A charging pile fault detection system and method based on the Internet of Things

Abstract

The application discloses a charging pile fault detection system and method based on an Internet of Things, relates to the technical field of charging equipment fault detection, and comprises the following steps: constructing a fault detection cloud platform, analyzing the influence degree of the charging state of a charging pile on the equipment operation state of power distribution equipment; obtaining the historical equipment operation record of target power distribution equipment, analyzing the correlation degree of the operation state of the target power distribution equipment and the charging pile, and obtaining equipment correlation data; obtaining the equipment correlation data of the power distribution equipment and the charging pile, obtaining a constructed fault detection model, optimizing the fault detection model based on the equipment correlation data, and obtaining a target fault detection model; monitoring the charging piles in the charging station and the target power distribution equipment in a current period, performing fault detection on the charging piles according to the target fault detection model, obtaining target detection data, and intelligently detecting and managing the charging piles based on the target detection data.

Description

Technical Field

[0001] This invention relates to the field of charging equipment fault detection technology, specifically a charging pile fault detection system and method based on the Internet of Things. Background Technology

[0002] In recent years, with the increasing number of electric vehicles, the usage and demand for charging piles have also increased significantly as an important infrastructure to ensure the normal operation of electric vehicles. Whether charging piles can be used normally and stably plays a crucial role in whether electric vehicles can be widely popularized. Therefore, the fault detection of charging piles is particularly important.

[0003] Currently, manual inspection is the primary method for fault detection of charging piles. However, this method has several drawbacks and problems. Manual inspection requires inspectors to check each charging pile sequentially, which is not only inefficient but also requires a significant investment of manpower, increasing the operating costs of charging piles. Furthermore, during the inspection process, inspectors rely mainly on their own experience to make judgments, leading to a degree of subjectivity in the test results. In addition to manual inspection, some methods analyze charging pile data by monitoring its operation. While this method can detect anomalies based on real-time monitoring data, it fails to consider that the charging piles within a charging station do not operate independently. The power distribution equipment within the charging station is responsible for supplying power to the charging piles. In fault analysis, the impact of the power distribution equipment on the charging piles is rarely considered, which can easily lead to inaccurate fault detection and affect the normal operation of the charging station. Summary of the Invention

[0004] The purpose of this invention is to provide a charging pile fault detection system and method based on the Internet of Things to solve the problems raised in the prior art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a charging pile fault detection method based on the Internet of Things, the method comprising:

[0006] Step S100: Construct a fault detection cloud platform, obtain historical charging records of charging piles, obtain historical equipment anomaly records of power distribution equipment that distributes power to charging piles, analyze the degree of influence of charging pile charging status on the equipment operating status of power distribution equipment, and obtain the target power distribution equipment.

[0007] Step S200: Obtain the historical operation records of the charging pile, obtain the historical equipment operation records of the target power distribution equipment, analyze the correlation between the operation status of the target power distribution equipment and the charging pile, and obtain equipment correlation data;

[0008] Step S300: Obtain the equipment association data between the power distribution equipment and the charging pile, obtain the constructed fault detection model, optimize the fault prediction model based on the equipment association data, and obtain the target fault detection model;

[0009] Step S400: Monitor the charging piles and target power distribution equipment in the charging station during the current cycle, and perform fault detection on the charging piles according to the target fault detection model to obtain target detection data. Based on the target detection data, perform intelligent detection management on the charging piles.

[0010] Furthermore, step S100 includes:

[0011] Step S101: Construct a fault detection cloud platform to monitor the charging process of the charging pile to the vehicle in the charging station, obtain the historical charging records of the charging pile, and obtain the average charging power of the charging pile from the historical charging records.

[0012] Step S102: Calculate the characteristic charging value of each charging station in each historical charging record, where the characteristic charging value R of a charging station in a certain historical charging record is:

[0013] ,

[0014] Where P represents the average charging power of a charging station in a certain historical charging record; P max P represents the maximum average charging power of the charging station across all historical charging records; min This represents the minimum average charging power of the charging station across all historical charging records.

[0015] Step S103: Obtain the average value of the characteristic charging value of each historical charging record. When the characteristic charging value of a certain historical charging record is greater than the average value, the historical charging record is recorded as the marked historical charging record of the charging pile.

[0016] Step S104: Obtain the power distribution equipment that distributes power to the charging pile, obtain the historical equipment anomaly records of the power distribution equipment, and extract the historical equipment anomaly data from the historical equipment anomaly records. The historical equipment anomaly data includes the data corresponding to various equipment indicators of the power distribution equipment.

[0017] Step S105: Obtain the preset data operating range of various equipment indicators of the power distribution equipment from the cloud platform. When all the equipment indicators of the power distribution equipment in a certain historical equipment anomaly record are within the data operating range of the equipment indicators, record the certain historical equipment anomaly record as the characteristic historical equipment anomaly record of the power distribution equipment.

[0018] Step S106: Obtain the historical equipment anomaly records for each feature of the power distribution equipment. The historical charging record is the total number of charging piles marked with historical charging records. Calculate the impact value S of the charging piles on the equipment status of the power distribution equipment.

[0019] ,

[0020] Where q represents the total number of characteristic historical equipment anomaly records of the power distribution equipment, and F i This represents the total number of charging piles marked with historical charging records within the i-th characteristic historical equipment anomaly record of the power distribution equipment; M sum This represents the total number of charging piles that provide power distribution for power distribution equipment;

[0021] Step S107: When the device status influence value is greater than the preset device status influence threshold, it is determined that the device operation status of the power distribution equipment is affected by the charging status of the charging pile, and the power distribution equipment is recorded as the target power distribution equipment.

[0022] Furthermore, step S200 includes:

[0023] Step S201: Obtain the historical operation records of the charging piles in the charging station, and extract the historical operation data of the charging piles from the historical operation records. The historical operation data includes the data corresponding to various equipment parameters of the charging piles.

[0024] Step S202: Obtain the historical equipment operation records of the target power distribution equipment, and obtain the data corresponding to the various equipment indicators of the target power distribution equipment from the historical equipment operation records;

[0025] Step S203: Analyze the correlation between the operating status of the target power distribution equipment and the charging piles. Specifically, the correlation between the c-th equipment indicator of the target power distribution equipment and the operating status of the charging piles within the charging pile is analyzed by constructing an equipment correlation regression model. The equipment correlation regression model Y... c :

[0026] ,

[0027] Where β0 represents the feature intercept; β1, β2, ..., β n Represented by the regression coefficients of various equipment parameters of the charging pile; ε is the error term; X1, X2, ..., X n These are the various equipment parameters of the charging pile;

[0028] Step S204: Obtain the data of the c-th equipment indicator of the target power distribution equipment in each historical equipment operation record, obtain the data of each equipment parameter of the charging pile in each historical operation record, and divide each historical equipment operation record and the historical operation record into a training set and a test set;

[0029] Step S205: Using the training set, solve for the regression coefficients using the squared residuals (SSE), where the squared residuals (SSE) are:

[0030] ,

[0031] Where j is the total number of historical equipment operation records of the target power distribution equipment in the training set; Y c，z For the target power distribution equipment, the value corresponding to the c-th equipment indicator in the z-th historical equipment operation record in the training set; Y´ c，z For the target power distribution equipment, the predicted value of the c-th equipment indicator in the z-th historical operation record of the training set;

[0032] Step S206: Minimize the squared residuals SSE, and use the squared residuals SSE to minimize β0 and β1 respectively. α Taking partial derivatives, where α = 1, 2, ..., n, we get:

[0033] ,

[0034] ,

[0035] Among them, X z，α This represents the value of the αth device indicator in the zth historical operation record of the training set, which is a charging pile.

[0036] For β0, β α Solving by taking the partial derivatives, we get:

[0037] ,

[0038] Where X represents the parameter matrix of various equipment parameters of the charging pile; Y c =Vβ+ε; β represents a vector of regression coefficients, where β = (β0, β1, ..., β...). n );

[0039] Step S207: Use the test set to evaluate the performance of the equipment association regression model, optimize the equipment management regression model, obtain the c-th equipment index of the preset target power distribution equipment, and the first feature regression coefficient threshold γ1 and the second feature regression coefficient threshold γ2 of the charging pile, where γ1>0>γ2.

[0040] Step S208: When the charging pile is in the e-th equipment parameter β in the equipment correlation regression model e >γ1, determine the c-th equipment index of the target power distribution equipment, which has a positive correlation with the e-th equipment parameter of the charging pile, when β e <γ2, it is determined that the c-th equipment indicator of the target power distribution equipment has a negative correlation with the e-th equipment parameter of the charging pile. When it is determined that the c-th equipment indicator of the target power distribution equipment has a correlation with the e-th equipment parameter of the charging pile, the c-th equipment indicator of the target power distribution equipment is recorded as the associated equipment indicator of the e-th equipment parameter of the charging pile. When γ1>β e >γ2, the c-th equipment indicator of the target power distribution equipment is not related to the e-th equipment parameter of the charging pile;

[0041] Step S209: Obtain the various equipment indicators of the target power distribution equipment, the correlation equipment indicators between them and the various equipment parameters of the charging pile, and the equipment correlation regression coefficients between the various equipment indicators of the target power distribution equipment and the various equipment parameters of the charging pile. Then, aggregate them to obtain the equipment correlation data between the target power distribution equipment and the charging pile.

[0042] Furthermore, step S300 includes:

[0043] Step S301: Obtain historical fault records and historical operation records of the charging station within the charging station, and construct a fault detection model for the charging pile;

[0044] Step S302: Obtain the device association data between the target power distribution equipment and the charging pile in the charging station. Based on the device association data, optimize the fault detection model of the charging pile and calculate the feature accuracy W=(TP+TN) / (TP+TN+FP+FN) of the fault detection model. TP represents the true instance of the fault detection model, TN represents the true negative instance of the fault detection model, FP represents the false positive instance of the fault detection model, and FN represents the false negative instance of the fault detection model. When the feature accuracy is greater than the preset feature accuracy threshold, the fault detection model is recorded as the target fault detection model of the charging pile.

[0045] In the above steps, a true positive example is the number of instances predicted as positive by the fault detection model, where a positive example is a charging pile that is determined to be faulty. A true negative example is the number of instances predicted as negative by the fault detection model, where a negative example is a charging pile that is determined to be operating normally. A false positive example is the number of instances where the model incorrectly predicts a negative example as positive, and a false negative example is the number of instances where the model incorrectly predicts a true example as negative. By calculating the feature accuracy, the proportion of correct predictions can be reflected, thus allowing for a correct evaluation of model performance and greatly increasing the accuracy and reliability of the model.

[0046] Furthermore, step S400 includes:

[0047] Step S401: Monitor the equipment status of the target power distribution equipment and charging piles in the charging station, and obtain the equipment data of the target power distribution equipment and charging piles respectively;

[0048] Step S402: Obtain the target fault detection model of each charging pile in the charging station, input the equipment data into the target fault detection model, perform fault detection on the charging piles in the charging station, obtain target detection data, and perform intelligent detection management of the charging piles based on the target detection data.

[0049] To better implement the above method, an IoT-based charging pile fault detection system is also proposed. The system includes a target power distribution equipment module, an equipment association data module, a target fault detection model module, and an intelligent detection module.

[0050] The target power distribution equipment module is used to acquire the historical charging records of the charging piles, analyze the impact of the charging status of the charging piles on the operating status of the power distribution equipment, and obtain the target power distribution equipment.

[0051] The equipment association data module is used to acquire historical equipment operation records of the target power distribution equipment, analyze the degree of correlation between the operation status of the target power distribution equipment and the charging pile, and obtain equipment association data.

[0052] The target fault detection model module is used to optimize the fault prediction model based on the equipment association data to obtain the target fault detection model.

[0053] The intelligent detection module is used to monitor the charging piles and power distribution equipment in the charging station during the current cycle, and to detect faults in the charging piles according to the target fault detection model, obtain target detection data, and perform intelligent management of the charging piles based on the target detection data.

[0054] Furthermore, the target power distribution equipment module includes an equipment status impact value unit and a target power distribution equipment unit;

[0055] The Equipment Status Impact Value Unit is used to monitor the charging process of vehicles by charging piles in charging stations, obtain historical charging records of charging piles, and calculate the equipment status impact value of charging piles on power distribution equipment.

[0056] The target power distribution equipment unit is used to determine the degree to which the operating status of the power distribution equipment is affected by the charging status of the charging pile based on the equipment status influence value, and thus obtain the target power distribution equipment.

[0057] Furthermore, the equipment association data module includes an equipment association analysis unit and an equipment association data unit;

[0058] The equipment correlation analysis unit is used to build an equipment correlation regression model to analyze the degree of correlation between the operating status of the target power distribution equipment and the charging pile.

[0059] The equipment association data unit is used to collect the equipment association data between the target power distribution equipment and the charging pile, as well as the equipment association regression coefficients between the target power distribution equipment and the charging pile.

[0060] Furthermore, the target fault detection model module includes a fault detection model unit and a target fault detection unit;

[0061] The fault detection model unit is used to construct a fault detection model for charging piles based on the historical fault records and historical operation records of the charging stations within the charging station.

[0062] The target fault detection unit is used to optimize the fault detection model of the charging pile based on the associated equipment data to obtain the target fault detection model.

[0063] Furthermore, the intelligent detection module includes an intelligent detection unit;

[0064] The intelligent detection unit is used to monitor the equipment status of the target power distribution equipment and charging piles in the charging station, obtain equipment data of the target power distribution equipment and charging piles respectively, perform fault detection on the charging piles in the charging station, obtain target detection data, and perform intelligent management of the charging piles based on the target detection data.

[0065] Compared with existing technologies, the beneficial effects of this invention are: This invention realizes intelligent fault detection for charging piles in charging stations. Considering that charging piles do not exist independently in practice, for each charging pile, a power distribution device needs to distribute power to different charging piles, and the different charging piles are also different. Furthermore, the equipment status of the power distribution device will also affect the charging piles. Therefore, this invention first identifies the target power distribution device affected by the charging status of the charging piles. By analyzing the correlation between the equipment status of the target power distribution device and the charging piles, the correlation between the target power distribution device and the charging piles is obtained. The constructed fault detection model is then optimized. Based on the real-time monitoring data of the target power distribution device and the charging piles, fault detection analysis is performed on the charging piles, thereby greatly improving the accuracy of fault detection for charging piles and enabling the charging station to operate efficiently. Attached Figure Description

[0066] Figure 1 This is a flowchart of a charging pile fault detection system and method based on the Internet of Things according to the present invention;

[0067] Figure 2 This is a schematic diagram of a charging pile fault detection system and method based on the Internet of Things according to the present invention. Detailed Implementation

[0068] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0069] Example: Figures 1-2 As shown, the present invention provides a technical solution, a charging pile fault detection method based on the Internet of Things, the method comprising:

[0070] Step S100: Construct a fault detection cloud platform, obtain historical charging records of charging piles, obtain historical equipment anomaly records of power distribution equipment that distributes power to charging piles, analyze the degree of influence of charging pile charging status on the equipment operating status of power distribution equipment, and obtain the target power distribution equipment.

[0071] Step S100 includes:

[0072] Step S101: Construct a fault detection cloud platform to monitor the charging process of the charging pile to the vehicle in the charging station, obtain the historical charging records of the charging pile, and obtain the average charging power of the charging pile from the historical charging records.

[0073] Step S102: Calculate the characteristic charging value of each charging station in each historical charging record, where the characteristic charging value R of a charging station in a certain historical charging record is:

[0074] ,

[0075] Where P represents the average charging power of a charging station in a certain historical charging record; P max P represents the maximum average charging power of the charging station across all historical charging records; min This represents the minimum average charging power of the charging station across all historical charging records.

[0076] Step S103: Obtain the average value of the characteristic charging value of each historical charging record. When the characteristic charging value of a certain historical charging record is greater than the average value, the historical charging record is recorded as the marked historical charging record of the charging pile.

[0077] Step S104: Obtain the power distribution equipment that distributes power to the charging pile, obtain the historical equipment anomaly records of the power distribution equipment, and extract the historical equipment anomaly data from the historical equipment anomaly records. The historical equipment anomaly data includes the data corresponding to various equipment indicators of the power distribution equipment.

[0078] For example, the various equipment specifications of power distribution equipment include equipment voltage, equipment current, frequency, etc.

[0079] Step S105: Obtain the preset data operating range of various equipment indicators of the power distribution equipment from the cloud platform. When all the equipment indicators of the power distribution equipment in a certain historical equipment anomaly record are within the data operating range of the equipment indicators, record the certain historical equipment anomaly record as the characteristic historical equipment anomaly record of the power distribution equipment.

[0080] Step S106: Obtain the historical equipment anomaly records for each feature of the power distribution equipment. The historical charging record is the total number of charging piles marked with historical charging records. Calculate the impact value S of the charging piles on the equipment status of the power distribution equipment.

[0081] ,

[0082] Where q represents the total number of characteristic historical equipment anomaly records of the power distribution equipment, and F i This represents the total number of charging piles marked with historical charging records within the i-th characteristic historical equipment anomaly record of the power distribution equipment; M sum This represents the total number of charging piles that provide power distribution for power distribution equipment;

[0083] For example, the total number of characteristic historical equipment anomaly records of the power distribution equipment, q, is represented as 3; the total number of charging piles marked with historical charging records in the first characteristic historical equipment anomaly record of the power distribution equipment, F1, is represented as 30; the total number of charging piles marked with historical charging records in the second characteristic historical equipment anomaly record of the power distribution equipment, F1, is represented as 20; the total number of charging piles marked with historical charging records in the first characteristic historical equipment anomaly record of the power distribution equipment, F3, is represented as 25; the total number of charging piles used for power distribution by the power distribution equipment, M, is... sum Represented as 100;

[0084] Calculate the impact value S of the charging pile on the equipment status of the power distribution equipment:

[0085] ,

[0086] Step S107: When the equipment status impact value is greater than the preset equipment status impact threshold, it is determined that the equipment operation status of the power distribution equipment is affected by the charging status of the charging pile, and the power distribution equipment is recorded as the target power distribution equipment.

[0087] Step S200: Obtain the historical operation records of the charging pile, obtain the historical equipment operation records of the target power distribution equipment, analyze the correlation between the operation status of the target power distribution equipment and the charging pile, and obtain equipment correlation data;

[0088] Step S200 includes:

[0089] Step S201: Obtain the historical operation records of the charging piles in the charging station, and extract the historical operation data of the charging piles from the historical operation records. The historical operation data includes the data corresponding to various equipment parameters of the charging piles.

[0090] For example, the various equipment parameters of a charging pile include charging power, rated voltage, etc.

[0091] Step S202: Obtain the historical equipment operation records of the target power distribution equipment, and obtain the data corresponding to the various equipment indicators of the target power distribution equipment from the historical equipment operation records;

[0092] Step S203: Analyze the correlation between the operating status of the target power distribution equipment and the charging piles. Specifically, the correlation between the c-th equipment indicator of the target power distribution equipment and the operating status of the charging piles within the charging pile is analyzed by constructing an equipment correlation regression model. The equipment correlation regression model Y... c :

[0093] ,

[0094] Where β0 represents the feature intercept; β1, β2, ..., β n Represented by the regression coefficients of various equipment parameters of the charging pile; ε is the error term; X1, X2, ..., X n These are the various equipment parameters of the charging pile;

[0095] Step S204: Obtain the data of the c-th equipment indicator of the target power distribution equipment in each historical equipment operation record, obtain the data of each equipment parameter of the charging pile in each historical operation record, and divide each historical equipment operation record and the historical operation record into a training set and a test set;

[0096] Step S205: Using the training set, solve for the regression coefficients using the squared residuals (SSE), where the squared residuals (SSE) are:

[0097] ,

[0098] Where j is the total number of historical equipment operation records of the target power distribution equipment in the training set; Y c，zFor the target power distribution equipment, the value corresponding to the c-th equipment indicator in the z-th historical equipment operation record in the training set; Y´ c，z For the target power distribution equipment, the predicted value of the c-th equipment indicator in the z-th historical operation record of the training set;

[0099] Step S206: Minimize the squared residuals SSE, and use the squared residuals SSE to minimize β0 and β1 respectively. α Taking partial derivatives, where α = 1, 2, ..., n, we get:

[0100] ,

[0101] ,

[0102] Among them, X z，α This represents the value of the αth device indicator in the zth historical operation record of the training set, which is a charging pile.

[0103] For β0, β α Solving by taking the partial derivatives, we get:

[0104] ,

[0105] Where X represents the parameter matrix of various equipment parameters of the charging pile; Y c =Vβ+ε; β represents a vector of regression coefficients, where β = (β0, β1, ..., β...). n );

[0106] Step S207: Use the test set to evaluate the performance of the equipment association regression model, optimize the equipment management regression model, obtain the c-th equipment index of the preset target power distribution equipment, and the first feature regression coefficient threshold γ1 and the second feature regression coefficient threshold γ2 of the charging pile, where γ1>0>γ2.

[0107] Step S208: When the charging pile is in the e-th equipment parameter β in the equipment correlation regression model e >γ1, determine the c-th equipment index of the target power distribution equipment, which has a positive correlation with the e-th equipment parameter of the charging pile, when β e <γ2, it is determined that the c-th equipment indicator of the target power distribution equipment has a negative correlation with the e-th equipment parameter of the charging pile. When it is determined that the c-th equipment indicator of the target power distribution equipment has a correlation with the e-th equipment parameter of the charging pile, the c-th equipment indicator of the target power distribution equipment is recorded as the associated equipment indicator of the e-th equipment parameter of the charging pile. When γ1>β e >γ2, the c-th equipment indicator of the target power distribution equipment is not related to the e-th equipment parameter of the charging pile;

[0108] Step S209: Obtain the various equipment indicators of the target power distribution equipment, the correlation equipment indicators between them and the various equipment parameters of the charging pile, and the equipment correlation regression coefficients between the various equipment indicators of the target power distribution equipment and the various equipment parameters of the charging pile, and aggregate them to obtain the equipment correlation data between the target power distribution equipment and the charging pile.

[0109] Step S300: Obtain the equipment association data between the power distribution equipment and the charging pile, obtain the constructed fault detection model, optimize the fault prediction model based on the equipment association data, and obtain the target fault detection model;

[0110] Step S300 includes:

[0111] Step S301: Obtain historical fault records and historical operation records of the charging station within the charging station, and construct a fault detection model for the charging pile;

[0112] Step S302: Obtain the device association data between the target power distribution equipment and the charging pile in the charging station. Based on the device association data, optimize the fault detection model of the charging pile and calculate the feature accuracy W=(TP+TN) / (TP+TN+FP+FN) of the fault detection model. TP represents the true instance of the fault detection model, TN represents the true negative instance of the fault detection model, FP represents the false positive instance of the fault detection model, and FN represents the false negative instance of the fault detection model. When the feature accuracy is greater than the preset feature accuracy threshold, the fault detection model is recorded as the target fault detection model of the charging pile.

[0113] Step S400: Monitor the charging piles and target power distribution equipment in the charging station during the current cycle, and perform fault detection on the charging piles according to the target fault detection model to obtain target detection data. Based on the target detection data, perform intelligent detection management on the charging piles.

[0114] Step S400 includes:

[0115] Step S401: Monitor the equipment status of the target power distribution equipment and charging piles in the charging station, and obtain the equipment data of the target power distribution equipment and charging piles respectively;

[0116] Step S402: Obtain the target fault detection model of each charging pile in the charging station, input the equipment data into the target fault detection model, perform fault detection on the charging piles in the charging station, obtain target detection data, and perform intelligent detection management on the charging piles based on the target detection data.

[0117] To better implement the above method, an IoT-based charging pile fault detection system is also proposed. The system includes a target power distribution equipment module, an equipment association data module, a target fault detection model module, and an intelligent detection module.

[0118] The target power distribution equipment module is used to acquire the historical charging records of the charging piles, analyze the impact of the charging status of the charging piles on the operating status of the power distribution equipment, and obtain the target power distribution equipment.

[0119] The equipment association data module is used to acquire historical equipment operation records of the target power distribution equipment, analyze the degree of correlation between the operation status of the target power distribution equipment and the charging pile, and obtain equipment association data.

[0120] The target fault detection model module is used to optimize the fault prediction model based on the equipment association data to obtain the target fault detection model.

[0121] The intelligent detection module is used to monitor the charging piles and power distribution equipment in the charging station during the current cycle, and to detect faults in the charging piles according to the target fault detection model, obtain target detection data, and perform intelligent management of the charging piles based on the target detection data.

[0122] The target power distribution equipment module includes an equipment status impact value unit and a target power distribution equipment unit.

[0123] The Equipment Status Impact Value Unit is used to monitor the charging process of vehicles by charging piles in charging stations, obtain historical charging records of charging piles, and calculate the equipment status impact value of charging piles on power distribution equipment.

[0124] The target power distribution equipment unit is used to determine the degree to which the operating status of the power distribution equipment is affected by the charging status of the charging pile based on the equipment status influence value, and thus obtain the target power distribution equipment.

[0125] The equipment association data module includes an equipment association analysis unit and an equipment association data unit.

[0126] The equipment correlation analysis unit is used to build an equipment correlation regression model to analyze the degree of correlation between the operating status of the target power distribution equipment and the charging pile.

[0127] The equipment association data unit is used to collect the equipment association data between the target power distribution equipment and the charging pile, as well as the equipment association regression coefficients between the target power distribution equipment and the charging pile.

[0128] The target fault detection model module includes a fault detection model unit and a target fault detection unit.

[0129] The fault detection model unit is used to construct a fault detection model for charging piles based on the historical fault records and historical operation records of the charging stations within the charging station.

[0130] The target fault detection unit is used to optimize the fault detection model of the charging pile based on the associated equipment data to obtain the target fault detection model.

[0131] The intelligent detection module includes an intelligent detection unit;

[0132] The intelligent detection unit is used to monitor the equipment status of the target power distribution equipment and charging piles in the charging station, obtain equipment data of the target power distribution equipment and charging piles respectively, perform fault detection on the charging piles in the charging station, obtain target detection data, and perform intelligent management of the charging piles based on the target detection data.

[0133] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A charging pile fault detection method based on the Internet of Things, characterized in that, The method includes: Step S100: Construct a fault detection cloud platform, obtain historical charging records of charging piles, obtain historical equipment anomaly records of power distribution equipment that distributes power to charging piles, analyze the degree of influence of charging pile charging status on the equipment operating status of power distribution equipment, and obtain the target power distribution equipment. Step S200: Obtain the historical operation record of the charging pile, obtain the historical equipment operation record of the target power distribution equipment, analyze the correlation between the operation status of the target power distribution equipment and the charging pile, and obtain equipment correlation data; Step S300: Obtain the equipment association data between the power distribution equipment and the charging pile, obtain the constructed fault detection model, and optimize the fault detection model based on the equipment association data to obtain the target fault detection model; Step S400: Monitor the charging piles and target power distribution equipment in the charging station during the current period, and perform fault detection on the charging piles according to the target fault detection model to obtain target detection data. Based on the target detection data, perform intelligent detection management on the charging piles. Step S200 includes: Step S201: Obtain the historical operation records of the charging piles in the charging station, and extract the historical operation data of the charging piles from the historical operation records. The historical operation data includes data corresponding to various equipment parameters of the charging piles. Step S202: Obtain the historical equipment operation records of the target power distribution equipment, and obtain the data corresponding to the various equipment indicators of the target power distribution equipment from the historical equipment operation records; Step S203: Analyze the correlation between the operating status of the target power distribution equipment and the charging piles. Specifically, the analysis process for the correlation between the c-th equipment indicator of the target power distribution equipment and the operating status of the charging piles within the charging pile is as follows: Construct an equipment correlation regression model, where the equipment correlation regression model Y... c : ， Where β0 represents the feature intercept; β1, β2, ..., β n The regression coefficients of the various equipment parameters of the charging pile are represented by X1, X2, ..., X... n These are the various equipment parameters of the charging pile; Step S204: Obtain the data of the c-th equipment indicator of the target power distribution equipment in each historical equipment operation record, obtain the data corresponding to each equipment parameter of the charging pile in each historical operation record, and divide the historical equipment operation records and the historical operation records into training set and test set; Step S205: Using the training set, solve for the regression coefficients using the squared residuals (SSE), where the squared residuals (SSE) are: ， Where j is the total number of historical equipment operation records of the target power distribution equipment in the training set; Y c，z For the target power distribution equipment, the value corresponding to the c-th equipment indicator in the z-th historical equipment operation record in the training set; Y´ c，z For the target power distribution equipment, the predicted value corresponding to the c-th equipment indicator in the z-th historical operation record of the training set; Step S206: Minimize the squared residual SSE, and use the squared residual SSE to apply to β0 and β1 respectively. α Taking partial derivatives, where α = 1, 2, ..., n, we get: ， ， Among them, X z，α This represents the value of the αth equipment indicator in the zth historical operation record of the training set for the charging pile. For β0, β α Solving by taking the partial derivatives, we get: ， Where X represents the parameter matrix of various equipment parameters of the charging pile; Y c =Vβ+ε; β represents a vector of regression coefficients, where β = (β0, β1, ..., β...). n ); Step S207: Use the test set to evaluate the performance of the equipment association regression model, optimize the equipment association regression model, obtain the preset c-th equipment index of the target power distribution equipment, and the first feature regression coefficient threshold γ1 and the second feature regression coefficient threshold γ2 of the charging pile, where γ1>0>γ2; Step S208: When the charging pile is in the e-th device parameter β in the device correlation regression model e >γ1, determine the c-th equipment index of the target power distribution equipment, which has a positive correlation with the e-th equipment parameter of the charging pile, when β e If γ1 > β, it is determined that the c-th equipment parameter of the target power distribution equipment has a negative correlation with the e-th equipment parameter of the charging pile. When the c-th equipment parameter of the target power distribution equipment is determined to be correlated with the e-th equipment parameter of the charging pile, the c-th equipment parameter of the target power distribution equipment is recorded as the correlated equipment parameter of the e-th equipment parameter of the charging pile. e >γ2, it is determined that the c-th equipment indicator of the target power distribution equipment is not related to the e-th equipment parameter of the charging pile; Step S209: Obtain the various equipment indicators of the target power distribution equipment, the correlation equipment indicators between them and the various equipment parameters of the charging pile, and the equipment correlation regression coefficients between the various equipment indicators of the target power distribution equipment and the various equipment parameters of the charging pile, and aggregate them to obtain the equipment correlation data between the target power distribution equipment and the charging pile.

2. The charging pile fault detection method based on the Internet of Things according to claim 1, characterized in that, Step S100 includes: Step S101: Construct a fault detection cloud platform to monitor the charging process of the charging pile to the vehicle in the charging station, obtain the historical charging records of the charging pile, and obtain the average charging power of the charging pile from the historical charging records. Step S102: Calculate the characteristic charging value of the charging pile in each historical charging record, wherein the characteristic charging value R of the charging pile in a certain historical charging record is: ， Wherein, P represents the average charging power of the charging pile in a certain historical charging record; P max P represents the maximum average charging power of the charging piles in each of the historical charging records; min It is represented as the minimum average charging power of the charging pile in each of the historical charging records; Step S103: Obtain the average value of the characteristic charging values ​​of each historical charging record. When the characteristic charging value of a certain historical charging record is greater than the average value, the historical charging record is recorded as the marked historical charging record of the charging pile. Step S104: Obtain the power distribution equipment that distributes power to the charging pile, obtain the historical equipment anomaly records of the power distribution equipment, and extract historical equipment anomaly data from the historical equipment anomaly records. The historical equipment anomaly data includes data corresponding to various equipment indicators of the power distribution equipment. Step S105: Obtain the preset data operating range of the various equipment indicators of the power distribution equipment from the cloud platform. When all the equipment indicators of the power distribution equipment in a certain historical equipment anomaly record are within the data operating range of the equipment indicators, record the certain historical equipment anomaly record as the characteristic historical equipment anomaly record of the power distribution equipment. Step S106: Obtain the historical equipment anomaly records of each feature of the power distribution equipment. The historical charging record is the total number of charging piles marked with historical charging records. Calculate the impact value S of the charging piles on the equipment status of the power distribution equipment. ， Where q represents the total number of characteristic historical equipment anomaly records of the power distribution equipment, and F i The historical charging record is represented by the total number of charging piles marked with historical charging records within the i-th characteristic historical equipment anomaly record of the power distribution equipment; M sum This represents the total number of charging piles that receive power from the power distribution equipment. Step S107: When the device status influence value is greater than the preset device status influence threshold, it is determined that the device operation status of the power distribution equipment is affected by the charging status of the charging pile, and the power distribution equipment is recorded as the target power distribution equipment.

3. The method for detecting charging pile faults based on the Internet of Things according to claim 2, characterized in that, Step S300 includes: Step S301: Obtain historical fault records and historical operation records of the charging station within the charging station, and construct a fault detection model for the charging pile; Step S302: Obtain the device association data between the target power distribution equipment and the charging pile in the charging station. Based on the device association data, optimize the fault detection model of the charging pile and calculate the feature accuracy W=(TP+TN) / (TP+TN+FP+FN) of the fault detection model, where TP represents the true positive instance of the fault detection model, TN represents the true negative instance of the fault detection model, FP represents the false positive instance of the fault detection model, and FN represents the false negative instance of the fault detection model. When the feature accuracy is greater than the preset feature accuracy threshold, the fault detection model is recorded as the target fault detection model of the charging pile.

4. The charging pile fault detection method based on the Internet of Things according to claim 3, characterized in that, Step S400 includes: Step S401: Monitor the equipment status of the target power distribution equipment and charging piles in the charging station, and obtain the equipment data of the target power distribution equipment and charging piles respectively; Step S402: Obtain the target fault detection model of each charging pile in the charging station, input the equipment data into the target fault detection model, perform fault detection on the charging piles in the charging station, obtain target detection data, and perform intelligent detection management on the charging piles based on the target detection data.

5. A charging pile fault detection system based on the Internet of Things (IoT), used to execute the charging pile fault detection method based on the IoT as described in any one of claims 1-4, characterized in that, The system includes a target power distribution equipment module, an equipment association data module, a target fault detection model module, and an intelligent detection module; The target power distribution equipment module is used to acquire the historical charging records of the charging pile, analyze the degree of influence of the charging status of the charging pile on the equipment operation status of the power distribution equipment, and obtain the target power distribution equipment. The device association data module is used to acquire the historical device operation records of the target power distribution equipment, analyze the degree of correlation between the operation status of the target power distribution equipment and the charging pile, and obtain device association data. The target fault detection model module is used to optimize the fault detection model based on the device association data to obtain the target fault detection model; The intelligent detection module is used to monitor the charging piles and power distribution equipment in the charging station during the current period, and to perform fault detection on the charging piles according to the target fault detection model to obtain target detection data. Based on the target detection data, the charging piles are intelligently managed.

6. The charging pile fault detection system based on the Internet of Things according to claim 5, characterized in that, The target power distribution equipment module includes an equipment status influence value unit and a target power distribution equipment unit; The device status impact value unit is used to monitor the charging process of the charging pile charging the car in the charging station, obtain the historical charging records of the charging pile, and calculate the device status impact value of the charging pile on the power distribution equipment. The target power distribution equipment unit is used to determine the degree to which the operating status of the power distribution equipment is affected by the charging status of the charging pile based on the equipment status influence value, and thus obtain the target power distribution equipment.

7. The charging pile fault detection system based on the Internet of Things according to claim 5, characterized in that, The device association data module includes a device association analysis unit and a device association data unit; The equipment correlation analysis unit is used to construct an equipment correlation regression model to analyze the degree of correlation between the operating status of the target power distribution equipment and the charging pile. The device association data unit is used to aggregate the device association data between the target power distribution equipment and the charging pile, including the device association regression coefficients between the device indicators of the target power distribution equipment and the charging pile.

8. The charging pile fault detection system based on the Internet of Things according to claim 5, characterized in that, The target fault detection model module includes a fault detection model unit and a target fault detection unit; The fault detection model unit is used to construct a fault detection model for the charging pile based on the historical fault records and historical operation records of the charging station. The target fault detection unit is used to optimize the fault detection model of the charging pile based on the equipment association data to obtain the target fault detection model.

9. A charging pile fault detection system based on the Internet of Things according to claim 5, characterized in that, The intelligent detection module includes an intelligent detection unit; The intelligent detection unit is used to monitor the equipment status of the target power distribution equipment and charging piles in the charging station, obtain equipment data of the target power distribution equipment and charging piles respectively, perform fault detection on the charging piles in the charging station to obtain target detection data, and perform intelligent management of the charging piles based on the target detection data.

Images