Electric vehicle charging pile intelligent test method, equipment and medium

Abstract

The invention discloses an intelligent test method and device for an electric vehicle charging pile and a medium, and relates to the field of the Internet of Things, and the method comprises the steps: connecting a to-be-tested charging pile through a test interface, recognizing the interface type and communication protocol of the to-be-tested charging pile, and calling a corresponding test engine; generating a corresponding test instruction set based on the pre-configured test parameters corresponding to different test scenes through a test engine; executing the test instruction set, collecting multi-source test data of the to-be-tested charging pile, and extracting multi-source features for fusion; according to the fused multi-source features, a fault diagnosis result is output through a real-time diagnosis model, and a maintenance suggestion is generated based on the fault diagnosis result; and generating a test report based on the fault diagnosis result and the maintenance suggestion, and uploading the test report to the cloud platform for storage. Through an automatic interface type and communication protocol identification mechanism, the method does not need to depend on multiple sets of independent equipment, and solves the problem of poor portability caused by heavy equipment in the traditional test from the flow.

Description

Technical Field

[0001] This application relates to the field of Internet of Things (IoT) technology, specifically to an intelligent testing method, equipment, and medium for electric vehicle charging piles. Background Technology

[0002] With the rapid development and widespread adoption of new energy vehicles, the construction scale and coverage density of charging piles, as a core supporting infrastructure, are also growing simultaneously. Currently, the market is flooded with charging pile brands, and the lack of unified technical standards results in inconsistent charging efficiency, stability, and safety. Issues such as sudden power outages, excessive current fluctuations, and exceeding metering standards occur frequently during charging, not only affecting the user's travel experience but also posing safety hazards such as electric shock and fire. Given that charging piles are a critical infrastructure for electric vehicles, conducting testing and fault diagnosis is particularly important.

[0003] Currently, the charging pile testing equipment on the market mainly includes two types: laboratory-level large-scale testing systems and portable fault diagnostic instruments. Although laboratory-level large-scale testing systems can perform detailed performance and protocol tests, they are complex in structure and large in size, making them inconvenient to carry and deploy on-site, thus limiting the flexibility and efficiency of testing. Portable fault diagnostic instruments are smaller in size and easy to carry, but their functions are relatively limited, mainly used for simple voltage and current measurements or partial protocol consistency tests, and cannot perform comprehensive testing of charging piles.

[0004] Furthermore, when the charging station is idle, the testing methods used by these two testing devices are difficult to simulate the complex operating conditions that the charging station may encounter in actual operation, such as network fluctuations, dynamic changes in the battery, and various fault injections, which leads to deviations between the test results and the actual operating conditions. Summary of the Invention

[0005] To address the aforementioned problems, this application proposes an intelligent testing method for electric vehicle charging stations, comprising: Connect to the charging pile under test through the test interface, identify the interface type and communication protocol of the charging pile under test, and call the corresponding test engine; The test engine generates corresponding test instruction sets based on pre-configured test parameters for different test scenarios; the test scenarios include load testing, vehicle simulation testing, and communication protocol transmission testing. The test instruction set is executed to collect multi-source test data of the charging pile under test, extract multi-source features corresponding to the multi-source test data respectively, and fuse the multi-source features; Based on the fused multi-source features, the fault diagnosis results of the charging pile under test are output through a real-time diagnostic model, and maintenance suggestions are generated based on the fault diagnosis results; the fault diagnosis results include the fault type and the corresponding fault root cause probability distribution. A test report is generated based on the fault diagnosis results and the maintenance suggestions, and then uploaded to the cloud platform for storage.

[0006] On the other hand, this application also proposes an intelligent testing device for electric vehicle charging piles, comprising: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform, for example, an intelligent testing method for electric vehicle charging piles as described in the above example.

[0007] On the other hand, this application also proposes a non-volatile computer storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured as: the intelligent testing method for electric vehicle charging piles described in the above example.

[0008] The intelligent testing method for electric vehicle charging piles proposed in this application can bring the following beneficial effects: By employing an automated interface type and communication protocol identification mechanism, combined with scenario-based test instruction set generation, the flexibility and efficiency of on-site testing are significantly improved. Through load testing, vehicle simulation testing, and communication protocol transmission testing, the limitations of traditional methods with their single function are overcome. This enables a comprehensive evaluation of charging pile electrical performance, protocol compatibility, and response to complex scenarios from multiple dimensions, effectively avoiding the omission of actual operational issues due to one-sided testing. At the same time, it eliminates the need for multiple independent devices, solving the portability problem caused by bulky equipment in traditional testing from a process perspective.

[0009] Furthermore, by collecting and fusing multi-source test data and performing real-time model diagnostics, the efficiency and accuracy of fault diagnosis have been significantly improved. Through the fusion of multi-source features, the working state of charging piles under complex scenarios such as network fluctuations and dynamic battery changes is realistically reproduced, solving the problem of unrealistic simulations in traditional test scenarios. Automated fault diagnosis and root cause probability analysis based on fused features replace traditional troubleshooting methods that rely on manual experience, significantly shortening fault location time. The process of uploading generated test reports to the cloud platform enables centralized management and efficient traceability of test data, providing precise data support for the R&D, production, and operation and maintenance of charging piles, and significantly reducing overall operating costs. Attached Figure Description

[0010] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 This is a flowchart illustrating an intelligent testing method for electric vehicle charging piles in an embodiment of this application. Figure 2 This is a schematic diagram of the system architecture of the electric vehicle charging pile testing system in the embodiments of this application; Figure 3 This is a schematic diagram of an intelligent testing device for electric vehicle charging piles in an embodiment of this application. Detailed Implementation

[0011] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0012] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0013] like Figure 1 As shown in the figure, this application provides an intelligent testing method for electric vehicle charging piles, including: S101: Connect to the charging pile under test through the test interface, identify the interface type and communication protocol of the charging pile under test, and call the corresponding test engine.

[0014] Specifically, a connection is established with the charging pile under test through the test interface. The physical structure and electrical parameters of the interface are automatically detected to identify the interface type. At the same time, a series of probe frames are sent to the charging pile, and the format, interaction rules, and verification methods of the returned data are analyzed to determine its communication protocol. Based on the identification results, a test engine compatible with the interface type and communication protocol is called from the built-in test engine library to provide a runtime environment for subsequent tests.

[0015] It should be noted that this application is implemented using an electric vehicle charging pile testing system, such as... Figure 2 The diagram shows the system architecture of an electric vehicle charging station testing system, including portable hardware, a software platform, and a mobile user interface. The portable hardware includes a multi-functional interface module, a built-in dynamic load simulation module, a programmable BMS / vehicle simulation module, a communication protocol simulation module, a power quality analysis module, and an environmental sensor suite.

[0016] The multi-functional interface module is compatible with multiple charging interface standards and has the ability to automatically identify the charging pile interface type and communication protocol, ensuring the safety and convenience of physical connection and data transmission. The built-in dynamic load simulation module uses programmable power electronics to simulate the real electrical characteristics of electric vehicle batteries during charging, including internal resistance, capacity, open-circuit voltage, and dynamic response at different charging stages. It supports power ranges from several kilowatts to several hundred kilowatts and rapid power changes to comprehensively evaluate the output performance and stability of the charging pile. The programmable BMS / vehicle simulation module uses a highly intelligent simulator capable of simulating various battery types, states of charge (SoC), temperatures, and various fault conditions such as overvoltage, undervoltage, overcurrent, communication errors, insulation faults, and contactor faults. It can also dynamically adjust parameters during testing to verify charging performance. The charging pile features a fault response mechanism and safety protection functions; a communication protocol simulation module that supports all mainstream charging communication protocols, such as CAN, PLC, and Ethernet, can simulate communication between the charging pile and the electric vehicle, as well as between the charging pile and the backend system, and can inject communication errors, such as packet loss, delay, out-of-order delivery, and message tampering, to test the stability and fault tolerance of the charging pile under harsh communication environments; a high-precision power quality analysis module that integrates high-precision voltage and current sensors and a power analyzer, can measure the output power quality parameters of the charging pile in real time and accurately, including voltage, current, active power, reactive power, power factor, harmonic analysis, and transient events; and an environmental sensor kit with built-in temperature and humidity sensors, which can be expanded to include light intensity, dust concentration, and vibration sensors, to evaluate the performance and reliability of the charging pile under different environmental conditions.

[0017] The software platform consists of two parts: device-side software and cloud-side software. The device-side software runs inside the portable hardware and is responsible for hardware control, data acquisition and preprocessing, test logic execution, local data storage, and local UI interaction. The cloud-side software is deployed on a cloud server and provides data aggregation and long-term storage, big data analysis, an AI-driven fault diagnosis engine, automated report generation services, remote equipment management, fleet-level analysis and management, and API interfaces.

[0018] In this embodiment, a connection is established with the charging pile under test through a multi-functional interface module of portable hardware. The physical form and electrical characteristics of the charging pile interface are automatically detected, and the interface type is identified. At the same time, the multi-functional interface module sends a probe signal, analyzes the format and rules of the interaction message, and automatically identifies the communication protocol used by the charging pile.

[0019] S102: Using the test engine, generate corresponding test instruction sets based on pre-configured test parameters corresponding to different test scenarios; the test scenarios include load testing, vehicle simulation testing, and communication protocol transmission testing.

[0020] Specifically, the test engine invokes corresponding functional modules based on different test scenarios and generates test instruction sets based on pre-configured parameters. Test scenarios include load testing, vehicle simulation testing, and communication protocol transmission testing, among others.

[0021] It should be noted that, for load testing, the test engine, in conjunction with the built-in dynamic load simulation module, generates instructions simulating changes in internal resistance, capacity, and voltage during battery charging based on preset parameters such as power range and dynamic response rhythm, to test the output stability of the charging pile. For vehicle simulation testing, the test engine calls the programmable BMS / vehicle simulation module to generate instructions simulating vehicle charging needs, status feedback, and fault signals based on pre-configured parameters such as battery type, charging status (SoC), temperature, and fault conditions (e.g., overvoltage, overcurrent), to verify the charging pile's safety response mechanism. For communication protocol transmission testing, the test engine, in collaboration with the communication protocol simulation module, generates instructions containing communication error injection according to preset network fluctuation parameters, to test the charging pile's fault tolerance capability in complex communication environments.

[0022] In this embodiment of the application, the specific process of generating corresponding test sequence data for different test scenarios through the test engine is as follows: based on the scenario tags corresponding to different test scenarios, the test parameter sets corresponding to different test scenarios are matched in the pre-configured database, the test parameter sets are input into the scenario test engine corresponding to different test scenarios, test instructions are generated, and the test instructions are sorted according to the preset time axis to obtain the test instruction set.

[0023] The test parameter set includes load characteristic parameters, vehicle behavior parameters, and communication anomaly parameters. The load characteristic parameters are input to the load control engine, which converts them into a load control signal sequence to generate load control commands. The vehicle behavior parameters are input to the vehicle simulation engine, which encodes them to obtain a vehicle battery control signal sequence and generates vehicle simulation commands. The communication anomaly parameters are input to the protocol simulation engine, which constructs anomaly communication test vectors and generates communication transmission commands.

[0024] Specifically, each test scenario is assigned a unique scenario label based on its core features. A pre-configured database stores test parameter sets categorized by scenario labels. Each label is mapped to a set of structured parameters. By accurately matching the scenario labels with the labels in the parameter set in the database, the complete set of test parameters required for the corresponding scenario can be quickly retrieved, ensuring the compatibility between parameters and scenarios.

[0025] Furthermore, after obtaining the matching test parameter set, the test parameter set is input into the dedicated test engine for the corresponding scenario. Each scenario test engine generates discrete test instructions based on the specific values ​​in the test parameter set, calls the preset time axis template, sets the execution order of instructions according to the timing logic of the real charging scenario, and arranges the start and end times of each instruction according to the time nodes, forming a test instruction set arranged in an orderly manner according to the time sequence, ensuring that the test process conforms to the timing characteristics of the actual use scenario.

[0026] Specifically, load characteristic parameters, including indicators related to the charging load such as current change gradient, voltage stability range, and power fluctuation threshold, are input into the load control engine. The load control engine has a built-in power electronic conversion model that transforms the abstract load characteristic parameters into an electrical signal sequence that can be recognized by the charging pile, generating specific load control commands to adjust the load intensity and change rate of the charging pile output.

[0027] Vehicle behavior parameters, including simulated vehicle battery capacity, state of charge (SoC) change curves, charging request signal formats, and fault alarm triggering conditions, are input into the vehicle simulation engine. The vehicle simulation engine, equipped with a vehicle charging interaction protocol parsing module, performs protocol encoding processing on the vehicle behavior parameters to form a sequence of vehicle battery control signals. This generates vehicle simulation commands, simulating real-world interactions between the vehicle and the charging station, such as charging requests, status feedback, and fault alarms.

[0028] For communication anomaly parameters, including network anomaly characteristics such as communication latency, packet loss rate, data verification error ratio, and out-of-order transmission probability, these parameters are input into the protocol simulation engine. The engine constructs an anomaly communication model, transforming these parameters into quantifiable anomaly test vectors, forming communication test vectors containing anomaly injection. Finally, it generates communication transmission commands to simulate anomaly scenarios that may occur in real-world applications, such as communication latency, packet loss, and data errors, thus testing the communication fault tolerance capability of the charging pile.

[0029] In this embodiment, users can also configure test parameters through the user interface, selecting automated standard testing, manual testing, or scenario-based testing modes. Specifically, after receiving the test requirement text input by the user through the mobile terminal interface, the text is parsed by the natural language processing module to extract scenario keywords and pattern keywords related to the custom scenario. The extracted pattern keywords are matched with a predefined fault template library, the semantic similarity between the pattern keywords and template feature identifiers is calculated, the most matching basic fault template is determined, and then the template parameters are adjusted according to the specific description in the user requirement text to generate a custom fault mode that meets the user's requirements.

[0030] Based on extracted scenario keywords and generated custom fault modes, predefined test parameter templates are invoked to generate parameters. These predefined templates are categorized by scenario type and fault mode, and include parameter frameworks and dynamic calculation rules. For example, the scenario keyword "low temperature environment" triggers the environmental parameter template, automatically filling in basic parameters such as temperature range and insulation duration. Custom fault modes activate corresponding fault parameter branches; for instance, the "intermittent communication interruption" mode adds dynamic parameters such as interruption interval and duration to the communication parameter template. By merging the environmental or operational parameters corresponding to the scenario keywords with the fault parameters corresponding to the custom fault modes, a custom test parameter set is generated, covering scenario conditions, fault characteristics, and test rhythm to meet users' personalized testing needs.

[0031] It should be noted that scenario keywords are used to reflect the environment, conditions, or target scenario characteristics of the test, such as "low temperature environment and continuous fast charging" in "continuous fast charging in low temperature environment"; mode keywords are fault characteristics or test modes that users are concerned about, such as "charging interruption and restart" in "restart after charging interruption". Through part-of-speech tagging and entity recognition technology, the system can accurately distinguish and extract these two types of keywords, providing a foundation for subsequent processing.

[0032] S103: Execute the test instruction set, collect multi-source test data of the charging pile under test, extract the multi-source features corresponding to the multi-source test data respectively, and fuse the multi-source features.

[0033] Specifically, when executing the generated test instruction set, a multi-dimensional data acquisition module is activated simultaneously. This includes: a high-precision power quality analysis module that collects real-time electrical waveform data of the charging pile, including voltage, current, power, and harmonic content; a communication protocol simulation module that captures communication interaction message data during protocol interaction, including message transmission delay, packet loss rate, and message integrity; a programmable BMS / vehicle simulation module that records simulation scenario log data during the simulation process, including state transitions and fault responses; and an environmental sensor suite that collects environmental sensor data, including temperature and humidity.

[0034] Furthermore, multi-source features corresponding to the multi-source test data are extracted separately and then fused. For electrical waveform data, statistical features of the electrical waveform data within a preset time window are extracted, including voltage fluctuation rate and current harmonic distortion rate; for communication interaction message data, the communication interaction message data is parsed to extract protocol event features, including handshake response delay and error code frequency; for environmental sensor data, environmental mutation features of the environmental sensor data are calculated; and for simulated scenario log data, marked faults and corresponding injection timing points are extracted from the simulated scenario log data.

[0035] Furthermore, using the injection timeline as a benchmark, the labeled faults are correlated with environmental mutation features within the same time period to analyze whether there is a temporal correlation between environmental mutations and fault injection. Simultaneously, the timestamps carried by environmental mutation features, electrical statistical features, and protocol event features are aligned with a pre-defined unified timeline, ensuring that features from different sources correspond at the same time points. Finally, the time-aligned multi-dimensional features are arranged chronologically to construct a fusion feature matrix containing electrical, communication, environmental, and fault injection information.

[0036] S104: Based on the fused multi-source features, output the fault diagnosis results of the charging pile under test through the real-time diagnostic model, and generate maintenance suggestions based on the fault diagnosis results; the fault diagnosis results include the fault type and the corresponding fault root cause probability distribution.

[0037] Specifically, the fused feature matrix is ​​transmitted to the intelligent software platform and input into the real-time diagnostic model. The real-time diagnostic model is based on a deep learning architecture and performs nonlinear mapping and pattern recognition on the multi-dimensional features in the matrix through a multi-layer neural network. Based on the association patterns of electrical, communication, and environmental features in the feature matrix, it matches the pre-trained fault feature library and outputs the corresponding fault type. At the same time, the model calculates the matching degree between the fault type and the feature matrix, and generates a quantitative anomaly score based on the severity of the feature anomaly. It also monitors in real time whether the anomaly score exceeds the preset anomaly threshold.

[0038] Furthermore, when the anomaly score exceeds a preset anomaly threshold, a deep diagnostic event is triggered, the historical fault case library is invoked, the feature similarity between the current fault type and the faults in the historical cases is calculated, and the set of cases with the highest matching degree is extracted. Based on the occurrence frequency and feature association strength of different root causes in the case set, the probability of occurrence of each possible root cause is calculated through probabilistic algorithms (such as Bayesian inference), and finally the probability distribution of the fault root cause corresponding to the fault type is output.

[0039] Furthermore, based on the diagnostic results, the built-in maintenance knowledge base is retrieved. This knowledge base contains standard maintenance procedures and component replacement guidelines for various faults, and maintenance solutions are extracted. Based on environmental sensor data, weights corresponding to different root cause probabilities are determined, fault maintenance priorities are generated, and maintenance solutions are sorted based on these priorities to generate structured maintenance work orders.

[0040] It should be noted that the historical failure case database stores a large number of handling records for similar failures, including information such as failure type, characteristics, actual root cause and solution.

[0041] S105: Generate a test report based on the fault diagnosis results and the maintenance suggestions, and upload it to the cloud platform for storage.

[0042] Specifically, the system summarizes fault diagnosis results, maintenance suggestions, key parameters and characteristic data from the testing process, and generates a structured test report according to a preset report template. This report includes modules such as test scenarios, data summaries, fault analysis, and maintenance plans. Once generated, the system uploads the test report to the cloud platform via an encrypted transmission channel. The cloud platform categorizes and stores the reports according to the unique identifier of each charging pile, and updates the health scores and test cycles in the test record files of the charging piles under test in the cloud platform, providing data support for subsequent traceability and analysis.

[0043] In addition, test reports are sent to a third-party operations and maintenance (O&M) platform via an interface. During the interface interaction, the test reports are formatted to conform to the data specifications of the third-party platform, and digital signatures are used to ensure data integrity and authenticity. After transmission is complete, the third-party O&M platform returns a receipt confirmation message and records the transmission status to complete the closed loop. Through this process, the third-party O&M team can obtain real-time test results and maintenance suggestions for charging piles, providing accurate data support for on-site O&M, component replacement, and other work, thereby improving O&M efficiency.

[0044] This application significantly improves the flexibility and efficiency of on-site testing by employing an automated interface type and communication protocol identification mechanism combined with scenario-based test instruction set generation. Through load testing, vehicle simulation testing, and communication protocol transmission testing, it overcomes the limitations of traditional methods with their single-function approach, achieving a comprehensive evaluation of charging pile electrical performance, protocol compatibility, and response to complex scenarios. This effectively avoids overlooking actual operational issues due to incomplete testing, and eliminates the need for multiple independent devices, thus solving the portability problem caused by bulky equipment in traditional testing.

[0045] Furthermore, by collecting and fusing multi-source test data and performing real-time model diagnostics, the efficiency and accuracy of fault diagnosis have been significantly improved. Through the fusion of multi-source features, the working state of charging piles under complex scenarios such as network fluctuations and dynamic battery changes is realistically reproduced, solving the problem of unrealistic simulations in traditional test scenarios. Automated fault diagnosis and root cause probability analysis based on fused features replace traditional troubleshooting methods that rely on manual experience, significantly shortening fault location time. The process of uploading generated test reports to the cloud platform enables centralized management and efficient traceability of test data, providing precise data support for the R&D, production, and operation and maintenance of charging piles, and significantly reducing overall operating costs.

[0046] like Figure 3 As shown in the figure, this application also proposes an intelligent testing device for electric vehicle charging piles, including: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform an intelligent testing method for electric vehicle charging piles as described in any of the above embodiments.

[0047] This application also provides a non-volatile computer storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured as: an intelligent testing method for electric vehicle charging piles as described in any of the above embodiments.

[0048] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device and medium embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the description of the method embodiments.

[0049] The devices and media provided in this application are one-to-one with the methods. Therefore, the devices and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0050] 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.

[0051] 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.

[0052] 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.

[0053] 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.

[0054] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0055] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0056] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0057] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0058] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A smart testing method for electric vehicle charging piles, characterized in that, include: Connect to the charging pile under test through the test interface, identify the interface type and communication protocol of the charging pile under test, and call the corresponding test engine; The test engine generates corresponding test instruction sets based on pre-configured test parameters for different test scenarios; the test scenarios include load testing, vehicle simulation testing, and communication protocol transmission testing. The test instruction set is executed to collect multi-source test data of the charging pile under test, extract multi-source features corresponding to the multi-source test data respectively, and fuse the multi-source features; Based on the fused multi-source features, the fault diagnosis results of the charging pile under test are output through the real-time diagnostic model, and maintenance suggestions are generated based on the fault diagnosis results. The fault diagnosis results include the fault type and the corresponding root cause probability distribution. A test report is generated based on the fault diagnosis results and the maintenance suggestions, and then uploaded to the cloud platform for storage.

2. The intelligent testing method for electric vehicle charging piles according to claim 1, characterized in that, The step of generating corresponding test sequence data based on pre-configured test parameters for different test scenarios through the test engine specifically includes: Based on the scenario tags corresponding to different test scenarios, the test parameter sets corresponding to the different test scenarios are matched in the pre-configured database; The test parameter set is input into the scene test engine corresponding to the different test scenarios to generate test instructions. The test instructions are sorted according to a preset time axis to obtain a test instruction set.

3. The intelligent testing method for electric vehicle charging piles according to claim 2, characterized in that, The test parameter set includes load characteristic parameters, vehicle behavior parameters, and communication anomaly parameters. The step of inputting the test parameter set into the scene test engine corresponding to the different test scenarios to generate test instructions specifically includes: The load characteristic parameters are input to the load control engine, which then converts them into a load control signal sequence to generate load control commands. The vehicle behavior parameters are input into the vehicle simulation engine, and the vehicle simulation engine encodes the vehicle behavior parameters to obtain the vehicle battery control signal sequence and generate vehicle simulation instructions. The communication anomaly parameters are input into the protocol simulation engine, which then constructs an abnormal communication test vector and generates communication transmission instructions.

4. The intelligent testing method for electric vehicle charging piles according to claim 1, characterized in that, After generating corresponding test instruction sets based on pre-configured test parameters corresponding to different test scenarios using the test engine, the method further includes: The test requirement text input by the user is received through the mobile terminal interface, and the scene keywords and pattern keywords corresponding to the custom scenario in the test requirement text are extracted. The pattern keywords are mapped to predefined fault templates to generate corresponding custom fault patterns; Based on the scenario keywords and the custom fault mode, a custom test parameter set corresponding to the custom scenario is generated through a predefined test parameter template.

5. The intelligent testing method for electric vehicle charging piles according to claim 1, characterized in that, The process of collecting multi-source test data from the charging pile under test, extracting multi-source features corresponding to the multi-source test data, and fusing the multi-source features specifically includes: Collect multi-source test data output by the charging pile under test; the multi-source test data includes electrical waveform data, communication interaction message data, environmental sensor data, and simulated scenario log data; Extract statistical features of the electrical waveform data within a preset time window; the statistical features include voltage fluctuation rate and current harmonic distortion rate. The communication interaction message data is parsed to extract protocol event features; the protocol event features include handshake response delay and error code frequency; Calculate the environmental abrupt change characteristics of the environmental sensor data; Extract the labeled faults and corresponding injection timing points from the simulated scenario log data; Based on the injection time point, the labeled fault is associated with the environmental mutation feature, and the environmental mutation feature, the statistical feature and the protocol event feature are aligned based on the timestamp and mapped to a unified time axis to generate a fused feature matrix.

6. The intelligent testing method for electric vehicle charging piles according to claim 5, characterized in that, The step of outputting the fault diagnosis result of the charging pile under test through a real-time diagnostic model based on the fused multi-source features specifically includes: The fused feature matrix is ​​input into the real-time diagnostic model, and the real-time diagnostic model outputs the fault type and the corresponding anomaly score, and monitors in real time whether the anomaly score exceeds the preset anomaly threshold. When the anomaly score exceeds the preset anomaly threshold, a deep diagnostic event is triggered, and the root cause probability distribution corresponding to the fault type is output based on historical fault cases.

7. The intelligent testing method for electric vehicle charging piles according to claim 6, characterized in that, The process of generating maintenance recommendations based on the fault diagnosis results specifically includes: Based on the probability distribution of the root causes of the faults, corresponding historical fault cases are matched in a pre-configured maintenance knowledge base, and maintenance solutions for the historical fault cases are extracted. Based on the environmental sensor data, determine the weights corresponding to different root cause probabilities of faults and generate fault repair priorities; Based on the maintenance priority, the maintenance plans are sorted to generate a structured maintenance work order.

8. The intelligent testing method for electric vehicle charging piles according to claim 1, characterized in that, The method of generating a test report based on the fault diagnosis results and the maintenance suggestions, and uploading it to the cloud platform for storage, further includes: A test report is generated based on the fault diagnosis results and the maintenance suggestions, and uploaded to the cloud platform for storage. The health score and test cycle of the charging pile under test in the cloud platform are updated. The test report is sent to the third-party operation and maintenance platform via the third-party operation and maintenance platform interface.

9. An intelligent testing device for electric vehicle charging piles, characterized in that, include: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform a smart testing method for electric vehicle charging piles as described in any one of claims 1 to 8.

10. A non-volatile computer storage medium storing computer-executable instructions, characterized in that, The computer-executable instructions are configured to execute the intelligent testing method for electric vehicle charging piles as described in any one of claims 1 to 8.

Images