to obtain a predicted fault type and a predicted fluctuation value.
The preset operation state prediction model is a preset model for predicting an operation state of the power distribution network device. The operational state of the device that may occur at some point in the future may be predicted by analyzing historical data, real-time monitoring data, and other relevant information.
It is understood that the predicted fault type is a model predicted type of fault in the distribution network equipment, such as a symmetrical fault, an asymmetrical fault, an interphase fault, a ground fault, etc.
The prediction fluctuation value is a fluctuation degree or fluctuation range of the model prediction power distribution network equipment failure, and the possibility of the power distribution network equipment failure can be judged through the prediction fluctuation value so as to improve timeliness of operation and maintenance.
In a specific implementation, the early warning device may perform association analysis on the operation condition data and the environmental image data, so as to obtain a current impact weight between the power distribution network device and the environmental image data. And then inputting the operation condition data, the environment image data and the current influence weight into a preset operation state prediction model to obtain a predicted fault type and a predicted fluctuation value. The environmental image data is associated with the operation of the power distribution network equipment, the accuracy of equipment fault monitoring is further improved, and meanwhile the possibility of the power distribution network equipment fault can be judged by predicting the fluctuation value, so that the timeliness of operation and maintenance is improved.
Step S40: and judging whether the predicted fluctuation value reaches a corresponding deviation value according to the predicted fault type.
Step S50: and when the predicted fluctuation value reaches a corresponding deviation value, performing fault early warning on the power distribution network equipment according to the operation condition data and the environment image data.
The deviation value is a difference or degree of deviation between the predicted fluctuation value corresponding to the different predicted fault types and the reference value. The abnormality or unusual of the predicted fault type of the distribution network equipment can be evaluated by the deviation value in order to evaluate the potential problem or abnormal situation.
In a specific implementation, the early warning device can judge whether the predicted fluctuation value reaches a corresponding deviation value according to the predicted fault type, and when the predicted fluctuation value reaches the corresponding deviation value, the early warning device performs fault early warning on the power distribution network device according to the operation condition data and the environment image data. The abnormality or the unusual of the predicted fault type of the power distribution network equipment can be evaluated through the deviation value, so that potential problems or abnormal conditions can be evaluated, the accuracy of fault early warning is improved, and the occurrence of invalid fault early warning is avoided.
Further, in the present embodiment, step S40 includes: when the predicted fluctuation value is within a first preset deviation value, judging that the power distribution network equipment is in a normal running state; when the predicted fluctuation value reaches a second preset deviation value, judging that the power distribution network equipment is in an abnormal running state; when the predicted fluctuation value reaches a third preset deviation value, judging that the power distribution network equipment is in a fault running state; correspondingly, the step S50 includes: and when the predicted fluctuation value reaches the second preset deviation value or the third preset deviation value, performing fault early warning on the power distribution network equipment according to the operation condition data and the environment image data.
It should be noted that the first preset deviation value, the second preset deviation value, and the third preset deviation value are preset deviation thresholds, and the different deviation thresholds represent different operation conditions of the power distribution network device, for example, the deviation values may include: within 0.5%, within 0.5-2.5%, over 2.5%, etc., this is not a limitation of the present embodiment.
In a specific implementation, the early warning device can compare a predicted fluctuation value of the running state of the power grid device with actual data of the running state of the power grid device and perform deviation statistics; when the predicted fluctuation value is within 0.5%, judging that the power distribution network equipment is in a normal running state; when the predicted fluctuation value is within 0.5-2.5%, judging that the power distribution network equipment is in an abnormal running state; and when the predicted fluctuation value exceeds 2.5% in majority, judging that the power distribution network equipment is in a fault state. Therefore, the normal fluctuation of the equipment is considered, the state of the power distribution network equipment can be judged according to different preset deviation values, early warning and reminding are carried out when faults are most likely to occur, invalid fault early warning is avoided, and the effectiveness of the fault early warning is improved.
The early warning device in this embodiment can monitor the power distribution network device in real time, and obtain the operation condition data of the power distribution network device and the environmental image data within a certain range of the power distribution network device, such as voltage and current data, temperature data, load data, switch state data, electric energy metering data, and the like, for example, whether a shielding object, a ventilation condition, a protective measure, and the like exist, so as to further improve the troubleshooting of the power distribution network device through the environmental image data. And performing association analysis on the operation condition data and the environment image data to obtain the current influence weight between the power distribution network equipment and the environment image data. And then inputting the operation condition data, the environment image data and the current influence weight into a preset operation state prediction model to obtain a predicted fault type and a predicted fluctuation value. The environmental image data is associated with the operation of the power distribution network equipment, the accuracy of equipment fault monitoring is further improved, and meanwhile the possibility of the power distribution network equipment fault can be judged by predicting the fluctuation value, so that the timeliness of operation and maintenance is improved. And finally judging whether the predicted fluctuation value reaches a corresponding deviation value according to the predicted fault type, and carrying out fault early warning on the power distribution network equipment according to the operation condition data and the environment image data when the predicted fluctuation value reaches the corresponding deviation value. The abnormality or the unusual of the predicted fault type of the power distribution network equipment can be evaluated through the deviation value, so that potential problems or abnormal conditions can be evaluated, the accuracy of fault early warning is improved, and the occurrence of invalid fault early warning is avoided. Because the power distribution network equipment is monitored in real time, fault prediction is carried out on the operation condition data and the environment image data obtained through monitoring based on the preset operation state prediction model, and fault early warning is carried out when the predicted fluctuation value reaches the deviation value. The situation that equipment faults are difficult to discover in time by means of manual experience is avoided, potential problems of power distribution network equipment can be discovered effectively in time, and then equipment fault processing efficiency is improved.
Referring to fig. 3, fig. 3 is a flowchart of a second embodiment of the power grid equipment fault early warning method according to the present invention.
Based on the first embodiment, in this embodiment, before step S10, the method further includes:
step S01: and performing feature extraction on the historical running state data of the power distribution network equipment to obtain fault feature data of the power distribution network equipment.
It should be noted that the historical operation status data is data recorded by various parameters, indexes and status information of the power distribution network equipment in the past period of time, such as voltage and current data, historical event records, maintenance records, and the like, and by learning and training these data, the performance, change and possible fault signs of the equipment can be analyzed.
It is understood that the fault characteristic data is information describing the fault state of the equipment, such as fluctuation amplitude, abnormal temperature, unbalanced current, etc., obtained by extracting characteristics of the historical operating state data, so as to help to quickly detect the signs and abnormal behaviors of the fault of the equipment by extracting specific modes or characteristics in the historical operating state data.
Step S02: and dividing the fault characteristic data and the historical operating state data into a training data set and a test data set.
It should be noted that the data may be divided into training data sets and test data sets to improve the performance and generalization ability of the model. The partitioning may include random partitioning, time series partitioning, hierarchical sampling partitioning, etc., which the present embodiment is not limited to.
Step S03: and training the initial neural network model according to the training data set to obtain a training model.
Step S04: and carrying out parameter optimization on the training model based on the test data set to obtain a preset running state prediction model of the power distribution network equipment.
In a specific implementation, the early warning device can perform feature extraction on historical operation state data of the power distribution network device, obtain fault feature data of the power distribution network device, such as fluctuation amplitude, abnormal temperature, unbalanced current and the like, and is beneficial to rapidly detecting signs and abnormal behaviors of the device fault by extracting specific modes or features in the historical operation state data. The data may then be divided into training data sets and test data sets to improve the performance and generalization ability of the model. Finally, in the training stage, the training data set can be used for fitting parameters and weights of the model for training, and a training model is obtained. In the test stage, the performance of the model can be evaluated by using a test data set, and parameter optimization and weight adjustment are performed to obtain a preset running state prediction model of the power distribution network equipment, so that the prediction accuracy of the model is improved.
Further, after step S01, the method in this embodiment further includes: constructing a fault characteristic database corresponding to the power distribution network equipment according to the fault characteristic data and the historical running state data; constructing a fault rule comparison library corresponding to the power distribution network equipment based on the fault characteristic data and the operation management rule data of the power distribution network equipment; correspondingly, the step S03 includes: and training the initial neural network model according to the training data set, the fault characteristic database and the fault rule comparison library to obtain a training model.
The fault characteristic database is a database for recording and storing fault related characteristics of power distribution network equipment, and includes various data related to faults, such as equipment sensor data, operation logs, maintenance records, and the like. By establishing and maintaining the fault characteristic database, the historical data can be used for carrying out fault analysis and prediction, and the reliability and maintenance efficiency of the equipment are improved. Meanwhile, rich training data is provided, and the construction and training of an accurate preset running state prediction model are facilitated.
It is understood that the operation management rule data is data of related rules, standards or guidelines for guiding and standardizing operation and management of the power distribution network equipment, such as safety operation rules, load management guidelines, equipment inspection and maintenance requirements, etc. The operation management rule data can enable the model to learn the operation rule of the safety of the power distribution network equipment, ensure the safe operation of the power distribution network and improve the reliability of the model.
It should be understood that the fault rule comparison library is a comparison database for recording and managing fault data and operation management rule data. The purpose of establishing the fault rule comparison library is to analyze the power grid equipment faults aiming at the operation information. The establishment of the fault rule comparison library requires a processing method for collecting power grid abnormal events, and comprehensively analyzes and refines the power grid abnormal events to form the fault rule comparison library.
In a specific implementation, the early warning device can construct a fault characteristic database corresponding to the power distribution network device according to the fault characteristic data and the historical running state data; by establishing and maintaining the fault characteristic database, the historical data can be used for carrying out fault analysis and prediction, and the reliability and maintenance efficiency of the equipment are improved. Meanwhile, rich training data is provided, and the construction and training of an accurate preset running state prediction model are facilitated. And then collecting a processing method of the power grid abnormal event, comprehensively analyzing and refining, and constructing a fault rule comparison library corresponding to the power distribution network equipment based on the fault characteristic data and the operation management rule data of the power distribution network equipment. And finally training the initial neural network model according to the training data set, the fault characteristic database and the fault rule comparison library to obtain a training model. Therefore, the model can learn the safe operation rule of the power distribution network equipment through the operation management rule data, the safe operation of the power distribution network is ensured, and the reliability of the model is improved.
Further, in the present embodiment, step S04 includes: inputting the test data set into the training model to obtain a test output result; judging whether the test output result reaches a preset accuracy rate or not; and when the test output result does not reach the preset accuracy, updating the bias coefficient of the training model until the test output result reaches the preset accuracy, and taking the training model corresponding to the preset accuracy as a preset running state prediction model of the power distribution network equipment.
It should be noted that the preset accuracy is used for evaluating a preset threshold of the accuracy of the model. In some cases, such as when there is a fault class imbalance in the test output results or the predicted data is far from being identical, it may be indicative of lower model performance.
It is understood that the Bias Coefficient (Bias Coefficient) is a parameter used to adjust the model prediction result in model learning. In the model, the bias coefficients represent predicted values of the dependent variable (or target variable) when the independent variable (or feature) is zero. By adjusting the bias coefficient, the training model can better fit the data, so that the prediction result of the model is as close as possible to the actual observation value, and the prediction accuracy is improved.
For example, the bias factor may be determined by the value to be fitted of the test data set, the mean of the values to be fitted, the fitting value of the training data set, the data size of the test data set, and the number of values to be fitted, for example:
wherein b is the value to be fitted of the test dataset,the method is characterized in that a is the mean value of the values to be fitted, a is the fitting value of a training data set, n is the size of a test data set, i is the number of the values to be fitted, and z is the bias coefficient of the model.
In a specific implementation, after training to obtain a training model, the performance of the model is also evaluated. At this time, the early warning device can input the test data set into the training model, and judges whether the test output result reaches the preset accuracy rate. For example, when there is a failure class imbalance in the test output results or the predicted data is far from being balanced, the representative model performance is low. At this time, the training model can be updated according to the bias coefficient until the test output result reaches the preset accuracy, and at this time, the performance of the representative model is qualified and reaches the expected value. And taking the training model corresponding to the preset accuracy as a preset running state prediction model of the power distribution network equipment. Therefore, the training model can better fit data by adjusting the bias coefficient, so that the prediction result of the model is as close as possible to the actual observation value, and the prediction accuracy is improved.
The early warning device of the embodiment can perform feature extraction on historical operation state data of the power distribution network device, obtain fault feature data of the power distribution network device, such as fluctuation amplitude, abnormal temperature, unbalanced current and the like, and is beneficial to rapidly detecting signs and abnormal behaviors of device faults by extracting specific modes or features in the historical operation state data. The data may then be divided into training data sets and test data sets to improve the performance and generalization ability of the model. Finally, in the training stage, the training data set can be used for fitting parameters and weights of the model for training, and a training model is obtained. In the test stage, the performance of the model can be evaluated by using a test data set, and parameter optimization and weight adjustment are performed to obtain a preset running state prediction model of the power distribution network equipment, so that the prediction accuracy of the model is improved. Further, the early warning device can also construct a fault characteristic database corresponding to the power distribution network device according to the fault characteristic data and the historical running state data; by establishing and maintaining the fault characteristic database, the historical data can be used for carrying out fault analysis and prediction, and the reliability and maintenance efficiency of the equipment are improved. Meanwhile, rich training data is provided, and the construction and training of an accurate preset running state prediction model are facilitated. And then collecting a processing method of the power grid abnormal event, comprehensively analyzing and refining, and constructing a fault rule comparison library corresponding to the power distribution network equipment based on the fault characteristic data and the operation management rule data of the power distribution network equipment. And finally training the initial neural network model according to the training data set, the fault characteristic database and the fault rule comparison library to obtain a training model. Therefore, the model can learn the safe operation rule of the power distribution network equipment through the operation management rule data, the safe operation of the power distribution network is ensured, and the reliability of the model is improved. Further, after training to obtain a training model, the performance of the model is also evaluated. At this time, the early warning device can input the test data set into the training model, and judges whether the test output result reaches the preset accuracy rate. For example, when there is a failure class imbalance in the test output results or the predicted data is far from being balanced, the representative model performance is low. At this time, the training model can be updated according to the bias coefficient until the test output result reaches the preset accuracy, and at this time, the performance of the representative model is qualified and reaches the expected value. And taking the training model corresponding to the preset accuracy as a preset running state prediction model of the power distribution network equipment. Therefore, the training model can better fit data by adjusting the bias coefficient, so that the prediction result of the model is as close as possible to the actual observation value, and the prediction accuracy is improved.
Referring to fig. 4, fig. 4 is a flowchart of a third embodiment of the power grid equipment fault early warning method according to the present invention.
Based on the above embodiments, in this embodiment, the step S50 includes:
step S51: and under the condition that the predicted fluctuation value reaches a corresponding deviation value, collecting load operation data and load operation indexes of the power distribution network transformer.
Step S52: and determining the execution form of the power distribution network transformer according to the load operation data.
The load operation data is data for recording and tracking the power load condition carried by each device (such as a transformer, a switch, a protection device and the like) in the power distribution network, such as power data, the load size carried by the power distribution network transformer, and the power supply quality condition. The load state, the power consumption condition and the system load characteristic of each device can be clearly known through the load operation data, so that reliable power supply and efficient operation of a power grid are ensured.
It is understood that load operation indicators refer to various performance indicators, such as load rates, peak loads, load balances, overload rates, etc., used to evaluate the load operation conditions of a power distribution network transformer. The system can be ensured to stably operate and perform fault diagnosis through the load operation index, so that the stability of the power distribution network equipment is improved.
It is understood that the implementation forms of the distribution network transformer include a power supply form and a power blocking form. The power supply mode is the current mode of the power distribution network transformer, and can actually comprise the mode of supplying power to the load of the power grid and the mode of supplying power to the primary side of the power distribution network transformer. The power-blocking mode is that the power distribution network transformer does not supply power to the load of the power grid, and the primary side of the power distribution network transformer is not transmitted, and the power distribution network transformer is in an isolated state and is not connected to any device.
In a specific implementation, when the predicted fluctuation value reaches a corresponding deviation value, the early warning device can acquire load operation data and load operation indexes of the power distribution network transformer, such as power data, load size carried by the power distribution network transformer, power supply quality condition, load rate, peak load, load balance, overload rate and the like, and can clearly know the load state, power consumption condition and system load characteristics of each device through the load operation data, so that stable operation and fault diagnosis of the system are ensured. And then determining the execution form, such as a power supply form and a power blocking form, of the power distribution network transformer according to the load operation data.
Step S53: judging whether the execution form belongs to a preset fault change form according to the load operation index.
Step S54: and when the execution form belongs to the fault change form, carrying out fault early warning on the power distribution network equipment based on the load operation data.
The fault change pattern is a corresponding fault pattern in the execution pattern, for example, the power is not supplied to the grid load, or the power supply process is in a blocking state.
In a specific implementation, the early warning device may determine, according to the load operation index, whether the execution form belongs to a preset fault variation form. And carrying out fault early warning on the power distribution network equipment based on the load operation data when the power distribution network transformer does not supply power to the power grid load or the power supply process is in a blocking state. Therefore, fault early warning can be carried out on the power distribution network equipment corresponding to the power distribution network transformer according to the corresponding power supply mode and the power blocking mode of the power distribution network transformer, so that the early warning accuracy is further improved.
Further, in the present embodiment, step S54 includes: when the execution form belongs to the fault change form, acquiring a line load rate and an electric medium number of a line where the power distribution network equipment is located; performing problem positioning on the power distribution network equipment according to the line load rate, the electrical betweenness and the load operation data to obtain a fault position corresponding to the power distribution network equipment; and carrying out fault early warning on the power distribution network equipment based on the fault position.
It should be noted that, the line load rate is the ratio of the actual load of the line where the power distribution network equipment is located to the rated load thereof at a certain moment, and can be used for measuring the load degree of the line where the power distribution network equipment is located.
It is understood that electrical bets are indicators used to evaluate the importance and impact of nodes in power distribution network equipment. The electrical betters may be used to characterize the ability of current or power through a distribution network equipment node to propagate throughout the distribution network equipment network. Nodes with high electrical betters have a greater impact in the distribution network equipment network, which may lead to instability of the distribution network equipment system if they fail. The system can be reasonably controlled through the line load rate to ensure the stable operation of the system, and the system structure can be better known through the electrical betters, so that reasonable operation scheduling and equipment maintenance are performed.
In a specific implementation, when the execution form belongs to the fault change form, the early warning equipment can acquire the line load rate and the electrical betweenness of the line where the power distribution network equipment is located; the system can be reasonably controlled through the line load rate so as to ensure the stable operation of the system, and the system structure can be better known through the electric betweenness. And then, carrying out problem positioning on the power distribution network equipment according to the line load rate, the electrical betters and the load operation data, for example, when the equipment fails, disconnecting or switching part of the equipment by a reverse tracing method, gradually reducing the fault range, and finally determining the fault position. And finally, carrying out fault early warning on the power distribution network equipment based on the fault position, so that the structure of the power distribution network equipment system is better defined through the line load rate and the electrical betweenness, reasonable operation scheduling and equipment maintenance are carried out, and the efficiency of fault maintenance is improved.
In this embodiment, when the predicted fluctuation value reaches the corresponding deviation value, the early warning device may collect load operation data and load operation indexes of the power distribution network transformer, for example, power data, a load size carried by the power distribution network transformer, a power quality condition, a load rate, a peak load, a load balance, an overload rate, and the like, and through the load operation data, the load state, the power consumption condition, and the system load characteristics of each device may be clearly known, so as to ensure stable operation and fault diagnosis of the system. And then determining the execution form, such as a power supply form and a power blocking form, of the power distribution network transformer according to the load operation data. The early warning device can judge whether the execution form belongs to a preset fault change form according to the load operation index. And carrying out fault early warning on the power distribution network equipment based on the load operation data when the power distribution network transformer does not supply power to the power grid load or the power supply process is in a blocking state. Therefore, fault early warning can be carried out on the power distribution network equipment corresponding to the power distribution network transformer according to the corresponding power supply mode and the power blocking mode of the power distribution network transformer, so that the early warning accuracy is further improved. Further, the early warning device may further obtain a line load rate and an electrical betweenness of a line where the power distribution network device is located when the execution form belongs to the fault change form; the system can be reasonably controlled through the line load rate so as to ensure the stable operation of the system, and the system structure can be better known through the electric betweenness. And then, carrying out problem positioning on the power distribution network equipment according to the line load rate, the electrical betters and the load operation data, for example, when the equipment fails, disconnecting or switching part of the equipment by a reverse tracing method, gradually reducing the fault range, and finally determining the fault position. And finally, carrying out fault early warning on the power distribution network equipment based on the fault position, so that the structure of the power distribution network equipment system is better defined through the line load rate and the electrical betweenness, reasonable operation scheduling and equipment maintenance are carried out, and the efficiency of fault maintenance is improved.
In addition, the embodiment of the invention also provides a storage medium, wherein the storage medium is stored with a power grid equipment fault early-warning program, and the power grid equipment fault early-warning program realizes the steps of the power grid equipment fault early-warning method when being executed by a processor.
Referring to fig. 5, fig. 5 is a block diagram of a first embodiment of a power grid equipment fault early warning device according to the present invention.
As shown in fig. 5, the power grid equipment fault early warning device provided by the embodiment of the invention includes:
the data monitoring module 501 is configured to monitor power distribution network equipment, and obtain operation condition data of the power distribution network equipment and environmental image data within a certain range of the power distribution network equipment;
the association analysis module 502 is configured to perform association analysis on the operation condition data and the environmental image data, so as to obtain a current impact weight between the power distribution network device and the environmental image data;
the model prediction module 503 is configured to input the operation condition data, the environmental image data, and the current impact weight into a preset operation state prediction model, so as to obtain a predicted fault type and a predicted fluctuation value;
a deviation judging module 504, configured to judge whether the predicted fluctuation value reaches a corresponding deviation value according to the predicted fault type;
And the fault early warning module 505 is configured to perform fault early warning on the power distribution network device according to the operation condition data and the environmental image data when the predicted fluctuation value reaches a corresponding deviation value.
The early warning device in this embodiment can monitor the power distribution network device in real time, and obtain the operation condition data of the power distribution network device and the environmental image data within a certain range of the power distribution network device, such as voltage and current data, temperature data, load data, switch state data, electric energy metering data, and the like, for example, whether a shielding object, a ventilation condition, a protective measure, and the like exist, so as to further improve the troubleshooting of the power distribution network device through the environmental image data. And performing association analysis on the operation condition data and the environment image data to obtain the current influence weight between the power distribution network equipment and the environment image data. And then inputting the operation condition data, the environment image data and the current influence weight into a preset operation state prediction model to obtain a predicted fault type and a predicted fluctuation value. The environmental image data is associated with the operation of the power distribution network equipment, the accuracy of equipment fault monitoring is further improved, and meanwhile the possibility of the power distribution network equipment fault can be judged by predicting the fluctuation value, so that the timeliness of operation and maintenance is improved. And finally judging whether the predicted fluctuation value reaches a corresponding deviation value according to the predicted fault type, and carrying out fault early warning on the power distribution network equipment according to the operation condition data and the environment image data when the predicted fluctuation value reaches the corresponding deviation value. The abnormality or the unusual of the predicted fault type of the power distribution network equipment can be evaluated through the deviation value, so that potential problems or abnormal conditions can be evaluated, the accuracy of fault early warning is improved, and the occurrence of invalid fault early warning is avoided. Because the power distribution network equipment is monitored in real time, fault prediction is carried out on the operation condition data and the environment image data obtained through monitoring based on the preset operation state prediction model, and fault early warning is carried out when the predicted fluctuation value reaches the deviation value. The situation that equipment faults are difficult to discover in time by means of manual experience is avoided, potential problems of power distribution network equipment can be discovered effectively in time, and then equipment fault processing efficiency is improved.
Based on the first embodiment of the power grid equipment fault early warning device, a second embodiment of the power grid equipment fault early warning device is provided.
In this embodiment, the power grid equipment fault early warning device further includes a model construction module 506, configured to perform feature extraction on historical operation state data of power distribution network equipment, and obtain fault feature data of the power distribution network equipment; dividing the fault characteristic data and the historical operating state data into a training data set and a test data set; training the initial neural network model according to the training data set to obtain a training model; and carrying out parameter optimization on the training model based on the test data set to obtain a preset running state prediction model of the power distribution network equipment.
Further, the model building module 506 is further configured to build a fault feature database corresponding to the power distribution network device according to the fault feature data and the historical operating state data; constructing a fault rule comparison library corresponding to the power distribution network equipment based on the fault characteristic data and the operation management rule data of the power distribution network equipment; correspondingly, training the initial neural network model according to the training data set, the fault characteristic database and the fault rule comparison library to obtain a training model.
Further, the model building module 506 is further configured to input the test data set to the training model to obtain a test output result; judging whether the test output result reaches a preset accuracy rate or not; and when the test output result does not reach the preset accuracy, updating the bias coefficient of the training model until the test output result reaches the preset accuracy, and taking the training model corresponding to the preset accuracy as a preset running state prediction model of the power distribution network equipment.
Further, the fault early warning module 505 is further configured to collect load operation data and load operation indexes of the power distribution network transformer when the predicted fluctuation value reaches a corresponding deviation value; determining the execution form of the power distribution network transformer according to the load operation data; judging whether the execution form belongs to a preset fault change form according to the load operation index; and when the execution form belongs to the fault change form, carrying out fault early warning on the power distribution network equipment based on the load operation data.
Further, the fault early warning module 505 is further configured to obtain a line load rate and an electrical betweenness of a line where the power distribution network device is located when the execution form belongs to the fault variation form; performing problem positioning on the power distribution network equipment according to the line load rate, the electrical betweenness and the load operation data to obtain a fault position corresponding to the power distribution network equipment; and carrying out fault early warning on the power distribution network equipment based on the fault position.
Further, the deviation determining module 504 is further configured to determine that the power distribution network device is in a normal operating state when the predicted fluctuation value is within a first preset deviation value; when the predicted fluctuation value reaches a second preset deviation value, judging that the power distribution network equipment is in an abnormal running state; when the predicted fluctuation value reaches a third preset deviation value, judging that the power distribution network equipment is in a fault running state; correspondingly, the fault early warning module 505 is further configured to perform fault early warning on the power distribution network device according to the operating condition data and the environmental image data when the predicted fluctuation value reaches the second preset deviation value or the third preset deviation value.
Other embodiments or specific implementation manners of the power grid equipment fault early warning device of the present invention may refer to the above method embodiments, and are not repeated herein.
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/random-access memory, magnetic disk, optical disk), comprising 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 utility model provides a power grid equipment fault early warning method which is characterized in that the power grid equipment fault early warning method comprises the following steps:
monitoring power distribution network equipment to obtain operation condition data of the power distribution network equipment and environment image data within a certain range of the power distribution network equipment;
performing association analysis on the operation condition data and the environment image data to obtain current influence weight between the power distribution network equipment and the environment image data;
inputting the operation condition data, the environment image data and the current influence weight into a preset operation state prediction model to obtain a predicted fault type and a predicted fluctuation value;
judging whether the predicted fluctuation value reaches a corresponding deviation value according to the predicted fault type;
and when the predicted fluctuation value reaches a corresponding deviation value, performing fault early warning on the power distribution network equipment according to the operation condition data and the environment image data.
2. The power grid equipment fault early warning method according to claim 1, wherein before monitoring power grid equipment to obtain operation condition data of the power grid equipment and environmental image data within a certain range of the power grid equipment, the method further comprises:
Performing feature extraction on historical operation state data of power distribution network equipment to obtain fault feature data of the power distribution network equipment;
dividing the fault characteristic data and the historical operating state data into a training data set and a test data set;
training the initial neural network model according to the training data set to obtain a training model;
and carrying out parameter optimization on the training model based on the test data set to obtain a preset running state prediction model of the power distribution network equipment.
3. The power grid equipment fault early warning method according to claim 2, wherein the feature extraction is performed on the historical operation state data of the power distribution network equipment, and after the fault feature data of the power distribution network equipment is obtained, the method further comprises:
constructing a fault characteristic database corresponding to the power distribution network equipment according to the fault characteristic data and the historical running state data;
constructing a fault rule comparison library corresponding to the power distribution network equipment based on the fault characteristic data and the operation management rule data of the power distribution network equipment;
correspondingly, the training the initial neural network model according to the training data set to obtain a training model comprises the following steps:
And training the initial neural network model according to the training data set, the fault characteristic database and the fault rule comparison library to obtain a training model.
4. The power grid equipment fault pre-warning method according to claim 3, wherein the performing parameter optimization on the training model based on the test data set to obtain a preset operation state prediction model of the power distribution network equipment comprises:
inputting the test data set into the training model to obtain a test output result;
judging whether the test output result reaches a preset accuracy rate or not;
and when the test output result does not reach the preset accuracy, updating the bias coefficient of the training model until the test output result reaches the preset accuracy, and taking the training model corresponding to the preset accuracy as a preset running state prediction model of the power distribution network equipment.
5. The power grid equipment fault early warning method according to claim 1, wherein the performing fault early warning on the power distribution network equipment according to the operation condition data and the environmental image data when the predicted fluctuation value reaches the corresponding deviation value comprises:
Under the condition that the predicted fluctuation value reaches a corresponding deviation value, collecting load operation data and load operation indexes of the power distribution network transformer;
determining the execution form of the power distribution network transformer according to the load operation data;
judging whether the execution form belongs to a preset fault change form according to the load operation index;
and when the execution form belongs to the fault change form, carrying out fault early warning on the power distribution network equipment based on the load operation data.
6. The power grid equipment fault pre-warning method according to claim 5, wherein the performing fault pre-warning on the power distribution network equipment based on the load operation data when the execution form belongs to the fault change form comprises:
when the execution form belongs to the fault change form, acquiring a line load rate and an electric medium number of a line where the power distribution network equipment is located;
performing problem positioning on the power distribution network equipment according to the line load rate, the electrical betweenness and the load operation data to obtain a fault position corresponding to the power distribution network equipment;
and carrying out fault early warning on the power distribution network equipment based on the fault position.
7. The power grid equipment fault early warning method according to any one of claims 1 to 6, wherein the judging whether the predicted fluctuation value reaches a corresponding deviation value according to the predicted fault type includes:
when the predicted fluctuation value is within a first preset deviation value, judging that the power distribution network equipment is in a normal running state;
when the predicted fluctuation value reaches a second preset deviation value, judging that the power distribution network equipment is in an abnormal running state;
when the predicted fluctuation value reaches a third preset deviation value, judging that the power distribution network equipment is in a fault running state;
correspondingly, when the predicted fluctuation value reaches a corresponding deviation value, performing fault early warning on the power distribution network equipment according to the operation condition data and the environment image data, including:
and when the predicted fluctuation value reaches the second preset deviation value or the third preset deviation value, performing fault early warning on the power distribution network equipment according to the operation condition data and the environment image data.
8. A power grid equipment fault early warning device, the device comprising:
the data monitoring module is used for monitoring the power distribution network equipment and obtaining the operation condition data of the power distribution network equipment and the environmental image data within a certain range of the power distribution network equipment;
The association analysis module is used for carrying out association analysis on the operation condition data and the environment image data to obtain the current influence weight between the power distribution network equipment and the environment image data;
the model prediction module is used for inputting the operation condition data, the environment image data and the current influence weight into a preset operation state prediction model to obtain a prediction fault type and a prediction fluctuation value;
the deviation judging module is used for judging whether the predicted fluctuation value reaches a corresponding deviation value according to the predicted fault type;
and the fault early warning module is used for carrying out fault early warning on the power distribution network equipment according to the operation condition data and the environment image data when the predicted fluctuation value reaches the corresponding deviation value.
9. A power grid equipment fault early warning device, the device comprising: a memory, a processor and a grid device fault pre-warning program stored on the memory and operable on the processor, the grid device fault pre-warning program being configured to implement the steps of the grid device fault pre-warning method of any one of claims 1 to 7.
10. A storage medium, wherein a grid equipment fault warning program is stored on the storage medium, and when executed by a processor, the grid equipment fault warning program implements the steps of the grid equipment fault warning method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311482179.4A CN117674407A (en) | 2023-11-08 | 2023-11-08 | Power grid equipment fault early warning method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311482179.4A CN117674407A (en) | 2023-11-08 | 2023-11-08 | Power grid equipment fault early warning method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117674407A true CN117674407A (en) | 2024-03-08 |
Family
ID=90076095
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311482179.4A Pending CN117674407A (en) | 2023-11-08 | 2023-11-08 | Power grid equipment fault early warning method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117674407A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118074243A (en) * | 2024-04-18 | 2024-05-24 | 国网山东省电力公司宁津县供电公司 | Power supply system stable operation control method based on fire-fighting water pump |
-
2023
- 2023-11-08 CN CN202311482179.4A patent/CN117674407A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118074243A (en) * | 2024-04-18 | 2024-05-24 | 国网山东省电力公司宁津县供电公司 | Power supply system stable operation control method based on fire-fighting water pump |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109146093B (en) | Power equipment field investigation method based on learning | |
| CN106980905A (en) | Power distribution network power supply reliability prediction method and system | |
| CN108491990A (en) | A kind of wind farm device state evaluation and maintenance decision support detection method and system | |
| US10310495B2 (en) | Systems and methods for monitoring automation systems | |
| CN112700144B (en) | Transformer substation operation state risk assessment method, device, equipment and storage medium | |
| CN115549094B (en) | Early warning evaluation method and system for substation equipment of smart power grid | |
| CN117674407A (en) | Power grid equipment fault early warning method, device, equipment and storage medium | |
| CN110826228B (en) | Regional power grid operation quality limit evaluation method | |
| CN117406026A (en) | Power distribution network fault detection method suitable for distributed power supply | |
| CN115456410A (en) | Power grid risk assessment method and system | |
| CN113763667A (en) | Fire early warning and state monitoring device and method based on 5G edge calculation | |
| CN115603459A (en) | Digital twin technology-based power distribution network key station monitoring method and system | |
| CN106408016A (en) | Distribution network power outage time automatic identification model construction method | |
| CN117390403A (en) | Power grid fault detection method and system for new energy lighthouse power station | |
| CN108596450B (en) | Power grid risk early warning method and system | |
| She et al. | Multi-dimensional health evaluation of equipment in electric power communication network | |
| CN114493238A (en) | Power supply service risk prediction method, system, storage medium and computer equipment | |
| CN114142614A (en) | Highway power distribution room intelligent operation and maintenance management system based on SD-WAN network | |
| CN117251810A (en) | Substation equipment state evaluation early warning system and method based on digital twin platform | |
| CN115586402B (en) | Power distribution network fault diagnosis and processing method | |
| CN115146715A (en) | Power utilization potential safety hazard diagnosis method, device, equipment and storage medium | |
| Fang et al. | Calculation method of outage probability of distribution network based on real-time failure rate of equipment | |
| Gong et al. | State detection method of secondary equipment in smart substation based on deep belief network and trend prediction | |
| CN117148048B (en) | Power distribution network fault prediction method and system based on digital twin technology | |
| Wang et al. | Research on reliability evaluation method of protection system based on Kaplan-Meier and GO 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 |