Method and system for monitoring charging pile assembly based on digital twin technology

Abstract

The invention provides a method and a system for monitoring a charging pile assembly based on a digital twin technology. The method comprises the following steps: acquiring historical basic power information data of a charging pile, and splitting the historical basic power information data of the charging pile; constructing a fault detection model and a charging pile digital twinborn body according to the split data, wherein the output of the fault detection model is connected to the charging pile digital twinborn body; collecting real-time operation data of the charging pile by adopting a first sampling frequency, and generating a data stream of the operation data of the charging pile; driving the digital twin of the charging pile by adopting a data stream; if it is determined that the charging pile breaks down according to the output of the fault detection model, real-time operation data of the charging pile are collected by adopting a second sampling frequency, and a component where the charging pile breaks down is verified, and the second sampling frequency is higher than the first sampling frequency; and if the verification is successful, displaying the faulted assembly of the charging pile through the digital twinborn body. The effect of monitoring the charging pile assembly in real time can be achieved.

Description

Technical Field

[0001] The present invention relates to the field of digital twins, and specifically to a method and system for monitoring charging pile components based on digital twin technology. Background Art

[0002] As the sales of new energy vehicles increase, the construction speed of charging piles is also increasing. As the supporting infrastructure of new energy vehicles and electric vehicle systems, charging piles will be ubiquitous in the future, and their safety and reliability are also very critical to the safe use of new energy vehicles.

[0003] As a typical complex electric control system, the charging pile has multiple functions such as rectification, protection, communication and output control. Its reliability during operation is affected by many factors, and the failure mechanism is complex. During the charging process, failures may occur. Therefore, it is difficult to effectively detect charging failures without determining the root cause of the failure.

[0004] Therefore, it is necessary to conduct regular troubleshooting on the charging piles. The existing troubleshooting method is that the operation and maintenance personnel regularly troubleshoot the charging piles. The troubleshooting cycle is long and the troubleshooting is not timely. When a charging pile fails, there is a problem that the fault cannot be handled in time. Summary of the invention

[0005] In order to solve the problem that when a charging pile fails, the fault cannot be confirmed and handled in time, the present application provides a method and system for monitoring charging pile components based on digital twin technology.

[0006] The first aspect of the present application provides a method for monitoring charging pile components based on digital twin technology, characterized in that the method includes: obtaining basic information data of the charging pile power history, and splitting the basic information data of the charging pile power history; constructing a fault detection model and a charging pile digital twin according to the split data, and the output of the fault detection model is connected to the charging pile digital twin; using a first sampling frequency to collect real-time operation data of the charging pile, and generating a data stream of the charging pile operation data; using the data stream to drive the charging pile digital twin; if it is determined that the charging pile has a fault according to the output of the fault detection model, using a second sampling frequency to collect the real-time operation data of the charging pile, and verifying the faulty component of the charging pile, wherein the second sampling frequency is higher than the first sampling frequency; if the verification is successful, the faulty component of the charging pile is displayed through the digital twin.

[0007] In this way, the digital twin is driven by the real-time operation data of the charging pile, and the operation status of the charging pile can be intuitively displayed. Under normal circumstances, the real-time operation data of the charging pile is collected at the first sampling frequency, which saves energy. When the fault detection model detects that the charging pile has a fault, the real-time operation data of the charging pile is collected at the second sampling frequency, which can quickly locate the faulty component of the charging pile and quickly verify the faulty component of the charging pile. In this way, on the one hand, the effect of real-time monitoring of the charging pile components can be achieved, and on the other hand, the fault of the charging pile can be quickly responded to, while saving energy.

[0008] In combination with the first aspect, in a possible implementation, the acquisition of the basic information data of the power history of the charging pile and the splitting of the basic information data of the power history of the charging pile specifically include: acquiring the charging start time, the charging DC output voltage curve, the charging DC output current curve, the battery power change curve, the battery temperature change curve, the charging end time, and the fault type; splitting the basic information data of the power history of the charging pile into at least two stages, and determining the split data ownership, wherein the data ownership includes the first stage historical data, the second stage historical data, the third stage historical data, and the fourth stage historical data, the connection state of the charging gun head of the charging pile in the first stage historical data is not connected, the charging DC output current curve in the second stage historical data fluctuates within the first current interval, the voltage in the third stage historical data fluctuates within the first voltage interval, and the battery power in the fourth stage historical data exceeds the first set power threshold. In this way, the basic information data of the power history of the charging pile is split and cleaned, which can prepare for the construction of the subsequent fault detection model.

[0009] In combination with the first aspect, in a possible implementation, the constructing of the fault detection model according to the charging pile power history basic information data specifically includes: preprocessing the first stage historical data, the second stage historical data, the third stage historical data and the fourth stage historical data, wherein the preprocessed sample data P = {I k ,U k ,T k ,S k ,a,b}, where, I k is the current change curve fitting function after preprocessing, U k is the fitting function of the voltage change curve after preprocessing, T k is the temperature change fitting function after preprocessing, S kis the preprocessed battery power change fitting function, a is a constant between 1 and 4, where 1 represents the first historical stage, 2 represents the second historical stage, 3 represents the third historical stage, 4 represents the fourth historical stage, and b represents the fault type; the sample data and the sample weight value are input into the BP neural network to train a fault detection model, wherein the output of the neural network in the fault detection model is Among them, F is the activation function of the neuron, i is the number of data, P i is the i-th data, w i is the weight matrix of the neural network, θ is the threshold, and the output range is (-1, 1). In this way, the fault detection model can be trained.

[0010] In combination with the first aspect, in a possible implementation method, determining that the charging pile has a fault based on the output of the fault detection model specifically includes: when the fault detection model outputs a result, determining the fault type corresponding to the output result from a pre-designed result comparison table based on the output result; using a second sampling frequency to collect the real-time operation data of the charging pile and verifying the faulty component of the charging pile specifically includes: obtaining the current charging stage of the charging pile, and verifying the fault type for the charging stage.

[0011] In this way, when the fault detection model outputs a result that determines the fault type, the real-time operation data of the charging pile can be collected at the second sampling frequency, and the fault type can be verified. On the one hand, the accuracy of the fault detection model can be verified, and on the other hand, the verification can avoid false alarms in the fault detection model. If the fault detection model outputs a result that shows that the charging pile is faulty, and it is verified that the charging pile is not faulty, the data can be saved and added to the training set for the next training.

[0012] In combination with the first aspect, in a possible implementation method, obtaining the charging stage of the current charging pile, and verifying the fault type for the charging stage specifically includes: when the fault type corresponding to the output result of the fault detection model is that the charging pile gun head is not correctly returned to its position, if it is determined that the charging pile is in a standby state, the output voltage of the charging pile is collected at a second sampling frequency and a scatter plot of the output voltage is drawn; if it is determined that within a first preset time range, the number of scatter points in the output voltage scatter plot with output voltage values ​​between 0 and the rated voltage exceeds a preset voltage scatter point number threshold, then it is determined that the fault type of the charging pile is that the charging pile gun head is not correctly returned to its position; if it is determined that the charging pile is in any one of a constant current charging mode, a constant voltage charging mode and a floating charging mode, then it is determined that the fault type corresponding to the output result of the fault detection model is incorrect, and it is recorded in the operation log.

[0013] Since the incorrect return of the charging pile gun head can only occur in the standby state, when the user inserts the charging pile gun head into the new energy vehicle, the charging pile will not be incorrectly returned. If it is determined that the charging pile is in any of the constant current charging mode, constant voltage charging mode and floating charging mode and the charging pile gun head is incorrect, then the fault type corresponding to the output result of the fault detection model is incorrect. When the charging pile gun head is not correctly returned, the output voltage of the charging pile should be between 0 and the rated voltage. By adopting the second sampling frequency, it can be verified whether the output voltage of the charging pile is between 0 and the rated voltage, so as to determine whether the charging pile gun head is indeed incorrectly returned. If the output result of the fault detection model shows that the charging pile is faulty, and it is verified that the charging pile is not faulty, the data can be saved and added to the training set for the next training.

[0014] In combination with the first aspect, in a possible implementation, obtaining the charging stage of the current charging pile, and verifying the fault type for the charging stage specifically includes: when the fault type corresponding to the output result of the fault detection model is a connector or current relay fault, if it is determined that the charging pile is in a constant current charging mode or a floating charging mode, the output current of the charging pile is collected using a second sampling frequency; when the charging pile is in a constant current charging mode, a scatter plot of the output current is drawn; if it is determined that within a first preset time range, the output current value in the scatter plot of the output current is not within the first current interval, the scatter point number When the value exceeds the preset current scatter point quantity threshold, it is determined that the fault type of the charging pile is a connector or current relay fault; when the charging pile is in a floating charge mode, a scatter diagram of the output current is drawn. If it is determined that within a first preset time range, the number of scatter points in the scatter diagram of the output current whose output current value is not within the second current interval exceeds the preset current scatter point quantity threshold, it is determined that the fault type of the charging pile is a connector or current relay fault; if it is determined that the charging pile is in a standby state or a constant voltage charging mode, it is determined that the fault type corresponding to the output result of the fault detection model is incorrect, and it is recorded in the operation log.

[0015] When the connector or current relay fails, it usually causes the current to rise. In the constant voltage charging mode, the current rise is normal, and there is almost no current in the standby state. Therefore, the constant voltage charging mode and the standby state are usually not considered when the fault type is a connector or current relay fault. Under normal circumstances, the current is relatively stable in the constant current charging mode or the floating charging mode. Therefore, if the fault type corresponding to the output result of the fault detection model is a connector or current relay fault, when the charging pile is in the constant current charging mode, a scatter plot of the output current is drawn. If it is determined that within the first preset time range, the number of scatter points in the scatter plot of the output current that are not within the first current interval exceeds the preset current scatter point number threshold, then the fault type of the charging pile is determined to be a connector or current relay fault; when the charging pile is in the floating charging mode, a scatter plot of the output current is drawn. If it is determined that within the first preset time range, the number of scatter points in the scatter plot of the output current that are not within the second current interval exceeds the preset current scatter point number threshold, then the fault type of the charging pile is determined to be a connector or current relay fault. Thus, it can be confirmed whether the fault is caused by the connector or the current relay. If the output result of the fault detection model shows that the charging pile is faulty, and the charging pile is verified to be not faulty, the data can be saved and added to the training set for the next training.

[0016] In combination with the first aspect, in a possible implementation method, obtaining the charging stage of the current charging pile, and verifying the fault type for the charging stage specifically includes: when the fault type corresponding to the output result of the fault detection model is a transformer fault, if it is determined that the charging pile is in a constant voltage charging mode, the output voltage of the charging pile is collected at a second sampling frequency and a scatter plot of the output voltage is drawn; if within a first preset time range, in the scatter plot of the output voltage, the number of scatter points that are not in the first voltage interval exceeds a preset current scatter point number threshold, then the fault type of the charging pile is determined to be a transformer fault; if it is determined that the charging pile is in any one of the standby mode, constant current charging mode and floating charging mode, then it is determined that the fault type corresponding to the output result of the fault detection model is incorrect, and it is recorded in the operation log.

[0017] When the transformer fails, it usually causes the voltage to rise, while the voltage will not change in the standby state. It is normal for the voltage to rise in the constant current charging mode and the floating charging mode. In the constant voltage charging mode, the voltage usually remains stable. Therefore, if it is determined that the charging pile is in the constant voltage charging mode, the output voltage of the charging pile is collected at a second sampling frequency and a scatter plot of the output voltage is drawn. If within the first preset time range, the number of scatter points in the scatter plot of the output voltage that are not in the first voltage interval exceeds the preset current scatter point number threshold, then the fault type of the charging pile is determined to be a transformer fault. In this way, it can be confirmed whether it is a transformer fault. If the output result of the fault detection model shows that the charging pile is faulty, and it is verified that the charging pile is not faulty, the data can be saved and added to the training set for the next training.

[0018] In combination with the first aspect, in a possible implementation method, the charging stage of the current charging pile is obtained, and the fault type is verified for the charging stage, specifically including: when the fault type corresponding to the output result of the fault detection model is a power acquisition module failure, if it is determined that the charging pile is in any one of the constant current charging mode, the constant voltage charging mode and the floating charging mode, the output voltage and the output current of the charging pile are collected at a second sampling frequency; the charging power is calculated based on the output voltage and the output current, and if the calculated charging power is inconsistent with the power acquired by the power acquisition module, it is determined that the fault type of the charging pile is a power acquisition module failure.

[0019] If the power acquisition module fails, the output voltage and output current of the charging pile are collected at the second sampling frequency; the charging power is calculated according to the output voltage and output current, and if the calculated charging power is inconsistent with the power acquired by the power acquisition module, it is determined that the fault type of the charging pile is a power acquisition module failure. Thus, the power is verified.

[0020] The second aspect of the present application provides a system for monitoring charging components based on digital twin technology, characterized in that the system includes a processor and a memory, and a computer program is stored in the memory. When the computer program is executed by the processor, the method for monitoring charging components based on digital twin technology as described in any one of the first aspect to the first aspect of the present application is implemented.

[0021] The present application provides a method and system for monitoring charging pile components based on digital twin technology. The method includes: obtaining the basic information data of the charging pile power history, and splitting the basic information data of the charging pile power history; constructing a fault detection model and a charging pile digital twin according to the split data, and the output of the fault detection model is connected to the charging pile digital twin; using a first sampling frequency to collect the real-time operation data of the charging pile, and generating a data stream of the charging pile operation data; using the data stream to drive the charging pile digital twin; if the charging pile is determined to be faulty according to the output of the fault detection model, using a second sampling frequency to collect the real-time operation data of the charging pile, and verifying the faulty component of the charging pile, wherein the second sampling frequency is higher than the first sampling frequency; if the verification is successful, the faulty component of the charging pile is displayed through the digital twin.

[0022] In this way, the digital twin is driven by the real-time operation data of the charging pile, and the operation status of the charging pile can be intuitively displayed. Under normal circumstances, the real-time operation data of the charging pile is collected at the first sampling frequency, which saves energy. When the fault detection model detects that the charging pile has a fault, the real-time operation data of the charging pile is collected at the second sampling frequency, which can quickly locate the faulty component of the charging pile and quickly verify the faulty component of the charging pile. In this way, on the one hand, the effect of real-time monitoring of the charging pile components can be achieved, and on the other hand, the fault of the charging pile can be quickly responded to, while saving energy. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A flow chart of a method for monitoring charging pile components based on digital twin technology provided in an embodiment of the present application;

[0024] Figure 2 A schematic diagram of a method flow for processing charging pile power history basic information data and building a fault detection model provided in an embodiment of the present application;

[0025] Figure 3 A specific flow chart for determining whether a charging pile is faulty provided in an embodiment of the present application;

[0026] Figure 4 A schematic diagram of a specific process for verifying the fault type of a charging pile at the charging stage provided in an embodiment of the present application;

[0027] Figure 5 A schematic diagram of a specific process for verifying the fault type of a charging pile at the charging stage provided in an embodiment of the present application;

[0028] Figure 6A schematic diagram of a specific process for verifying the fault type of a charging pile at the charging stage provided in an embodiment of the present application;

[0029] Figure 7 A schematic diagram of a specific process for verifying the fault type of a charging pile at the charging stage provided in an embodiment of the present application;

[0030] Figure 8 A schematic diagram of a system for monitoring charging components based on digital twin technology provided in an embodiment of the present application. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0032] The term "and / or" in this application can be a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this application generally indicates that the associated objects before and after are in an "or" relationship.

[0033] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or modules is not necessarily limited to those steps or modules that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices.

[0034] As a typical complex electric control system, the charging pile has multiple functions such as rectification, protection, communication and output control. Its reliability during operation is affected by many factors, and the failure mechanism is complex. During the charging process, failures may occur. Therefore, it is difficult to effectively detect charging failures without determining the root cause of the failure.

[0035] Therefore, it is necessary to conduct regular troubleshooting on the charging piles. The existing troubleshooting method is that the operation and maintenance personnel regularly troubleshoot the charging piles. The troubleshooting cycle is long and the troubleshooting is not timely. When a charging pile fails, there is a problem that the fault cannot be handled in time.

[0036] Therefore, this application provides a method for monitoring charging pile components based on digital twin technology, see Figure 1 , the method comprising:

[0037] 101. Obtain the basic information data of the charging pile power history, and split the basic information data of the charging pile power history.

[0038] Obtain the basic historical information data of the charging pile power and split the basic historical information data of the charging pile power.

[0039] The charging pile power history basic information data may include data types based on the charging pile, such as current, voltage, temperature, and fault type.

[0040] The basic information data of the charging pile power history is split, and the basis for splitting the basic information data of the charging pile power history can be split according to the characteristics of charging in different stages of three-stage charging.

[0041] The charging method includes three stages: constant current charging stage, constant voltage charging stage and floating charging stage (also called trickle charging stage). In addition, before charging starts, it can be considered as a standby stage. A total of four stages can be distinguished.

[0042] In the standby stage, since the charging head of the charging pile is not connected to the new energy vehicle, the voltage at the charging head is theoretically zero. In the constant current charging stage, the charging current of the charger remains constant, the charged amount increases rapidly, and the battery voltage rises. In the constant voltage charging stage, the charging voltage of the charger remains constant, the charged amount continues to increase, the battery voltage rises slowly, and the charging current decreases. In the floating charging stage, the battery is nearly full and continues to charge at a smaller current.

[0043] 102. Build a fault detection model and a charging pile digital twin based on the split data.

[0044] The fault detection model and the charging pile digital twin are constructed based on the split data. The fault detection model is trained based on the split data.

[0045] By using digital twin technology, a digital twin of the charging pile is established. The digital twin of the operating status is presented using visualization methods and mapped with the operating data of the physical charging pile in the real environment to reflect the current operating status in real time.

[0046] The system software design architecture is divided into five layers: (1) Data layer: mainly includes basic information database, historical database and real-time database. Through the integration and management of these data, it provides overall data support for the software system. (2) Interface layer: as the support for the equipment management system and other systems, including simulation tool interface and data forwarding interface. (3) Component layer: it is the basic support to ensure the operation of the entire equipment management and control system, including log management, task management, security management, plug-in management, transaction management and configuration control. (4) Service layer: encapsulates system functions in the form of services, including data collection, data transmission protocol analysis, data preprocessing, data statistical analysis, algorithm library call, fault prediction and life prediction.

[0047] 103. Use a first sampling frequency to collect real-time operation data of the charging pile, and generate a data stream of the charging pile operation data.

[0048] The real-time operation data of the charging pile is collected using a first sampling frequency, and a data stream of the charging pile operation data is generated. The first sampling frequency can be relatively low, because in general, the refresh frequency of the charging pile digital twin data does not need to be very high, and too high a sampling frequency will consume too much power. Exemplarily, the first sampling frequency can be 15 seconds / time.

[0049] 104. Use data stream to drive the digital twin of the charging pile.

[0050] The charging pile digital twin is driven by a data stream. The real-time operation data of the charging pile is collected according to the first sampling frequency, and the front-end display of the charging pile digital twin is refreshed every time the data is collected.

[0051] 105. If it is determined that the charging pile is faulty according to the output of the fault detection model, the real-time operation data of the charging pile is collected using the second sampling frequency, and the faulty component of the charging pile is verified.

[0052] If it is determined that the charging pile is faulty according to the output of the fault detection model, the real-time operation data of the charging pile is collected using the second sampling frequency, and the faulty component of the charging pile is verified.

[0053] The second sampling frequency is higher than the first sampling frequency. Exemplarily, the second sampling frequency may be 1 second / time.

[0054] In general, the first sampling frequency is used to collect the real-time operation data of the charging pile, which saves energy. When the fault detection model detects that the charging pile has a fault, the second sampling frequency is used to collect the real-time operation data of the charging pile, which can quickly locate the faulty component of the charging pile and quickly verify the faulty component of the charging pile. This can not only meet the effect of real-time monitoring of the charging pile components, but also quickly respond to the fault of the charging pile, and save energy.

[0055] 106. If the verification is successful, the faulty component of the charging pile will be displayed through the digital twin.

[0056] If the verification is successful (i.e., it is confirmed that the charging pile component output by the fault detection model is indeed faulty), the faulty component of the charging pile will be displayed through the digital twin.

[0057] If the verification fails, that is, when the charging pile component is verified to be not faulty, it is determined that the fault detection model has an error, and the data can be saved. Waiting for maintenance personnel to inspect, if an actual fault is found, it will be added to the training set for the next training.

[0058] It should be noted that due to the small number of charging piles and the small amount of data on faults, the accuracy of the fault detection model provided by this application is not very high. Therefore, false alarms may occur, so for this situation, it is necessary to verify again.

[0059] The method for monitoring charging pile components based on digital twin technology provided in the present application drives the digital twin through the real-time operation data of the charging pile, and can intuitively display the operating status of the charging pile. Under normal circumstances, the real-time operation data of the charging pile is collected using the first sampling frequency, which is more energy-saving. When the fault detection model detects that the charging pile has a fault, the real-time operation data of the charging pile is collected using the second sampling frequency, which can quickly locate the faulty component of the charging pile and quickly verify the faulty component of the charging pile. In this way, on the one hand, the effect of real-time monitoring of the charging pile component can be met, and on the other hand, the fault of the charging pile can be quickly responded to, and energy consumption can be saved at the same time.

[0060] With respect to obtaining the charging pile power history basic information data in step 101, splitting the charging pile power history basic information data, and constructing a fault detection model in step 102, the present application also provides a method for processing the charging pile power history basic information data and constructing a fault detection model, see Figure 2 , the method comprising:

[0061] 201. Obtain charging start time, charging DC output voltage curve, charging DC output current curve, battery power change curve, battery temperature change curve, charging end time, and fault type.

[0062] Obtain charging data of a charging pile. It should be noted that the charging data is collected when a fault occurs and the charging data of the faulty component has been verified.

[0063] The charging data includes charging start time, charging DC output voltage curve, charging DC output current curve, battery power change curve, battery temperature change curve, charging end time, and fault type.

[0064] 202. Split the charging pile power history basic information data into at least two stages, and determine the ownership of the split data.

[0065] The charging pile power history basic information data is split into at least two stages, and the ownership of the split data is determined.

[0066] Among them, the data attribution includes historical data of the first stage, historical data of the second stage, historical data of the third stage and historical data of the fourth stage. In the historical data of the first stage, the connection status of the charging gun head of the charging pile is not connected. In the historical data of the second stage, the charging DC output current curve fluctuates within the first current range. In the historical data of the third stage, the voltage fluctuates within the first voltage range. In the historical data of the fourth stage, the battery power exceeds the first set power threshold.

[0067] It should be noted that the first stage historical data corresponds to the standby stage, the second standby stage corresponds to the constant current charging stage, the third stage historical data corresponds to the constant voltage charging stage, and the fourth stage corresponds to the floating charging stage. The charging data of the charging pile failure obtained in step 201 at least includes the standby stage and the constant current charging stage.

[0068] When the charging pile is inserted into the new energy vehicle, it enters the constant current charging stage. Therefore, when the charging pile starts to charge the new energy vehicle, if a fault occurs, the fault data at least includes the standby stage and the constant current charging stage, that is, a charging pile power history basic information data at least includes the first stage historical data and the second stage historical data. The first stage historical data is in the standby stage and usually retains the data 2 minutes before the charging pile is inserted into the new energy vehicle.

[0069] It should be noted that after splitting the basic information data of the charging pile's power history, this solution only retains the data of the fault stage and filters out the data of the normal stage. In practice, if a fault is detected in a stage, charging will be stopped immediately. For example, if a fault occurs in the constant voltage charging stage, the floating charging stage will not be entered. Therefore, if a fault occurs in the constant voltage charging stage in a piece of basic information data of the charging pile's power history, it will only contain the historical data of the first stage, the historical data of the second stage, and the historical data of the third stage, but there will be no historical data of the fourth stage.

[0070] For example, if the fault occurs during the constant current charging stage, the historical data of the first stage and the historical data of the second stage are separated. If the fault occurs during the constant voltage charging stage, the historical data of the first stage, the historical data of the second stage, and the historical data of the third stage are separated. If the fault occurs during the floating charging stage, the historical data of the first stage, the historical data of the second stage, the historical data of the third stage, and the historical data of the fourth stage are separated.

[0071] 203. Preprocess the historical data of the first stage, the historical data of the second stage, the historical data of the third stage, and the historical data of the fourth stage.

[0072] The historical data of the first stage, the historical data of the second stage, the historical data of the third stage and the historical data of the fourth stage are preprocessed. According to different stages, the current change curve, the voltage change curve, the temperature change curve and the battery power change curve are fitted respectively.

[0073] Among them, the preprocessed sample data P = {I k ,U k ,T k ,S k ,a,b}, where, I k is the current change curve fitting function after preprocessing, U k is the fitting function of the voltage change curve after preprocessing, T k is the temperature change fitting function after preprocessing, S k is the fitting function of the battery power change after preprocessing, a is a constant between 1 and 4, where 1 represents the first historical stage, 2 represents the second historical stage, 3 represents the third historical stage, 4 represents the fourth historical stage, and b represents the fault type.

[0074] The fault type may be a pre-set code, which may correspond to a uniquely determined fault type. For example, when the code is 1, it means that the charging gun head is not properly reset, when the code is 2, it means that the connector or current relay is faulty, when the code is 3, it means that the transformer is faulty, when the code is 4, it means that the power acquisition module is faulty...

[0075] 204. Input the sample data into the BP neural network to train a fault detection model.

[0076] The sample data is input into the BP neural network to train a fault detection model, wherein the output of the neural network in the fault detection model is Among them, F is the activation function of the neuron, i is the number of data, P i is the i-th data, w i is the weight matrix of the neural network, θ is the threshold, and the output range is (-1, 1).

[0077] The output results of the fault detection model can correspond to the fault type according to the interval. For example, when the output range is (-1, -0.5], it means that the charging gun head is not properly reset, when the output range is (-0.5, -0.25], it means that the connector or current relay is faulty, when the output range is (-0.25, 0.25], it means that the transformer is faulty, and when the output range is (-0.25, 1), it means that the power acquisition module is faulty...

[0078] It should be noted that due to the small sample size of fault data, the reliability of the fault detection model is not high, so further verification of the output results of the fault detection model is required. Figure 3 , the present application also provides a specific flow chart for determining whether a charging pile has a fault.

[0079] 301. When the fault detection model outputs a result, the fault type corresponding to the output result is determined from a pre-designed result comparison table according to the output result.

[0080] When the fault detection model outputs a result, the fault type corresponding to the output result is determined from a pre-designed result comparison table according to the output result.

[0081] According to the output result of the fault detection model, the corresponding interval is determined, and then the fault type corresponding to the interval is obtained. See step 204.

[0082] 302. Obtain the current charging stage of the charging pile, and verify the fault type according to the charging stage.

[0083] The charging stage of the current charging pile is obtained, and the fault type is verified for the charging stage.

[0084] See also Figure 4 , the application also provides a specific process for verifying the fault type according to the charging stage of the charging pile.

[0085] 3011. The fault type corresponding to the output result of the fault detection model is that the charging pile gun head is not correctly returned to its position.

[0086] The fault type corresponding to the output result of the fault detection model is that the charging pile gun head is not properly returned to its original position.

[0087] 3012. If it is determined that the charging pile is in standby mode, the output voltage of the charging pile is collected at a second sampling frequency and a scatter plot of the output voltage is drawn. If it is determined that within the first preset time range, the number of scatter points in the scatter plot of the output voltage between 0 and the rated voltage exceeds the preset voltage scatter point number threshold, then it is determined that the fault type of the charging pile is that the charging pile gun head is not correctly returned to its position.

[0088] If it is determined that the charging pile is in standby state, the output voltage of the charging pile is collected at a second sampling frequency and a scatter plot of the output voltage is drawn. If it is determined that within the first preset time range, the number of scatter points in the output voltage scatter plot between 0 and the rated voltage exceeds the preset voltage scatter point number threshold, then it is determined that the fault type of the charging pile is that the charging pile gun head is not correctly returned to its position.

[0089] Exemplarily, the first preset time range may be 30 seconds, and the second sampling frequency may be 1 second / time, then 30 scattered data of the output voltage may be collected within the first preset range. The scattered point number threshold may be 15. That is, when the number of scattered points of the output voltage value between 0 and the rated voltage collected within 30 seconds exceeds 15, it can be confirmed that the charging pile gun head is not correctly returned to the position.

[0090] 3013. If it is determined that the charging pile is in any one of the constant current charging mode, the constant voltage charging mode and the floating charging mode, it is determined that the fault type corresponding to the output result of the fault detection model is incorrect.

[0091] If it is determined that the charging pile is in any of the constant current charging mode, constant voltage charging mode and floating charging mode, it is determined that the fault type corresponding to the output result of the fault detection model is incorrect, which can be recorded in the operation log.

[0092] Since the incorrect return of the charging pile gun head can only occur in the standby state, when the user inserts the charging pile gun head into the new energy vehicle, the charging pile will not be incorrectly returned. If it is determined that the charging pile is in any of the constant current charging mode, constant voltage charging mode and floating charging mode and the charging pile gun head is incorrect, then the fault type corresponding to the output result of the fault detection model is incorrect. When the charging pile gun head is not correctly returned, the output voltage of the charging pile should be between 0 and the rated voltage. By adopting the second sampling frequency, it can be verified whether the output voltage of the charging pile is between 0 and the rated voltage, so as to determine whether the charging pile gun head is indeed incorrectly returned. If the output result of the fault detection model shows that the charging pile is faulty, and it is verified that the charging pile is not faulty, the data can be saved immediately. Wait for maintenance personnel to inspect, if an actual fault is found, and add it to the training set for the next training.

[0093] See also Figure 5 , this application also provides a specific process for verifying the fault type according to the charging stage of the charging pile:

[0094] 3021. The fault type corresponding to the output result of the fault detection model is a connector or current relay fault.

[0095] The fault type corresponding to the output result of the fault detection model is a connector or current relay fault.

[0096] 3022. If it is determined that the charging pile is in a constant current charging mode or a floating charging mode, the output current of the charging pile is collected at a second sampling frequency; when the charging pile is in a constant current charging mode, a scatter plot of the output current is drawn, and if it is determined that within a first preset time range, the number of scatter points in the scatter plot of the output current whose output current value is not within the first current interval exceeds the preset current scatter point number threshold, then the fault type of the charging pile is determined to be a connector or current relay fault; when the charging pile is in a floating charging mode, a scatter plot of the output current is drawn, and if it is determined that within a first preset time range, the number of scatter points in the scatter plot of the output current whose output current value is not within the second current interval exceeds the preset current scatter point number threshold, then the fault type of the charging pile is determined to be a connector or current relay fault.

[0097] If it is determined that the charging pile is in a constant current charging mode or a floating charging mode, the output current of the charging pile is collected at a second sampling frequency; when the charging pile is in a constant current charging mode, a scatter plot of the output current is drawn, and if it is determined that within a first preset time range, the number of scatter points in the scatter plot of the output current whose output current value is not within the first current interval exceeds the preset current scatter point number threshold, then the fault type of the charging pile is determined to be a connector or current relay fault; when the charging pile is in a floating charging mode, a scatter plot of the output current is drawn, and if it is determined that within a first preset time range, the number of scatter points in the scatter plot of the output current whose output current value is not within the second current interval exceeds the preset current scatter point number threshold, then the fault type of the charging pile is determined to be a connector or current relay fault.

[0098] Exemplarily, the first preset time range may be 30 seconds, the second sampling frequency may be 1 second / time, and 30 scattered point data of the output current may be collected within the first preset range. The scattered point number threshold may be 15.

[0099] Taking the battery of a new energy vehicle as a 40V battery as an example, in the constant current mode, the first current interval can be between 1.8A-2.5A. The second current interval can be 0.4A-0.5A. That is, when the charging pile is in the constant current charging mode, a scatter plot of the output current is drawn. If it is determined that within 30 seconds, the number of scatter points in the scatter plot of the output current that are not within 1.8A-2.5A exceeds 15, then the fault type of the charging pile is determined to be a connector or current relay fault.

[0100] When the charging pile is in floating charging mode, draw a scatter plot of the output current. If it is determined that within 30 seconds, the number of scatter points in the scatter plot of the output current that are not within 0.4A-0.5A exceeds 15, then the fault type of the charging pile is determined to be a connector or current relay fault.

[0101] 3023. If it is determined that the charging pile is in a standby state or a constant voltage charging mode, it is determined that the fault type corresponding to the output result of the fault detection model is incorrect.

[0102] If it is determined that the charging pile is in a standby state or a constant voltage charging mode, it is determined that the fault type corresponding to the output result of the fault detection model is incorrect.

[0103] When the connector or current relay fails, it usually causes the current to rise. In the constant voltage charging mode, the current rise is normal, and there is almost no current in the standby state. Therefore, the constant voltage charging mode and the standby state are usually not considered when the fault type is a connector or current relay fault. Under normal circumstances, the current is relatively stable in the constant current charging mode or the floating charging mode. Therefore, if the fault type corresponding to the output result of the fault detection model is a connector or current relay fault, when the charging pile is in the constant current charging mode, a scatter plot of the output current is drawn. If it is determined that within the first preset time range, the number of scatter points in the scatter plot of the output current that are not within the first current interval exceeds the preset current scatter point number threshold, then the fault type of the charging pile is determined to be a connector or current relay fault; when the charging pile is in the floating charging mode, a scatter plot of the output current is drawn. If it is determined that within the first preset time range, the number of scatter points in the scatter plot of the output current that are not within the second current interval exceeds the preset current scatter point number threshold, then the fault type of the charging pile is determined to be a connector or current relay fault. This allows confirmation of whether the fault is a connector or current relay fault. If the fault detection model outputs a result showing a charging pile fault, and the charging pile is verified to be fault-free, the data can be saved. The maintenance personnel will inspect the charging pile, and if an actual fault is found, the fault will be added to the training set for the next training.

[0104] See also Figure 6 , this application also provides a specific process for verifying the fault type according to the charging stage of the charging pile:

[0105] 3031. The fault type corresponding to the output result of the fault detection model is transformer fault.

[0106] The fault type corresponding to the output result of the fault detection model is transformer fault.

[0107] 3032. If it is determined that the charging pile is in the constant voltage charging mode, the output voltage of the charging pile is collected at a second sampling frequency and a scatter plot of the output voltage is drawn. If, within a first preset time range, in the scatter plot of the output voltage, the number of scatter points that are not in the first voltage interval exceeds a preset current scatter point number threshold, it is determined that the fault type of the charging pile is a transformer fault.

[0108] If it is determined that the charging pile is in constant voltage charging mode, the output voltage of the charging pile is collected at a second sampling frequency and a scatter plot of the output voltage is drawn. If within the first preset time range, in the scatter plot of the output voltage, the number of scatter points that are not in the first voltage interval exceeds the preset current scatter point number threshold, then the fault type of the charging pile is determined to be a transformer fault.

[0109] Exemplarily, the first preset time range may be 30 seconds, the second sampling frequency may be 1 second / time, and 30 scattered point data of the output current may be collected within the first preset range. The scattered point number threshold may be 15.

[0110] Taking the battery of a new energy vehicle as a 40V storage battery as an example, in the constant current mode, the first voltage interval can be between 58V and 59V. That is, when the charging pile is in the constant voltage charging mode, a scatter plot of the output current is drawn. If it is determined that within 30 seconds, the number of scatter points in the scatter plot of the output current whose output voltage value is not within 58V-59V exceeds 15, then the fault type of the charging pile is determined to be a transformer fault.

[0111] 3033. It is determined that the charging pile is in any of the standby mode, constant current charging mode and floating charging mode, and it is determined that the fault type corresponding to the output result of the fault detection model is incorrect.

[0112] It is determined that the charging pile is in any one of the standby state, the constant current charging mode and the floating charging mode, and it is determined that the fault type corresponding to the output result of the fault detection model is incorrect.

[0113] When the transformer fails, it usually causes the voltage to rise, while the voltage will not change in the standby state. It is normal for the voltage to rise in the constant current charging mode and the floating charging mode. In the constant voltage charging mode, the voltage usually remains stable. Therefore, if it is determined that the charging pile is in the constant voltage charging mode, the output voltage of the charging pile is collected at a second sampling frequency and a scatter plot of the output voltage is drawn. If within the first preset time range, the number of scatter points in the scatter plot of the output voltage that are not in the first voltage interval exceeds the preset current scatter point number threshold, then the fault type of the charging pile is determined to be a transformer fault. In this way, it can be confirmed whether it is a transformer fault. If the output result of the fault detection model shows that the charging pile is faulty, and it is verified that the charging pile is not faulty, the data can be saved and added to the training set for the next training.

[0114] See also Figure 7 , this application also provides a specific process for verifying the fault type according to the charging stage of the charging pile:

[0115] 3041. The fault type corresponding to the output result of the fault detection model is a power acquisition module fault.

[0116] The fault type corresponding to the output result of the fault detection model is power acquisition module failure.

[0117] 3042. If it is determined that the charging pile is in any one of the constant current charging mode, the constant voltage charging mode and the floating charging mode, the output voltage and the output current of the charging pile are collected using a second sampling frequency.

[0118] If it is determined that the charging pile is in any one of the constant current charging mode, the constant voltage charging mode and the floating charging mode, the output voltage and the output current of the charging pile are collected using a second sampling frequency.

[0119] 3043. Calculate the charging power according to the output voltage and the output current. If the calculated charging power is inconsistent with the power acquired by the power acquisition module, determine that the fault type of the charging pile is a power acquisition module fault.

[0120] The charging power is calculated according to the output voltage and the output current. If the calculated charging power is inconsistent with the power acquired by the power acquisition module, it is determined that the fault type of the charging pile is a power acquisition module fault.

[0121] If the power acquisition module fails, the output voltage and output current of the charging pile are collected at the second sampling frequency; the charging power is calculated according to the output voltage and output current, and if the calculated charging power is inconsistent with the power acquired by the power acquisition module, it is determined that the fault type of the charging pile is a power acquisition module failure. Thus, the power is verified.

[0122] The present application also provides a system for monitoring charging components based on digital twin technology. The system for monitoring charging components based on digital twin technology includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the aforementioned method for monitoring charging components based on digital twin technology is implemented.

[0123] like Figure 8 As shown, the system 40 for monitoring charging components based on digital twin technology includes:

[0124] One or more processors 410 and memory 420, Figure 8 A processor 410 is used as an example for description. The processor 410 and the memory 420 may be connected via a bus or other means. Figure 8 The example of connecting through bus is taken in the following.

[0125] Processor 410 is used to complete various control logics of system 10, which can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a single-chip microcomputer, an ARM (Acorn RISC Machine) or other programmable logic device, a discrete gate or transistor logic, a discrete hardware component, or any combination of these components. In addition, processor 410 can also be any traditional processor, microprocessor or state machine. Processor 410 can also be implemented as a combination of computing devices, for example, a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors combined with a DSP core, or any other such configuration.

[0126] The memory 420, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions corresponding to a ground filtering method in an embodiment of the present invention. The processor 410 executes various functional applications and data processing of the system 40 for monitoring charging components based on digital twin technology by running the non-volatile software programs, instructions and units stored in the memory 420, that is, implements the ground filtering method in the above method embodiment.

[0127] The memory 420 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created based on the use of the system 40 for monitoring charging components based on digital twin technology, etc. In addition, the memory 420 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 420 may optionally include a memory remotely arranged relative to the processor 410, and these remote memories may be connected to the system 40 for monitoring charging components based on digital twin technology via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0128] One or more units are stored in the memory 420, and when executed by one or more processors 410, a method for monitoring a charging component based on digital twin technology in any of the above method embodiments is executed, for example, the above described method is executed. Figure 1-7 The methods and steps in any one of the embodiments.

[0129] An embodiment of the present invention provides a non-volatile computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are executed by one or more processors, for example, to execute the above-described Figure 1-7The method and steps of any embodiment.

[0130] As an example, the non-volatile storage medium can include a read-only memory (ROM), a programmable ROM (PROM), an electrically programmable ROM (EPROM), an electrically erasable ROM (EEPROM), or a flash memory. Volatile memory can include a random access memory (RAM) as an external cache memory. By way of illustration and not limitation, RAM can be obtained in many forms such as synchronous RAM (SRAM), dynamic RAM, (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), and direct Rambus RAM (DRRAM). The disclosed memory components or memories of the operating environment described herein are intended to include one or more of these and / or any other suitable types of memory.

[0131] Another embodiment of the present invention provides a computer program product, the computer program product includes a computer program stored in a non-volatile computer-readable storage medium, the computer program includes program instructions, when the program instructions are executed by a processor, the processor is caused to perform a ground filtering method of the above method embodiment. For example, the above described Figure 1-7 The methods and steps in any one of the embodiments.

[0132] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a general hardware platform, and of course can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can exist in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer electronic device (which can be a personal computer, a server, or a network electronic device, etc.) to execute the methods of each embodiment or some parts of the embodiment.

[0133] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0134] In the embodiments provided in this application, it should be understood that the disclosed methods can be implemented in other ways without exceeding the spirit and scope of this application. The current embodiment is only an illustrative example and should not be used as a limitation. The specific content given should not limit the purpose of this application. For example, some features can be ignored or not executed.

[0135] The technical means disclosed in the present application are not limited to the technical means disclosed in the above-mentioned implementation methods, but also include technical solutions composed of any combination of the above technical features. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of this application, and these improvements and modifications are also regarded as the protection scope of this application.

[0136] The above is a detailed introduction to a method and system for monitoring charging components based on digital twin technology provided by the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for those of ordinary skill in the art, according to the ideas of the present application, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on the present application. Although the present application has been described in detail with reference to the aforementioned embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the aforementioned embodiments, or replace some of the technical features therein by equivalents; and these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for monitoring charging pile components based on digital twin technology, characterized in that: The method comprises: Obtaining charging pile power history basic information data, and splitting the charging pile power history basic information data; Constructing a fault detection model and a charging pile digital twin according to the split data, wherein the output of the fault detection model is connected to the charging pile digital twin; Using a first sampling frequency to collect real-time operation data of the charging pile, and generating a data stream of the operation data of the charging pile; Using the data stream to drive the charging pile digital twin; If it is determined that the charging pile has a fault according to the output of the fault detection model, real-time operation data of the charging pile is collected using a second sampling frequency, and the faulty component of the charging pile is verified, wherein the second sampling frequency is higher than the first sampling frequency; If the verification is successful, the faulty component of the charging pile is displayed through the digital twin.

2. The method for monitoring charging pile components based on digital twin technology according to claim 1, characterized in that: The acquiring of the charging pile power history basic information data and splitting the charging pile power history basic information data specifically includes: Obtain charging start time, charging DC output voltage curve, charging DC output current curve, battery power change curve, battery temperature change curve, charging end time, and fault type; The charging pile power history basic information data is split into at least two stages, and the split data ownership is determined, wherein the data ownership includes the first stage historical data, the second stage historical data, the third stage historical data and the fourth stage historical data, the first stage historical data shows that the connection status of the charging gun head of the charging pile is not connected, the second stage historical data shows that the charging DC output current curve fluctuates within the first current range, the third stage historical data shows that the voltage fluctuates within the first voltage range, and the fourth stage historical data shows that the battery power exceeds the first set power threshold.

3. The method for monitoring charging pile components based on digital twin technology according to claim 2, characterized in that: The construction of a fault detection model based on the historical basic information data of the charging pile power specifically includes: The first stage historical data, the second stage historical data, the third stage historical data and the fourth stage historical data are preprocessed, wherein the preprocessed sample data P = {I k ,U k ,T k ,S k ,a,b}, where, I k is the current change curve fitting function after preprocessing, U k is the fitting function of the voltage change curve after preprocessing, T k is the temperature change fitting function after preprocessing, S k is the fitting function of the battery power change after preprocessing, a is a constant between 1 and 4, where 1 represents the first historical stage, 2 represents the second historical stage, 3 represents the third historical stage, 4 represents the fourth historical stage, and b represents the fault type; The sample data is input into the BP neural network to train a fault detection model, wherein the output of the neural network in the fault detection model is Among them, F is the activation function of the neuron, i is the number of data, P i is the i-th data, w i is the weight matrix of the neural network, θ is the threshold, and the output range is (-1, 1).

4. The method for monitoring charging pile components based on digital twin technology according to claim 1, characterized in that: Determining that the charging pile has a fault according to the output of the fault detection model specifically includes: When the fault detection model outputs a result, the fault type corresponding to the output result is determined from a pre-designed result comparison table according to the output result; The method of collecting the real-time operation data of the charging pile using the second sampling frequency and verifying the faulty component of the charging pile specifically includes: The charging stage of the current charging pile is obtained, and the fault type is verified for the charging stage.

5. The method for monitoring charging pile components based on digital twin technology according to claim 4 is characterized in that: Obtaining the charging stage of the current charging pile and verifying the fault type according to the charging stage specifically includes: When the fault type corresponding to the output result of the fault detection model is that the charging pile gun head is not correctly returned to its position, If it is determined that the charging pile is in a standby state, the output voltage of the charging pile is collected at a second sampling frequency and a scatter plot of the output voltage is drawn; if it is determined that within a first preset time range, the number of scatter points in the scatter plot of the output voltage between 0 and the rated voltage exceeds a preset voltage scatter point number threshold, it is determined that the fault type of the charging pile is that the charging pile gun head is not correctly returned to its position; If it is determined that the charging pile is in any one of the constant current charging mode, the constant voltage charging mode and the floating charging mode, it is determined that the fault type corresponding to the output result of the fault detection model is incorrect, and it is recorded in the operation log.

6. The method for monitoring charging pile components based on digital twin technology according to claim 4, characterized in that: Obtaining the charging stage of the current charging pile and verifying the fault type according to the charging stage specifically includes: When the fault type corresponding to the output result of the fault detection model is a connector or current relay fault, If it is determined that the charging pile is in a constant current charging mode or a floating charging mode, the output current of the charging pile is collected at a second sampling frequency; when the charging pile is in a constant current charging mode, a scatter plot of the output current is drawn, and if it is determined that within a first preset time range, the number of scatter points in the scatter plot of the output current whose output current value is not within a first current interval exceeds a preset current scatter point number threshold, the fault type of the charging pile is determined to be a connector or current relay fault; when the charging pile is in a floating charging mode, a scatter plot of the output current is drawn, and if it is determined that within a first preset time range, the number of scatter points in the scatter plot of the output current whose output current value is not within a second current interval exceeds a preset current scatter point number threshold, the fault type of the charging pile is determined to be a connector or current relay fault; If it is determined that the charging pile is in a standby state or a constant voltage charging mode, it is determined that the fault type corresponding to the output result of the fault detection model is incorrect, and it is recorded in the operation log.

7. The method for monitoring charging pile components based on digital twin technology according to claim 4, characterized in that: Obtaining the charging stage of the current charging pile and verifying the fault type according to the charging stage specifically includes: When the fault type corresponding to the output result of the fault detection model is a transformer fault, If it is determined that the charging pile is in the constant voltage charging mode, the output voltage of the charging pile is collected at a second sampling frequency and a scatter plot of the output voltage is drawn. If, within a first preset time range, in the scatter plot of the output voltage, the number of scatter points that are not in the first voltage interval exceeds a preset current scatter point number threshold, it is determined that the fault type of the charging pile is a transformer fault; If it is determined that the charging pile is in any one of the standby state, constant current charging mode and floating charging mode, it is determined that the fault type corresponding to the output result of the fault detection model is incorrect, and it is recorded in the operation log.

8. The method for monitoring charging pile components based on digital twin technology according to claim 4, characterized in that: Obtaining the charging stage of the current charging pile and verifying the fault type according to the charging stage specifically includes: When the fault type corresponding to the output result of the fault detection model is a power acquisition module fault, If it is determined that the charging pile is in any one of the constant current charging mode, the constant voltage charging mode and the floating charging mode, the output voltage and the output current of the charging pile are collected using a second sampling frequency; The charging power is calculated according to the output voltage and the output current. If the calculated charging power is inconsistent with the power acquired by the power acquisition module, it is determined that the fault type of the charging pile is a power acquisition module fault.

9. A system for monitoring charging components based on digital twin technology, characterized in that: The system includes a processor and a memory, wherein a computer program is stored in the memory. When the computer program is executed by the processor, the method for monitoring charging components based on digital twin technology as described in any one of claims 1 to 8 is implemented.

Images