An electric vehicle charging infrastructure fault tracing method and device

Abstract

This invention relates to the field of electric vehicle charging facility data analysis technology, specifically providing a method and apparatus for tracing the source of faults in electric vehicle charging infrastructure. The method includes: constructing a time-series feature curve for charging orders, using the State of Charge (SOC) of the electric vehicle corresponding to each charging order as the horizontal axis and the core features corresponding to each charging order as the vertical axis; clustering the charging orders based on the time-series feature curve, and identifying abnormal clusters within each cluster; and locating electric vehicles, charging piles, charging stations, and combinations thereof in each charging order within the abnormal clusters that have a frequency exceeding a threshold as fault units. The technical solution provided by this invention enables accurate tracing of the causes of anomalies, providing core technical support for intelligent and refined operation and maintenance of charging facilities.

Description

Technical Field

[0001] This invention relates to the field of electric vehicle charging facility data analysis technology, specifically to a method and apparatus for tracing the source of faults in electric vehicle charging infrastructure. Background Technology

[0002] With the rapid development of the electric vehicle industry, the scale of charging infrastructure continues to expand, and its operational reliability and safety have become key factors affecting user experience and power grid stability. Currently, the operation and maintenance management of charging facilities generally faces the following technical bottlenecks: First, data heterogeneity and data silos are prominent issues. The charging process involves multiple data sources, including vehicle-side parameters such as BMS battery management system parameters, vehicle identification number, and battery capacity; charging pile-side parameters such as rated power, module configuration, and output parameters; and platform-side data such as order information and environmental data. These data come from diverse sources, have varying structures, and contain a mixture of time-series and non-time-series data, scattered across different management systems, forming severe data silos. Traditional threshold alarms or single-data-source analysis methods are insufficient to gain a holistic understanding of the true operating status of the charging system and cannot effectively uncover potential problems such as vehicle-charging pile mismatch and charging pile performance degradation.

[0003] Secondly, anomaly detection suffers from low accuracy and difficulty in tracing the source. Existing technologies largely rely on simple statistical thresholds or fixed rules for anomaly detection, such as setting upper and lower limits for current or power. This approach is extremely insensitive to complex fault modes commonly encountered during charging, which manifest as abnormal curve shapes or gradual performance degradation, leading to persistently high false alarm and false negative rates. More importantly, even when anomalies are detected, the lack of correlation analysis of multi-dimensional features makes it difficult for maintenance personnel to quickly and accurately pinpoint the root cause of the fault—whether it is the vehicle, the charging station, or the communication link—resulting in low troubleshooting efficiency and high maintenance costs.

[0004] Finally, there is a lack of ability to identify clustered problems with charging equipment. While occasional malfunctions of individual charging piles may be easy to handle, clustered performance anomalies among charging piles of the same model, batch, or region may indicate greater safety hazards or design flaws. Existing methods lack effective clustering and pattern mining techniques, failing to automatically identify "families" with similar abnormal patterns from massive amounts of charging events, thus missing opportunities for early warning and batch intervention.

[0005] Therefore, there is an urgent need in this field for an intelligent analysis method that can integrate multi-source data, accurately identify abnormal charging parameters, and effectively trace the root cause of problems, so as to improve the operation and maintenance efficiency and service quality of charging facilities. Summary of the Invention

[0006] To overcome the above-mentioned shortcomings, this invention proposes a method and device for tracing the source of faults in electric vehicle charging infrastructure.

[0007] Firstly, a method for tracing the source of faults in electric vehicle charging infrastructure is provided, the method comprising: Using the electric vehicle SOC corresponding to the charging order as the coordinate value of the horizontal axis and the core features corresponding to the charging order as the coordinate value of the vertical axis, a time-series feature curve of the charging order is constructed. Based on the time-series characteristic curves of charging orders, charging orders are clustered, and abnormal clusters are identified in each cluster. Electric vehicles, charging piles, charging stations, and combinations thereof that appear more frequently than a threshold in each charging order within the abnormal cluster are identified as fault units.

[0008] Preferably, before constructing the time-series feature curve of the charging order using the electric vehicle SOC corresponding to the charging order as the coordinate value of the horizontal axis and the core feature corresponding to the charging order as the coordinate value of the vertical axis, the following steps are included: Preprocess the multi-source data of electric vehicle charging facilities and calculate the index values ​​of preset indicators; Based on the similarity between the preprocessed multi-source data and preset indicators, key features are screened from the preprocessed multi-source data, and core features are selected from the key features.

[0009] Furthermore, the multi-source data includes: static asset files of charging piles, static vehicle information, and dynamic time-series data of the charging process.

[0010] Furthermore, the preprocessing includes: data cleaning, logical error data correction, and timing alignment.

[0011] Furthermore, linear interpolation is used to perform time-series alignment of the multi-source data. The interpolation calculation formula corresponding to the linear interpolation method is as follows:

[0012] In the above formula, These are the interpolated parameter values. For the timestamp of the target interpolation point, For the previous timestamp of the target interpolation point corresponding to the multi-source data, For the next timestamp of the target interpolation point corresponding to the multi-source data, The parameter value is the previous timestamp of the target interpolation point corresponding to the multi-source data. The parameter value is the next timestamp of the target interpolation point corresponding to the multi-source data.

[0013] Furthermore, the preset indicator is charging efficiency, and its calculation formula is as follows:

[0014] In the above formula, For charging efficiency, The sampling period is Let be the output power at time t. The sampling time interval, Let t be the power required at time t.

[0015] Preferably, the K-Shape clustering algorithm is used in the process of clustering charging orders.

[0016] Preferably, identifying anomalous clusters within each cluster includes: Obtain the average charging capacity of the charging piles corresponding to the charging orders in the cluster; If the average charging capacity is less than the first preset value, the cluster is an abnormal cluster; otherwise, the cluster is a normal cluster.

[0017] Furthermore, the average charging capacity of the charging piles corresponding to the charging orders in the clusters are as follows:

[0018] In the above formula, The cluster contains the average charging capacity of the charging piles corresponding to the charging orders. The total number of sampling times. Let t be the average charging voltage of the charging piles corresponding to the charging orders in the cluster. Let t be the average charging current of the charging piles corresponding to the charging orders in the cluster. This refers to the rated power of the charging station.

[0019] Furthermore, identifying anomalous clusters within each cluster includes: Obtain box plots of key features corresponding to charging orders within clusters; If the similarity between the box plot and the preset normal box plot exceeds a second preset value, then the cluster is a normal cluster; otherwise, the cluster is an abnormal cluster.

[0020] Secondly, a fault tracing device for electric vehicle charging infrastructure is provided, the electric vehicle charging infrastructure fault tracing device comprising: The module is used to construct the time-series feature curve of a charging order, with the electric vehicle SOC corresponding to the charging order as the coordinate value of the horizontal axis and the core feature corresponding to the charging order as the coordinate value of the vertical axis. The clustering module is used to cluster charging orders based on their time-series characteristic curves and to identify outlier clusters within each cluster. The traceability module is used to locate electric vehicles, charging piles, charging stations and their combinations that appear more frequently than a threshold in each charging order within the abnormal cluster as fault units.

[0021] Preferably, before constructing the time-series feature curve of the charging order using the electric vehicle SOC corresponding to the charging order as the coordinate value of the horizontal axis and the core feature corresponding to the charging order as the coordinate value of the vertical axis, the following steps are included: Preprocess the multi-source data of electric vehicle charging facilities and calculate the index values ​​of preset indicators; Based on the similarity between the preprocessed multi-source data and preset indicators, key features are screened from the preprocessed multi-source data, and core features are selected from the key features.

[0022] Furthermore, the multi-source data includes: static asset files of charging piles, static vehicle information, and dynamic time-series data of the charging process.

[0023] Furthermore, the preprocessing includes: data cleaning, logical error data correction, and timing alignment.

[0024] Furthermore, linear interpolation is used to perform time-series alignment of the multi-source data. The interpolation calculation formula corresponding to the linear interpolation method is as follows:

[0025] In the above formula, These are the interpolated parameter values. For the timestamp of the target interpolation point, For the previous timestamp of the target interpolation point corresponding to the multi-source data, For the next timestamp of the target interpolation point corresponding to the multi-source data, The parameter value is the previous timestamp of the target interpolation point corresponding to the multi-source data. The parameter value is the next timestamp of the target interpolation point corresponding to the multi-source data.

[0026] Furthermore, the preset indicator is charging efficiency, and its calculation formula is as follows:

[0027] In the above formula, For charging efficiency, The sampling period is Let be the output power at time t. The sampling time interval, Let t be the power required at time t.

[0028] Preferably, the K-Shape clustering algorithm is used in the process of clustering charging orders.

[0029] Preferably, identifying anomalous clusters within each cluster includes: Obtain the average charging capacity of the charging piles corresponding to the charging orders in the cluster; If the average charging capacity is less than the first preset value, the cluster is an abnormal cluster; otherwise, the cluster is a normal cluster.

[0030] Furthermore, the average charging capacity of the charging piles corresponding to the charging orders in the clusters are as follows:

[0031] In the above formula, The cluster contains the average charging capacity of the charging piles corresponding to the charging orders. The total number of sampling times. Let t be the average charging voltage of the charging piles corresponding to the charging orders in the cluster. Let t be the average charging current of the charging piles corresponding to the charging orders in the cluster. This refers to the rated power of the charging station.

[0032] Furthermore, identifying anomalous clusters within each cluster includes: Obtain box plots of key features corresponding to charging orders within clusters; If the similarity between the box plot and the preset normal box plot exceeds a second preset value, then the cluster is a normal cluster; otherwise, the cluster is an abnormal cluster.

[0033] Thirdly, a computer device is provided, comprising: one or more processors; The processor is used to execute one or more programs; When the one or more programs are executed by the one or more processors, the electric vehicle charging infrastructure fault tracing method is implemented.

[0034] Fourthly, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed, implements the method for tracing faults in electric vehicle charging infrastructure.

[0035] The above-described technical solutions of the present invention have at least one or more of the following beneficial effects: This invention provides a method and apparatus for tracing faults in electric vehicle charging infrastructure, comprising: constructing a time-series feature curve of a charging order, using the State of Charge (SOC) of the electric vehicle corresponding to the charging order as the coordinate value of the horizontal axis and the core features corresponding to the charging order as the coordinate value of the vertical axis; clustering the charging orders based on the time-series feature curve, and identifying abnormal clusters in each cluster; and locating electric vehicles, charging piles, charging stations, and combinations thereof in each charging order of the abnormal clusters that have a frequency exceeding a threshold as fault units. The technical solution provided by this invention can effectively identify complex faults that exhibit abnormal curve shapes and cannot be detected by traditional threshold methods, greatly improving the sensitivity and accuracy of anomaly detection. It can automatically discover groups of charging piles or vehicles with the same abnormal pattern, providing data support for batch troubleshooting of equipment, supplier quality assessment, and preventive maintenance. Attached Figure Description

[0036] Figure 1 This is a schematic diagram of the main steps of the electric vehicle charging infrastructure fault tracing method according to an embodiment of the present invention. Detailed Implementation

[0037] The specific embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0038] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0039] Example 1 See appendix Figure 1 , Figure 1 This is a schematic flowchart illustrating the main steps of a fault tracing method for electric vehicle charging infrastructure according to an embodiment of the present invention. Figure 1 As shown, the electric vehicle charging infrastructure fault tracing method in this embodiment of the invention mainly includes the following steps: Step S101: Construct a time-series feature curve for charging orders by using the electric vehicle SOC corresponding to the charging order as the coordinate value of the horizontal axis and the core features corresponding to the charging order as the coordinate value of the vertical axis. Step S102: Based on the time-series characteristic curve of charging orders, cluster the charging orders and identify abnormal clusters in each cluster; Step S103: Identify electric vehicles, charging piles, charging stations, and combinations thereof that occur more frequently than a threshold in each charging order within the abnormal cluster as fault units.

[0040] In this embodiment, before constructing the time-series feature curve of the charging order using the electric vehicle SOC corresponding to the charging order as the coordinate value of the horizontal axis and the core feature corresponding to the charging order as the coordinate value of the vertical axis, the following steps are included: Preprocess the multi-source data of electric vehicle charging facilities and calculate the index values ​​of preset indicators; Based on the similarity between the preprocessed multi-source data and preset indicators, key features (such as output current, output power, vehicle model, SOC change curve, etc.) are screened from the preprocessed multi-source data, and core features are selected from the key features.

[0041] In one implementation, the multi-source data includes: static asset files of charging piles (such as equipment number, location, rated power, equipment model), static vehicle information (such as VIN code, battery type, battery capacity), and dynamic time-series data of the charging process (such as timestamp, charging pile output voltage / current / power, vehicle required voltage / current / power, battery SOC, charging gun temperature, and charging shutdown reason code).

[0042] In one implementation, the preprocessing includes: data cleaning, logical error correction, and time series alignment. For example, the acquired raw data is cleaned and integrated, including: removing order records with missing key information (such as VIN code, charging pile number); correcting logical error data (such as charging end time being earlier than start time); and using linear interpolation and other methods to normalize time series data sampled at non-equal intervals to ensure data quality and the accuracy of subsequent analysis, ultimately forming a complete and clean charging order time series data table.

[0043] In one implementation, linear interpolation is used to perform time-series alignment of multi-source data. The interpolation calculation formula corresponding to the linear interpolation method is as follows:

[0044] In the above formula, These are the interpolated parameter values. For the timestamp of the target interpolation point, For the previous timestamp of the target interpolation point corresponding to the multi-source data, For the next timestamp of the target interpolation point corresponding to the multi-source data, The parameter value is the previous timestamp of the target interpolation point corresponding to the multi-source data. The parameter value is the next timestamp of the target interpolation point corresponding to the multi-source data.

[0045] In one implementation, the preset indicator is charging efficiency, and its calculation formula is as follows:

[0046] In the above formula, For charging efficiency, The sampling period is Let be the output power at time t. The sampling time interval, Let t be the power required at time t.

[0047] In this embodiment, the K-Shape clustering algorithm is used to cluster charging orders, and the optimal number of clusters is determined by the elbow rule. The K-Shape clustering algorithm uses a distance metric based on cross-relationships.

[0048] In this embodiment, identifying anomalous clusters within each cluster includes: Obtain the average charging capacity of the charging piles corresponding to the charging orders in the cluster; If the average charging capacity is less than the first preset value, the cluster is an abnormal cluster; otherwise, the cluster is a normal cluster.

[0049] In one implementation, the clusters comprise the average charging capacity of the charging stations corresponding to the charging orders as follows:

[0050] In the above formula, The cluster contains the average charging capacity of the charging piles corresponding to the charging orders. The total number of sampling times. Let t be the average charging voltage of the charging piles corresponding to the charging orders in the cluster. Let t be the average charging current of the charging piles corresponding to the charging orders in the cluster. This refers to the rated power of the charging station.

[0051] In one implementation, identifying anomalous clusters within each cluster includes: Obtain box plots of key features corresponding to charging orders within clusters; If the similarity between the box plot and the preset normal box plot exceeds a second preset value, then the cluster is a normal cluster; otherwise, the cluster is an abnormal cluster.

[0052] In one specific implementation, in-depth analysis is performed on the identified anomaly clusters. By statistically analyzing the frequency of occurrence of different vehicle models, charging piles, and charging stations within the anomaly clusters, high-risk "vehicle-charging pile-station" combinations causing the anomalies are identified. For example, if a specific vehicle model exhibits similar insufficient power output anomalies on multiple charging piles at a specific charging station, the problem can be traced back to a compatibility issue between that vehicle model and the charging piles at that station. If the same charging pile exhibits anomalies for different vehicle models, the problem is likely due to a hardware failure or incorrect parameter configuration of the charging pile itself. This achieves a leap from "anomaly detection" to "root cause identification."

[0053] Example 2 Based on the same inventive concept, the present invention also provides a fault tracing device for electric vehicle charging infrastructure, the fault tracing device for electric vehicle charging infrastructure comprising: The module is used to construct the time-series feature curve of a charging order, with the electric vehicle SOC corresponding to the charging order as the coordinate value of the horizontal axis and the core feature corresponding to the charging order as the coordinate value of the vertical axis. The clustering module is used to cluster charging orders based on their time-series characteristic curves and to identify outlier clusters within each cluster. The traceability module is used to locate electric vehicles, charging piles, charging stations and their combinations that appear more frequently than a threshold in each charging order within the abnormal cluster as fault units.

[0054] Preferably, before constructing the time-series feature curve of the charging order using the electric vehicle SOC corresponding to the charging order as the coordinate value of the horizontal axis and the core feature corresponding to the charging order as the coordinate value of the vertical axis, the following steps are included: Preprocess the multi-source data of electric vehicle charging facilities and calculate the index values ​​of preset indicators; Based on the similarity between the preprocessed multi-source data and preset indicators, key features are screened from the preprocessed multi-source data, and core features are selected from the key features.

[0055] Furthermore, the multi-source data includes: static asset files of charging piles, static vehicle information, and dynamic time-series data of the charging process.

[0056] Furthermore, the preprocessing includes: data cleaning, logical error data correction, and timing alignment.

[0057] Furthermore, linear interpolation is used to perform time-series alignment of the multi-source data. The interpolation calculation formula corresponding to the linear interpolation method is as follows:

[0058] In the above formula, These are the interpolated parameter values. For the timestamp of the target interpolation point, For the previous timestamp of the target interpolation point corresponding to the multi-source data, For the next timestamp of the target interpolation point corresponding to the multi-source data, The parameter value is the previous timestamp of the target interpolation point corresponding to the multi-source data. The parameter value is the next timestamp of the target interpolation point corresponding to the multi-source data.

[0059] Furthermore, the preset indicator is charging efficiency, and its calculation formula is as follows:

[0060] In the above formula, For charging efficiency, The sampling period is Let be the output power at time t. The sampling time interval, Let t be the power required at time t.

[0061] Preferably, the K-Shape clustering algorithm is used in the process of clustering charging orders.

[0062] Preferably, identifying anomalous clusters within each cluster includes: Obtain the average charging capacity of the charging piles corresponding to the charging orders in the cluster; If the average charging capacity is less than the first preset value, the cluster is an abnormal cluster; otherwise, the cluster is a normal cluster.

[0063] Furthermore, the average charging capacity of the charging piles corresponding to the charging orders in the clusters are as follows:

[0064] In the above formula, The cluster contains the average charging capacity of the charging piles corresponding to the charging orders. The total number of sampling times. Let t be the average charging voltage of the charging piles corresponding to the charging orders in the cluster. Let t be the average charging current of the charging piles corresponding to the charging orders in the cluster. This refers to the rated power of the charging station.

[0065] Furthermore, identifying anomalous clusters within each cluster includes: Obtain box plots of key features corresponding to charging orders within clusters; If the similarity between the box plot and the preset normal box plot exceeds a second preset value, then the cluster is a normal cluster; otherwise, the cluster is an abnormal cluster.

[0066] Example 3 Based on the same inventive concept, this invention also provides a computer device, which includes a processor and a memory. The memory stores a computer program, which includes program instructions. The processor executes the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions in the computer storage medium to implement corresponding method flows or corresponding functions, thereby implementing the steps of the electric vehicle charging infrastructure fault tracing method in the above embodiments.

[0067] Example 4 Based on the same inventive concept, this invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and extended storage media supported by the computer device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, this storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the steps of the electric vehicle charging infrastructure fault tracing method in the above embodiments.

[0068] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0069] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0070] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0071] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0072] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for fault localization in electric vehicle charging infrastructure, characterized in that, The method includes: Using the electric vehicle SOC corresponding to the charging order as the coordinate value of the horizontal axis and the core features corresponding to the charging order as the coordinate value of the vertical axis, a time-series feature curve of the charging order is constructed. Based on the time-series characteristic curves of charging orders, charging orders are clustered, and abnormal clusters are identified in each cluster. Electric vehicles, charging piles, charging stations, and combinations thereof that appear more frequently than a threshold in each charging order within the abnormal cluster are identified as fault units.

2. The method of claim 1, wherein, Before constructing the time-series feature curve of a charging order using the electric vehicle's SOC corresponding to the charging order as the horizontal axis and the core features corresponding to the charging order as the vertical axis, the following steps are included: Preprocess the multi-source data of electric vehicle charging facilities and calculate the index values ​​of preset indicators; Based on the similarity between the preprocessed multi-source data and preset indicators, key features are screened from the preprocessed multi-source data, and core features are selected from the key features.

3. The method of claim 2, wherein, The multi-source data includes: static asset files of charging piles, static vehicle information, and dynamic time-series data of the charging process.

4. The method as described in claim 2, characterized in that, The preprocessing includes: data cleaning, logical error correction, and timing alignment.

5. The method as described in claim 4, characterized in that, A linear interpolation method is used to perform time-series alignment of multi-source data. The interpolation calculation formula corresponding to the linear interpolation method is as follows: In the above formula, These are the interpolated parameter values. For the timestamp of the target interpolation point, For the previous timestamp of the target interpolation point corresponding to the multi-source data, For the next timestamp of the target interpolation point corresponding to the multi-source data, The parameter value is the previous timestamp of the target interpolation point corresponding to the multi-source data. The parameter value is the next timestamp of the target interpolation point corresponding to the multi-source data.

6. The method as described in claim 2, characterized in that, The preset indicator is charging efficiency, and its calculation formula is as follows: In the above formula, For charging efficiency, The sampling period is Let be the output power at time t. The sampling time interval, Let t be the power required at time t.

7. The method as described in claim 1, characterized in that, The K-Shape clustering algorithm is used in the process of clustering charging orders.

8. The method as described in claim 1, characterized in that, The process of identifying anomalous clusters within each cluster includes: Obtain the average charging capacity of the charging piles corresponding to the charging orders in the cluster; If the average charging capacity is less than the first preset value, the cluster is an abnormal cluster; otherwise, the cluster is a normal cluster.

9. The method as described in claim 8, characterized in that, The clusters contain the average charging capacity of the charging piles corresponding to the charging orders, as follows: In the above formula, The cluster contains the average charging capacity of the charging piles corresponding to the charging orders. The total number of sampling times. Let t be the average charging voltage of the charging piles corresponding to the charging orders in the cluster. Let t be the average charging current of the charging piles corresponding to the charging orders in the cluster. This refers to the rated power of the charging station.

10. The method as described in claim 2, characterized in that, The process of identifying anomalous clusters within each cluster includes: Obtain box plots of key features corresponding to charging orders within clusters; If the similarity between the box plot and the preset normal box plot exceeds a second preset value, then the cluster is a normal cluster; otherwise, the cluster is an abnormal cluster.

11. A fault tracing device for electric vehicle charging infrastructure, characterized in that, The device includes: The module is used to construct the time-series feature curve of a charging order, with the electric vehicle SOC corresponding to the charging order as the coordinate value of the horizontal axis and the core feature corresponding to the charging order as the coordinate value of the vertical axis. The clustering module is used to cluster charging orders based on their time-series characteristic curves and to identify outlier clusters within each cluster. The traceability module is used to locate electric vehicles, charging piles, charging stations and their combinations that appear more frequently than a threshold in each charging order within the abnormal cluster as fault units.

12. The apparatus as claimed in claim 11, characterized in that, Before constructing the time-series feature curve of a charging order using the electric vehicle's SOC corresponding to the charging order as the horizontal axis and the core features corresponding to the charging order as the vertical axis, the following steps are included: Preprocess the multi-source data of electric vehicle charging facilities and calculate the index values ​​of preset indicators; Based on the similarity between the preprocessed multi-source data and preset indicators, key features are screened from the preprocessed multi-source data, and core features are selected from the key features.

13. The apparatus as claimed in claim 12, characterized in that, The multi-source data includes: static asset files of charging piles, static vehicle information, and dynamic time-series data of the charging process.

14. The apparatus as claimed in claim 12, characterized in that, The preprocessing includes: data cleaning, logical error correction, and timing alignment.

15. The apparatus as claimed in claim 14, characterized in that, A linear interpolation method is used to perform time-series alignment of multi-source data. The interpolation calculation formula corresponding to the linear interpolation method is as follows: In the above formula, These are the interpolated parameter values. For the timestamp of the target interpolation point, For the previous timestamp of the target interpolation point corresponding to the multi-source data, For the next timestamp of the target interpolation point corresponding to the multi-source data, The parameter value is the previous timestamp of the target interpolation point corresponding to the multi-source data. The parameter value is the next timestamp of the target interpolation point corresponding to the multi-source data.

16. The apparatus as claimed in claim 12, characterized in that, The preset indicator is charging efficiency, and its calculation formula is as follows: In the above formula, For charging efficiency, The sampling period is Let be the output power at time t. The sampling time interval, Let t be the power required at time t.

17. The apparatus as claimed in claim 11, characterized in that, The K-Shape clustering algorithm is used in the process of clustering charging orders.

18. The apparatus as claimed in claim 11, characterized in that, The process of identifying anomalous clusters within each cluster includes: Obtain the average charging capacity of the charging piles corresponding to the charging orders in the cluster; If the average charging capacity is less than the first preset value, the cluster is an abnormal cluster; otherwise, the cluster is a normal cluster.

19. The apparatus as claimed in claim 18, characterized in that, The clusters contain the average charging capacity of the charging piles corresponding to the charging orders, as follows: In the above formula, The cluster contains the average charging capacity of the charging piles corresponding to the charging orders. The total number of sampling times. Let t be the average charging voltage of the charging piles corresponding to the charging orders in the cluster. Let t be the average charging current of the charging piles corresponding to the charging orders in the cluster. This refers to the rated power of the charging station.

20. The apparatus as claimed in claim 12, characterized in that, The process of identifying anomalous clusters within each cluster includes: Obtain box plots of key features corresponding to charging orders within clusters; If the similarity between the box plot and the preset normal box plot exceeds a second preset value, then the cluster is a normal cluster; otherwise, the cluster is an abnormal cluster.

21. A computer device, characterized in that, include: One or more processors; The processor is used to execute one or more programs; When the one or more programs are executed by the one or more processors, the fault tracing method for electric vehicle charging infrastructure as described in any one of claims 1 to 10 is implemented.

22. A computer-readable storage medium, characterized in that, It contains a computer program, which, when executed, implements the electric vehicle charging infrastructure fault tracing method as described in any one of claims 1 to 10.

Images