CN118585755A - Safety monitoring and fault diagnosis method and system for charging pile based on artificial intelligence - Google Patents
Safety monitoring and fault diagnosis method and system for charging pile based on artificial intelligence Download PDFInfo
- Publication number
- CN118585755A CN118585755A CN202411056070.9A CN202411056070A CN118585755A CN 118585755 A CN118585755 A CN 118585755A CN 202411056070 A CN202411056070 A CN 202411056070A CN 118585755 A CN118585755 A CN 118585755A
- Authority
- CN
- China
- Prior art keywords
- data
- model
- fault
- charging pile
- association
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000012544 monitoring process Methods 0.000 title claims abstract description 28
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 21
- 238000012549 training Methods 0.000 claims abstract description 31
- 230000002159 abnormal effect Effects 0.000 claims abstract description 13
- 238000007781 pre-processing Methods 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims description 42
- 238000003066 decision tree Methods 0.000 claims description 34
- 238000004590 computer program Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000012952 Resampling Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 2
- 230000005856 abnormality Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 208000033999 Device damage Diseases 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of artificial intelligence, and solves the problem of abnormality of a charging pile, and discloses a charging pile safety monitoring and fault diagnosis method and system based on artificial intelligence, wherein the method comprises the following steps: acquiring relevant data of each time sequence of the intelligent charging pile to form a historical data set, preprocessing the historical data set to obtain a processed data set, constructing a work association model, and dividing the work association model into a normal state work association mode and an abnormal state work association mode; calculating corresponding association error data based on the work association model respectively; training and verifying the fault prediction pre-training model through the association error data set to obtain a prediction result of the fault prediction model; and calculating the probability of failure of the prediction result based on a preset failure probability model, and if the probability exceeds a preset probability threshold, analyzing the related data of the current time sequence to obtain a failure diagnosis result. The invention can analyze the charging pile and judge whether the charging pile is abnormal or not.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a charging pile safety monitoring and fault diagnosis method and system based on artificial intelligence.
Background
The intelligent charging pile is a high-tech charging device which is raised along with the development of the new energy automobile industry. Has the following characteristics: through the internet technology, the intelligent charging pile can remotely monitor the charging state, so that fault diagnosis and remote maintenance are realized; the intelligent charging pile is provided with a touch screen or keys, and a user can perform charging operation through the interfaces, such as selecting a charging mode, paying fees and the like; the intelligent charging pile can collect charging data, including charging time, electric quantity, user usage habit and the like, and provides data support for operators to optimize services; when unsafe conditions such as overload, short circuit, electric leakage and the like occur, the protection function can be automatically started, and the safety of the charging process is ensured; according to the power grid load and the user demand, the charging power and time can be intelligently scheduled, and ordered charging can be realized; information security can also be achieved, preventing user data from being revealed or unauthorized access.
Although the intelligent charging pile can remotely monitor the charging state in real time, some problems still can be encountered in actual operation, such as: the monitoring system may have technical faults, such as software defects, hardware damage or network connection problems, which lead to inaccurate monitoring data or interruption of monitoring; real-time monitoring involves the transmission and storage of large amounts of data, potentially facing the risk of data leakage or unauthorized access; the monitoring system needs to be capable of timely identifying abnormal conditions and giving an alarm, and if the alarm system is slow in response, the problem can not be timely processed; severe weather or other environmental factors may affect the operation of the monitoring device, resulting in inaccurate monitoring data or device damage; the real-time monitoring system is sensitive to time, any delay can affect the monitoring effect, and high real-time performance of the system needs to be ensured.
The problems are directly or indirectly caused to deviate from the monitoring result, so that fault diagnosis is not accurate enough, and therefore, whether prediction and charging pile safety are monitored and fault diagnosis are combined can be judged, so that the probability of fault occurrence in the next period can be predicted, corresponding measures are timely taken in the current period, and an alarm or maintenance system can know the problem and further a worker can timely process the problem.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a charging pile safety monitoring and fault diagnosis method and system based on artificial intelligence.
In order to solve the technical problems, the invention is solved by the following technical scheme: a charging pile safety monitoring and fault diagnosis method based on artificial intelligence comprises the following steps: based on a preset time sequence, acquiring related data of each time sequence of the intelligent charging pile to form a historical data set, wherein the related data at least comprises temperature data, voltage data and current data; preprocessing the historical data set to obtain a processed data set, constructing a work association model of temperature data, voltage data and current data, and dividing the work association model into a normal state work association mode and an abnormal state work association mode according to a work state; identifying a state work association mode based on the processed data set and respectively calculating corresponding association error data based on the work association mode to obtain an association error data set; constructing a fault prediction pre-training model, training and verifying the fault prediction pre-training model through a correlation error data set to obtain a fault prediction model, and predicting correlation error data of a state work correlation mode at the next moment of the intelligent charging pile based on the fault prediction model to obtain a prediction result; and calculating the probability of failure of the prediction result based on a preset failure probability model, and if the probability exceeds a preset probability threshold, analyzing the related data of the current time sequence of the intelligent charging pile to obtain a failure diagnosis result.
As one implementation manner, the construction of the operation association mode of the temperature data, the voltage data and the current data includes the following processes: the temperature data are temperature data before working and temperature data after working; the voltage data are input voltage data and output voltage data; the current data are input current data and output current data; obtaining input power data based on the input voltage data and the input current data, obtaining output power data based on the output voltage data and the output current data, and obtaining temperature change data based on the temperature data before and the temperature data after the operation; obtaining power loss data based on the input power data and the output power data; constructing a work association model according to the temperature change data, the power consumption data and the time, and obtaining association error data based on the work association model; the work association model is expressed as follows:
；
wherein, Representing the associated error data and,The data representing the temperature change is displayed,Represent the firstThe power consumption data of the time series,Represent the firstThe time series of the time series,Indicating the temperature influence factor(s),Indicating the range of influence of the temperature,，Represent the firstA time series of input power data,Represent the firstTime-series output power data.
As an implementation manner, the preprocessing includes data cleaning processing, removing or filling in missing data, and identifying and processing abnormal data or outlier data; or time alignment processing; or data type conversion processing; or time series decomposition processing; or data resampling processing; or sliding window feature processing; or time feature engineering treatment; or normalization/normalization processing; or differential processing; or data denoising processing; or data segmentation processing; or one or more of the data scrolling processes.
As an embodiment, the constructing the failure prediction pre-training model includes the following steps: constructing an initial fault prediction model based on a plurality of decision trees; obtaining importance weights of each decision tree through the error sum of each data in the associated error data set in the fault prediction model; the importance weight evaluates importance coefficients of the corresponding decision tree for prediction accuracy, the importance coefficients representing the following:
；
wherein T represents the number of decision trees, Representing a decision tree, y representing a decision treeThe prediction error sum of all sample predictions, X represents the importance coefficient of the corresponding decision tree; updating the initial fault prediction model according to the importance weight of each decision tree until the preset iteration times or the convergence of the performance of the initial fault prediction model are reached, so as to obtain a fault prediction pre-training model.
As an embodiment, the fault prediction model is expressed as follows:
；
wherein, Represents a fault prediction model, N represents the number of decision trees,Represent the firstThe predicted outcome of the decision tree is then determined,Representing the errors of the prediction result and the real data,Representing the importance coefficient.
As an implementation manner, the preset fault probability model is expressed as follows:
；
wherein, Representing predicted resultsThe probability value of the occurrence of a fault,Representing predicted resultsIs used for the adjustment factor of (a),The mean value is represented as such,Representing standard deviation.
As an implementation manner, the analyzing the related data of the current time sequence of the intelligent charging pile to obtain the fault diagnosis result includes the following steps: at least respectively analyzing input voltage data and output voltage data, input current data and output current data, pre-working temperature data and post-working temperature data which are related to the current time sequence; if any one of the input voltage data and the output voltage data, the input current data and the output current data, the temperature data before operation and the temperature data after operation has a problem, matching the corresponding fault diagnosis result.
The charging pile safety monitoring and fault diagnosis system based on artificial intelligence comprises a data acquisition module, a processing and constructing module, an identification and calculation module, a construction and prediction module and a judgment and analysis module; the data acquisition module is used for acquiring related data of each time sequence of the intelligent charging pile based on a preset time sequence to form a historical data set, wherein the related data at least comprises temperature data, voltage data and current data; the processing and constructing module is used for preprocessing the historical data set to obtain a processed data set, constructing a work association model of temperature data, voltage data and current data, and dividing the work association model into a normal state work association mode and an abnormal state work association mode according to the working state; the recognition calculation module is used for recognizing a state work association mode based on the processed data set and respectively calculating corresponding association error data based on the work association model so as to obtain an association error data set; the construction prediction module is used for constructing a fault prediction pre-training model, training and verifying the fault prediction pre-training model through the association error data set to obtain a fault prediction model, and predicting association error data of a state work association mode at the next moment of the intelligent charging pile based on the fault prediction model to obtain a prediction result; and the judging and analyzing module is used for calculating the probability of the occurrence of faults of the prediction result based on a preset fault probability model, and analyzing the related data of the current time sequence of the intelligent charging pile if the probability exceeds a preset probability threshold value to obtain a fault diagnosis result.
A computer readable storage medium storing a computer program which when executed by a processor performs the method of: based on a preset time sequence, acquiring related data of each time sequence of the intelligent charging pile to form a historical data set, wherein the related data at least comprises temperature data, voltage data and current data; preprocessing the historical data set to obtain a processed data set, constructing a work association model of temperature data, voltage data and current data, and dividing the work association model into a normal state work association mode and an abnormal state work association mode according to a work state; identifying a state work association mode based on the processed data set and respectively calculating corresponding association error data based on the work association mode to obtain an association error data set; constructing a fault prediction pre-training model, training and verifying the fault prediction pre-training model through a correlation error data set to obtain a fault prediction model, and predicting correlation error data of a state work correlation mode at the next moment of the intelligent charging pile based on the fault prediction model to obtain a prediction result; and calculating the probability of failure of the prediction result based on a preset failure probability model, and if the probability exceeds a preset probability threshold, analyzing the related data of the current time sequence of the intelligent charging pile to obtain a failure diagnosis result.
An artificial intelligence based charging pile safety monitoring and fault diagnosis device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor executing the computer program to implement the method as set forth in the following claims: based on a preset time sequence, acquiring related data of each time sequence of the intelligent charging pile to form a historical data set, wherein the related data at least comprises temperature data, voltage data and current data; preprocessing the historical data set to obtain a processed data set, constructing a work association model of temperature data, voltage data and current data, and dividing the work association model into a normal state work association mode and an abnormal state work association mode according to a work state; identifying a state work association mode based on the processed data set and respectively calculating corresponding association error data based on the work association mode to obtain an association error data set; constructing a fault prediction pre-training model, training and verifying the fault prediction pre-training model through a correlation error data set to obtain a fault prediction model, and predicting correlation error data of a state work correlation mode at the next moment of the intelligent charging pile based on the fault prediction model to obtain a prediction result; and calculating the probability of failure of the prediction result based on a preset failure probability model, and if the probability exceeds a preset probability threshold, analyzing the related data of the current time sequence of the intelligent charging pile to obtain a failure diagnosis result.
The invention has the remarkable technical effects due to the adoption of the technical scheme: through the method and the system, the fault prediction model is designed, the probability of faults in the next time period can be predicted, and then various data in the time period are analyzed, so that the problem can be prevented, and an alarm or maintenance system can know the problem, so that staff can timely handle the problem.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
FIG. 1 is a schematic overall flow diagram of the method of the present invention;
FIG. 2 is a schematic diagram of the overall structure of the system of the present invention;
FIG. 3 is a flow chart corresponding to one embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the following examples, which are illustrative of the present invention and are not intended to limit the present invention thereto.
Example 1
A charging pile safety monitoring and fault diagnosis method based on artificial intelligence, as shown in figure 1, comprises the following steps:
S100, based on preset time sequences, acquiring relevant data of each time sequence of the intelligent charging pile to form a historical data set, wherein the relevant data at least comprises temperature data, voltage data and current data;
S200, preprocessing the historical data set to obtain a processed data set, constructing a work association model of temperature data, voltage data and current data, and dividing the work association model into a normal state work association mode and an abnormal state work association mode according to a work state;
S300, identifying a state work association mode based on the processed data set and respectively calculating corresponding association error data based on the work association mode to obtain an association error data set;
S400, constructing a fault prediction pre-training model, training and verifying the fault prediction pre-training model through a correlation error data set to obtain a fault prediction model, and predicting correlation error data of a state work correlation mode at the next moment of the intelligent charging pile based on the fault prediction model to obtain a prediction result;
s500, calculating the probability of faults of the prediction result based on a preset fault probability model, and if the probability exceeds a preset probability threshold, analyzing the related data of the current time sequence of the intelligent charging pile to obtain a fault diagnosis result.
In step S200, the operation association mode of the temperature data, the voltage data, and the current data is constructed, as shown in fig. 3, including the following procedures:
S210, the temperature data are temperature data before working and temperature data after working; the voltage data are input voltage data and output voltage data; the current data are input current data and output current data;
S220, obtaining input power data based on the input voltage data and the input current data, obtaining output power data based on the output voltage data and the output current data, and obtaining temperature change data based on the temperature data before and the temperature data after the operation;
s230, obtaining power loss data based on the input power data and the output power data;
S240, constructing a work association model according to the temperature change data, the power consumption data and the time, and obtaining association error data based on the work association model; the work association model is expressed as follows:
；
wherein, Representing the associated error data and,The data representing the temperature change is displayed,Represent the firstThe power consumption data of the time series,Represent the firstThe time series of the time series,Indicating the temperature influence factor(s),Indicating the range of influence of the temperature,，Represent the firstA time series of input power data,Represent the firstTime-series output power data.
Here, based on the input voltage data and the input current data, input power data is obtained, and an expression of the input power data may be expressed as，Represent the firstA time series of input voltage data,Represent the firstThe time series input current data, based on the output voltage data and the output current data, obtains output power data, wherein the expression of the output power data can be as follows，Represent the firstA time series of output voltage data,Represent the firstThe output current data of each time sequence, the input voltage data, the input current data, the output voltage data and the output current data can be obtained in real time, and can be obtained without related calculation, and the real-time obtaining mode can be realized by the prior art means, so that the problem to be solved in the embodiment is only to carry out subsequent related application based on the data obtained in real time.
In one embodiment, the preprocessing includes a data cleansing process to remove or fill in missing data, identify and process outlier or outlier data; or time alignment processing; or data type conversion processing; or time series decomposition processing; or data resampling processing; or sliding window feature processing; or time feature engineering treatment; or normalization/normalization processing; or differential processing; or data denoising processing; or data segmentation processing; or one or more of the data scrolling processes. The preprocessing can be performed by selecting a specific processing mode of preprocessing according to the specific situation of the data set, and finally obtaining the processed data set.
Decision trees are commonly used for classification and regression tasks. The data is partitioned into smaller and smaller subsets by a series of questions until a stop condition is met, eventually giving a prediction result at each leaf node. Decision trees consist of nodes (including internal nodes and leaf nodes) and edges. The internal nodes represent attribute tests, and the leaf nodes give out prediction results. At each internal node, the decision tree selects a feature and threshold to segment the data. Feature selection is based on an opacity metric. The data is partitioned into different subsets according to the eigenvalues, and this process is recursively performed until a stop condition is met. The stop condition may be that a preset maximum depth is reached, the number of samples in the node is less than a certain threshold, or further segmentation does not significantly reduce the non-purity. In classification problems, leaf nodes typically give a class label; in the regression problem, the leaf node gives a value. Therefore, the embodiment is a fault prediction pre-training model constructed by adopting a decision tree, and comprises the following steps: constructing an initial fault prediction model based on a plurality of decision trees; obtaining importance weights of each decision tree through the error sum of each data in the associated error data set in the fault prediction model; the importance weight evaluates importance coefficients of the corresponding decision tree for prediction accuracy, the importance coefficients representing the following:
；
wherein T represents the number of decision trees, Representing a decision tree, y representing a decision treeThe prediction error sum of all sample predictions, X represents the importance coefficient of the corresponding decision tree; updating the initial fault prediction model according to the importance weight of each decision tree until the preset iteration times or the convergence of the performance of the initial fault prediction model are reached, so as to obtain a fault prediction pre-training model.
In this embodiment, the failure prediction model is expressed as follows:
；
wherein, Represents a fault prediction model, N represents the number of decision trees,Represent the firstThe predicted outcome of the decision tree is then determined,Representing the errors of the prediction result and the real data,Representing the importance coefficient.
In one embodiment of the present invention, the preset failure probability model is expressed as follows:
；
wherein, Representing predicted resultsThe probability value of the occurrence of a fault,Representing predicted resultsIs used for the adjustment factor of (a),The mean value is represented as such,Representing standard deviation. According to the measurement and calculation, the prediction result meets normal distribution within a certain range, so that the possibility of faults is judged by calculating the fault probability, and if the probability exceeds a set threshold value, the follow-up specific fault analysis process, namely the follow-up operation step, is required to be executed.
In one embodiment, the analyzing the related data of the current time sequence of the intelligent charging pile to obtain the fault diagnosis result includes the following steps: at least respectively analyzing input voltage data and output voltage data, input current data and output current data, pre-working temperature data and post-working temperature data which are related to the current time sequence; if any one of the input voltage data and the output voltage data, the input current data and the output current data, the temperature data before operation and the temperature data after operation has a problem, matching the corresponding fault diagnosis result.
In this embodiment, the method is formulated for predicting that the predicted result of the next time sequence does not meet the requirement, if the predicted result of the next time sequence has a problem, it is indicated that the related data of the current time sequence may have a potential problem, then the related data of the current time sequence is analyzed, of course, not only the input voltage data and the output voltage data, the input current data and the output current data, the temperature data before operation and the temperature data after operation, but also other related data, such as protection technical parameters, may be analyzed, if the data has a problem, then a specific fault diagnosis result may be matched or analyzed, for example, a simple fault diagnosis table may be set in advance, if a very simple fault is found, then the fault diagnosis result may be directly matched to the corresponding result, if the fault is too complex, then detailed analysis and calculation may be performed according to the related data, and finally a specific fault diagnosis result may be obtained.
Example 2
The system for monitoring safety and diagnosing faults of the charging pile based on artificial intelligence comprises a data acquisition module 100, a processing and constructing module 200, an identification and calculation module 300, a construction and prediction module 400 and a judgment and analysis module 500 as shown in fig. 2; the data acquisition module 100 is configured to acquire, based on a preset time sequence, relevant data of each time sequence of the intelligent charging pile to form a historical data set, where the relevant data at least includes temperature data, voltage data, and current data; the processing and constructing module 200 is configured to preprocess the historical data set to obtain a processed data set, construct a working association model of temperature data, voltage data and current data, and divide the working association model into a normal state working association mode and an abnormal state working association mode according to a working state; the recognition calculation module 300 is configured to recognize a state work association mode based on the processed data set and calculate corresponding association error data based on the work association model, so as to obtain an association error data set; the construction prediction module 400 is configured to construct a failure prediction pre-training model, train and verify the failure prediction pre-training model through a correlation error data set to obtain a failure prediction model, and predict correlation error data of a state work correlation mode at the next moment of the intelligent charging pile based on the failure prediction model to obtain a prediction result; the judgment analysis module 500 calculates the probability of failure of the prediction result based on a preset failure probability model, and if the probability exceeds a preset probability threshold, analyzes the related data of the current time sequence of the intelligent charging pile to obtain a failure diagnosis result.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other.
It will be apparent to those skilled in the art that embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should be noted that: reference in the specification to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the invention. Thus, the appearances of the phrase "one embodiment" or "an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment.
In addition, the specific embodiments described in the present specification may differ in terms of parts, shapes of components, names, and the like. All equivalent or simple changes of the structure, characteristics and principle according to the inventive concept are included in the protection scope of the present invention. Those skilled in the art may make various modifications or additions to the described embodiments or substitutions in a similar manner without departing from the scope of the invention as defined in the accompanying claims.
Claims (10)
1. The safety monitoring and fault diagnosis method for the charging pile based on the artificial intelligence is characterized by comprising the following steps of: based on a preset time sequence, acquiring related data of each time sequence of the intelligent charging pile to form a historical data set, wherein the related data at least comprises temperature data, voltage data and current data; preprocessing the historical data set to obtain a processed data set, constructing a work association model of temperature data, voltage data and current data, and dividing the work association model into a normal state work association mode and an abnormal state work association mode according to a work state; identifying a state work association mode based on the processed data set and respectively calculating corresponding association error data based on the work association mode to obtain an association error data set; constructing a fault prediction pre-training model, training and verifying the fault prediction pre-training model through a correlation error data set to obtain a fault prediction model, and predicting correlation error data of a state work correlation mode at the next moment of the intelligent charging pile based on the fault prediction model to obtain a prediction result; and calculating the probability of failure of the prediction result based on a preset failure probability model, and if the probability exceeds a preset probability threshold, analyzing the related data of the current time sequence of the intelligent charging pile to obtain a failure diagnosis result.
2. The method for monitoring safety and diagnosing faults of the charging pile based on artificial intelligence according to claim 1, wherein the construction of the operation association mode of temperature data, voltage data and current data comprises the following processes: the temperature data are temperature data before working and temperature data after working; the voltage data are input voltage data and output voltage data; the current data are input current data and output current data; obtaining input power data based on the input voltage data and the input current data, obtaining output power data based on the output voltage data and the output current data, and obtaining temperature change data based on the temperature data before and the temperature data after the operation; obtaining power loss data based on the input power data and the output power data, and obtaining the power loss data; constructing a work association model according to the temperature change data, the power consumption data and the time, and obtaining association error data based on the work association model; the work association model is expressed as follows:
；
wherein, Representing the associated error data and,The data representing the temperature change is displayed,Represent the firstThe power consumption data of the time series,Represent the firstThe time series of the time series,Indicating the temperature influence factor(s),Indicating the range of influence of the temperature,，Represent the firstA time series of input power data,Represent the firstTime-series output power data.
3. The artificial intelligence based charging pile safety monitoring and fault diagnosis method according to claim 1, wherein the preprocessing comprises data cleaning processing, removing or filling up missing data, identifying and processing abnormal data or outlier data; or time alignment processing; or data type conversion processing; or time series decomposition processing; or data resampling processing; or sliding window feature processing; or time feature engineering treatment; or normalization/normalization processing; or differential processing; or data denoising processing; or data segmentation processing; or one or more of the data scrolling processes.
4. The method for monitoring safety and diagnosing faults of the charging pile based on artificial intelligence according to claim 1, wherein the constructing of the fault prediction pre-training model comprises the following steps: constructing an initial fault prediction model based on a plurality of decision trees; obtaining importance weights of each decision tree through the error sum of each data in the associated error data set in the fault prediction model; the importance weight evaluates importance coefficients of the corresponding decision tree for prediction accuracy, the importance coefficients representing the following:
；
wherein T represents the number of decision trees, Representing a decision tree, y representing a decision treeThe prediction error sum of all sample predictions, X represents the importance coefficient of the corresponding decision tree; updating the initial fault prediction model according to the importance weight of each decision tree until the preset iteration times or the convergence of the performance of the initial fault prediction model are reached, so as to obtain a fault prediction pre-training model.
5. The artificial intelligence based charging pile safety monitoring and fault diagnosis method according to claim 1, wherein the fault prediction model is represented as follows:
；
wherein, Represents a fault prediction model, N represents the number of decision trees,Represent the firstThe predicted outcome of the decision tree is then determined,Representing the errors of the prediction result and the real data,Representing the importance coefficient.
6. The safety monitoring and fault diagnosis method for charging piles based on artificial intelligence according to claim 1, wherein the preset fault probability model is represented as follows:
；
wherein, Representing predicted resultsThe probability value of the occurrence of a fault,Representing predicted resultsIs used for the adjustment factor of (a),The mean value is represented as such,Representing standard deviation.
7. The safety monitoring and fault diagnosis method for charging piles based on artificial intelligence according to claim 1, wherein the analysis of the related data of the current time sequence of the intelligent charging piles to obtain the fault diagnosis result comprises the following steps: at least respectively analyzing input voltage data and output voltage data, input current data and output current data, pre-working temperature data and post-working temperature data which are related to the current time sequence; if any one of the input voltage data and the output voltage data, the input current data and the output current data, the temperature data before operation and the temperature data after operation has a problem, matching the corresponding fault diagnosis result.
8. The charging pile safety monitoring and fault diagnosis system based on the artificial intelligence is characterized by comprising a data acquisition module, a processing and constructing module, an identification and calculation module, a construction and prediction module and a judgment and analysis module; the data acquisition module is used for acquiring related data of each time sequence of the intelligent charging pile based on a preset time sequence to form a historical data set, wherein the related data at least comprises temperature data, voltage data and current data; the processing and constructing module is used for preprocessing the historical data set to obtain a processed data set, constructing a work association model of temperature data, voltage data and current data, and dividing the work association model into a normal state work association mode and an abnormal state work association mode according to the working state; the recognition calculation module is used for recognizing a state work association mode based on the processed data set and respectively calculating corresponding association error data based on the work association model so as to obtain an association error data set; the construction prediction module is used for constructing a fault prediction pre-training model, training and verifying the fault prediction pre-training model through the association error data set to obtain a fault prediction model, and predicting association error data of a state work association mode at the next moment of the intelligent charging pile based on the fault prediction model to obtain a prediction result; and the judging and analyzing module is used for calculating the probability of the occurrence of faults of the prediction result based on a preset fault probability model, and analyzing the related data of the current time sequence of the intelligent charging pile if the probability exceeds a preset probability threshold value to obtain a fault diagnosis result.
9. A computer readable storage medium storing a computer program, which when executed by a processor implements the method of any one of claims 1 to 7.
10. A charging pile safety monitoring and fault diagnosis device based on artificial intelligence, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the method according to any one of claims 1 to 7 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411056070.9A CN118585755A (en) | 2024-08-02 | 2024-08-02 | Safety monitoring and fault diagnosis method and system for charging pile based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411056070.9A CN118585755A (en) | 2024-08-02 | 2024-08-02 | Safety monitoring and fault diagnosis method and system for charging pile based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118585755A true CN118585755A (en) | 2024-09-03 |
Family
ID=92528549
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411056070.9A Pending CN118585755A (en) | 2024-08-02 | 2024-08-02 | Safety monitoring and fault diagnosis method and system for charging pile based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118585755A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115238752A (en) * | 2022-08-15 | 2022-10-25 | 福州亿力卓越管理顾问有限公司 | Fill electric pile fault prediction system based on artificial intelligence |
| WO2023130898A1 (en) * | 2022-01-05 | 2023-07-13 | 中车唐山机车车辆有限公司 | System fault monitoring method and apparatus, and electronic device and storage medium |
| CN116578873A (en) * | 2023-06-14 | 2023-08-11 | 国网北京市电力公司 | Method, device, equipment and medium for diagnosing faults of charging pile |
| CN117435984A (en) * | 2023-10-30 | 2024-01-23 | 深圳市皇驰科技有限公司 | Charging pile fault prediction method and system |
-
2024
- 2024-08-02 CN CN202411056070.9A patent/CN118585755A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023130898A1 (en) * | 2022-01-05 | 2023-07-13 | 中车唐山机车车辆有限公司 | System fault monitoring method and apparatus, and electronic device and storage medium |
| CN115238752A (en) * | 2022-08-15 | 2022-10-25 | 福州亿力卓越管理顾问有限公司 | Fill electric pile fault prediction system based on artificial intelligence |
| CN116578873A (en) * | 2023-06-14 | 2023-08-11 | 国网北京市电力公司 | Method, device, equipment and medium for diagnosing faults of charging pile |
| CN117435984A (en) * | 2023-10-30 | 2024-01-23 | 深圳市皇驰科技有限公司 | Charging pile fault prediction method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108375715B (en) | Power distribution network line fault risk day prediction method and system | |
| JP6141235B2 (en) | How to detect anomalies in time series data | |
| CN115760484B (en) | Method, device and system for improving hidden danger identification capability of power distribution area and storage medium | |
| CN117114454B (en) | DC sleeve state evaluation method and system based on Apriori algorithm | |
| CN113036913B (en) | Method and device for monitoring state of comprehensive energy equipment | |
| CN111262750B (en) | Method and system for evaluating baseline model | |
| CN117176560B (en) | Monitoring equipment supervision system and method based on Internet of things | |
| CN117408162B (en) | Power grid fault control method based on digital twin | |
| CN114551271A (en) | Method and device for monitoring machine operation condition, storage medium and electronic equipment | |
| KR101953558B1 (en) | Apparatus and Method for Fault Management of Smart Devices | |
| CN111612149A (en) | Main network line state detection method, system and medium based on decision tree | |
| CN118395358B (en) | Intelligent anti-misoperation topology analysis method for transformer substation | |
| CN118096131B (en) | Operation and maintenance inspection method based on electric power scene model | |
| CN117471346A (en) | Method and system for determining remaining life and health status of retired battery module | |
| US20230297095A1 (en) | Monitoring device and method for detecting anomalies | |
| CN117113157B (en) | Platform district power consumption fault detection system based on artificial intelligence | |
| CN109523030B (en) | Telemetering parameter abnormity monitoring system based on machine learning | |
| CN112128950B (en) | Machine room temperature and humidity prediction method and system based on multiple model comparisons | |
| CN113868948A (en) | User-oriented dynamic threshold model training system and method | |
| CN117977536A (en) | Smart power grid load identification method | |
| CN116258467A (en) | Electric power construction management and control system | |
| US11339763B2 (en) | Method for windmill farm monitoring | |
| CN118585755A (en) | Safety monitoring and fault diagnosis method and system for charging pile based on artificial intelligence | |
| CN111382946B (en) | Autonomous evaluation method and system for health state of equipment and industrial internet equipment | |
| Junhong et al. | Software reliability nonlinear modeling and its fuzzy evaluation |
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 |