Fault detection method and device for charging pile and electronic equipment

Abstract

The invention provides a fault detection method and device for a charging pile and electronic equipment, and relates to the technical field of detection. According to the method, operation data of a charging pile during working are obtained, the operation data comprise multiple sub-operation data, and the sub-operation data are any one of temperature, voltage, current, power factor, frequency, harmonic content and insulation resistance; inputting the operation data into a preset support vector machine model to obtain a detection result; if it is determined that the detection result indicates that abnormal sub-operation data exists in the multiple pieces of sub-operation data, it is determined that potential faults exist in the charging pile; determining a fault level based on the abnormal sub-operation data; and triggering an early warning mechanism according to the fault level. By implementing the technical scheme provided by the invention, the accuracy of fault detection of the charging pile is improved.

Description

Technical Field

[0001] The present application relates to the technical field of detection technology, and specifically to a fault detection method, device and electronic equipment for a charging pile. Background Art

[0002] With the continuous development and innovation of new energy vehicle technology, the application scope of charging piles has become very wide, not only covering major areas such as public places, residential areas, commercial areas, but also constantly expanding to other fields.

[0003] At present, the fault detection of charging piles often relies on manual experience judgment, but manual experience judgment is extremely dependent on the intuition, experience and historical cases of the detection, and lacks objective and unified standards and basis. Due to the differences in the experience level and cognition of each detection, the fault judgment of the same charging pile may have different results, and there may even be misjudgments and missed judgments, which makes the accuracy of the fault detection of charging piles low.

[0004] Therefore, there is an urgent need for a charging pile fault detection method, device and electronic equipment. Summary of the invention

[0005] The present application provides a charging pile fault detection method, device and electronic equipment, which are convenient for improving the accuracy of charging pile fault detection.

[0006] In a first aspect of the present application, a fault detection method for a charging pile is provided, the method comprising: obtaining operating data of the charging pile when it is working, the operating data comprising multiple sub-operating data, and the sub-operating data being any one of temperature, voltage, current, power factor, frequency, harmonic content and insulation resistance; inputting the operating data into a preset support vector machine model to obtain a detection result; if it is determined that the detection result indicates that there are abnormal sub-operating data among the multiple sub-operating data, then it is determined that the charging pile has a potential fault; based on the abnormal sub-operating data, determining the fault level; and triggering an early warning mechanism according to the fault level.

[0007] By adopting the above technical solution, by inputting multiple sub-operation data of the charging pile during operation into the preset support vector machine model, the method can use the powerful ability of machine learning to perform in-depth analysis and pattern recognition on complex data. Since the method can monitor the operation data of the charging pile in real time and immediately trigger the early warning mechanism when an abnormality is detected, the timeliness of fault early warning can be achieved. This helps to take measures to intervene before the fault occurs, avoiding the expansion of the fault or causing more serious consequences. Once the abnormal sub-operation data is detected and the fault level is determined, the method can immediately trigger the corresponding early warning mechanism, which helps to quickly locate the fault point, shorten the time of fault handling, and improve the efficiency of fault handling. Compared with traditional manual experience judgment or simple threshold detection, this method can more accurately identify anomalies in the operation data, thereby improving the accuracy of fault detection.

[0008] Optionally, the obtaining of the operating data of the charging pile when it is working specifically includes: when the charging pile is working, real-time obtaining the original data group sent by the temperature sensor, voltmeter, ammeter, power meter, frequency meter, harmonic analyzer and insulation resistance tester; performing data processing on the original data group to obtain the operating data, and the data processing includes data cleaning, data conversion, data classification and data calculation.

[0009] By adopting the above technical solutions, real-time acquisition ensures that the data is obtained when the charging pile is actually working, reflecting the actual operating status of the charging pile. By acquiring data from multiple sources such as temperature sensors, voltmeters, and ammeters, a more comprehensive data set can be formed to improve the accuracy and reliability of data analysis. Data cleaning removes noise, duplicate values, and invalid values ​​in the data to ensure the data quality of subsequent analysis. Data conversion converts data of different formats and units in a unified manner to facilitate subsequent data analysis and comparison. Data classification classifies data according to different attributes, such as temperature, voltage, and current, to facilitate subsequent data processing and model training. Calculate the data as needed, such as calculating power factor, harmonic content, etc., to obtain richer operating data. Through a series of data processing steps, it can be ensured that the final operating data is accurate, reliable, and easy to analyze. This helps to accurately judge the operating status of the charging pile in the future. When the charging pile fails, the abnormal changes in these data can be more accurately reflected, improving the sensitivity of fault detection.

[0010] Optionally, the inputting the operating data into a preset support vector machine model to obtain a detection result specifically includes: predicting the operating data through the preset support vector machine model to obtain an abnormality probability; determining the abnormal sub-operation data from multiple sub-operation data, and storing it in the detection result together with the abnormality probability.

[0011] By adopting the above technical solution, the operation data is predicted by the support vector machine model, and the probability of abnormality of each sub-operation data can be obtained. This probabilistic output makes the detection results more accurate and can reflect the confidence of data anomalies. After obtaining the abnormal probability, it is possible to further determine which sub-operation data are abnormal. This precise positioning helps to quickly diagnose the cause of the charging pile failure in the future. Since the support vector machine model can process the operation data in real time and give the abnormal probability, it can issue an early warning before or at the early stage of the failure. This helps to take timely measures to intervene and prevent the failure from expanding or causing more serious consequences. The abnormal sub-operation data and the corresponding abnormal probability are stored in the test results, providing data support for subsequent decision-making. The test personnel can make more accurate judgments based on these data and formulate more effective maintenance plans.

[0012] Optionally, if it is determined that the detection result indicates that there are abnormal sub-operation data among the multiple sub-operation data, then it is determined that the charging pile has a potential fault, which specifically includes: comparing the abnormal probability with a preset threshold, and the preset threshold is pre-trained according to the preset support vector machine model; if it is determined that the abnormal probability is greater than the preset threshold, then it is determined that the charging pile has a potential fault.

[0013] By adopting the above technical solution, by comparing the abnormal probability with the preset threshold, the objectivity of the judgment of the charging pile fault can be achieved. This data-based judgment method avoids the interference of human factors and improves the accuracy and reliability of the judgment. The preset threshold is pre-trained according to the preset support vector machine model, which can reflect the fluctuation range of each sub-operation data under the normal operation of the charging pile. When the abnormal probability exceeds this threshold, it means that the operating state of the charging pile has deviated from the normal range, and an early warning can be issued in time to improve the sensitivity of the fault early warning. Once it is determined that there is a potential fault in the charging pile, measures can be taken immediately to intervene, such as further diagnosis, repair or replacement of the faulty parts. This timely fault handling helps to reduce the impact of the fault on the operation of the charging pile and improve the availability and reliability of the charging pile. By reasonably setting the preset threshold, the false alarm rate can be reduced. Only when the abnormal probability actually exceeds the threshold, the charging pile is considered to have a potential fault, avoiding false alarms caused by data fluctuations or noise and improving the accuracy of detection.

[0014] Optionally, before inputting the operating data into the preset support vector machine model to obtain the detection result, the preset support vector machine model is trained; the training of the preset support vector machine model specifically includes: obtaining the working data of the charging pile within a preset time period; standardizing the working data to obtain training data; extracting temperature change rate characteristics, voltage fluctuation range characteristics, current stability characteristics, power factor change characteristics, frequency change characteristics, harmonic content change characteristics and insulation resistance change characteristics from the training data according to the operating characteristics and fault detection requirements of the charging pile; statistically analyzing the temperature change rate characteristics, voltage fluctuation range characteristics, current stability characteristics, power factor change characteristics, frequency change characteristics, harmonic content change characteristics and insulation resistance change characteristics to obtain the mean, standard deviation, maximum value and minimum value corresponding to each characteristic; based on the mean, standard deviation, maximum value and minimum value corresponding to each characteristic, an initial model is constructed using a radial basis kernel; and the parameters of the initial model are tuned through cross-validation to obtain the preset support vector machine model.

[0015] By adopting the above technical solution, by obtaining the working data of the charging pile within the preset time period, the training data is ensured to be representative and comprehensive, which helps to improve the generalization ability of the model. According to the operating characteristics and fault detection requirements of the charging pile, key features such as temperature change rate, voltage fluctuation range, and current stability are extracted. These features can reflect the operating status and potential faults of the charging pile, thereby improving the prediction accuracy of the model. The extracted features are statistically analyzed to obtain statistics such as mean, standard deviation, maximum value and minimum value. These statistics can more comprehensively describe the distribution of features and provide more valuable information for model construction. The initial model is constructed using the radial basis kernel. The kernel function has strong nonlinear mapping ability and can handle complex data distribution. It is suitable for nonlinear problems such as charging pile fault detection. By tuning the parameters of the initial model through cross-validation, the optimal parameter combination can be found, so that the model can achieve good performance on both the training set and the test set, and the stability and reliability of the model are improved. Standardization of the working data eliminates the dimensional differences between different features, which helps to speed up the training speed of the model and improve the accuracy of the model. By extracting key features and performing statistics, the impact of redundant information on model training is reduced, and the efficiency and accuracy of model training are improved.

[0016] Optionally, determining the fault level based on the abnormal sub-operation data specifically includes: if the abnormal sub-operation data is determined to be temperature, voltage, current and power factor, determining the fault level to be a first-level fault level; if the abnormal sub-operation data is determined to be frequency, harmonic content and insulation resistance, determining the fault level to be a second-level fault level, and the fault handling priority corresponding to the second-level fault level is lower than the fault handling priority corresponding to the first-level fault level; if the abnormal sub-operation data is determined to be insulation resistance, determining the fault level to be a third-level fault level, and the fault handling priority corresponding to the third-level fault level is lower than the fault handling priority corresponding to the second-level fault level.

[0017] By adopting the above technical solution, the abnormal sub-operation data is divided into different categories and corresponds to different fault levels, so that the classification of fault levels is clearer and more specific. This helps the detection personnel to quickly identify the fault type and severity, so as to take corresponding treatment measures. The fault handling priorities corresponding to different fault levels are different, which reflects the urgency of the fault and the possible impact. The first-level fault level involves the core operating parameters of the charging pile, which has a greater impact on the safety and performance of the charging pile, so it has the highest processing priority. The second-level fault level and the third-level fault level are relatively minor, but they also need timely attention and processing. This priority setting helps the detection personnel to reasonably allocate resources and give priority to emergency and important faults. By clarifying the fault level and the corresponding processing priority, standardized fault handling processes and standards can be formulated to improve the standardization and efficiency of fault handling. According to the fault level and priority, the detection personnel can quickly formulate a processing plan to reduce the time and cost of fault handling.

[0018] Optionally, triggering an early warning mechanism according to the fault level specifically includes: if the fault level is the first-level fault level, triggering the early warning mechanism is an acoustic and optical alarm at the site of the charging pile, forcibly cutting off the power supply of the charging pile, and sending a text message alarm or an email alarm to the charging pile manager; if the fault level is the second-level fault level, triggering the early warning mechanism is sending a text message alarm or an email alarm to the charging pile manager; if the fault level is the third-level fault level, triggering the early warning mechanism is recording a system log, and sending an email notification to the charging pile manager.

[0019] By adopting the above technical solution, triggering the on-site sound and light alarm and power supply cut-off, it can immediately attract the attention of on-site personnel and take emergency measures to prevent the fault from expanding or causing more serious consequences. At the same time, alarm information is sent to managers through SMS and email to ensure that managers can quickly learn about the fault situation and conduct remote command or dispatch. Although it is not as urgent as a level 1 fault, it still requires timely attention from managers. Through SMS and email alarms, managers can understand the fault situation at the first time and decide whether on-site processing or remote guidance is required based on the actual situation. Although the fault level is low, it still needs to be recorded and notified to managers. By recording system logs and sending email notifications, managers can understand the operating status of the charging pile and provide a basis for subsequent equipment maintenance and fault analysis. The early warning mechanism includes multiple methods such as on-site alarm, remote alarm, and system log recording, which can meet the needs of different fault levels and scenarios. This diverse early warning mechanism helps ensure that managers can obtain fault information in a timely manner and take corresponding measures in any case. By triggering the early warning mechanism, managers can quickly understand the fault situation and take corresponding treatment measures based on the fault level and early warning mechanism. This rapid response and accurate processing helps to improve the efficiency and accuracy of fault handling and reduce the impact of faults on the operation of charging piles and user charging.

[0020] In a second aspect of the present application, a fault detection device for a charging pile is provided, the fault detection device comprising an acquisition module and a processing module, wherein the acquisition module is used to acquire operating data of the charging pile when it is working, the operating data comprising multiple sub-operating data, and the sub-operating data is any one of temperature, voltage, current, power factor, frequency, harmonic content and insulation resistance; the processing module is used to input the operating data into a preset support vector machine model to obtain a detection result; the processing module is also used to determine that the charging pile has a potential fault if it is determined that the detection result indicates that there is abnormal sub-operating data among the multiple sub-operating data; the processing module is also used to determine the fault level based on the abnormal sub-operating data; the processing module is also used to trigger an early warning mechanism according to the fault level.

[0021] In the third aspect of the present application, an electronic device is provided, which includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device performs the method described above.

[0022] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, the method described above is executed.

[0023] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: By inputting multiple sub-operation data of the charging pile during operation into the preset support vector machine model, this method can use the powerful ability of machine learning to perform in-depth analysis and pattern recognition on complex data. Since this method can monitor the operation data of the charging pile in real time and immediately trigger the early warning mechanism when an abnormality is detected, the timeliness of fault early warning can be achieved. This helps to take measures to intervene before the fault occurs, avoiding the expansion of the fault or causing more serious consequences. Once the abnormal sub-operation data is detected and the fault level is determined, the method can immediately trigger the corresponding early warning mechanism, which helps to quickly locate the fault point, shorten the time of fault handling, and improve the efficiency of fault handling. Compared with traditional manual experience judgment or simple threshold detection, this method can more accurately identify anomalies in operation data, thereby improving the accuracy of fault detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A schematic flow chart of a charging pile fault detection method provided in an embodiment of the present application.

[0025] Figure 2 Another schematic flow chart of a charging pile fault detection method provided in an embodiment of the present application.

[0026] Figure 3 A module schematic diagram of a charging pile fault detection device provided in an embodiment of the present application.

[0027] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0028] Explanation of the reference numerals: 31, acquisition module; 32, processing module; 41, processor; 42, communication bus; 43, user interface; 44, network interface; 45, memory. DETAILED DESCRIPTION

[0029] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0030] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0031] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0032] With the continuous progress and innovation of new energy vehicle technology, the application scenarios of charging piles have become extremely wide, not only covering core areas such as public places, residential areas, commercial areas, etc., but are also constantly extending to more emerging fields.

[0033] However, the current fault detection of charging piles mainly relies on manual experience. This method is greatly limited by the intuition, past experience and historical cases of the inspectors, and lacks an objective and unified standard system as support. Due to the differences in the experience level and cognition of the inspectors, different judgment results may be generated for the same charging pile fault, and even lead to misjudgment or missed judgment, which seriously affects the accuracy of charging pile fault detection.

[0034] In order to solve the above technical problems, the present application provides a charging pile fault detection method, referring to Figure 1 , Figure 1 A schematic flow chart of a method for detecting a fault of a charging pile provided in an embodiment of the present application. The method for detecting a fault of a charging pile is applied to a server and includes steps S110 to S150, which are as follows: S110. Obtaining operation data of the charging pile when it is working, where the operation data includes a plurality of sub-operation data, and the sub-operation data is any one of temperature, voltage, current, power factor, frequency, harmonic content, and insulation resistance.

[0035] Specifically, a server refers to a computer system or device that is responsible for receiving, storing, processing or forwarding data. In an embodiment of the present application, the server is used to obtain the operating data of the charging pile and perform fault detection and analysis. A charging pile refers to a device that provides charging services for electric vehicles or other rechargeable devices. Operating data refers to various data generated by the charging pile during operation, which reflect the operating status and performance of the charging pile. The operating data consists of multiple sub-operating data, each of which reflects the operating information of a certain aspect of the charging pile. The sub-operating data includes any one of temperature, voltage, current, power factor, frequency, harmonic content, and insulation resistance. These parameters are important indicators for evaluating the operating status and performance of the charging pile.

[0036] Among them, the charging pile will generate heat when working, and the temperature data can reflect the heat dissipation performance of the charging pile and whether there is an overheating risk. The voltage data can reflect whether the output voltage of the charging pile is stable and whether it meets the charging requirements of electric vehicles. The current data can reflect the output current of the charging pile and whether there is overcurrent or undercurrent. The power factor reflects the energy utilization efficiency of the charging pile. The higher the power factor, the more fully the energy is utilized. The frequency data can reflect whether the output frequency of the charging pile is stable and whether it meets the requirements of the power system. The harmonic content reflects the harmonic components in the output current of the charging pile. Excessive harmonic content may cause interference to the power grid and other equipment. The insulation resistance data can reflect the insulation performance of the charging pile and whether there is a risk of insulation damage or leakage.

[0037] In a possible implementation, the operating data of the charging pile when it is working is obtained, specifically including: when the charging pile is working, real-time acquisition of original data groups sent by temperature sensors, voltmeters, ammeters, power meters, frequency meters, harmonic analyzers, and insulation resistance testers; data processing is performed on the original data groups to obtain operating data, and the data processing includes data cleaning, data conversion, data classification, and data calculation.

[0038] Specifically, real-time acquisition by the server means that the data is captured while the charging pile is working, ensuring the real-time and accuracy of the data. The charging pile is equipped with a variety of sensors and instruments, such as temperature sensors, voltmeters, ammeters, power meters, frequency meters, harmonic analyzers, and insulation resistance testers. These devices send their respective measurement data in real time to form a raw data set. Because the raw data may contain erroneous, abnormal, or missing data points. The purpose of data cleaning is to identify and correct these problems to ensure the accuracy and integrity of the data. Because the raw data may be presented in different formats or units, the purpose of data conversion is to convert the data into a unified format and unit for subsequent analysis and processing. The cleaned and converted data is classified according to the physical quantity or function it represents, such as temperature data, voltage data, current data, etc. Based on the classified data, necessary calculations are performed to obtain higher-level operating data, such as power factor, harmonic content, etc.

[0039] S120, inputting the operating data into a preset support vector machine model to obtain a detection result.

[0040] Specifically, the preset support vector machine model is a machine learning algorithm for classification and regression analysis. In an embodiment of the present application, the support vector machine model has been trained and can identify abnormal or fault conditions based on the operating data of the charging pile. The detection result refers to the conclusion drawn by the support vector machine model after processing and analyzing the operating data, which is used to indicate whether the charging pile is operating normally or there are potential problems. Among them, the support vector machine model uses its internal decision function to perform classification or regression analysis based on the input operating data. For the operating data of the charging pile, the current operating status will be identified based on historical data and failure modes. After the model processes the input data, it will output a detection result, which can be a classification label, such as "normal", "abnormal" or a specific fault type, or a continuous value, such as a probability or score indicating the possibility of a fault. In an embodiment of the present application, the detection result is preferably a result containing an abnormal probability.

[0041] In one possible implementation, the operating data is input into a preset support vector machine model to obtain a detection result, which specifically includes: predicting the operating data through a preset support vector machine model to obtain an abnormality probability; determining abnormal sub-operation data from multiple sub-operation data, and storing them together with the abnormality probability in the detection result.

[0042] Specifically, the server inputs the operation data of the charging pile into the preset support vector machine model. The model processes the input data, uses its internal decision function to predict whether there is an abnormality in the charging pile, and gives a probability value indicating the possibility of an abnormality. During the prediction process, the support vector machine model not only gives the probability of an abnormality, but also identifies the specific sub-operation data that causes the abnormality. This is achieved by analyzing the contribution of each sub-operation data to the model prediction results. The server stores the abnormal probability and the abnormal sub-operation data together in the test result. This test result can be used for subsequent operation and maintenance management, fault warning and performance evaluation.

[0043] For example, suppose there is a trained support vector machine model for detecting whether a charging pile has overheating or abnormal voltage. The charging pile operation data received by the server includes information such as temperature, voltage, and current. The following is an example of the processing process: The server receives the operation data of the charging pile, where the temperature data is 90 degrees Celsius, the voltage data is 250 volts (outside the normal range), and the current data is within the normal range. The support vector machine model processes the input data and predicts that the charging pile is abnormal and gives an abnormal probability of 85%. During the prediction process, the support vector machine model identifies that the temperature and voltage data are the main causes of the abnormality. In particular, the voltage data, whose value exceeds the normal range, is determined to be an abnormal sub-operation data. The server stores the abnormal probability (85%) and the abnormal sub-operation data (voltage) together in the detection result. This result shows that the operation status of the charging pile is abnormal, and the voltage data is the main abnormal indicator. Through this process, the server can use the support vector machine model to conduct an in-depth analysis of the operation data of the charging pile, not only giving the probability of abnormality, but also identifying the specific sub-operation data that causes the abnormality. This helps inspectors understand the operating status of the charging pile more accurately and take appropriate measures to solve the problem.

[0044] S130: If it is determined that the detection result indicates that abnormal sub-operation data exists in the plurality of sub-operation data, it is determined that a potential fault exists in the charging pile.

[0045] Specifically, the server checks the abnormal sub-operation data in the detection result. If the detection result indicates that there are at least one or more abnormal sub-operation data in the multiple sub-operation data, this means that there may be problems with some aspects of the charging pile. Based on the presence of abnormal sub-operation data, the server determines that the charging pile has a potential fault. This means that although the charging pile may still be working, its performance may have been affected, or there is a risk of imminent failure.

[0046] In one possible implementation, if it is determined that the detection result indicates that there is abnormal sub-operation data among multiple sub-operation data, it is determined that the charging pile has a potential fault, specifically including: comparing the abnormal probability with a preset threshold, the preset threshold is pre-trained according to a preset support vector machine model; if it is determined that the abnormal probability is greater than the preset threshold, it is determined that the charging pile has a potential fault.

[0047] Specifically, the server first receives the detection results output by the support vector machine model, which includes the abnormal probability. Then, the server compares this abnormal probability with a preset threshold. This preset threshold is determined during the training process of the support vector machine model and is used to distinguish between normal and abnormal operating states. If the abnormal probability is greater than the preset threshold, it means that the operating state of the charging pile is significantly different from the normal state, so the server determines that the charging pile has a potential fault.

[0048] For example, suppose there is a charging pile whose operating data includes temperature, voltage, and current. The server uses the support vector machine model to analyze these data and obtains the following detection results: the probability of abnormality is 80%; the abnormal sub-operation data are temperature and voltage. At the same time, according to the training results of the support vector machine model, the preset threshold is 75%. In this example, the probability of abnormality in the detection result is 80%, which is greater than the preset threshold of 75%. Therefore, the server determines that there is a potential fault in the charging pile. This means that the inspector needs to further inspect the charging pile to determine the specific cause of the fault and take appropriate measures to solve the problem. Through this process, the server is able to use the detection results and preset thresholds provided by the support vector machine model to promptly detect potential problems with the charging pile, thereby avoiding more serious faults.

[0049] S140: Determine the fault level based on the abnormal sub-operation data.

[0050] Specifically, based on the analysis of the abnormal sub-operation data, the server determines a fault level. This level can be qualitative, such as minor, moderate, severe, or quantitative, such as level one, level two, level three, etc. The determination of the fault level depends on multiple factors, including the type, quantity, and duration of the abnormal data, and their impact on the overall operation of the charging pile. The fault level provides a clear indication for inspectors to help them understand the severity of the charging pile failure and decide what measures to take to solve the problem. For example, for a minor fault, simple monitoring and recording may be required; for a serious fault, immediate measures need to be taken to avoid further damage.

[0051] In a possible implementation, the fault level is determined based on the abnormal sub-operation data, specifically including: if the abnormal sub-operation data is determined to be temperature, voltage, current and power factor, the fault level is determined to be a first-level fault level; if the abnormal sub-operation data is determined to be frequency, harmonic content and insulation resistance, the fault level is determined to be a second-level fault level, and the fault handling priority corresponding to the second-level fault level is lower than the fault handling priority corresponding to the first-level fault level; if the abnormal sub-operation data is determined to be insulation resistance, the fault level is determined to be a third-level fault level, and the fault handling priority corresponding to the third-level fault level is lower than the fault handling priority corresponding to the second-level fault level.

[0052] Specifically, if the abnormal sub-operation data includes temperature, voltage, current and power factor, these parameters are directly related to the safe operation and performance of the charging pile. Therefore, when these parameters are abnormal, the server determines the fault level as level one, which means that this is a serious problem and needs to be dealt with immediately. If the abnormal sub-operation data includes frequency, harmonic content and insulation resistance, these parameters are also important, but they will not directly affect the safe operation of the charging pile in the short term. Therefore, when these parameters are abnormal, the server determines the fault level as level two, which means that this is a problem that needs attention, but the processing priority is lower than the level one fault. If the abnormal sub-operation data is only insulation resistance, this is a relatively minor fault and may not have a significant impact on the immediate operation of the charging pile. Therefore, the server determines the fault level as level three, which means that this is a problem that can be dealt with later, and the processing priority is lower than the level two fault. Among them, the fault level supports custom settings by the detection personnel, which will not be repeated here.

[0053] For example, suppose there is a charging pile. After analyzing its operating data, the server obtains the following detection results: the abnormal sub-operation data are temperature and voltage, such as abnormally high temperature and voltage fluctuations beyond the normal range. Based on the above judgment logic, the server determines the fault level as level 1. Because temperature and voltage are key parameters directly related to the safe operation of the charging pile, this is a serious problem and immediate measures need to be taken to deal with it, such as shutting down the charging pile, checking the cooling system, adjusting the voltage stabilizer, etc.

[0054] Assume another scenario, after analyzing the operating data of another charging pile, the server obtains the following detection results: the abnormal sub-operation data is frequency and harmonic content, such as a slight deviation in frequency and a harmonic content exceeding the standard range. At this time, the server determines the fault level as level 2. Although the abnormality of frequency and harmonic content may have an adverse effect on the long-term operation of the charging pile, it will not cause serious consequences in the short term. Therefore, the inspection personnel can investigate and deal with this problem after dealing with more urgent faults.

[0055] Finally, suppose that after analyzing the operating data of the third charging pile, the server obtains the following detection results: the abnormal sub-operation data is insulation resistance, and the insulation resistance value has dropped slightly, but it is still within the safe range. At this time, the server determines the fault level as level three. Because the slight drop in insulation resistance does not immediately affect the operation of the charging pile, this problem can be handled over a longer period of time or together with other maintenance tasks. Through this process, the server is able to set reasonable levels and processing priorities for charging pile faults based on the type and severity of the abnormal sub-operation data, thereby ensuring that the inspection personnel can efficiently handle various faults and ensure the safe operation of the charging pile.

[0056] S150. Trigger an early warning mechanism according to the fault level.

[0057] Specifically, the server first determines the fault level based on the abnormal sub-operation data of the charging pile. This process may involve analysis, comparison and judgment of the data to determine the severity of the fault. Once the fault level is determined, the server will trigger the corresponding early warning mechanism according to this level. This means that the server will automatically send notifications or alarm information to relevant personnel or systems according to preset rules or logic. The notification or alarm information sent by the early warning mechanism includes the fault level, identification information of the charging pile, such as location, number, etc., as well as the cause of the fault and recommended treatment measures. This information helps the detection personnel to quickly understand the fault situation and respond accordingly. After receiving the early warning information, the detection personnel or related systems will take appropriate measures to deal with the fault according to the severity and urgency of the fault. This may include on-site inspection, maintenance, replacement of parts or adjustment of operating parameters.

[0058] Therefore, by inputting multiple sub-operation data of the charging pile during operation into the preset support vector machine model, this method can use the powerful ability of machine learning to perform in-depth analysis and pattern recognition on complex data. Since this method can monitor the operation data of the charging pile in real time and immediately trigger the early warning mechanism when an abnormality is detected, the timeliness of fault early warning can be achieved. This helps to take measures to intervene before the fault occurs, avoiding the expansion of the fault or causing more serious consequences. Once the abnormal sub-operation data is detected and the fault level is determined, the method can immediately trigger the corresponding early warning mechanism, which helps to quickly locate the fault point, shorten the time of fault handling, and improve the efficiency of fault handling. Compared with traditional manual experience judgment or simple threshold detection, this method can more accurately identify anomalies in the operation data, thereby improving the accuracy of fault detection.

[0059] In one possible implementation, refer to Figure 2 , Figure 2Another flow chart of a method for detecting a fault of a charging pile provided in an embodiment of the present application. According to the fault level, the early warning mechanism is triggered, specifically including steps S210 to S230: S210, if the fault level is the first level, the early warning mechanism is triggered to sound and light alarms at the site of the charging pile, the power supply of the charging pile is forcibly cut off, and a text message alarm or an email alarm is sent to the charging pile manager; S220, if the fault level is the second level, the early warning mechanism is triggered to send a text message alarm or an email alarm to the charging pile manager; S230, if the fault level is the third level, the early warning mechanism is triggered to record the system log, and send an email notification to the charging pile manager.

[0060] Specifically, the first-level fault level warning mechanism: trigger the sound and light alarm device at the site of the charging pile to alert nearby personnel in a visual and auditory way. In order to ensure safety, the power supply of the charging pile is directly cut off to prevent the fault from further expanding or causing more serious consequences. Send text messages and emails containing fault information to the charging pile managers so that they can understand the fault situation in time and respond. The second-level fault level warning mechanism: the same as the first-level fault level, send text messages and emails to the charging pile managers, but do not trigger the on-site sound and light alarm and power cut-off actions. The third-level fault level warning mechanism: record the fault information in the system log file for subsequent analysis and tracking. Send an email containing fault information to the charging pile managers, but no longer send text message alarms, and do not trigger the on-site sound and light alarm and power cut-off actions. Through these specific warning mechanisms, the server can take corresponding warning actions according to different levels of fault conditions, ensuring that the detection personnel can understand the fault situation in time and take corresponding treatment measures according to the severity and urgency of the fault.

[0061] In a possible implementation, before inputting the operating data into a preset support vector machine model to obtain the detection results, the preset support vector machine model is trained; the training of the preset support vector machine model specifically includes: obtaining the working data of the charging pile within a preset time period; standardizing the working data to obtain training data; extracting temperature change rate characteristics, voltage fluctuation range characteristics, current stability characteristics, power factor change characteristics, frequency change characteristics, harmonic content change characteristics and insulation resistance change characteristics from the training data according to the operating characteristics and fault detection requirements of the charging pile; statistically analyzing the temperature change rate characteristics, voltage fluctuation range characteristics, current stability characteristics, power factor change characteristics, frequency change characteristics, harmonic content change characteristics and insulation resistance change characteristics to obtain the mean, standard deviation, maximum value and minimum value corresponding to each characteristic; based on the mean, standard deviation, maximum value and minimum value corresponding to each characteristic, an initial model is constructed using a radial basis kernel; and the parameters of the initial model are tuned through cross-validation to obtain the preset support vector machine model.

[0062] Specifically, the server collects operating data within a certain period of time from the log system or monitoring system of the charging pile. These data include key parameters such as temperature, voltage, current, power factor, frequency, harmonic content and insulation resistance. The server preprocesses the collected data to eliminate the dimensional differences between different features and make the data more suitable for machine learning. Standardization processing includes removing the mean and scaling to unit variance. According to the operating characteristics and fault detection requirements of the charging pile, the server extracts features such as temperature change rate, voltage fluctuation range, current stability, power factor change, frequency change, harmonic content change and insulation resistance change from the standardized data. These features can reflect the operating status and potential faults of the charging pile. The server performs statistics on the extracted features and calculates the mean, standard deviation, maximum and minimum values ​​of each feature. These statistics help to understand the distribution of features and provide a basis for subsequent model construction. Based on the feature statistical results, the server uses the radial basis kernel function to construct the initial model of the support vector machine, which can handle nonlinear problems. The server tunes the parameters of the initial model, such as the penalty parameter C and the width parameter γ of the radial basis kernel function, through cross-validation, such as K-fold cross-validation, to find the best parameter combination so that the model achieves optimal performance on the validation set.

[0063] The present application also provides a charging pile fault detection device, referring to Figure 3 , Figure 3 A module schematic diagram of a fault detection device for a charging pile provided in an embodiment of the present application. The fault detection device is a server, and the server includes an acquisition module 31 and a processing module 32, wherein the acquisition module 31 acquires the operation data of the charging pile when it is working, and the operation data includes multiple sub-operation data, and the sub-operation data is any one of temperature, voltage, current, power factor, frequency, harmonic content and insulation resistance; the processing module 32 inputs the operation data into a preset support vector machine model to obtain a detection result; if the processing module 32 determines that the detection result indicates that there are abnormal sub-operation data in the multiple sub-operation data, it determines that the charging pile has a potential fault; the processing module 32 determines the fault level based on the abnormal sub-operation data; the processing module 32 triggers the early warning mechanism according to the fault level.

[0064] In a possible implementation, the acquisition module 31 acquires the operating data of the charging pile when it is working, specifically including: the acquisition module 31 acquires the original data group sent by the temperature sensor, voltmeter, ammeter, power meter, frequency meter, harmonic analyzer and insulation resistance tester in real time when the charging pile is working; the processing module 32 processes the original data group to obtain operating data, and the data processing includes data cleaning, data conversion, data classification and data calculation.

[0065] In one possible implementation, the processing module 32 inputs the operating data into a preset support vector machine model to obtain a detection result, which specifically includes: the processing module 32 predicts the operating data through a preset support vector machine model to obtain an abnormality probability; the processing module 32 determines abnormal sub-operation data from multiple sub-operation data, and stores it in the detection result together with the abnormality probability.

[0066] In a possible implementation, if the processing module 32 determines that the detection result indicates that there are abnormal sub-operation data in multiple sub-operation data, it determines that there is a potential fault in the charging pile, specifically including: the processing module 32 compares the abnormal probability with a preset threshold, and the preset threshold is pre-trained according to a preset support vector machine model; if the processing module 32 determines that the abnormal probability is greater than the preset threshold, it determines that there is a potential fault in the charging pile.

[0067] In a possible implementation, the processing module 32 trains the preset support vector machine model before inputting the operating data into the preset support vector machine model to obtain the detection results; the training of the preset support vector machine model specifically includes: the acquisition module 31 acquires the working data of the charging pile within a preset time period; the processing module 32 standardizes the working data to obtain training data; the processing module 32 extracts temperature change rate characteristics, voltage fluctuation range characteristics, current stability characteristics, power factor change characteristics, frequency change characteristics, harmonic content change characteristics and insulation resistance change characteristics from the training data according to the operating characteristics and fault detection requirements of the charging pile; the processing module 32 performs statistics on the temperature change rate characteristics, voltage fluctuation range characteristics, current stability characteristics, power factor change characteristics, frequency change characteristics, harmonic content change characteristics and insulation resistance change characteristics to obtain the mean, standard deviation, maximum value and minimum value corresponding to each characteristic; the processing module 32 constructs an initial model using a radial basis kernel based on the mean, standard deviation, maximum value and minimum value corresponding to each characteristic; the processing module 32 tunes the parameters of the initial model through cross-validation to obtain the preset support vector machine model.

[0068] In a possible implementation, the processing module 32 determines the fault level based on the abnormal sub-operation data, specifically including: if the processing module 32 determines that the abnormal sub-operation data is temperature, voltage, current and power factor, the fault level is determined to be a first-level fault level; if the processing module 32 determines that the abnormal sub-operation data is frequency, harmonic content and insulation resistance, the fault level is determined to be a second-level fault level, and the fault handling priority corresponding to the second-level fault level is lower than the fault handling priority corresponding to the first-level fault level; if the processing module 32 determines that the abnormal sub-operation data is insulation resistance, the fault level is determined to be a third-level fault level, and the fault handling priority corresponding to the third-level fault level is lower than the fault handling priority corresponding to the second-level fault level.

[0069] In a possible implementation, the processing module 32 triggers an early warning mechanism according to the fault level, specifically including: if the fault level of the processing module 32 is a first-level fault level, the early warning mechanism is triggered to sound and light alarms at the site of the charging pile, the power supply of the charging pile is forced to be cut off, and a text message alarm and an email alarm are sent to the charging pile manager; if the fault level of the processing module 32 is a second-level fault level, the early warning mechanism is triggered to send a text message alarm and an email alarm to the charging pile manager; if the fault level of the processing module 32 is a third-level fault level, the early warning mechanism is triggered to record system logs, and an email notification is sent to the charging pile manager.

[0070] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0071] The present application also provides an electronic device, referring to Figure 4 , Figure 4 The electronic device may include: at least one processor 41 , at least one network interface 44 , a user interface 43 , a memory 45 , and at least one communication bus 42 .

[0072] The communication bus 42 is used to realize the connection and communication between these components.

[0073] The user interface 43 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 43 may also include a standard wired interface and a wireless interface.

[0074] The network interface 44 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0075] Among them, the processor 41 may include one or more processing cores. The processor 41 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 45, and calling data stored in the memory 45. Optionally, the processor 41 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 41 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 41, and it can be implemented separately through a chip.

[0076] Among them, the memory 45 may include a random access memory (RAM) or a read-only memory (Read-Only Memory). Optionally, the memory 45 includes a non-transitory computer-readable storage medium. The memory 45 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 45 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area may store data involved in the above-mentioned method embodiments, etc. The memory 45 may also be optionally at least one storage device located away from the aforementioned processor 41. As Figure 4 As shown, the memory 45 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program of a charging pile fault detection method.

[0077] exist Figure 4In the electronic device shown, the user interface 43 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 41 can be used to call an application program for a charging pile fault detection method stored in the memory 45. When executed by one or more processors, the electronic device executes one or more methods in the above-mentioned embodiments.

[0078] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0079] The present application also provides a computer-readable storage medium, which stores instructions. When executed by one or more processors, the electronic device executes one or more of the methods described in the above embodiments.

[0080] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0081] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0082] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0083] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0084] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0085] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, it will be easy for those skilled in the art to think of other embodiments of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field that are not recorded in the present disclosure. The description and examples are regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A charging pile fault detection method, characterized in that: The method comprises: Acquire operation data of the charging pile when it is working, wherein the operation data includes a plurality of sub-operation data, and the sub-operation data is any one of temperature, voltage, current, power factor, frequency, harmonic content and insulation resistance; Inputting the operating data into a preset support vector machine model to obtain a detection result; If it is determined that the detection result indicates that there is abnormal sub-operation data among the plurality of sub-operation data, it is determined that there is a potential fault in the charging pile; determining a fault level based on the abnormal sub-operation data; According to the fault level, an early warning mechanism is triggered.

2. The charging pile fault detection method according to claim 1, characterized in that: The obtaining of the operating data of the charging pile during operation specifically includes: When the charging pile is working, the original data group sent by the temperature sensor, the voltmeter, the ammeter, the power meter, the frequency meter, the harmonic analyzer and the insulation resistance tester is obtained in real time; The original data group is processed to obtain the operating data, wherein the data processing includes data cleaning, data conversion, data classification and data calculation.

3. The charging pile fault detection method according to claim 1, characterized in that: The step of inputting the operating data into a preset support vector machine model to obtain a detection result specifically includes: Predicting the operating data by using the preset support vector machine model to obtain an abnormality probability; The abnormal sub-operation data is determined from the plurality of sub-operation data, and is stored in the detection result together with the abnormal probability.

4. The charging pile fault detection method according to claim 3, characterized in that: If it is determined that the detection result indicates that there is abnormal sub-operation data in the plurality of sub-operation data, then it is determined that there is a potential fault in the charging pile, specifically including: Comparing the abnormal probability with a preset threshold, wherein the preset threshold is pre-trained according to the preset support vector machine model; If it is determined that the abnormal probability is greater than the preset threshold, it is determined that the charging pile has a potential fault.

5. The charging pile fault detection method according to claim 1, characterized in that: Before inputting the operating data into a preset support vector machine model to obtain a detection result, training the preset support vector machine model; the training of the preset support vector machine model specifically includes: Obtaining working data of the charging pile within a preset time period; Performing standardization on the working data to obtain training data; According to the operating characteristics and fault detection requirements of the charging pile, the temperature change rate characteristics, voltage fluctuation range characteristics, current stability characteristics, power factor change characteristics, frequency change characteristics, harmonic content change characteristics and insulation resistance change characteristics are extracted from the training data; The temperature change rate characteristic, voltage fluctuation range characteristic, current stability characteristic, power factor change characteristic, frequency change characteristic, harmonic content change characteristic and insulation resistance change characteristic are statistically analyzed to obtain the mean, standard deviation, maximum value and minimum value corresponding to each characteristic; Based on the mean, standard deviation, maximum value and minimum value corresponding to each feature, the initial model is constructed using the radial basis kernel; The parameters of the initial model are tuned through cross-validation to obtain the preset support vector machine model.

6. The charging pile fault detection method according to claim 1, characterized in that: The determining of the fault level based on the abnormal sub-operation data specifically includes: If it is determined that the abnormal sub-operation data is temperature, voltage, current and power factor, then the fault level is determined to be a primary fault level; If it is determined that the abnormal sub-operation data is frequency, harmonic content and insulation resistance, the fault level is determined to be a secondary fault level, and the fault processing priority corresponding to the secondary fault level is lower than the fault processing priority corresponding to the primary fault level; If it is determined that the abnormal sub-operation data is insulation resistance, the fault level is determined to be a third-level fault level, and the fault processing priority corresponding to the third-level fault level is lower than the fault processing priority corresponding to the second-level fault level.

7. The charging pile fault detection method according to claim 6, characterized in that: The triggering of the early warning mechanism according to the fault level specifically includes: If the fault level is the first level fault level, the early warning mechanism is triggered to sound and light alarms at the charging pile site, the charging pile power is forcibly cut off, and a text message alarm or email alarm is sent to the charging pile manager; If the fault level is the secondary fault level, the early warning mechanism is triggered to send a text message alarm or an email alarm to the charging pile manager; If the fault level is the third level fault level, the early warning mechanism is triggered to record the system log and send an email notification to the charging pile manager.

8. A fault detection device for a charging pile, characterized in that: The fault detection device comprises an acquisition module (31) and a processing module (32), wherein: The acquisition module (31) is used to acquire the operation data of the charging pile when it is working, wherein the operation data includes a plurality of sub-operation data, and the sub-operation data is any one of temperature, voltage, current, power factor, frequency, harmonic content and insulation resistance; The processing module (32) is used to input the operating data into a preset support vector machine model to obtain a detection result; The processing module (32) is further configured to determine that a potential fault exists in the charging pile if it is determined that the detection result indicates that abnormal sub-operation data exists in the plurality of sub-operation data; The processing module (32) is further used to determine the fault level based on the abnormal sub-operation data; The processing module (32) is further configured to trigger an early warning mechanism according to the fault level.

9. An electronic device, characterized in that: The electronic device comprises a processor (41), a memory (45), a user interface (43) and a network interface (44), wherein the memory (45) is used to store instructions, the user interface (43) and the network interface (44) are both used to communicate with other devices, and the processor (41) is used to execute the instructions stored in the memory (45) so that the electronic device executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is performed.

Images