CN117633479A - Method and system for analyzing and processing faults of charging piles - Google Patents
Method and system for analyzing and processing faults of charging piles Download PDFInfo
- Publication number
- CN117633479A CN117633479A CN202410107129.6A CN202410107129A CN117633479A CN 117633479 A CN117633479 A CN 117633479A CN 202410107129 A CN202410107129 A CN 202410107129A CN 117633479 A CN117633479 A CN 117633479A
- Authority
- CN
- China
- Prior art keywords
- data
- parameter
- environmental
- characteristic data
- target
- 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.)
- Granted
Links
- 238000012545 processing Methods 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000004458 analytical method Methods 0.000 claims abstract description 78
- 238000012549 training Methods 0.000 claims abstract description 70
- 238000012937 correction Methods 0.000 claims abstract description 46
- 238000001514 detection method Methods 0.000 claims abstract description 32
- 230000011218 segmentation Effects 0.000 claims abstract description 10
- 230000007613 environmental effect Effects 0.000 claims description 97
- 239000013598 vector Substances 0.000 claims description 50
- 238000003745 diagnosis Methods 0.000 claims description 43
- 238000003891 environmental analysis Methods 0.000 claims description 33
- 230000002159 abnormal effect Effects 0.000 claims description 31
- 238000010276 construction Methods 0.000 claims description 8
- 238000012544 monitoring process Methods 0.000 claims description 7
- 238000003062 neural network model Methods 0.000 claims description 4
- 238000012512 characterization method Methods 0.000 claims 2
- 238000000638 solvent extraction Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
Classifications
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/70—Energy storage systems for electromobility, e.g. batteries
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method and a system for analyzing and processing faults of a charging pile, and relates to the technical field of fault analysis. The method comprises the following steps: acquiring historical fault detection data of the charging pile; performing data segmentation and clustering on the historical fault detection data to obtain a first data set and a second data set, constructing a first training data set and training an environment analysis model; constructing a second training data set and training a fault analysis model; and extracting target environment characteristic data and first target parameter characteristic data of the charging pile, processing the target environment characteristic data through an environment analysis model to generate target correction data, processing the first target parameter characteristic data to generate second target parameter characteristic data, inputting the second target parameter characteristic data into a fault analysis model, and generating a fault analysis result. The invention can improve the accuracy of fault analysis of the charging pile and the efficiency of fault analysis.
Description
Technical Field
The invention relates to the technical field of fault analysis, in particular to a method and a system for analyzing and processing faults of a charging pile.
Background
The charging pile, also called electric vehicle charging pile or charging station, is a device that provides electric energy charging service for electric vehicles. With the continuous popularization of electric vehicles, a charging pile is becoming a key node for sustainable urban traffic development as an important component for supporting an electric vehicle charging infrastructure.
The fault analysis of the charging pile has important significance for maintaining the reliability and stability of the charging infrastructure of the electric vehicle, and at present, when the fault analysis of the charging pile is carried out, the detection data of the charging pile is analyzed by combining with a preset threshold parameter so as to determine whether the fault exists. However, aiming at complex use environments, it is difficult to accurately set threshold parameters in different environments, so that false alarm or untimely alarm can occur in the fault analysis process, and the fault analysis of the charging pile is not accurate enough.
Disclosure of Invention
The embodiment of the invention provides a method and a system for analyzing and processing faults of a charging pile, which are used for improving the accuracy of fault analysis of the charging pile so as to improve the efficiency of fault analysis.
In a first aspect of the embodiment of the present invention, a method for analyzing and processing a fault of a charging pile is provided, including:
acquiring historical fault detection data of a charging pile, wherein the historical fault detection data comprises a plurality of fault diagnosis results, and environment monitoring data and equipment parameter data corresponding to each fault diagnosis result;
performing data segmentation and clustering on the historical fault detection data based on a fault diagnosis result to obtain a first data set comprising a plurality of groups of normal working data and a second data set comprising a plurality of groups of abnormal working data;
extracting first environmental characteristic data and first parameter characteristic data of each group of normal working data in the first data set, constructing a first training data set and training an environmental analysis model;
extracting fault diagnosis results of each group of abnormal working data in the second data set, and second environment characteristic data and second parameter characteristic data corresponding to each fault diagnosis result;
processing each group of second environmental characteristic data based on the environmental analysis model, correcting a plurality of groups of second parameter characteristic data according to the processing result, constructing a second training data set, and training the fault analysis model through the second training data set;
collecting working environment data and working parameter data of the charging pile in real time, extracting target environment characteristic data and first target parameter characteristic data of the charging pile, processing the target environment characteristic data through an environment analysis model to generate target correction data, processing the first target parameter characteristic data based on the target correction data to generate second target parameter characteristic data, inputting the second target parameter characteristic data into a fault analysis model, and generating a fault analysis result.
Further, processing each set of second environmental feature data based on the environmental analysis model, and correcting the plurality of sets of second parameter feature data according to the processing result, including:
and processing each group of second environmental characteristic data through an environmental analysis model to generate parameter correction data corresponding to each group of second environmental characteristic data, correcting the second parameter characteristic data corresponding to each group of second environmental characteristic data through a plurality of groups of parameter correction data, and generating third parameter characteristic data corresponding to each group of second environmental characteristic data.
Further, for the first training data set and the second training data set, further comprising:
the first training data set comprises a plurality of first data subsets, each first data subset comprises first environmental characteristic data and first parameter characteristic data of a group of normal and abnormal working data, the first environmental characteristic data of each first data subset is used as input of an environmental analysis model, the first parameter characteristic data of each first data subset is used as output of the environmental analysis model, and the environmental analysis model is obtained through training;
the second training data set comprises a plurality of second data subsets, each second data subset comprises third parameter characteristic data of a group of abnormal working data and fault diagnosis results, the third parameter characteristic data of each second data subset is taken as input of a fault analysis model, the fault diagnosis results of each second data subset are taken as output of the fault analysis model, and the fault analysis model is obtained through training.
Further, extracting target environmental characteristic data and first target parameter characteristic data of the charging pile includes:
acquiring working environment data and working parameter data of a charging pile in a preset time range before a current time, dividing the preset time range into a plurality of time intervals, determining an environment parameter factor and an environment parameter difference factor of each environment parameter in each time interval, generating an environment characteristic vector of each environment parameter in the preset time range before the current time, and obtaining target environment characteristic data of the charging pile comprising a plurality of environment characteristic vectors in the preset time range before the current time, wherein the value of the environment parameter in the ending time of any one time interval is recorded as the environment parameter factor of the time interval, and the difference value of the environment parameter in the ending time of any one time interval and the value of the starting time is recorded as the environment parameter difference factor of the time interval;
determining a device parameter factor and a device parameter difference factor of each device parameter in each time interval, generating a first parameter feature vector of each device parameter in a preset time range before the current time, and obtaining first target parameter feature data of a charging pile comprising a plurality of first parameter feature vectors in the preset time range before the current time, wherein the value of the device parameter at the ending time of any one time interval is recorded as the device parameter factor of the time interval, and the difference value of the device parameter at the ending time of any one time interval and the value of the starting time is recorded as the device parameter difference factor of the time interval.
Further, for the target environmental feature data and the first target parameter feature data, further comprising:
for the first item in the target environment characteristic dataEnvironmental feature vector of individual environmental parameters +.>There is，/>For the number of duration intervals +.>Wherein->For the environmental feature vector->In->Environmental parameter factors for individual time intervals, +.>For the environmental feature vector->In->Environmental parameter differential factors of the individual duration intervals;
for the first object parameter characteristic dataEnvironmental feature vector of individual environmental parameters +.>Corresponding first parameter feature vector ++>There is->，/>Wherein->For the first parameter feature vector->In->Device parameter factors for individual time intervals, +.>For the first parameter feature vector->In->The device parameter differential factor for each duration interval.
Further, processing the first target parameter feature data based on the target correction data to generate second target parameter feature data, including:
the target correction data comprises correction feature vectors corresponding to each first parameter feature vector in the first target parameter feature data;
for the first object parameter feature dataFirst parameter feature vector->And a first parameter feature vector->Corresponding correction feature vector->There is->，/>By correcting eigenvectors->For the first parameter feature vector->Correcting to obtain a second parameter feature vectorThere is->Wherein->For the second parameter feature vector->In->Device parameter factors for individual time intervals, +.>Is of the second parameterSyndrome vector->In->A device parameter differential factor for each duration interval;
，/>for the first parameter feature vector->In->Device parameter factors for individual time intervals, +.>For correcting feature vector +.>In->A device parameter factor for each duration interval;
，/>for the first parameter feature vector->In->Device parameter differential factors for individual time intervals, +.>For correcting feature vector +.>In->A device parameter differential factor for each duration interval;
and correcting the plurality of first parameter feature vectors in the first target parameter feature data through the plurality of correction feature vectors in the target correction data to obtain second target parameter feature data containing a plurality of second parameter feature vectors.
Further, performing data segmentation and clustering on the historical fault detection data based on the fault diagnosis result comprises:
determining a plurality of fault time points according to a plurality of fault diagnosis results with faults, extracting historical fault detection data of a preset time range before each fault time point to obtain a plurality of groups of abnormal working data, dividing the rest historical fault detection data based on the preset time range to obtain a plurality of groups of normal working data, clustering the plurality of groups of normal working data and the plurality of groups of abnormal working data respectively, and constructing a first data set and a second data set.
Further, the environmental analysis model and the fault analysis model are BP neural network models.
In a second aspect of the embodiment of the present invention, a system for analyzing and processing a fault of a charging pile is provided, where the system is configured to implement the foregoing method for analyzing and processing a fault of a charging pile, and the method includes:
the data acquisition module is used for acquiring historical fault detection data of the charging pile, and comprises a plurality of fault diagnosis results, environment monitoring data and equipment parameter data corresponding to each fault diagnosis result;
the data processing module is used for carrying out data segmentation and clustering on the historical fault detection data based on the fault diagnosis result to obtain a first data set comprising a plurality of groups of normal working data and a second data set comprising a plurality of groups of abnormal working data;
the first data set construction module is used for extracting first environment characteristic data and first parameter characteristic data of each group of normal working data in the first data set and constructing to obtain a first training data set;
the first model training module is used for training through a first training data set to obtain an environment analysis model;
the second data set construction module is used for extracting fault diagnosis results of each group of abnormal working data in the second data set, second environment characteristic data and second parameter characteristic data corresponding to each fault diagnosis result, processing each group of second environment characteristic data based on an environment analysis model, correcting a plurality of groups of second parameter characteristic data according to the processing results, and constructing a second training data set;
the second model training module is used for training through a second training data set to obtain a fault analysis model;
the fault analysis module is used for collecting working environment data and working parameter data of the charging pile in real time, extracting target environment characteristic data and first target parameter characteristic data of the charging pile, processing the target environment characteristic data through the environment analysis model to generate target correction data, processing the first target parameter characteristic data based on the target correction data to generate second target parameter characteristic data, inputting the second target parameter characteristic data into the fault analysis model, and generating a fault analysis result.
Further, for the second data set construction module, processing each set of second environmental feature data based on the environmental analysis model, and correcting the plurality of sets of second parameter feature data according to the processing result, including:
and processing each group of second environmental characteristic data through an environmental analysis model to generate parameter correction data corresponding to each group of second environmental characteristic data, correcting the second parameter characteristic data corresponding to each group of second environmental characteristic data through a plurality of groups of parameter correction data, and generating third parameter characteristic data corresponding to each group of second environmental characteristic data.
The invention has the following advantages:
according to the invention, the first training data set for training the environment analysis model and the second training data set for training the fault analysis model are constructed by analyzing the historical fault detection data of the charging pile, the collected working environment data of the charging pile is processed by the environment analysis model obtained through training, the equipment parameter data under the condition of normal operation of the charging pile is analyzed and predicted, the collected working parameter data of the charging pile is corrected based on the equipment parameter data under the condition of normal operation of the charging pile obtained through analysis and prediction, the influence of environmental factors on the working parameter data of the charging pile is reduced, the working parameter data of the corrected charging pile is processed by the fault analysis model, the fault analysis result of the charging pile is generated, the possibility of false alarm or missing alarm when the fault analysis is carried out on the charging pile due to the environmental factors is reduced, the accuracy of fault analysis on the charging pile is improved, and the efficiency of the fault analysis is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below.
Fig. 1 is a flow chart illustrating an exemplary method for analyzing and processing a fault of a charging pile according to an embodiment of the present invention.
Fig. 2 is a block diagram illustrating a system for analyzing and processing a fault of a charging pile according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, some embodiments of the present invention will be described in further detail below with reference to the accompanying drawings and examples. It should be noted that in the description of the present invention, the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
Fig. 1 is a schematic flow chart of an exemplary method for analyzing and processing a fault of a charging pile according to an embodiment of the present invention, please refer to fig. 1, and an embodiment of the present invention provides a method for analyzing and processing a fault of a charging pile, which includes:
s100, acquiring historical fault detection data of the charging pile, and performing data segmentation and clustering on the historical fault detection data to obtain a first data set and a second data set.
In this embodiment, at least a plurality of fault diagnosis results in the historical fault detection data of the charging pile and environment monitoring data and equipment parameter data corresponding to each fault diagnosis result, where the environment monitoring data includes relevant data of environmental parameters such as air temperature, air pressure, humidity, illumination intensity, etc., the equipment parameter data includes relevant data of equipment parameters related to the operation process of the charging pile such as voltage, current, temperature, power, network delay, etc., the historical fault detection data is subjected to data segmentation according to the presence or absence of a fault in the fault diagnosis results, multiple groups of abnormal working data with faults and multiple groups of this working data without faults are extracted, and a first data set including multiple groups of normal working data and a second data set including multiple groups of abnormal working data are respectively constructed.
For example, a plurality of fault time points are determined according to a plurality of fault diagnosis results of faults, historical fault detection data of a preset duration range before each fault time point is extracted, and a plurality of groups of abnormal working data are obtained. If it is determined that the charging pile has a fault according to the parameter of the charging pile detected at a certain moment, the moment is regarded as a fault time point, and considering the difference of the output power of the charging pile, a preset duration range may be reasonably set based on the specification of the charging pile or the charging pile in a working mode, for example, for a non-fast charging pile, the preset duration may be 1h, 2.5h, etc., and for a fast charging pile, a shorter duration range may be set, which is not specifically limited in this embodiment.
After a plurality of groups of abnormal working data are extracted from the historical fault detection data, the remaining historical fault detection data are segmented based on a preset duration range to obtain a plurality of groups of normal working data, a plurality of groups of normal working data without faults are clustered to obtain a first data set, and a plurality of groups of abnormal working data with faults are clustered to obtain a second data set.
S200, extracting first environmental characteristic data and first parameter characteristic data of each group of normal working data in the first data set, constructing a first training data set and training an environmental analysis model.
In this embodiment, the first environmental characteristic data includes data of a plurality of environmental parameters that change with time in a set of normal operation data, the first parameter characteristic data includes data of a plurality of equipment parameters that change with time in a set of normal operation data, and a first training data set for training the environmental analysis model is constructed according to the first environmental characteristic data and the first parameter characteristic data.
In this embodiment, the first training data set includes a plurality of first data subsets, each first data subset includes a set of first environmental feature data and first parameter feature data corresponding to normal abnormal working data, in a training process of the environmental analysis model, the first environmental feature data of the plurality of first data subsets are used as input of the environmental analysis model, the first parameter feature data of the plurality of first data subsets are used as output of the environmental analysis model, the environmental analysis model capable of predicting and analyzing the device parameter data of the charging pile under the normal working condition by analyzing the environmental parameter data is obtained through training, wherein the environmental analysis model and a fault analysis model described below are both neural network models, in this embodiment, the environmental analysis model and the fault analysis model are obtained by pre-constructing based on a BP neural network model as an example, and training of the environmental analysis model is completed by the first training data set.
S300, extracting fault diagnosis results of each group of abnormal working data in the second data set, and second environment characteristic data and second parameter characteristic data corresponding to each fault diagnosis result.
S400, processing each group of second environmental characteristic data based on the environmental analysis model, correcting a plurality of groups of second parameter characteristic data according to the processing result, constructing a second training data set, and training the fault analysis model through the second training data set.
In this embodiment, the second environmental characteristic data includes data of time-varying multiple environmental parameters in a set of abnormal working data, the second parameter characteristic data includes data of time-varying multiple equipment parameters in a set of abnormal working data, and for the second parameter characteristic data in the abnormal working data, the second parameter characteristic data is affected by environmental factors, for example, air temperature, air pressure, humidity, illumination intensity, etc., in a high or low environment, part of the equipment parameters of the charging pile may be affected, so that small amplitude of rise, fall or up-down fluctuation of part of the equipment parameters, for example, temperature, power, voltage current, etc., occurs, and in the process of analyzing whether the charging pile has a fault through a threshold value, the influence of the environmental factors on the equipment parameters may cause a false alarm or a missing alarm. Under the condition, the second parameter characteristic data are processed through the environment analysis model, the equipment parameters of the charging pile under each group of the second environment characteristic data in normal operation are predicted and analyzed, the influence of the environment factors on the second parameter characteristic data is eliminated, and the second training data set is constructed based on the corrected second parameter characteristic data.
In this embodiment, processing each set of second environmental feature data by using an environmental analysis model to generate parameter correction data corresponding to each set of second environmental feature data, where the parameter correction data corresponding to the second environmental feature data is specifically an equipment parameter of each set of second environmental feature data when the charging pile works normally, analyzing a difference between the parameter correction data and the second environmental feature data, correcting the second parameter feature data corresponding to each set of second environmental feature data by using multiple sets of parameter correction data, and generating third parameter feature data corresponding to each set of second environmental feature data.
In this embodiment, the second training data set includes a plurality of second data subsets, each second data subset includes a set of third parameter feature data corresponding to abnormal working data and a fault diagnosis result, the third parameter feature data of the plurality of second data subsets is used as input of a fault analysis model, the fault diagnosis result of the plurality of second data subsets is used as output of the fault analysis model, and a fault analysis model capable of predicting and analyzing whether the charging pile has a fault through analyzing equipment parameter data is obtained through training.
S500, working environment data and working parameter data of the charging pile are collected in real time, target environment characteristic data and first target parameter characteristic data of the charging pile are extracted, and the target environment characteristic data are processed through an environment analysis model to generate target correction data.
S600, processing the first target parameter characteristic data based on the target correction data, generating second target parameter characteristic data, inputting the second target parameter characteristic data into a fault analysis model, and generating a fault analysis result.
In this embodiment, the collected working environment data and working parameter data of the charging pile may be periodically analyzed, the environment data in a certain period of time is processed by the environment analysis model, the parameter data of the charging pile during normal working in the certain period of time is determined, the parameter data output by the environment analysis model and the actually collected working data of the charging pile are analyzed, the theoretical parameter data of the charging pile under the condition of not being affected by the environment is extracted according to the difference between the parameter data and the actually collected working data of the charging pile, and the theoretical parameter data is input into the fault analysis model to generate a fault analysis result of the charging pile, so that the possibility of false alarm or missing alarm occurring when the fault analysis is performed on the charging pile due to the environmental factors is reduced, the accuracy of the fault analysis on the charging pile is improved, and the efficiency of the fault analysis is improved.
In some optional implementation processes, for step S500, extracting the target environmental feature data and the first target parameter feature data of the charging pile specifically includes:
the method comprises the steps of obtaining working environment data and working parameter data of a charging pile in a preset time length range before a current moment, dividing the preset time length range into a plurality of time length intervals, and determining an environment parameter factor and an environment parameter difference factor of each environment parameter in each time length interval.
In this embodiment, the dividing of the duration intervals may be reasonably set based on the preset duration range, and in consideration of the difference between the working model and the model of the charging pile, in this case, the duration intervals of a uniform range, for example, 2min, 3min or 5min, may be used as the length of one duration interval, and the specific dividing manner is not specifically limited in this embodiment, so that a person skilled in the art may reasonably set the length of the duration interval based on the actual situation.
After a plurality of time intervals are determined, determining an environmental parameter factor and an environmental parameter difference factor of each environmental parameter in each time interval, wherein the value of the environmental parameter at the ending time of any one time interval is recorded as the environmental parameter factor of the time interval, and the difference value of the environmental parameter at the ending time of any one time interval and the value of the starting time is recorded as the environmental parameter difference factor of the time interval.
For the air temperature parameters, data of temperature change along with time in a preset time range are extracted from working environment data of the charging pile in the preset time range, n+1 starting moments and finishing moments of n time intervals exist in practice for n time intervals, and environmental parameter factors and environmental parameter difference factors of each time interval are determined according to the air temperature data of the starting moments and the finishing moments of each time interval.
Generating environmental characteristic vectors of each environmental parameter in a preset time range before the current moment according to environmental parameter factors and environmental parameter difference factors of each environmental parameter in n time intervals, wherein the extracted target environmental characteristic data of the charging pile comprise a plurality of environmental characteristic vectors respectively corresponding to one environmental parameter.
In the present embodiment, for the first of the target environmental characteristic dataEnvironmental feature vector of individual environmental parameters +.>There is，/>For the number of duration intervals +.>Wherein->For the environmental feature vector->In->Environmental parameter factors for individual time intervals, +.>For the environmental feature vector->In->Environmental parameter differential factors for each duration interval.
For the first target parameter characteristic data, determining a device parameter factor and a device parameter difference factor of each device parameter in each time interval, specifically, marking the value of the device parameter at the ending time of any one time interval as the device parameter factor of the time interval, and marking the difference value of the device parameter at the ending time of any one time interval and the value of the starting time as the device parameter difference factor of the time interval. Generating a first parameter feature vector of each equipment parameter in a preset time range before the current moment according to equipment parameter factors and equipment parameter difference factors of each equipment parameter in n time intervals, wherein the extracted first target equipment feature data of the charging pile comprise a plurality of first parameter feature vectors respectively corresponding to one equipment parameter.
In the present embodiment, for the first target parameter feature dataEnvironmental feature vector of individual environmental parameters +.>Corresponding first parameter feature vector ++>There is->，/>Wherein->For the first parameter feature vector->In->Device parameter factors for individual time intervals, +.>For the first parameter feature vector->In->The device parameter differential factor for each duration interval.
In some optional implementations, for step S600, processing the first target parameter feature data based on the target correction data to generate second target parameter feature data specifically includes:
the target correction data comprises correction feature vectors corresponding to each first parameter feature vector in the first target parameter feature data.
Characterizing the first object parameter in the dataFirst parameter feature vector->For example, for the first target parameter characteristic data +.>First parameter feature vector->And a first parameter feature vector->Corresponding correction feature vector->There is->，/>Wherein the first parameter feature vectorAnd a first parameter feature vector->Corresponding correction feature vector->Each element of the system comprises a device parameter factor and a device parameter difference factor of a time duration interval respectively.
By correcting eigenvectorsFor the first parameter feature vector->Correcting to obtain a second parameter feature vectorWherein->Specific:
for the second parameter feature vectorThe%>Individual element->There is->Wherein->For the second parameter feature vector->In->Device parameter factors for individual time intervals, +.>For the second parameter feature vector->In->A device parameter differential factor for each duration interval;
for device parameter factorsThere is->Wherein->For the first parameter feature vector->In->Device parameter factors for individual time intervals, +.>For correcting feature vector +.>In->A device parameter factor for each duration interval;
differential factors for device parametersThere is->，/>For the first parameter feature vector->In->Device parameter differential factors for individual time intervals, +.>For correcting feature vector +.>In->A device parameter differential factor for each duration interval;
by adopting the mode, each first parameter characteristic vector in the first target parameter characteristic data is corrected through a plurality of correction characteristic vectors in the target correction data, a plurality of second parameter characteristic vectors are obtained, and second target parameter characteristic data comprising the plurality of second parameter characteristic vectors are generated.
Fig. 2 is a block diagram of an exemplary system for analyzing and processing a fault of a charging pile according to an embodiment of the present invention, referring to fig. 2, the embodiment of the present invention further provides a system for analyzing and processing a fault of a charging pile, including:
the data acquisition module is used for acquiring historical fault detection data of the charging pile, and comprises a plurality of fault diagnosis results, environment monitoring data and equipment parameter data corresponding to each fault diagnosis result;
the data processing module is used for carrying out data segmentation and clustering on the historical fault detection data based on the fault diagnosis result to obtain a first data set comprising a plurality of groups of normal working data and a second data set comprising a plurality of groups of abnormal working data;
the method for carrying out data segmentation and clustering on the historical fault detection data based on the fault diagnosis result specifically comprises the following steps:
determining a plurality of fault time points according to a plurality of fault diagnosis results with faults, extracting historical fault detection data of a preset time range before each fault time point to obtain a plurality of groups of abnormal working data, dividing the rest historical fault detection data based on the preset time range to obtain a plurality of groups of normal working data, clustering the plurality of groups of normal working data and the plurality of groups of abnormal working data respectively, and constructing a first data set and a second data set.
The first data set construction module is used for extracting first environment characteristic data and first parameter characteristic data of each group of normal working data in the first data set and constructing to obtain a first training data set;
the first model training module is used for training through a first training data set to obtain an environment analysis model;
the second data set construction module is used for extracting fault diagnosis results of each group of abnormal working data in the second data set, second environment characteristic data and second parameter characteristic data corresponding to each fault diagnosis result, processing each group of second environment characteristic data based on an environment analysis model, correcting a plurality of groups of second parameter characteristic data according to the processing results, and constructing a second training data set;
processing each group of second environmental characteristic data based on an environmental analysis model, and correcting a plurality of groups of second parameter characteristic data according to a processing result, wherein the method specifically comprises the following steps:
and processing each group of second environmental characteristic data through an environmental analysis model to generate parameter correction data corresponding to each group of second environmental characteristic data, correcting the second parameter characteristic data corresponding to each group of second environmental characteristic data through a plurality of groups of parameter correction data, and generating third parameter characteristic data corresponding to each group of second environmental characteristic data.
The second model training module is used for training through a second training data set to obtain a fault analysis model;
the fault analysis module is used for collecting working environment data and working parameter data of the charging pile in real time, extracting target environment characteristic data and first target parameter characteristic data of the charging pile, processing the target environment characteristic data through the environment analysis model to generate target correction data, processing the first target parameter characteristic data based on the target correction data to generate second target parameter characteristic data, inputting the second target parameter characteristic data into the fault analysis model, and generating a fault analysis result.
It will be understood that modifications and variations will be apparent to those skilled in the art from the foregoing description, and it is intended that all such modifications and variations be included within the scope of the following claims. Parts of the specification not described in detail belong to the prior art known to those skilled in the art.
Claims (10)
1. The method for analyzing and processing the faults of the charging pile is characterized by comprising the following steps of:
acquiring historical fault detection data of a charging pile, wherein the historical fault detection data comprises a plurality of fault diagnosis results, and environment monitoring data and equipment parameter data corresponding to each fault diagnosis result;
performing data segmentation and clustering on the historical fault detection data based on a fault diagnosis result to obtain a first data set comprising a plurality of groups of normal working data and a second data set comprising a plurality of groups of abnormal working data;
extracting first environmental characteristic data and first parameter characteristic data of each group of normal working data in the first data set, constructing a first training data set and training an environmental analysis model;
extracting fault diagnosis results of each group of abnormal working data in the second data set, and second environment characteristic data and second parameter characteristic data corresponding to each fault diagnosis result;
processing each group of second environmental characteristic data based on the environmental analysis model, correcting a plurality of groups of second parameter characteristic data according to the processing result, constructing a second training data set, and training the fault analysis model through the second training data set;
collecting working environment data and working parameter data of the charging pile in real time, extracting target environment characteristic data and first target parameter characteristic data of the charging pile, processing the target environment characteristic data through an environment analysis model to generate target correction data, processing the first target parameter characteristic data based on the target correction data to generate second target parameter characteristic data, inputting the second target parameter characteristic data into a fault analysis model, and generating a fault analysis result.
2. The method of claim 1, wherein processing each set of second environmental characteristic data based on the environmental analysis model, and correcting the plurality of sets of second parametric characteristic data based on the processing results, comprises:
and processing each group of second environmental characteristic data through an environmental analysis model to generate parameter correction data corresponding to each group of second environmental characteristic data, correcting the second parameter characteristic data corresponding to each group of second environmental characteristic data through a plurality of groups of parameter correction data, and generating third parameter characteristic data corresponding to each group of second environmental characteristic data.
3. The method of claim 2, wherein for the first training data set and the second training data set, further comprising:
the first training data set comprises a plurality of first data subsets, each first data subset comprises first environmental characteristic data and first parameter characteristic data of a group of normal and abnormal working data, the first environmental characteristic data of each first data subset is used as input of an environmental analysis model, the first parameter characteristic data of each first data subset is used as output of the environmental analysis model, and the environmental analysis model is obtained through training;
the second training data set comprises a plurality of second data subsets, each second data subset comprises third parameter characteristic data of a group of abnormal working data and fault diagnosis results, the third parameter characteristic data of each second data subset is taken as input of a fault analysis model, the fault diagnosis results of each second data subset are taken as output of the fault analysis model, and the fault analysis model is obtained through training.
4. The method of claim 1, wherein extracting target environmental characteristic data and first target parametric characteristic data of the charging stake comprises:
acquiring working environment data and working parameter data of a charging pile in a preset time range before a current time, dividing the preset time range into a plurality of time intervals, determining an environment parameter factor and an environment parameter difference factor of each environment parameter in each time interval, generating an environment characteristic vector of each environment parameter in the preset time range before the current time, and obtaining target environment characteristic data of the charging pile comprising a plurality of environment characteristic vectors in the preset time range before the current time, wherein the value of the environment parameter in the ending time of any one time interval is recorded as the environment parameter factor of the time interval, and the difference value of the environment parameter in the ending time of any one time interval and the value of the starting time is recorded as the environment parameter difference factor of the time interval;
determining a device parameter factor and a device parameter difference factor of each device parameter in each time interval, generating a first parameter feature vector of each device parameter in a preset time range before the current time, and obtaining first target parameter feature data of a charging pile comprising a plurality of first parameter feature vectors in the preset time range before the current time, wherein the value of the device parameter at the ending time of any one time interval is recorded as the device parameter factor of the time interval, and the difference value of the device parameter at the ending time of any one time interval and the value of the starting time is recorded as the device parameter difference factor of the time interval.
5. The method of claim 4, wherein for the target environmental characteristic data and the first target parametric characteristic data, further comprising:
for the first item in the target environment characteristic dataEnvironmental feature vector of individual environmental parameters +.>There is，/>For the number of duration intervals +.>Wherein->For the environmental feature vector->In->Environmental parameter factors for individual time intervals, +.>For the environmental feature vector->In->Environmental parameter differential factors of the individual duration intervals;
for the first object parameter characteristic dataEnvironmental feature vector of individual environmental parameters +.>Corresponding first parameter feature vector ++>There is->，/>Wherein->For the first parameter feature vectorIn->Device parameter factors for individual time intervals, +.>For the first parameter feature vector->In->Each time length zoneA device parameter differential factor therebetween.
6. The method of claim 5, wherein processing the first target parametric characterization data based on the target correction data to generate the second target parametric characterization data comprises:
the target correction data comprises correction feature vectors corresponding to each first parameter feature vector in the first target parameter feature data;
for the first object parameter feature dataFirst parameter feature vector->And a first parameter feature vectorCorresponding correction feature vector->There is->，/>By correcting eigenvectors->For the first parameter feature vector->Correcting to obtain a second parameter feature vectorThere is->Wherein->For the second parameter feature vector->In->Device parameter factors for individual time intervals, +.>For the second parameter feature vector->In->A device parameter differential factor for each duration interval;
，/>for the first parameter feature vector->In->Device parameter factors for individual time intervals, +.>For correcting feature vector +.>In->A device parameter factor for each duration interval;
，/>for the first parameter feature vector->In->Device parameter differential factors for individual time intervals, +.>For correcting feature vector +.>In->A device parameter differential factor for each duration interval;
and correcting the plurality of first parameter feature vectors in the first target parameter feature data through the plurality of correction feature vectors in the target correction data to obtain second target parameter feature data containing a plurality of second parameter feature vectors.
7. The method of claim 4, wherein data partitioning and clustering the historical fault detection data based on the fault diagnosis results comprises:
determining a plurality of fault time points according to a plurality of fault diagnosis results with faults, extracting historical fault detection data of a preset time range before each fault time point to obtain a plurality of groups of abnormal working data, dividing the rest historical fault detection data based on the preset time range to obtain a plurality of groups of normal working data, clustering the plurality of groups of normal working data and the plurality of groups of abnormal working data respectively, and constructing a first data set and a second data set.
8. The method of claim 1, wherein the environmental analysis model and the fault analysis model are BP neural network models.
9. A system for analyzing and processing a fault of a charging pile, characterized in that the system is selected for implementing a method for analyzing and processing a fault of a charging pile according to any one of claims 1 to 8, comprising:
the data acquisition module is used for acquiring historical fault detection data of the charging pile, and comprises a plurality of fault diagnosis results, environment monitoring data and equipment parameter data corresponding to each fault diagnosis result;
the data processing module is used for carrying out data segmentation and clustering on the historical fault detection data based on the fault diagnosis result to obtain a first data set comprising a plurality of groups of normal working data and a second data set comprising a plurality of groups of abnormal working data;
the first data set construction module is used for extracting first environment characteristic data and first parameter characteristic data of each group of normal working data in the first data set and constructing to obtain a first training data set;
the first model training module is used for training through a first training data set to obtain an environment analysis model;
the second data set construction module is used for extracting fault diagnosis results of each group of abnormal working data in the second data set, second environment characteristic data and second parameter characteristic data corresponding to each fault diagnosis result, processing each group of second environment characteristic data based on an environment analysis model, correcting a plurality of groups of second parameter characteristic data according to the processing results, and constructing a second training data set;
the second model training module is used for training through a second training data set to obtain a fault analysis model;
the fault analysis module is used for collecting working environment data and working parameter data of the charging pile in real time, extracting target environment characteristic data and first target parameter characteristic data of the charging pile, processing the target environment characteristic data through the environment analysis model to generate target correction data, processing the first target parameter characteristic data based on the target correction data to generate second target parameter characteristic data, inputting the second target parameter characteristic data into the fault analysis model, and generating a fault analysis result.
10. The system of claim 9, wherein for the second dataset construction module, processing each set of second environmental characteristic data based on the environmental analysis model, and correcting the plurality of sets of second parametric characteristic data based on the processing results, comprises:
and processing each group of second environmental characteristic data through an environmental analysis model to generate parameter correction data corresponding to each group of second environmental characteristic data, correcting the second parameter characteristic data corresponding to each group of second environmental characteristic data through a plurality of groups of parameter correction data, and generating third parameter characteristic data corresponding to each group of second environmental characteristic data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410107129.6A CN117633479B (en) | 2024-01-26 | 2024-01-26 | Method and system for analyzing and processing faults of charging piles |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410107129.6A CN117633479B (en) | 2024-01-26 | 2024-01-26 | Method and system for analyzing and processing faults of charging piles |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117633479A true CN117633479A (en) | 2024-03-01 |
| CN117633479B CN117633479B (en) | 2024-04-09 |
Family
ID=90025549
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410107129.6A Active CN117633479B (en) | 2024-01-26 | 2024-01-26 | Method and system for analyzing and processing faults of charging piles |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117633479B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2014100712A4 (en) * | 2013-01-08 | 2014-09-11 | State Grid Corporation Of China | A new intelligent transformer and its application method |
| US20190095313A1 (en) * | 2017-09-22 | 2019-03-28 | Nec Laboratories America, Inc. | Log-based system maintenance and management |
| CN110533331A (en) * | 2019-08-30 | 2019-12-03 | 广东电网有限责任公司江门供电局 | A kind of fault early warning method and system based on transmission line of electricity data mining |
| CN114167837A (en) * | 2021-12-02 | 2022-03-11 | 中国路桥工程有限责任公司 | Intelligent fault diagnosis method and system for railway signal system |
| CN116226469A (en) * | 2023-05-09 | 2023-06-06 | 华南理工大学 | Intelligent diagnosis method and system for energy storage equipment faults |
| CN116842463A (en) * | 2023-07-05 | 2023-10-03 | 淮阴工学院 | Electric automobile charging pile equipment fault diagnosis method |
| CN117231439A (en) * | 2023-09-13 | 2023-12-15 | 西安热工研究院有限公司 | Fault diagnosis and control method and device for wind turbine generator set and electronic equipment |
-
2024
- 2024-01-26 CN CN202410107129.6A patent/CN117633479B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2014100712A4 (en) * | 2013-01-08 | 2014-09-11 | State Grid Corporation Of China | A new intelligent transformer and its application method |
| US20190095313A1 (en) * | 2017-09-22 | 2019-03-28 | Nec Laboratories America, Inc. | Log-based system maintenance and management |
| CN110533331A (en) * | 2019-08-30 | 2019-12-03 | 广东电网有限责任公司江门供电局 | A kind of fault early warning method and system based on transmission line of electricity data mining |
| CN114167837A (en) * | 2021-12-02 | 2022-03-11 | 中国路桥工程有限责任公司 | Intelligent fault diagnosis method and system for railway signal system |
| CN116226469A (en) * | 2023-05-09 | 2023-06-06 | 华南理工大学 | Intelligent diagnosis method and system for energy storage equipment faults |
| CN116842463A (en) * | 2023-07-05 | 2023-10-03 | 淮阴工学院 | Electric automobile charging pile equipment fault diagnosis method |
| CN117231439A (en) * | 2023-09-13 | 2023-12-15 | 西安热工研究院有限公司 | Fault diagnosis and control method and device for wind turbine generator set and electronic equipment |
Non-Patent Citations (2)
| Title |
|---|
| DE-XIN GAO 等: "Fault diagnosis system for electric vehicle charging devices based on fault tree analysis", IEEE, 31 December 2018 (2018-12-31) * |
| 林越 等: "基于AP-HMM混合模型的充电桩故障诊断", 广西师范大学学报(自然科学版), no. 01, 15 January 2018 (2018-01-15) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117633479B (en) | 2024-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106780121B (en) | Power consumption abnormity identification method based on power consumption load mode analysis | |
| EP1764728A1 (en) | Data compressing device and method, data analyzing device and method, and data managing system | |
| CN111241154A (en) | Storage battery fault early warning method and system based on big data | |
| CN111208445A (en) | Power battery abnormal monomer identification method and system | |
| CN110929934A (en) | Equipment failure prediction method and device, computer equipment and storage medium | |
| CN109143094B (en) | Abnormal data detection method and device for power battery | |
| CN116975378B (en) | Equipment environment monitoring method and system based on big data | |
| CN108957331B (en) | Battery performance detection method and battery performance detection system | |
| CN112990330B (en) | User energy abnormal data detection method and device | |
| CN113340353B (en) | Monitoring method, equipment and medium for power transmission line | |
| CN115800272B (en) | Power grid fault analysis method, system, terminal and medium based on topology identification | |
| CN114545234A (en) | Method for monitoring battery state based on battery temperature gradient change | |
| CN116552306B (en) | Monitoring system and method for direct current pile | |
| CN112529109A (en) | Unsupervised multi-model-based anomaly detection method and system | |
| CN116823227A (en) | Intelligent equipment management system and method based on Internet of things | |
| CN113218537A (en) | Training method, device, equipment and storage medium of temperature anomaly detection model | |
| CN112816881A (en) | Battery differential pressure abnormality detection method, battery differential pressure abnormality detection device and computer storage medium | |
| CN115327417A (en) | Early warning method and system for abnormity of power battery monomer and electronic equipment | |
| CN117076258A (en) | Remote monitoring method and system based on Internet cloud | |
| CN114839492A (en) | Method and device for identifying GIS partial discharge type based on MOBILE NETV3 | |
| CN114879070A (en) | Battery state evaluation method and related equipment | |
| CN117633479B (en) | Method and system for analyzing and processing faults of charging piles | |
| CN117110794A (en) | Intelligent diagnosis system and method for cable faults | |
| CN115659249B (en) | Abnormality detection method for intelligent station measurement control system | |
| CN117031201A (en) | Multi-scene topology anomaly identification method and system for power distribution network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |