Charging pile fault detection system and method based on Internet of Things

Abstract

The invention discloses a charging pile fault detection system and method based on the Internet of Things, and relates to the technical field of charging equipment fault detection, and the method comprises the steps: constructing a fault detection cloud platform, and analyzing the influence degree of the charging state of a charging pile on the equipment operation state of power distribution equipment; acquiring a historical equipment operation record of the target power distribution equipment, and analyzing an association degree between the target power distribution equipment and the operation state of the charging pile to obtain equipment association data; acquiring equipment associated data of the power distribution equipment and the charging pile, acquiring a constructed fault detection model, and optimizing the fault detection model based on the equipment associated data to obtain a target fault detection model; and monitoring the charging piles in the charging station in the current period and the target power distribution equipment, performing fault detection on the charging piles according to the target fault detection model to obtain target detection data, and performing intelligent detection management on the charging piles based on the target detection data.

Description

Technical Field

[0001] The present invention relates to the technical field of charging equipment fault detection, and in particular to a charging pile fault detection system and method based on the Internet of Things. Background Art

[0002] In recent years, there are more and more electric vehicles. As an important infrastructure to ensure the normal operation of electric vehicles, the usage and demand of charging piles have also greatly increased. Whether the charging piles can be used normally and stably plays a vital role in whether electric vehicles can be widely popularized. Therefore, fault detection of charging piles is particularly important.

[0003] At present, manual inspection is mainly used to detect faults in charging piles, but this method has many shortcomings and problems. Manual inspection requires inspectors to inspect the charging piles one by one. This method not only leads to low efficiency, but also requires a lot of human resources, increasing the operating costs of the charging piles. In addition, during the inspection process, inspectors mainly rely on their own experience to make judgments, which will make the detection results subjective. In addition to manual inspections, some people will analyze the data anomalies of the charging piles by monitoring the operating data of the charging piles. Although this method can detect the anomalies of the charging piles based on real-time monitoring data, it does not take into account that the charging piles in the charging station are not operated independently of each other. The power distribution equipment in the charging station is responsible for supplying power to the charging piles. In the fault analysis of the charging piles, the impact of the power distribution equipment on the charging piles is basically rarely considered, which can easily lead to inaccurate fault detection of the charging piles and affect the normal operation of the charging station. Summary of the invention

[0004] The purpose of the present 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 object, the present invention provides the following technical solution: a charging pile fault detection method based on the Internet of Things, the method comprising: Step S100: construct a fault detection cloud platform, obtain historical charging records of charging piles, obtain historical equipment abnormality records of power distribution equipment that distributes power to charging piles, analyze the degree of influence of charging status of charging piles on equipment operation status of power distribution equipment, and obtain target power distribution equipment; Step S200: Obtain historical operation records of the charging pile, obtain historical equipment operation records of the target power distribution equipment, analyze the degree of correlation between the operating status of the target power distribution equipment and the charging pile, and obtain equipment correlation data; Step S300: Obtain device association data of the power distribution equipment and the charging pile, obtain the constructed fault detection model, optimize the fault detection model based on the device association data, and obtain a target fault detection model; Step S400: monitor the charging piles in the charging station in the current cycle and the target power distribution equipment, and perform fault detection on the charging piles according to the target fault detection model to obtain target detection data, and perform intelligent detection and management on the charging piles based on the target detection data.

[0006] Furthermore, step S100 includes: Step S101: construct a fault detection cloud platform, monitor the process of the charging pile charging the car in the charging station, obtain various 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: , Where P represents the average charging power of the charging pile in a certain historical charging record; P max It is represented by the maximum value of the average charging power of the charging pile in each historical charging record; P min It is represented by the minimum value of the average charging power of the charging piles in each historical charging record; Step S103: obtaining an average value of characteristic charging values ​​of each historical charging record, and when the characteristic charging value of a certain historical charging record is greater than the average value, recording the historical charging record as a marked historical charging record of the charging pile; Step S104: obtaining a power distribution device for distributing power to a charging pile, obtaining a historical device abnormality record of the power distribution device, and extracting historical device abnormality data from the historical device abnormality record, wherein the historical device abnormality data includes data corresponding to various device indicators of the power distribution device; Step S105: obtaining preset data operating ranges of various equipment indicators of the power distribution equipment from the cloud platform, and when various equipment indicators of the power distribution equipment in a certain historical equipment abnormality record are within the data operating range of the equipment indicators, the certain historical equipment abnormality record is recorded as a characteristic historical equipment abnormality record of the power distribution equipment; Step S106: Obtain each characteristic historical device abnormality record of the power distribution equipment, the historical charging record is the total number of charging piles marked with the historical charging record, and calculate the device status impact value S of the charging pile on the power distribution equipment: , Where q represents the total number of characteristic historical equipment abnormality records of the power distribution equipment, F iIt is represented by the i-th characteristic historical equipment abnormality record of the power distribution equipment, and the historical charging record is the total number of charging piles marked with the historical charging record; M sum Indicates the total number of charging piles that distribute power to the power distribution equipment; Step S107: When the device state impact value is greater than a preset device state impact threshold, it is determined that the device operation state of the power distribution device is affected by the charging state of the charging pile, and the power distribution device is recorded as a target power distribution device.

[0007] Further, step S200 includes: Step S201: acquiring historical operation records of charging piles in the charging station, and extracting historical operation data of the charging piles from the historical operation records, wherein the historical operation data includes data corresponding to various equipment parameters of the charging piles; Step S202: Acquire each historical equipment operation record of the target power distribution equipment, and acquire data corresponding to each equipment indicator of the target power distribution equipment from the historical equipment operation record; Step S203: Analyze the correlation between the operating status of the target power distribution equipment and the charging pile, wherein the correlation between the cth equipment indicator of the target power distribution equipment and the operating status of the charging piles in the charging pile is analyzed by constructing a device correlation regression model. The device correlation regression model Y c : , Among them, β0 represents the characteristic intercept; β1, β2, ..., β n It is represented by the regression coefficient of each equipment parameter of the charging pile; ε is the error term; X1, X2, ..., X n Represents various equipment parameters of the charging pile; Step S204: obtaining data of the cth equipment indicator of the target power distribution equipment in each historical equipment operation record, obtaining data corresponding to each equipment parameter of the charging pile in each historical operation record, and dividing each historical equipment operation record and the historical operation record into a training set and a test set; Step S205: Using the training set, the regression coefficient is solved by the residual square SSE, where the residual square SSE is: , Where j is the total number of historical equipment operation records of the target power distribution equipment in the training set; Y c，z is the target power distribution equipment, the value corresponding to the cth equipment indicator in the zth historical equipment operation record in the training set; Y´ c，z is the predicted value corresponding to the cth equipment indicator in the zth historical operation record in the training set for the target power distribution equipment; Step S206: Minimize the residual square SSE, and use the residual square SSE to calculate β0, β α Perform partial derivatives, where α=1, 2, ..., n, and we get: , , Among them, X z，α Represented as a charging pile, the value corresponding to the αth equipment indicator in the zth historical operation record in the training set; For β0, β α Solving the partial derivative of , we can get: , Where X represents the parameter matrix of various equipment parameters of the charging pile; Y c =Vβ+ε; β is represented as a vector of regression coefficients, where β=(β0, β2, ..., β n ); Step S207: Use the test set to evaluate the performance of the device-associated regression model, optimize the device-associated regression model, obtain the cth device index of the preset target power distribution equipment, and the first characteristic regression coefficient threshold γ1 and the second characteristic regression coefficient threshold γ2 of the charging pile, where γ1>0>γ2; Step S208: When the charging pile has the e-th device parameter β in the device-associated regression model e >γ1, it is determined that the cth equipment index of the target power distribution equipment has a positive correlation with the eth equipment parameter of the charging pile. e <γ2, it is determined that the cth equipment index of the target power distribution equipment has a negative correlation with the eth equipment parameter of the charging pile. When it is determined that the cth equipment index of the target power distribution equipment has a correlation with the eth equipment parameter of the charging pile, the cth equipment index of the target power distribution equipment is recorded as the associated equipment index of the eth equipment parameter of the charging pile. When γ1>β e >γ2, it is determined that the c-th equipment index of the target power distribution equipment has no relevance to the e-th equipment parameter of the charging pile; Step S209: Obtain various equipment indicators of the target power distribution equipment, associated equipment indicators between various equipment parameters of the charging pile, and equipment association regression coefficients between various equipment indicators of the target power distribution equipment and various equipment parameters of the charging pile, and aggregate them to obtain equipment association data between the target power distribution equipment and the charging pile.

[0008] Furthermore, step S300 includes: Step S301: Obtain historical fault records and historical operation records of the charging station in the charging station, and construct a fault detection model for the charging pile; Step S302: Obtain device association data between the target power distribution equipment and the charging pile in the charging station, optimize the fault detection model of the charging pile based on the device association data, and calculate the feature accuracy W=(TP+TN) / (TP+TN+FP+FN) of the fault detection model, where TP represents the true positive example of the fault detection model, TN represents the true negative example of the fault detection model, FP represents the false positive example of the fault detection model, and FN represents the false negative example 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; The true positive examples in the above steps are the number of instances predicted as positive by the fault detection model, where the positive class is the charging pile judged to be faulty; the true negative examples are the number of instances predicted as negative by the fault detection model, where the negative class is the charging pile judged to be operating normally; the false positive examples are the number of instances where the model mistakenly predicts the negative class as positive; the false negative examples are the number of instances where the model mistakenly predicts the true class as negative. By calculating the feature precision rate, it can reflect the correct proportion of the model in all predictions, so that the model performance can be correctly evaluated, which greatly increases the accuracy and reliability of the model.

[0009] Furthermore, step S400 includes: Step S401: monitoring the equipment status of the target power distribution equipment and the charging pile in the charging station, and obtaining equipment data of the target power distribution equipment and the charging pile respectively; Step S402: Obtain a target fault detection model for each charging pile in the charging station, input device 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 and management on the charging piles based on the target detection data.

[0010] In order to better implement the above method, a charging pile fault detection system based on the Internet of Things is also proposed. The system includes a target power distribution equipment module, an equipment associated data module, a target fault detection model module, and an intelligent detection module; The target power distribution equipment module is used to obtain the historical charging records of the charging pile, analyze the impact 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 obtain the historical equipment operation records of the target power distribution equipment, analyze the degree of association between the target power distribution equipment and the operating status of the charging pile, and obtain the equipment association data; A target fault detection model module is used to optimize the fault detection model according to the device-related data to obtain a target fault detection model; The intelligent detection module is used to monitor the charging piles and power distribution equipment in the charging station within the current cycle, and perform fault detection on the charging piles according to the target fault detection model to obtain target detection data, and perform intelligent management of the charging piles based on the target detection data.

[0011] Further, the target power distribution equipment module includes a device status impact value unit and a target power distribution equipment unit; The device status impact value unit is used to monitor the process of the charging pile charging the car in the charging station, obtain various 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 equipment operation state of the power distribution equipment is affected by the charging state of the charging pile according to the equipment state impact value, and obtain the target power distribution equipment.

[0012] Further, the device association data module includes a device association analysis unit and a device association data unit; The device association analysis unit is used to construct a device association regression model to analyze the degree of association between the operating status of the target power distribution equipment and the charging pile; The equipment association data unit is used to collect the equipment indicators of the target power distribution equipment and the associated equipment indicators between the various equipment parameters of the charging pile, as well as the equipment association regression coefficients between the various equipment indicators of the target power distribution equipment and the various equipment parameters of the charging pile, to obtain the equipment association data between the target power distribution equipment and the charging pile.

[0013] Further, the target fault detection model module includes a fault detection model unit and a target fault detection unit; a fault detection model unit, for constructing a fault detection model of a charging pile based on the historical fault records and historical operation records of the charging station in the charging station; The target fault detection unit is used to optimize the fault detection model of the charging pile according to the device-related data to obtain a target fault detection model.

[0014] Further, 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 the 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.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention realizes intelligent fault detection for charging piles in charging stations. Considering that charging piles do not exist independently in actual processes, for charging piles, one power distribution equipment needs to distribute power to different charging piles. At the same time, different charging piles are also different, and the equipment status of the power distribution equipment will also affect the charging piles. Therefore, the present invention first finds the target power distribution equipment affected by the charging status of the charging piles, and obtains the correlation between the target power distribution equipment and the charging piles by analyzing the correlation between the equipment status of the target power distribution equipment and the charging piles, and optimizes the constructed fault detection model. According to the equipment data of the target power distribution equipment and the charging piles monitored in real time, the charging piles are subjected to fault detection and analysis, thereby greatly improving the accuracy of fault detection of the charging piles and enabling the charging station to operate efficiently. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a method flow chart of a charging pile fault detection system and method based on the Internet of Things of the present invention; Figure 2 It is a module schematic diagram of a charging pile fault detection system and method based on the Internet of Things of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] Example: Figure 1-Figure 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: Step S100: construct a fault detection cloud platform, obtain historical charging records of charging piles, obtain historical equipment abnormality records of power distribution equipment that distributes power to charging piles, analyze the degree of influence of charging status of charging piles on equipment operation status of power distribution equipment, and obtain target power distribution equipment; Wherein, step S100 includes: Step S101: construct a fault detection cloud platform, monitor the process of the charging pile charging the car in the charging station, obtain various 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: , Where P represents the average charging power of the charging pile in a certain historical charging record; P max It is represented by the maximum value of the average charging power of the charging pile in each historical charging record; P min It is represented by the minimum value of the average charging power of the charging piles in each historical charging record; Step S103: obtaining an average value of characteristic charging values ​​of each historical charging record, and when the characteristic charging value of a certain historical charging record is greater than the average value, recording the historical charging record as a marked historical charging record of the charging pile; Step S104: obtaining a power distribution device for distributing power to a charging pile, obtaining a historical device abnormality record of the power distribution device, and extracting historical device abnormality data from the historical device abnormality record, wherein the historical device abnormality data includes data corresponding to various device indicators of the power distribution device; For example, the equipment indicators of power distribution equipment include equipment voltage, equipment current, frequency, etc.; Step S105: obtaining preset data operating ranges of various equipment indicators of the power distribution equipment from the cloud platform, and when various equipment indicators of the power distribution equipment in a certain historical equipment abnormality record are within the data operating range of the equipment indicators, the certain historical equipment abnormality record is recorded as a characteristic historical equipment abnormality record of the power distribution equipment; Step S106: Obtain each characteristic historical device abnormality record of the power distribution equipment, the historical charging record is the total number of charging piles marked with the historical charging record, and calculate the device status impact value S of the charging pile on the power distribution equipment: , Where q represents the total number of characteristic historical equipment abnormality records of the power distribution equipment, F i It is represented by the i-th characteristic historical equipment abnormality record of the power distribution equipment, and the historical charging record is the total number of charging piles marked with the historical charging record; M sum Indicates the total number of charging piles that distribute power to the power distribution equipment; For example, the total number q of characteristic historical equipment abnormality records of the power distribution equipment is expressed as 3; in the first characteristic historical equipment abnormality record of the power distribution equipment, the total number F1 of charging piles with historical charging records marked as historical charging records is expressed as 30; in the second characteristic historical equipment abnormality record of the power distribution equipment, the total number F1 of charging piles with historical charging records marked as historical charging records is expressed as 20; in the first characteristic historical equipment abnormality record of the power distribution equipment, the total number F3 of charging piles with historical charging records marked as historical charging records is expressed as 25; the total number M of charging piles for power distribution by the power distribution equipment sum It is expressed as 100; Calculate the impact value S of the charging pile on the equipment status of the power distribution equipment: , Step S107: when the device state impact value is greater than a preset device state impact threshold, it is determined that the device operation state of the power distribution device is affected by the charging state of the charging pile, and the power distribution device is recorded as a target power distribution device; Step S200: Obtain historical operation records of the charging pile, obtain historical equipment operation records of the target power distribution equipment, analyze the degree of correlation between the operating status of the target power distribution equipment and the charging pile, and obtain equipment correlation data; Wherein, step S200 includes: Step S201: acquiring historical operation records of charging piles in the charging station, and extracting historical operation data of the charging piles from the historical operation records, wherein the historical operation data includes data corresponding to various equipment parameters of the charging piles; For example, the equipment parameters of the charging pile include charging power, rated voltage, etc. Step S202: Acquire each historical equipment operation record of the target power distribution equipment, and acquire data corresponding to each equipment indicator of the target power distribution equipment from the historical equipment operation record; Step S203: Analyze the correlation between the operating status of the target power distribution equipment and the charging pile, wherein the correlation between the cth equipment indicator of the target power distribution equipment and the operating status of the charging piles in the charging pile is analyzed by constructing a device correlation regression model. The device correlation regression model Y c : , Among them, β0 represents the characteristic intercept; β1, β2, ..., β n It is represented by the regression coefficient of each equipment parameter of the charging pile; ε is the error term; X1, X2, ..., X n Represents various equipment parameters of the charging pile; Step S204: obtaining data of the cth equipment indicator of the target power distribution equipment in each historical equipment operation record, obtaining data corresponding to each equipment parameter of the charging pile in each historical operation record, and dividing each historical equipment operation record and the historical operation record into a training set and a test set; Step S205: Using the training set, the regression coefficient is solved by the residual square SSE, where the residual square SSE is: , Where j is the total number of historical equipment operation records of the target power distribution equipment in the training set; Y c，z is the target power distribution equipment, the value corresponding to the cth equipment indicator in the zth historical equipment operation record in the training set; Y´ c，zis the predicted value corresponding to the cth equipment indicator in the zth historical operation record in the training set for the target power distribution equipment; Step S206: Minimize the residual square SSE, and use the residual square SSE to calculate β0, β α Perform partial derivatives, where α=1, 2, ..., n, and we get: , , Among them, X z，α Represented as a charging pile, the value corresponding to the αth equipment indicator in the zth historical operation record in the training set; For β0, β α Solving the partial derivative of , we can get: , Where X represents the parameter matrix of various equipment parameters of the charging pile; Y c =Vβ+ε; β is represented as a vector of regression coefficients, where β=(β0, β2, ..., β n ); Step S207: Use the test set to evaluate the performance of the device-associated regression model, optimize the device-associated regression model, obtain the cth device index of the preset target power distribution equipment, and the first characteristic regression coefficient threshold γ1 and the second characteristic regression coefficient threshold γ2 of the charging pile, where γ1>0>γ2; Step S208: When the charging pile has the e-th device parameter β in the device-associated regression model e >γ1, it is determined that the cth equipment index of the target power distribution equipment has a positive correlation with the eth equipment parameter of the charging pile. e <γ2, it is determined that the cth equipment index of the target power distribution equipment has a negative correlation with the eth equipment parameter of the charging pile. When it is determined that the cth equipment index of the target power distribution equipment has a correlation with the eth equipment parameter of the charging pile, the cth equipment index of the target power distribution equipment is recorded as the associated equipment index of the eth equipment parameter of the charging pile. When γ1>β e >γ2, it is determined that the c-th equipment index of the target power distribution equipment has no relevance to the e-th equipment parameter of the charging pile; Step S209: Obtain various equipment indicators of the target power distribution equipment, associated equipment indicators between various equipment parameters of the charging pile, and equipment associated regression coefficients between various equipment indicators of the target power distribution equipment and various equipment parameters of the charging pile, and aggregate them to obtain equipment associated data between the target power distribution equipment and the charging pile; Step S300: Obtain device association data of the power distribution equipment and the charging pile, obtain the constructed fault detection model, optimize the fault detection model based on the device association data, and obtain a target fault detection model; Wherein, step S300 includes: Step S301: Obtain historical fault records and historical operation records of the charging station in the charging station, and construct a fault detection model for the charging pile; Step S302: Obtain device association data between the target power distribution equipment and the charging pile in the charging station, optimize the fault detection model of the charging pile based on the device association data, and calculate the feature accuracy W=(TP+TN) / (TP+TN+FP+FN) of the fault detection model, where TP represents the true positive example of the fault detection model, TN represents the true negative example of the fault detection model, FP represents the false positive example of the fault detection model, and FN represents the false negative example 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; Step S400: monitoring the charging piles in the charging station in the current cycle and the target power distribution equipment, and performing fault detection on the charging piles according to the target fault detection model to obtain target detection data, and performing intelligent detection management on the charging piles based on the target detection data; Wherein, step S400 includes: Step S401: monitoring the equipment status of the target power distribution equipment and the charging pile in the charging station, and obtaining equipment data of the target power distribution equipment and the charging pile respectively; Step S402: Obtain a target fault detection model for each charging pile in the charging station, input device 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; In order to better implement the above method, a charging pile fault detection system based on the Internet of Things is also proposed. The system includes a target power distribution equipment module, an equipment associated data module, a target fault detection model module, and an intelligent detection module; The target power distribution equipment module is used to obtain the historical charging records of the charging pile, analyze the impact 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 obtain the historical equipment operation records of the target power distribution equipment, analyze the degree of association between the target power distribution equipment and the operating status of the charging pile, and obtain the equipment association data; A target fault detection model module is used to optimize the fault detection model according to the device-related data to obtain a target fault detection model; The intelligent detection module is used to monitor the charging piles and power distribution equipment in the charging station in the current cycle, and perform fault detection on the charging piles according to the target fault detection model to obtain target detection data, and perform intelligent management on the charging piles based on the target detection data; Wherein, the target power distribution equipment module includes a device status impact value unit and a target power distribution equipment unit; The device status impact value unit is used to monitor the process of the charging pile charging the car in the charging station, obtain various historical charging records of the charging pile, and calculate the device status impact value of the charging pile on the power distribution equipment; A target power distribution equipment unit is used to determine the degree to which the equipment operation state of the power distribution equipment is affected by the charging state of the charging pile according to the equipment state impact value, and obtain the target power distribution equipment; Among them, the device association data module includes a device association analysis unit and a device association data unit; The device association analysis unit is used to construct a device association regression model to analyze the degree of association between the operating status of the target power distribution equipment and the charging pile; The device association data unit is used to collect the associated device indicators between the target power distribution equipment and the various device parameters of the charging pile, as well as the device association regression coefficients between the various device indicators of the target power distribution equipment and the various device parameters of the charging pile, to obtain the device association data between the target power distribution equipment and the charging pile; Wherein, the target fault detection model module includes a fault detection model unit and a target fault detection unit; a fault detection model unit, for constructing a fault detection model of a charging pile based on the historical fault records and historical operation records of the charging station in the charging station; A target fault detection unit, used to optimize the fault detection model of the charging pile according to the device-related data to obtain a target fault detection model; Wherein, 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 the 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.

[0019] It will be apparent to those skilled in the art that the 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 the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A charging pile fault detection method based on the Internet of Things, characterized in that: The method comprises: Step S100: construct a fault detection cloud platform, obtain historical charging records of charging piles, obtain historical equipment abnormality records of power distribution equipment that distributes power to charging piles, analyze the degree of influence of charging status of charging piles on equipment operation status of power distribution equipment, and obtain target power distribution equipment; Step S200: obtaining the historical operation record of the charging pile, obtaining the historical equipment operation record of the target power distribution equipment, analyzing the correlation degree between the operation status of the target power distribution equipment and the charging pile, and obtaining equipment correlation data; Step S300: obtaining device association data of the power distribution equipment and the charging pile, obtaining a constructed fault detection model, and optimizing the fault detection model based on the device association data to obtain a target fault detection model; Step S400: monitor the charging piles in the charging station in the current cycle and the target power distribution equipment, and perform fault detection on the charging piles according to the target fault detection model to obtain target detection data, and perform intelligent detection and management on the charging piles based on the target detection data.

2. A charging pile fault detection method based on the Internet of Things according to claim 1, characterized in that: The step S100 includes: Step S101: construct a fault detection cloud platform, monitor the process of a charging pile charging a car in a charging station, obtain various 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 the historical charging record; P max It is represented by the maximum value of the average charging power of the charging piles in the above-mentioned historical charging records; P min It is represented by the minimum value of the average charging power of the charging piles in each of the historical charging records; Step S103: obtaining an average value of the characteristic charging values ​​of the various historical charging records, and when the characteristic charging value of a certain historical charging record is greater than the average value, recording the historical charging record as a marked historical charging record of the charging pile; Step S104: obtaining a power distribution device that distributes power to the charging pile, obtaining a historical device abnormality record of the power distribution device, and extracting historical device abnormality data from the historical device abnormality record, wherein the historical device abnormality data includes data corresponding to various device indicators of the power distribution device; Step S105: obtaining the preset data operating range of each device indicator of the power distribution equipment from the cloud platform, and when each device indicator of the power distribution equipment in a certain historical device abnormality record is within the data operating range of the device indicator, the certain historical device abnormality record is recorded as a characteristic historical device abnormality record of the power distribution equipment; Step S106: Obtain the total number of charging piles in each characteristic historical device abnormality record of the power distribution device, where the historical charging record is marked with the historical charging record, and calculate the impact value S of the charging pile on the device state of the power distribution device: ， Where q represents the total number of characteristic historical equipment abnormality records of the power distribution equipment, F i M is represented by the i-th characteristic historical device abnormality record of the power distribution equipment, and the historical charging record is the total number of charging piles marked with the historical charging record; sum Indicates the total number of charging piles that distribute power to the power distribution equipment; Step S107: When the device state impact value is greater than a preset device state impact threshold, it is determined that the device operation state of the power distribution device is affected by the charging state of the charging pile, and the power distribution device is recorded as a target power distribution device.

3. A charging pile fault detection method based on the Internet of Things according to claim 2, characterized in that: The step S200 includes: Step S201: acquiring the historical operation records of the charging pile in the charging station, and extracting the historical operation data of the charging pile from the historical operation records, wherein the historical operation data includes data corresponding to various equipment parameters of the charging pile; Step S202: Acquire each historical device operation record of the target power distribution device, and acquire data corresponding to each device indicator of the target power distribution device from the historical device operation record; Step S203: Analyze the correlation between the target power distribution equipment and the operating status of the charging pile, wherein the correlation between the cth equipment indicator of the target power distribution equipment and the operating status of the charging piles in the charging pile is specifically analyzed by constructing a device correlation regression model, wherein the device correlation regression model Y c : ， Among them, β0 represents the characteristic intercept; β1, β2, ..., β n It is represented by the regression coefficient of each equipment parameter of the charging pile; ε is the error term; X1, X2, ..., X n Represented as various equipment parameters of the charging pile; Step S204: obtaining data of the cth equipment indicator of the target power distribution equipment in each historical equipment operation record, obtaining data corresponding to each equipment parameter of the charging pile in each historical operation record, and dividing each historical equipment operation record and the historical operation record into a training set and a test set; Step S205: Using the training set, the regression coefficient is solved by the residual square SSE, where the residual square SSE is: ， Wherein, j is the total number of historical equipment operation records of the target power distribution equipment in the training set; Y c，z is the target power distribution equipment, and the value corresponding to the cth equipment indicator in the zth historical equipment operation record in the training set; Y´ c，z is the predicted value corresponding to the cth equipment indicator in the zth historical operation record in the training set for the target power distribution equipment; Step S206: Minimize the residual square SSE, and use the residual square SSE to calculate β0, β α Perform partial derivatives, where α=1, 2, ..., n, and we get: ， ， Among them, X z，α It is represented as the value corresponding to the αth equipment indicator in the zth historical operation record in the training set for the charging pile; For β0, β α Solving the partial derivative of , we can get: ， Wherein, X represents the parameter matrix of various equipment parameters of the charging pile; Y c =Vβ+ε; β is represented as a vector of regression coefficients, where β=(β0, β2, ..., β n ); Step S207: Use the test set to perform performance evaluation on the device-associated regression model, optimize the device-associated regression model, obtain the preset c-th device index of the target power distribution device, and the first characteristic regression coefficient threshold γ1 and the second characteristic regression coefficient threshold γ2 of the charging pile, where γ1>0>γ2; Step S208: When the e-th device parameter β of the charging pile in the device-associated regression model e >γ1, it is determined that the cth equipment index of the target power distribution equipment has a positive correlation with the eth equipment parameter of the charging pile, when β e <γ2, it is determined that the cth equipment index of the target power distribution equipment has a negative correlation with the eth equipment parameter of the charging pile. When it is determined that the cth equipment index of the target power distribution equipment has a correlation with the eth equipment parameter of the charging pile, the cth equipment index of the target power distribution equipment is recorded as the associated equipment index of the eth equipment parameter of the charging pile. When γ1>β e >γ2, determining that the cth equipment index of the target power distribution equipment has no relevance to the eth equipment parameter of the charging pile; Step S209: Obtain various equipment indicators of the target power distribution equipment, associated equipment indicators between the various equipment parameters of the charging pile, and equipment association regression coefficients between various equipment indicators of the target power distribution equipment and various equipment parameters of the charging pile, and aggregate them to obtain equipment association data between the target power distribution equipment and the charging pile.

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

5. A charging pile fault detection method based on the Internet of Things according to claim 4, characterized in that: The step S400 includes: Step S401: monitoring the equipment status of the target power distribution equipment and the charging pile in the charging station, and obtaining equipment data of the target power distribution equipment and the charging pile respectively; Step S402: Obtain a target fault detection model for each charging pile in the charging station, input the device 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 and management on the charging piles based on the target detection data.

6. A charging pile fault detection system based on the Internet of Things, used to execute a charging pile fault detection method based on the Internet of Things as described in any one of claims 1 to 5, characterized in that: The system includes a target power distribution equipment module, an equipment associated data module, a target fault detection model module, and an intelligent detection module; The target power distribution equipment module is used to obtain the historical charging records of the charging pile, analyze the influence of the charging state of the charging pile on the equipment operation state of the power distribution equipment, and obtain the target power distribution equipment; The device association data module is used to obtain the historical device operation records of the target power distribution device, analyze the degree of association between the target power distribution device and the operating status of the charging pile, and obtain device association data; The target fault detection model module is used to optimize the fault detection model according to the device association data to obtain a target fault detection model; The intelligent detection module is used to monitor the charging piles and power distribution equipment in the charging station in the current cycle, and perform fault detection on the charging piles according to the target fault detection model to obtain target detection data, and perform intelligent management of the charging piles based on the target detection data.

7. The charging pile fault detection system based on the Internet of Things according to claim 6 is characterized in that: The target power distribution equipment module includes a device status impact value unit and a target power distribution equipment unit; The device state impact value unit is used to monitor the process of the charging pile charging the car in the charging station, obtain various historical charging records of the charging pile, and calculate the device state 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 equipment operation state of the power distribution equipment is affected by the charging state of the charging pile according to the equipment state impact value, so as to obtain the target power distribution equipment.

8. The charging pile fault detection system based on the Internet of Things according to claim 6 is characterized in that: The device association data module includes a device association analysis unit and a device association data unit; The device association analysis unit is used to construct a device association regression model to analyze the degree of association between the operating status of the target power distribution equipment and the charging pile; The device association data unit is used to collect the associated equipment indicators between the various equipment indicators of the target power distribution equipment and the various equipment parameters of the charging pile, as well as the equipment association regression coefficients between the various equipment indicators of the target power distribution equipment and the various equipment parameters of the charging pile, to obtain the equipment association data between the target power distribution equipment and the charging pile.

9. The charging pile fault detection system based on the Internet of Things according to claim 6 is 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 of the charging pile based on the historical fault records and historical operation records of the charging station in the charging station; The target fault detection unit is used to optimize the fault detection model of the charging pile according to the device association data to obtain a target fault detection model.

10. The charging pile fault detection system based on the Internet of Things according to claim 6, 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 the equipment data of the target power distribution equipment and the 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.

Images