Charging pile health state evaluation system and method

Abstract

The invention provides a charging pile health state evaluation system and method, and relates to the field of charging pile health detection, and the method comprises the steps: carrying out the feature extraction of the input voltage, output voltage, input current, output current, output power and input active power of a charging pile at a plurality of time points, so as to know the operation condition of a power module of the charging pile; meanwhile, through feature extraction of TCU fault times, AC contactor fault times, charging gun fault times, emergency stop switch fault times, card reader fault times, fan fault times, lightning arrester fault times and door control switch fault times in a period of time, fault conditions of key parts of the charging pile are known; and the health state of the charging pile is evaluated by considering the operation condition of the power module of the charging pile and the fault condition of key components of the charging pile. In this way, the health condition of the charging pile can be comprehensively evaluated, potential faults can be found in time, and corresponding maintenance measures can be taken.

Description

Technical Field

[0001] The present application relates to the field of charging pile health detection, and more specifically, to a charging pile health status assessment system and method. Background Art

[0002] In recent years, with the popularization and promotion of electric vehicles, their number has shown a significant growth trend worldwide. This growth has not only promoted the development of the new energy vehicle industry, but also driven the construction of related supporting facilities, especially charging infrastructure. Charging piles are important equipment for charging electric vehicles, and their quantity and quality directly affect the user experience and promotion effect of electric vehicles.

[0003] However, as the number of charging piles continues to increase, the maintenance and management of charging piles has become increasingly complex. Charging piles may encounter various faults during use, such as low charging efficiency, damaged charging interface, software system failure, etc. These problems not only affect the user's charging experience, but may also bring safety hazards. It is particularly important to evaluate and monitor the health status of charging piles.

[0004] Therefore, a charging pile health status assessment solution is needed. Summary of the invention

[0005] In order to solve the above technical problems, the present application is proposed. The embodiments of the present application provide a charging pile health status assessment system and method.

[0006] According to one aspect of the present application, a charging pile health status assessment system is provided, which includes:

[0007] The charging pile health status assessment related data acquisition module is used to obtain the input voltage, output voltage, input current, output current, output power, input active power of the charging pile at multiple predetermined time points within a predetermined time period, as well as the number of TCU failures, AC contactor failures, charging gun failures, emergency stop switch failures, card reader failures, fan failures, lightning arrester failures, and door control switch failures in the predetermined time period;

[0008] A charging pile health status assessment related data encoding module, used for encoding the input voltage, output voltage, input current, output current, output power, input active power of the charging pile at the plurality of predetermined time points, and the number of TCU failures, AC contactor failures, charging gun failures, emergency stop switch failures, card reader failures, fan failures, lightning arrester failures, and gate switch failures in the predetermined time period to obtain a charging pile health monitoring feature vector;

[0009] The charging pile health status result generation module is used to obtain the charging pile health status level based on the charging pile health monitoring feature vector.

[0010] According to another aspect of the present application, a charging pile health status assessment method is provided, which includes:

[0011] Obtain the input voltage, output voltage, input current, output current, output power, input active power of the charging pile at multiple predetermined time points within a predetermined time period, as well as the number of TCU failures, AC contactor failures, charging gun failures, emergency stop switch failures, card reader failures, fan failures, lightning arrester failures, and door switch failures within the predetermined time period;

[0012] Characterize the input voltage, output voltage, input current, output current, output power, input active power of the charging pile at the plurality of predetermined time points, and the number of TCU failures, AC contactor failures, charging gun failures, emergency stop switch failures, card reader failures, fan failures, lightning arrester failures, and gate switch failures in the predetermined time period to obtain a charging pile health monitoring feature vector;

[0013] Based on the charging pile health monitoring feature vector, a charging pile health status level is obtained.

[0014] Compared with the prior art, the charging pile health status assessment system and method provided by the present application extracts features of the input voltage, output voltage, input current, output current, output power, and input active power of the charging pile at multiple time points to understand the operation of the charging pile power module, and extracts features of the number of TCU failures, AC contactor failures, charging gun failures, emergency stop switch failures, card reader failures, fan failures, lightning arrester failures, and gate switch failures within a period of time to understand the failure of key components of the charging pile, and evaluates the health status of the charging pile by considering the operation of the charging pile power module and the failure of key components of the charging pile. In this way, the health status of the charging pile can be comprehensively assessed, which helps to timely discover potential faults and take corresponding maintenance measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0016] Figure 1Flow chart of a charging pile health status assessment method according to an embodiment of the present application.

[0017] Figure 2 In the charging pile health status assessment method according to the embodiment of the present application, feature encoding is performed on the input voltage, output voltage, input current, output current, output power, input active power of the charging pile at the multiple predetermined time points, and the number of TCU failures, AC contactor failures, charging gun failures, emergency stop switch failures, card reader failures, fan failures, lightning arrester failures, and gate switch failures in the predetermined time period to obtain a flowchart of the charging pile health monitoring feature vector.

[0018] Figure 3 In the charging pile health status assessment method according to an embodiment of the present application, timing feature extraction is performed on the input voltage, output voltage, input current, output current, output power, and input active power of the charging pile at the multiple predetermined time points to obtain a flowchart of the timing feature vector of the charging pile power module monitoring parameters.

[0019] Figure 4 The present invention is a flowchart of obtaining the health status level of a charging pile based on the health monitoring feature vector of the charging pile in the health status assessment method of the charging pile according to an embodiment of the present application.

[0020] Figure 5 4 is a system block diagram of a charging pile health status assessment system according to an embodiment of the present application. DETAILED DESCRIPTION

[0021] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0022] In recent years, with the popularization and promotion of electric vehicles (EV), the number of electric vehicles (EV) has shown a significant growth trend worldwide. This growth has not only promoted the development of the new energy vehicle industry, but also driven the construction of related supporting facilities, especially charging infrastructure. Charging piles are important equipment for charging electric vehicles. Their quantity and quality directly affect the user experience and promotion effect of electric vehicles.

[0023] With the booming electric vehicle market, the demand for charging piles has also surged. The layout of charging piles has become increasingly dense not only in urban centers but also in remote areas. However, this rapid expansion has also brought a series of challenges. Charging piles may encounter various failure problems during use, such as low charging efficiency, damaged charging interface, software system failure, etc. These problems not only affect the user's charging experience, but also may bring safety hazards. For example, low charging efficiency may prevent users from charging in time in an emergency, while damaged charging interface may cause short circuit or fire, resulting in serious consequences. In order to meet these challenges, the health status assessment and monitoring of charging piles has become particularly important. Therefore, a charging pile health status assessment solution is expected.

[0024] In recent years, deep learning and neural networks have been widely used in computer vision, natural language processing, text signal processing and other fields. In addition, deep learning and neural networks have also demonstrated a level close to or even beyond that of humans in image classification, object detection, semantic segmentation, text translation and other fields. The development of deep learning and neural networks provides new solutions and solutions for the health status assessment of charging piles.

[0025] Figure 1 Flow chart of a charging pile health status assessment method according to an embodiment of the present application. Figure 2 FIG. 1 is a schematic diagram of a charging pile health status assessment method according to an embodiment of the present application. Figure 1 and Figure 2 As shown, the charging pile health status assessment method according to the embodiment of the present application includes: S110, obtaining the input voltage, output voltage, input current, output current, output power, input active power of the charging pile at multiple predetermined time points within a predetermined time period, and the number of TCU faults, AC contactor faults, charging gun faults, emergency stop switch faults, card reader faults, fan faults, lightning arrester faults, and gate switch faults in the predetermined time period; S120, feature encoding the input voltage, output voltage, input current, output current, output power, input active power of the charging pile at the multiple predetermined time points, and the number of TCU faults, AC contactor faults, charging gun faults, emergency stop switch faults, card reader faults, fan faults, lightning arrester faults, and gate switch faults in the predetermined time period to obtain a charging pile health monitoring feature vector; S130, obtaining the charging pile health status level based on the charging pile health monitoring feature vector.

[0026] Specifically, in the technical solution of the present application, first, the input voltage, output voltage, input current, output current, output power, input active power of the charging pile at multiple predetermined time points within a predetermined time period and the number of TCU failures, AC contactor failures, charging gun failures, emergency stop switch failures, card reader failures, fan failures, lightning arrester failures, and gate switch failures in the predetermined time period are obtained.

[0027] It should be understood that the input voltage and output voltage of the charging pile directly reflect the power transmission between the charging pile and the power grid and the electric vehicle. The stability of the input voltage affects the efficiency and quality of the charging pile to obtain power from the power grid, while the output voltage is directly related to the charging effect and safety of the electric vehicle battery. Abnormal voltage fluctuations may be caused by power grid problems, internal circuit failures or aging of the charging pile. Input current and output current are direct manifestations of power transmission. The input current reflects the ability of the charging pile to absorb power from the power grid, while the output current determines the charging speed of the electric vehicle battery. Abnormal current (such as too large, too small or unstable) may indicate that the charging pile has problems such as short circuit, overload or circuit aging, which will affect the normal operation and health of the charging pile. The output power is the power provided by the charging pile to the electric vehicle battery, while the input active power is the power actually absorbed by the charging pile from the power grid. The ratio of these two parameters (i.e. efficiency) can reflect the conversion efficiency and energy loss of the charging pile. A decrease in efficiency may mean that there are problems such as increased energy loss, component aging or poor heat dissipation inside the charging pile, which are important factors affecting the health of the charging pile. The health status of the charging pile is a dynamic process, which is affected by many factors. By obtaining the input voltage, output voltage, input current, output current, output power, and input active power data of the charging pile at multiple time points, the continuous monitoring and dynamic analysis of the charging pile operation status can be realized, so as to more accurately evaluate its health status. The charging pile is composed of multiple key components, and the number of failures of these components directly reflects the health status and reliability of the charging pile. Frequently failing components are often the key factors affecting the normal operation and life of the charging pile. As the core control unit of the charging pile, the number of failures of the TCU directly reflects the stability and reliability of the control system of the charging pile; the AC contactor is used to control the power transmission between the charging pile and the power grid. The number of failures may be caused by overload, aging or circuit problems, affecting the normal operation of the charging pile; the charging gun is the connecting component between the electric vehicle and the charging pile. The number of failures may be caused by wear, improper plugging or electrical failure, affecting the charging efficiency and safety; the number of failures of the emergency stop switch, card reader, fan, lightning arrester, and door switch also reflects the health status of the charging pile in terms of safety, comfort, protection performance, etc.

[0028] In general, combining the number of failures of key components with the operating parameters of the charging pile can achieve a comprehensive assessment of the health status of the charging pile. This comprehensive assessment method not only takes into account the current operating status of the charging pile, but also its historical fault records, so as to more accurately judge the health status and potential risks of the charging pile.

[0029] In an embodiment of the present application, an implementation method for obtaining the input voltage, output voltage, input current, output current, output power, input active power of a charging pile at multiple predetermined time points within a predetermined time period, as well as the number of TCU failures, AC contactor failures, charging gun failures, emergency stop switch failures, card reader failures, fan failures, lightning arrester failures, and gate switch failures in the predetermined time period can be: a. Acquisition of electrical parameters: a data collector can be installed on the charging pile to monitor the input voltage, output voltage, input current, output current, output power, input active power and other parameters of the charging pile in real time; b. A fault detection module can be installed in the charging pile to monitor the fault status of various components of the charging pile.

[0030] Figure 2 In the charging pile health status assessment method according to the embodiment of the present application, the input voltage, output voltage, input current, output current, output power, input active power of the charging pile at the plurality of predetermined time points and the number of TCU failures, AC contactor failures, charging gun failures, emergency stop switch failures, card reader failures, fan failures, lightning arrester failures, and gate switch failures in the predetermined time period are feature-encoded to obtain a flow chart of the charging pile health monitoring feature vector. Figure 2As shown, the input voltage, output voltage, input current, output current, output power, input active power of the charging pile at the plurality of predetermined time points and the number of TCU failures, AC contactor failures, charging gun failures, emergency stop switch failures, card reader failures, fan failures, lightning arrester failures, and gate switch failures in the predetermined time period are feature encoded to obtain a charging pile health monitoring feature vector, including: S121, the input voltage, output voltage, input current, output current, output power, input active power of the charging pile at the plurality of predetermined time points, the number of TCU failures, AC contactor failures, charging gun failures, emergency stop switch failures, card reader failures, fan failures, lightning arrester failures, and gate switch failures in the predetermined time period are feature encoded to obtain a charging pile health monitoring feature vector. The timing feature vector of the monitoring parameter of the power module of the charging pile is extracted according to the time series feature of the active power; S122, the timing feature vector of the monitoring parameter of the power module of the charging pile is extracted according to the time series feature of the active power to obtain the timing feature vector of the monitoring parameter of the power module of the charging pile; S123, the timing feature vector of the monitoring parameter of the power module of the charging pile and the fault condition feature vector of the key components of the charging pile are integrated to obtain the health monitoring feature vector of the charging pile.

[0031] Figure 3 The present invention is a flowchart of extracting the time series characteristics of the input voltage, output voltage, input current, output current, output power, and input active power of the charging pile at the plurality of predetermined time points in the charging pile health status assessment method according to the embodiment of the present application to obtain the time series characteristic vector of the monitoring parameter of the charging pile power module. Figure 3 As shown, the timing feature extraction of the input voltage, output voltage, input current, output current, output power, and input active power of the charging pile at the multiple predetermined time points to obtain the timing feature vector of the charging pile power module monitoring parameter includes: S1211, arranging the input voltage, output voltage, input current, output current, output power, and input active power of the charging pile at the multiple predetermined time points into a charging pile power module monitoring parameter timing input matrix according to the time dimension; S1212, passing the charging pile power module monitoring parameter timing input matrix through a charging pile parameter timing encoder based on a multi-scale convolution kernel to obtain a charging pile power module monitoring parameter timing feature matrix; S1213, expanding the charging pile power module monitoring parameter timing feature matrix to obtain the charging pile power module monitoring parameter timing feature vector.

[0032] The operating status of the charging pile changes with time. In order to understand the changing trends and fluctuations of these electrical parameters over time, and thus better understand the operating characteristics of the charging pile, it is necessary to arrange the input voltage, output voltage, input current, output current, output power, and input active power of the charging pile at the multiple predetermined time points according to the time dimension into a charging pile power module monitoring parameter time series input matrix. By analyzing and processing the time series data obtained by the arrangement, the operating status and health status of the charging pile can be understood from the perspective of the charging pile power module.

[0033] Next, the charging pile power module monitoring parameter timing input matrix is ​​passed through a charging pile parameter timing encoder based on a multi-scale convolution kernel to obtain a charging pile power module monitoring parameter timing feature matrix. It should be easy to understand that the charging pile power module monitoring parameter timing input matrix contains important information about the operating status of the charging pile power module, but when used directly, there is often noise, redundancy and irregularity, which makes it difficult to use directly for health status assessment. Therefore, it is necessary to perform feature extraction processing on the charging pile power module monitoring parameter timing input matrix. Through the processing of the charging pile parameter timing encoder based on a multi-scale convolution kernel, the information in the input matrix is ​​converted into a time-effect feature matrix that can characterize the key characteristics of the charging pile electrical parameter timing.

[0034] In detail, the charging pile parameter timing encoder based on multi-scale convolution kernel in the present application is a first convolution neural network model and a second convolution neural network model using convolution kernels with different void rates, wherein the first convolution neural network model uses a convolution kernel of a first size and a first void rate, and the second convolution neural network model uses a convolution neural network model of a first size and a second void rate, and the first void rate is different from the second void rate. Convolution kernels with different void rates can provide receptive fields of different sizes, thereby capturing feature information of different time scales, and due to the characteristics of void convolution (i.e., there are intervals between pixels in the convolution kernel), the receptive field can be expanded without increasing the size of the convolution kernel, thereby reducing the amount of calculation and the number of parameters. In this way, by fusing the feature information extracted by convolution kernels with different void rates, the complex temporal and spatial relationships between the electrical monitoring parameters of the charging pile can be captured.

[0035] In order to make the calculation speed of the model faster, it is necessary to expand the charging pile power module monitoring parameter timing feature matrix to obtain the charging pile power module monitoring parameter timing feature vector. It should be well understood that the charging pile power module monitoring parameter timing feature matrix is ​​two-dimensional data. Two-dimensional data is often more complex than one-dimensional data during calculation, and more time and computing resources are required for calculation. Therefore, the two-dimensional timing feature matrix is ​​expanded into a one-dimensional timing vector, and in the process of expansion, the key feature information is not lost, and will not affect the subsequent classifier to judge the health status of the charging pile.

[0036] At the same time, the number of TCU failures, the number of AC contactor failures, the number of charging gun failures, the number of emergency stop switch failures, the number of card reader failures, the number of fan failures, the number of arrester failures, and the number of gate switch failures in the predetermined time period are arranged into the input vector of the failure conditions of the key components of the charging pile, and then passed through the sequence encoder to obtain the characteristic vector of the failure conditions of the key components of the charging pile. It should be understood that the number of failures of the key components of the charging pile directly reflects the failure conditions of the key components of the charging pile, which is an important basis for judging the health status of the charging pile. Specifically, the more failures of the key components, the lower the reliability of the component, and the worse the health status of the charging pile. By analyzing the failure conditions of the key components of the charging pile in a certain period of time, these data can be effectively used to evaluate the health status of the charging pile. In this application, the sequence encoder is a convolutional neural network model using a one-dimensional convolution kernel. The neurons in the convolutional neural network using a one-dimensional convolution kernel are only connected to some neurons in the previous layer. This local connection characteristic enables the model to focus on the local features of the sequence data, thereby better capturing the changes in the health status of the key components of the charging pile.

[0037] Parameters such as input voltage, output voltage, input current, output current, output power, and input active power directly reflect the efficiency and stability of the charging pile in the process of power conversion and transmission. The timing characteristic vector of the charging pile power module monitoring parameters obtained by the timing analysis of these parameters can capture the dynamic performance changes of the charging pile during operation; the number of failures of key components directly points to the specific problems that may exist in the charging pile. The characteristic vector of the failure situation of the key components of the charging pile obtained by analyzing the failure information of the key components can capture the potential failure of the charging pile. When evaluating the health status of the charging pile, these two aspects of information can be fused together. Therefore, in the technical solution of the present application, the timing characteristic vector of the monitoring parameters of the charging pile power module and the characteristic vector of the failure situation of the key components of the charging pile are fused to obtain the charging pile health monitoring characteristic vector. By fusing these two characteristic vectors, richer and more comprehensive information can be used to evaluate the health status of the charging pile.

[0038] Figure 4 The present invention is a flowchart of obtaining the health status level of a charging pile based on the health monitoring feature vector of the charging pile in the method for evaluating the health status of the charging pile according to the embodiment of the present application. Figure 4As shown, the health status level of the charging pile is obtained based on the charging pile health monitoring feature vector, including: S131, dynamically normalizing the data of the charging pile health monitoring feature vector based on the disturbance control variable to obtain an optimized charging pile health monitoring feature vector; S132, passing the optimized charging pile health monitoring feature vector through a charging pile health status classifier to obtain a classification result, and the classification result is used to represent the health status level of the charging pile.

[0039] In particular, the monitoring of charging piles relies on various sensors to obtain data such as voltage and current, and the accuracy and aging of the sensors will lead to data errors, and environmental factors such as temperature, humidity, and electromagnetic interference will also affect the sensor readings, resulting in fluctuations in the monitored charging pile data. Accordingly, in the technical solution of the present application, considering that the neural network model performs feature mining on the input charging pile health monitoring related data based on the network parameter matrix, if the inherent implicit correlation between the network output characteristics and the network parameter matrix can be further considered, the prior information of the neural network model can be further used to modulate the characteristic manifold of the charging pile health monitoring feature vector to reduce the possibility of special instance disturbances of its eigenvalues. That is, the charging pile health monitoring feature vector is dynamically normalized based on the disturbance control variable to obtain an optimized charging pile health monitoring feature vector.

[0040] Specifically, in an embodiment of the present application, the charging pile health monitoring feature vector is dynamically normalized based on the disturbance control variable to obtain an optimized charging pile health monitoring feature vector, including: calculating the mean and variance of the charging pile health monitoring feature vector; calculating the difference between the eigenvalue of the predetermined position of the charging pile health monitoring feature vector and the mean of the charging pile health monitoring feature vector to obtain a first intermediate calculated value; multiplying the network parameter matrix by the charging pile health monitoring feature vector and then subtracting it from the charging pile health monitoring feature vector by position to obtain a first intermediate vector, and calculating the Frobenius norm of the first intermediate vector to obtain a first norm value; adding the first norm value to the charging pile The variance of the health monitoring feature vector is calculated and then a square root operation is performed to obtain a second intermediate calculation value; the first intermediate calculation value is divided by the second intermediate calculation value to obtain a third intermediate calculation value; the squares of each position of the charging pile health monitoring feature vector are calculated and then accumulated to obtain a first total value; the square root of the first total value is divided by the scale of the network parameter matrix and then the natural exponential function value is calculated to obtain a fourth intermediate calculation value, wherein the scale of the network parameter matrix is ​​equal to the product of the width value of the network parameter matrix and its height value; the fourth intermediate calculation value is multiplied by the weighted hyperparameter and then added to the third intermediate calculation value to obtain the eigenvalue of the predetermined position of the optimized charging pile health monitoring feature vector.

[0041] In an embodiment of the present application, another expression of dynamically normalizing the data of the charging pile health monitoring feature vector based on the disturbance control variable to obtain the optimized charging pile health monitoring feature vector is: processing the charging pile health monitoring feature vector with the following formula to obtain the optimized charging pile health monitoring feature vector; wherein the formula is:

[0042]

[0043] Where V is the charging pile health monitoring feature vector, M is the network parameter matrix, β represents the weighted hyperparameter, and v i is the eigenvalue of the ith position of the charging pile health monitoring feature vector, N is the scale of the network parameter matrix, the scale of the network parameter matrix is ​​equal to the product of the width value and the height value of the network parameter matrix, L is the length of the charging pile health monitoring feature vector, ||·|| F represents the F norm of the feature vector, μ represents the mean value of the charging pile health monitoring feature vector, σ 2 represents the variance of the charging pile health monitoring feature vector, exp(·) represents the exponential function with the natural constant e as the base, v' i represents the eigenvalue of the i-th position of the optimized charging pile health monitoring eigenvector, Represents matrix multiplication.

[0044] It should be understood that in the technical solution of the present application, considering that when the neural network model performs feature mining on the input data based on the network parameter matrix, if the inherent implicit association between the network output feature and the network parameter matrix can be further considered, the prior information of the neural network model can be further used to modulate the characteristic manifold of the charging pile health monitoring feature vector to reduce the possibility of the occurrence of special instance disturbances of its characteristic values. Based on this, in a preferred embodiment, the charging pile health monitoring feature vector is subjected to data dynamic normalization based on the disturbance control variable, which first maps the charging pile health monitoring feature vector to the high-dimensional feature space where the network parameter matrix is ​​located, and uses the compatibility perception factor between the mapping result and the original input as the inherent implicit association descriptor between the network output feature and the network parameter matrix. Then, the statistical characteristics of the feature group of the charging pile health monitoring feature vector are used as the inherent modal information of the charging pile health monitoring feature vector and the inherent implicit association descriptor is used as the instance disturbance differential adjustment variable to perform data dynamic normalization on the attribute values ​​of each position of the charging pile health monitoring feature vector. At the same time, the class-standardized modulus data of the charging pile health monitoring feature vector is used as a bias item to constrain the acceptable range of the group distribution of the charging pile health monitoring feature vector. In this way, the attribute influence of the interference distribution of abnormal samples can be suppressed as much as possible, thereby improving the expression accuracy of the charging pile health monitoring feature vector.

[0045] Finally, the optimized charging pile health monitoring feature vector is passed through the charging pile health status classifier to obtain a classification result, and the classification result is used to represent the charging pile health status level. It should be understood that the optimized charging pile health monitoring feature vector contains information that characterizes the health status of the charging pile, but does not directly represent the health status of the charging pile. Therefore, it is necessary to process the optimized charging pile health monitoring feature vector through the charging pile health status classifier. The charging pile health status classifier is a model based on machine learning, which is used to classify and process the optimized charging pile health monitoring feature vector. The classifier learns the mapping relationship between the charging pile health status and the charging pile monitoring data through the training process, and outputs the corresponding classification result according to the input feature vector in the test phase. The classification result can be "charging pile health status is good", "charging pile health status is general", "charging pile health status is poor". The classification result provides clear guidance for operation and maintenance personnel to help them understand the health status of the charging pile. Through the classification results, the charging piles can be managed in a hierarchical manner and the operation and maintenance resources can be reasonably allocated. For charging piles that need to be focused on, more resources and energy can be invested in monitoring and maintenance; while for charging piles with better health, the monitoring frequency and maintenance intensity can be appropriately reduced.

[0046] In summary, the charging pile health status assessment method based on the embodiment of the present application is explained, which extracts features of the input voltage, output voltage, input current, output current, output power, and input active power of the charging pile at multiple time points to understand the operation of the charging pile power module, and extracts features of the number of TCU failures, AC contactor failures, charging gun failures, emergency stop switch failures, card reader failures, fan failures, lightning arrester failures, and gate switch failures within a period of time to understand the failure of key components of the charging pile, and combines the operation of the charging pile power module and the failure of key components of the charging pile to evaluate the health status of the charging pile. In this way, the health status of the charging pile can be comprehensively evaluated, which helps to timely discover potential faults and take corresponding maintenance measures.

[0047] Figure 5 : is a system block diagram of a charging pile health status assessment system according to an embodiment of the present application. Figure 5 As shown, according to the embodiment of the present application, the charging pile health status assessment system 100 includes: a charging pile health status assessment related data acquisition module 110, which is used to obtain the input voltage, output voltage, input current, output current, output power, input active power of the charging pile at multiple predetermined time points within a predetermined time period, and the number of TCU faults, AC contactor faults, charging gun faults, emergency stop switch faults, card reader faults, fan faults, lightning arrester faults, and gate switch faults in the predetermined time period; a charging pile health status assessment related data encoding module 120, which is used to feature encode the input voltage, output voltage, input current, output current, output power, input active power of the charging pile at the multiple predetermined time points, and the number of TCU faults, AC contactor faults, charging gun faults, emergency stop switch faults, card reader faults, fan faults, lightning arrester faults, and gate switch faults in the predetermined time period to obtain a charging pile health monitoring feature vector; a charging pile health status result generation module 130, which is used to obtain the charging pile health status level based on the charging pile health monitoring feature vector.

[0048] Here, those skilled in the art can understand that the specific functions and operations of each unit and module in the above-mentioned charging pile health status assessment system 100 have been described in the above reference. Figures 1 to 4 The description of the charging pile health status assessment method has been described in detail, and therefore, its repeated description will be omitted.

[0049] In summary, the charging pile health status assessment system 100 based on the embodiment of the present application is explained, which extracts features of the input voltage, output voltage, input current, output current, output power, and input active power of the charging pile at multiple time points to understand the operation of the charging pile power module, and extracts features of the number of TCU failures, AC contactor failures, charging gun failures, emergency stop switch failures, card reader failures, fan failures, lightning arrester failures, and gate switch failures within a period of time to understand the failure of key components of the charging pile, and combines the operation of the charging pile power module and the failure of key components of the charging pile to evaluate the health status of the charging pile. In this way, the health status of the charging pile can be comprehensively evaluated, which helps to timely discover potential faults and take corresponding maintenance measures.

[0050] As described above, the charging pile health status assessment system 100 according to the embodiment of the present application can be implemented in various wireless terminals, such as a server for charging pile health status assessment. In one example, the charging pile health status assessment system 100 according to the embodiment of the present application can be integrated into the wireless terminal as a software module and / or a hardware module. For example, the charging pile health status assessment system 100 can be a software module in the operating system of the wireless terminal, or it can be an application developed for the wireless terminal; of course, the charging pile health status assessment system 100 can also be one of the many hardware modules of the wireless terminal.

[0051] Alternatively, in another example, the charging pile health status assessment system 100 and the wireless terminal may also be separate devices, and the charging pile health status assessment system 100 may be connected to the wireless terminal via a wired and / or wireless network and transmit interactive information in accordance with an agreed data format.

Claims

1. A charging pile health status assessment method, It is characterized in that include: Obtain the input voltage, output voltage, input current, output current, output power, input active power of the charging pile at multiple predetermined time points within a predetermined time period, as well as the number of TCU failures, AC contactor failures, charging gun failures, emergency stop switch failures, card reader failures, fan failures, lightning arrester failures, and door switch failures within the predetermined time period; Characterize the input voltage, output voltage, input current, output current, output power, input active power of the charging pile at the plurality of predetermined time points, and the number of TCU failures, AC contactor failures, charging gun failures, emergency stop switch failures, card reader failures, fan failures, lightning arrester failures, and gate switch failures in the predetermined time period to obtain a charging pile health monitoring feature vector; Based on the charging pile health monitoring feature vector, a charging pile health status level is obtained.

2. The charging pile health status assessment method according to claim 1, It is characterized in that The input voltage, output voltage, input current, output current, output power, input active power of the charging pile at the plurality of predetermined time points and the number of TCU failures, the number of AC contactor failures, the number of charging gun failures, the number of emergency stop switch failures, the number of card reader failures, the number of fan failures, the number of lightning arrester failures, and the number of gate switch failures in the predetermined time period are feature-encoded to obtain a charging pile health monitoring feature vector, including: Extracting the time series characteristics of the input voltage, output voltage, input current, output current, output power, and input active power of the charging pile at the plurality of predetermined time points to obtain a time series characteristic vector of the monitoring parameters of the power module of the charging pile; Extract the time series features of the TCU failure times, AC contactor failure times, charging gun failure times, emergency stop switch failure times, card reader failure times, fan failure times, lightning arrester failure times, and gate switch failure times in the predetermined time period to obtain the characteristic vector of the failure conditions of the key components of the charging pile; The charging pile health monitoring feature vector is obtained by fusing the charging pile power module monitoring parameter time series feature vector and the charging pile key component failure feature vector.

3. The charging pile health status assessment method according to claim 2, It is characterized in that Extracting the time series characteristics of the input voltage, output voltage, input current, output current, output power, and input active power of the charging pile at the plurality of predetermined time points to obtain a time series characteristic vector of the monitoring parameters of the charging pile power module includes: Arrange the input voltage, output voltage, input current, output current, output power, and input active power of the charging pile at the plurality of predetermined time points according to the time dimension into a charging pile power module monitoring parameter timing input matrix; The charging pile power module monitoring parameter timing input matrix is ​​passed through a charging pile parameter timing encoder based on a multi-scale convolution kernel to obtain a charging pile power module monitoring parameter timing feature matrix; The charging pile power module monitoring parameter timing characteristic matrix is ​​expanded to obtain the charging pile power module monitoring parameter timing characteristic vector.

4. The charging pile health status assessment method according to claim 3, It is characterized in that The time series feature extraction is performed on the number of TCU failures, AC contactor failures, charging gun failures, emergency stop switch failures, card reader failures, fan failures, lightning arrester failures, and gate switch failures in the predetermined time period to obtain a characteristic vector of the failure condition of key components of the charging pile, including: arranging the number of TCU failures, AC contactor failures, charging gun failures, emergency stop switch failures, card reader failures, fan failures, lightning arrester failures, and gate switch failures in the predetermined time period into a charging pile key component failure condition input vector and then passing it through a sequence encoder to obtain the charging pile key component failure condition characteristic vector.

5. The charging pile health status assessment method according to claim 4, It is characterized in that The charging pile parameter timing encoder based on multi-scale convolution kernel is a first convolutional neural network model and a second convolutional neural network model using convolution kernels with different void ratios, wherein the first convolutional neural network model uses a convolution kernel of a first size and a first void ratio, and the second convolutional neural network model uses a convolutional neural network model of a first size and a second void ratio, and the first void ratio is different from the second void ratio.

6. The charging pile health status assessment method according to claim 5, It is characterized in that The sequence encoder is a convolutional neural network model using a one-dimensional convolution kernel.

7. The charging pile health status assessment method according to claim 6, It is characterized in that Based on the charging pile health monitoring feature vector, the health status level of the charging pile is obtained, including: Performing data dynamic normalization on the charging pile health monitoring feature vector based on a disturbance control variable to obtain an optimized charging pile health monitoring feature vector; The optimized charging pile health monitoring feature vector is passed through a charging pile health status classifier to obtain a classification result, and the classification result is used to represent the charging pile health status level.

8. The charging pile health status assessment method according to claim 7, It is characterized in that The charging pile health monitoring feature vector is subjected to data dynamic normalization based on a disturbance control variable to obtain an optimized charging pile health monitoring feature vector, including: Calculating the mean and variance of the charging pile health monitoring feature vector; Calculating a difference between a characteristic value at a predetermined position of the charging pile health monitoring characteristic vector and a mean value of the charging pile health monitoring characteristic vector to obtain a first intermediate calculated value; Multiplying the network parameter matrix by the charging pile health monitoring feature vector and then subtracting the network parameter matrix from the charging pile health monitoring feature vector by position to obtain a first intermediate vector, and calculating the Frobenius norm of the first intermediate vector to obtain a first norm value; Adding the first norm value to the variance of the charging pile health monitoring feature vector and then performing a square root operation to obtain a second intermediate calculation value; dividing the first intermediate calculated value by the second intermediate calculated value to obtain a third intermediate calculated value; Calculating the square of each position of the charging pile health monitoring feature vector and then accumulating and summing them to obtain a first total value; Calculate a natural exponential function value after taking the square root of the first sum value and dividing it by the scale of the network parameter matrix to obtain a fourth intermediate calculation value, wherein the scale of the network parameter matrix is ​​equal to the product of the width value of the network parameter matrix and the height value thereof; The fourth intermediate calculated value is multiplied by the weighted hyperparameter and then added to the third intermediate calculated value to obtain the characteristic value of the predetermined position of the optimized charging pile health monitoring characteristic vector.

9. A charging pile health status assessment system, It is characterized in that include: The charging pile health status assessment related data acquisition module is used to obtain the input voltage, output voltage, input current, output current, output power, input active power of the charging pile at multiple predetermined time points within a predetermined time period, as well as the number of TCU failures, AC contactor failures, charging gun failures, emergency stop switch failures, card reader failures, fan failures, lightning arrester failures, and door control switch failures in the predetermined time period; A charging pile health status assessment related data encoding module, used for encoding the input voltage, output voltage, input current, output current, output power, input active power of the charging pile at the plurality of predetermined time points, and the number of TCU failures, AC contactor failures, charging gun failures, emergency stop switch failures, card reader failures, fan failures, lightning arrester failures, and gate switch failures in the predetermined time period to obtain a charging pile health monitoring feature vector; The charging pile health status result generation module is used to obtain the charging pile health status level based on the charging pile health monitoring feature vector.

10. The charging pile health status assessment system according to claim 9, It is characterized in that The charging pile health status assessment related data encoding module includes: A charging pile power module monitoring parameter timing feature extraction unit, used to extract the timing features of the input voltage, output voltage, input current, output current, output power, and input active power of the charging pile at the plurality of predetermined time points to obtain a charging pile power module monitoring parameter timing feature vector; A charging pile key component failure condition feature extraction unit is used to extract the time series features of the TCU failure times, AC contactor failure times, charging gun failure times, emergency stop switch failure times, card reader failure times, fan failure times, lightning arrester failure times, and gate switch failure times in the predetermined time period to obtain a charging pile key component failure condition feature vector; A feature fusion unit is used to fuse the charging pile power module monitoring parameter time series feature vector and the charging pile key component failure feature vector to obtain the charging pile health monitoring feature vector.

Images