Charging pile intelligent analysis method, intelligent charging pile and intelligent charging system

Abstract

The invention provides a charging pile intelligent analysis method, an intelligent charging pile and an intelligent charging system, and belongs to the technical field of charging piles. The method is applied to an artificial intelligence module, the artificial intelligence module runs in a controller of the intelligent charging pile in an independent software program mode, and the artificial intelligence module collects hardware running parameter information of the intelligent charging pile in real time based on a sensor in the intelligent charging pile; acquiring software running state information and software program information of the intelligent charging pile; collecting disk information of the intelligent charging pile in real time; and based on the neural network model, training the hardware operation parameter information, the software operation state information, the software program information and the disk information, and generating an analysis result of the intelligent charging pile. The service life of the charging pile can be prolonged, and the stability and reliability of the charging pile can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of charging piles, and in particular to an intelligent analysis method for charging piles, an intelligent charging pile, and an intelligent charging system. Background Art

[0002] As crucial infrastructure for charging and recharging electric vehicles, electric vehicle charging piles are increasingly becoming intelligent with the rapid development of smart electric vehicles. These piles typically consist of a charging station, charging module, controller, meter, and communication module. The controller, as the core component of the charging station, runs the entire charging station control system logic, enabling communication between the charging station and the electric vehicle's battery management system, demand response, and power distribution.

[0003] If a charging pile lacks hardware detection, software detection, and fault prediction capabilities, an abnormality in the charging pile will cause the controller's control logic to fail, directly affecting the charging pile's service life and operational reliability, and further increasing the charging pile's operation and maintenance costs. Therefore, there is an urgent need for a smart charging pile with hardware detection, software monitoring, and fault prediction capabilities. Summary of the Invention

[0004] The purpose of this application is to provide an intelligent analysis method for charging piles, an intelligent charging pile and an intelligent charging system, which can extend the service life of the charging piles and improve the stability and reliability of the charging piles.

[0005] The embodiment of the present application is implemented as follows: In a first aspect of an embodiment of the present application, a charging pile intelligent analysis method is provided. The method is applied to an artificial intelligence module, which runs in the controller of the intelligent charging pile in the form of an independent software program. The method includes: The artificial intelligence module collects the hardware operating parameter information of the smart charging pile in real time based on the sensors in the smart charging pile; and obtains the software operating status information and software program information of the smart charging pile; Real-time collection of disk information of smart charging piles; Based on the neural network model, the hardware operating parameter information, software operating status information, software program information and disk information are trained to generate analysis results for the smart charging pile.

[0006] As a possible implementation method, the artificial intelligence module has an independent resource space, and the resource space is allocated to the artificial intelligence module based on the process management mechanism provided by the operating system of the smart charging pile.

[0007] As a possible implementation method, the above charging pile intelligent analysis method further includes: The artificial intelligence module sends a version query request to the cloud server according to a first preset period, where the version query request includes: an identifier of the current version; The artificial intelligence module receives the response information sent by the cloud server; If the response information indicates that there is a new version, the artificial intelligence module automatically downloads the data package to be updated from the cloud server and performs data integrity verification on the data package to be updated. After the verification passes, the data package to be updated is installed to complete the version upgrade.

[0008] As a possible implementation method, the neural network model includes a hardware fault prediction model. Based on the neural network model, hardware operating parameter information, software operating status information, software program information, and disk information are trained to generate analysis results for the smart charging pile, including: Determine the hardware status monitoring results and hardware fault prediction results of the smart charging pile based on the hardware operating parameter information and the hardware fault prediction model; Determine the software detection result of the smart charging pile based on the software running status information and software program information, the software detection result including: software running status detection result and software vulnerability detection result; The database detection results and log file detection results of the smart charging pile are determined based on the disk information. The disk information includes: database files and log files.

[0009] As a possible implementation method, based on the hardware parameter information and the hardware fault prediction model, the hardware status monitoring results and hardware fault prediction results of the smart charging pile are determined, including: Determine the hardware status monitoring results of the smart charging pile based on the hardware operating parameter information and preset thresholds; The hardware operating parameter information is input into the hardware fault prediction model to obtain the hardware fault prediction result of the smart charging pile, wherein the hardware fault prediction model is trained based on the historical hardware operating data and historical hardware fault types of multiple smart charging piles.

[0010] As a possible implementation method, the software detection result of the smart charging pile is determined based on the software running status information and software program information, including: Based on the preset software process tool, real-time monitoring of the software running status information of the smart charging pile; Determine the software operation status detection result of the smart charging pile based on the software operation status information and the preset software standard process; Perform static analysis on the software program information according to the second preset cycle to determine the vulnerability information of the software program, and determine the software vulnerability detection results of the smart charging pile based on the vulnerability information. The software vulnerability detection results include: the location of the vulnerability, the time of the vulnerability, the type of vulnerability, and the impact of the vulnerability.

[0011] As a possible implementation method, the database detection results and log file detection results of the smart charging pile are determined based on the disk information, including: Invoking a preset database management tool to check a database file according to a third preset period to obtain a database detection result of the smart charging pile, the database detection result including: at least one of an abnormal table name, an abnormal field name, and an abnormal data example; Keyword information is extracted from the log file, and the log file detection result is determined based on the keyword information. The keyword information includes: error information, operation information, and system status change information.

[0012] As a possible implementation method, based on the neural network model, hardware operating parameter information, software operating status information, software program information and disk information are trained to generate analysis results for the smart charging pile, which also includes: According to the abnormality level corresponding to the analysis result, determine whether the abnormal phenomenon corresponding to the analysis result can be self-repaired; If so, the preset script file will be automatically executed to automatically repair the abnormal phenomenon; If not, a corresponding alarm message is generated according to the abnormal phenomenon.

[0013] According to a second aspect of an embodiment of the present application, a smart charging pile is provided, which includes: a charging pile body and a controller deployed inside the charging pile body, wherein an artificial intelligence module is deployed in the controller, and the controller executes the steps of the charging pile intelligent analysis method described in the first aspect based on the artificial intelligence module.

[0014] A third aspect of the embodiments of the present application provides a smart charging system, comprising: a cloud server and a plurality of smart charging piles as described in the second aspect above, each smart charging pile being communicatively connected to the cloud server; The cloud server is used to receive the analysis results and historical operation data sent by each smart charging pile, and generate a performance evaluation report corresponding to each smart charging pile based on the analysis results, historical operation data and preset scoring standards.

[0015] The beneficial effects of the embodiments of the present application include: An embodiment of the present application provides an intelligent charging pile analysis method. By embedding an artificial intelligence module, running as an independent software program, in the controller of a smart charging pile, the intelligent charging pile is equipped with hardware detection, software detection, and fault prediction functions. The artificial intelligence module collects hardware operating parameter information of the smart charging pile in real time based on sensors in the smart charging pile, obtains software operating status information and software program information in real time from software components in the smart charging pile controller, and scans the smart charging pile's disk in real time to obtain disk information. Based on a neural network model, the module trains the hardware operating parameter information, software operating status information, software program information, and disk information to generate analysis results for hardware faults, software faults, and fault predictions in the smart charging pile. Furthermore, the artificial intelligence module is independent of the main charging control logic in the controller. Without affecting the normal operation of the smart charging pile, it provides a safety monitoring system for the smart charging pile, providing early warning of hardware and software faults in the smart charging pile, thereby ensuring the continued stable operation of the smart charging pile. This can extend the service life of the charging pile and improve its stability and reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 A schematic diagram of the structure of a smart charging pile provided in an embodiment of the present application; Figure 2 Flowchart of the first charging pile intelligent analysis method provided in the embodiment of the present application; Figure 3 Flowchart of the second charging pile intelligent analysis method provided in the embodiment of the present application; Figure 4 Flowchart of the third charging pile intelligent analysis method provided in the embodiment of the present application; Figure 5 Flowchart of the fourth charging pile intelligent analysis method provided in the embodiment of the present application; Figure 6 A flowchart of the fifth charging pile intelligent analysis method provided in an embodiment of the present application; Figure 7 Flowchart of the sixth charging pile intelligent analysis method provided in the embodiment of the present application; Figure 8 Flowchart of the seventh charging pile intelligent analysis method provided in the embodiment of the present application; Figure 9 A schematic diagram of the structure of a smart charging system provided in an embodiment of the present application.

[0018] Figure symbols: 10: smart charging system; 101: smart charging pile; 1011: controller; 111: artificial intelligence module; 102: cloud server. DETAILED DESCRIPTION

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Generally, the components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations.

[0020] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for protection, but merely represents selected embodiments of the present application. All other embodiments obtained by persons of ordinary skill in the art based on the embodiments in the present application without creative work are within the scope of protection of the present application.

[0021] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not require further definition or explanation in subsequent drawings.

[0022] Currently, electric vehicle charging piles typically consist of a charging pile, charging module, controller, meter, and communication module. The controller integrates the entire charging pile's system control logic, enabling communication between the charging pile and the electric vehicle's battery management system, demand response, and power distribution. However, these charging piles lack hardware detection, software detection, and fault prediction capabilities. When an abnormal condition occurs in the charging pile, the controller's control logic will fail, seriously affecting the charging pile's service life and operational reliability, and increasing the charging pile's operation and maintenance costs.

[0023] To this end, an embodiment of the present application provides an intelligent analysis method for charging piles. By deploying an artificial intelligence module running as an independent software program within the controller of the charging pile, the artificial intelligence module collects the hardware operating parameter information of the smart charging pile in real time based on the sensors in the smart charging pile; and obtains the software operating status information and software program information of the smart charging pile in real time based on the interaction between software components in the controller of the smart charging pile; and obtains the disk information of the smart charging pile in real time by scanning the disk in the controller; Based on the neural network model, the hardware operating parameter information, software operating status information, software program information, and disk information are trained to generate analysis results for the smart charging pile, and the analysis results are uploaded to the cloud server. The cloud server generates an evaluation report based on the analysis results and historical operation data. Maintenance personnel can inspect and maintain the charging pile based on the evaluation report. In this way, the service life of the charging pile can be extended and the stability and reliability of the charging pile can be improved.

[0024] The following is a detailed explanation of the smart charging pile and the smart charging pile analysis method provided in the embodiments of the present application with reference to the accompanying drawings.

[0025] Figure 1 For a schematic diagram of the structure of a smart charging pile provided in this application, see Figure 1 , an embodiment of the present application provides a smart charging pile 101 including a charging pile body and a controller 1011 deployed inside the charging pile body. Among them, an artificial intelligence module 111 is deployed on the controller 1011, and the artificial intelligence module 111 can run independently inside the controller 1011, and is independent of the original charging pile control software program of the controller 1011, and does not interfere with each other. Among them, the artificial intelligence module 111 is implemented by an independently running software program. The artificial intelligence module 111 can intelligently analyze and monitor the hardware resources, software programs, database files, and log files of the smart charging pile 101 without affecting the charging control logic of the smart charging pile 101, and upload the analysis results and monitoring results to the intelligent operation and maintenance platform in the cloud server 102. The intelligent operation and maintenance platform generates a health analysis report for the smart charging pile 101 based on the analysis results currently sent by the artificial intelligence module 111 and the historical analysis results sent previously.

[0026] In addition, the intelligent operation and maintenance platform can not only archive the health analysis reports of each smart charging pile 101 it manages, but also send alarm information of abnormal conditions to maintenance personnel or manufacturers in real time through email, SMS, phone, work order, etc., so that relevant personnel can maintain the smart charging pile 101 in advance to ensure the sustainable and healthy operation of the smart charging pile 101.

[0027] Figure 2This is a flow chart of a charging pile intelligent analysis method provided by this application, which can be applied to the artificial intelligence module 111 deployed in the controller 1011 in the aforementioned smart charging pile 101. Figure 2 , the embodiment of the present application provides a charging pile intelligent analysis method, including: S201. The artificial intelligence module collects hardware operating parameter information of the smart charging pile in real time based on the sensors in the smart charging pile; and obtains software operating status information and software program information of the smart charging pile.

[0028] Optionally, the hardware sensor in the smart charging pile can be one or more of a variety of sensors such as a voltage sensor, a current sensor, a temperature sensor, a photoelectric sensor, a humidity sensor, etc., and this application does not make specific limitations on this.

[0029] Optionally, the first interface between the artificial intelligence module and each hardware sensor in the smart charging pile can be shared or independently configured, which is not specifically limited in this application. The first interface can be any of a variety of interfaces, such as a digital interface, an analog interface, or an electrical interface. The specific type of the first interface is determined by the type of hardware sensor being sampled, which is not specifically limited in this application.

[0030] Optionally, hardware operating parameter information refers to the operating parameters generated by each hardware sensor when the smart charging pile executes the charging control logic. The hardware operating parameter information includes: ambient temperature, real-time current, real-time voltage, usage time and other hardware operating data. This application does not make specific restrictions on this.

[0031] Optionally, the artificial intelligence module reads the hardware operating parameters of each hardware sensor in the smart charging pile in real time through the first interface between the artificial intelligence module and each hardware sensor in the smart charging pile to realize hardware detection of the smart charging pile.

[0032] Optionally, the software component within the controller specifically refers to a system control program that controls the smart charging pile to charge the electric vehicle. The software component within the controller is a software control program pre-written into the controller before the smart charging pile leaves the factory. The controller, through the software component, can implement functions such as communication between the smart charging pile and the electric vehicle, demand response, and power distribution. Furthermore, the controller may contain multiple software components. In addition to the main control logic for charging the smart charging pile, it may also include side control logic such as a program for scheduling the smart charging pile's fan to start and cool down the vehicle. This application does not specifically limit this.

[0033] Optionally, the second interface between the artificial intelligence module and the software component in the controller can be implemented in various ways such as serial interface, named pipe, shared memory, etc., and this application does not make specific limitations on this.

[0034] Optionally, software running status information refers to status data generated when the controller runs software components, such as memory occupancy, refresh rate, running speed, response speed, abnormal exit and other data; software program information refers to code data of software components.

[0035] Optionally, the artificial intelligence module reads the software running status information and static code data of each software component generated during operation in real time through a second interface between the artificial intelligence module and the software components in the controller to realize software detection of the smart charging pile.

[0036] S202: Collect disk information of the smart charging pile in real time.

[0037] Optionally, the artificial intelligence module scans the disk in the controller in real time to obtain disk information of the smart charging pile. The disk information includes database file information and log file information. The database file information refers to information such as keywords, database table structures, and data records in the controller's database. The log file information refers to log files generated when the controller controls the smart charging pile to execute charging instructions.

[0038] Optionally, the artificial intelligence module scans the controller's disk in real time to achieve real-time monitoring of disk hardware failures and network status.

[0039] S203: Based on the neural network model, the hardware operation parameter information, software operation status information, software program information and disk information are trained to generate analysis results for the smart charging pile.

[0040] Optionally, the analysis results include: hardware failures of the smart charging pile, software failures of the smart charging pile, and future failure risk predictions of the smart charging pile, etc., which are not specifically limited in this application. The artificial intelligence module is internally provided with a neural network model. The artificial intelligence module trains the collected hardware operating parameter information, software operating status information, software program information, and disk information based on the neural network model to perform dynamic and static analysis of the smart charging pile, ultimately achieving the purpose of hardware monitoring and software detection of the smart charging pile. At the same time, the artificial intelligence module can also predict the future operating status of the smart charging pile based on historical data and current data.

[0041] In an embodiment of the present application, an artificial intelligence module, running as an independent software program, is embedded in the controller of a smart charging pile, enabling the smart charging pile to have hardware detection, software detection, and fault prediction functions. The artificial intelligence module collects the hardware operating parameter information of the smart charging pile in real time based on sensors in the smart charging pile, obtains the software operating status information and software program information of the smart charging pile in real time based on software components in the smart charging pile controller, and scans the smart charging pile's disk in real time to obtain disk information. The artificial intelligence module trains the hardware operating parameter information, software operating status information, software program information, and disk information based on a neural network model to generate analysis results such as hardware faults, software faults, and fault predictions for the smart charging pile. Furthermore, the artificial intelligence module is independent of the main charging control logic in the controller. Without affecting the normal operation of the smart charging pile, it provides a safety monitoring system for the smart charging pile, providing early warning of hardware and software faults in the smart charging pile, thereby ensuring the continued stable operation of the smart charging pile. This can extend the service life of the charging pile and improve the stability and reliability of the charging pile.

[0042] In an optional embodiment, the artificial intelligence module 111 has an independent resource space, and the resource space is allocated to the artificial intelligence module 111 based on a process management mechanism provided by the operating system of the smart charging pile 101.

[0043] Optionally, independent resource space refers to an independent operating space allocated by the smart charging pile for the artificial intelligence module, ensuring that the operation of the artificial intelligence module does not affect or interfere with other software components in the controller. The smart charging pile utilizes the process management mechanism provided by the operating system to divide an independent resource space for the artificial intelligence module. For example, in a charging pile device running a Linux system, by creating a new process and setting reasonable resource limit parameters for the artificial intelligence module, this ensures that the operation of the artificial intelligence module program does not affect the native software components of the charging pile.

[0044] The resource limitation parameters include the upper limit of the usage of the central processing unit (CPU), the upper limit of the memory usage, etc., which are not specifically limited in this application.

[0045] In an optional embodiment, see Figure 3 The charging pile intelligent analysis method provided in the embodiment of the present application further includes: S301. The artificial intelligence module sends a version query request to the cloud server according to a first preset period. The version query request includes: an identifier of the current version.

[0046] Optionally, the first preset period is a version update period preset by the user. The first preset period may be 24 hours, 48 ​​hours, etc., and this application does not make any specific limitation on this.

[0047] Optionally, the cloud server stores the latest version of the software program for the artificial intelligence module. The version query request is a software program version access request sent by the artificial intelligence module to the cloud server. The version query request carries a version identifier of the current software program for the artificial intelligence module. The current version identifier refers to the version number of the software program currently running in the artificial intelligence module.

[0048] S302. The artificial intelligence module receives the response information sent by the cloud server.

[0049] Optionally, after the cloud server receives the version query request sent by the artificial intelligence module, based on the comparison result of the identifier of the current version carried in the version query request and the identifier of the latest version of the software program in the cloud server, the cloud server feeds back a response message to the artificial intelligence module. The response information is used to inform the artificial intelligence module whether the software program needs to be updated for version upgrade.

[0050] Optionally, if the version number of the current version included in the version query request is the same as the version number of the latest version stored in the cloud server, the artificial intelligence module does not need to perform a software upgrade, and the response information sent by the cloud server to the artificial intelligence module indicates that there is no new version of the software program; conversely, if the version number of the current version included in the version query request is different from the version number of the latest version stored in the cloud server, the artificial intelligence module needs to perform a software upgrade, and the response information sent by the cloud server to the artificial intelligence module indicates that there is a new version of the software program.

[0051] S303. If the response information indicates that there is a new version, the artificial intelligence module automatically downloads the data package to be updated from the cloud server and performs data integrity verification on the data package to be updated. After the verification passes, the data package to be updated is installed to complete the version upgrade.

[0052] Optionally, if the response information received by the artificial intelligence module indicates the existence of a new version of the artificial intelligence module's software program, the artificial intelligence module automatically downloads the data package to be updated from the cloud server based on a secure network protocol. After the data package to be updated is downloaded, the artificial intelligence module performs data integrity verification on the data package to confirm that the software program in the data package to be updated has not been tampered with and no data has been lost. After the verification is passed, the artificial intelligence module first stops the software program currently running in the artificial intelligence module according to a pre-set installation process, backs up the currently running software program file, decompresses and replaces the data package to be updated to obtain the new version of the software program, and restarts the artificial intelligence module to complete the software program version upgrade. The data package to be updated refers to the compressed data package of the new version of the artificial intelligence module's software program.

[0053] Among them, the secure network protocol can be the HTTPS protocol or other network protocols, and this application does not make specific limitations on this.

[0054] It is worth noting that performing data integrity verification on the update data packets can ensure that the new version of the software program downloaded by the artificial intelligence module from the cloud server has not been tampered with, lost packets, or other defects, thereby improving the reliability of the software version upgrade. Data integrity verification can be implemented using hash algorithms such as MD5 and SHA-256, which are not specifically limited in this application.

[0055] In an optional embodiment, the neural network model includes: a hardware failure prediction model, see Figure 4 The operation of step S203 may specifically be: S401. Determine hardware status monitoring results and hardware fault prediction results of the smart charging pile based on hardware operating parameter information and a hardware fault prediction model.

[0056] Optionally, the hardware failure prediction model is pre-trained by the user based on the historical hardware operation data of the same type of smart charging piles and the historical hardware failure cases of the same type of smart charging piles. The hardware failure prediction module can be a deep learning LSTM model or other neural network models. This application does not make specific limitations on this.

[0057] Among them, historical hardware operation data and historical hardware failure cases of the same type of smart charging piles are used as training data sets for the hardware failure prediction model.

[0058] Optionally, the hardware status monitoring result is used to indicate the analysis result of the real-time operating status of each hardware component in the smart charging pile, and the hardware fault prediction result refers to the fault prediction of each hardware component in the smart charging pile in the future period.

[0059] Optionally, the AI ​​module can analyze the current operating status of each hardware component in the smart charging pile based on real-time hardware operating parameter information. Furthermore, the AI ​​module can combine historical hardware operating parameter information, currently acquired hardware operating parameter information, and hardware failure development patterns indicated by the hardware failure prediction model to predict the likelihood of failures in each electronic component in the smart charging pile in the future.

[0060] S402: Determine the software detection result of the smart charging pile according to the software running status information and the software program information. The software detection result includes: a software running status detection result and a software vulnerability detection result.

[0061] Optionally, the software running status detection result is used to indicate the real-time running status monitoring result when the controller runs the software component, such as abnormal exit or abnormal interruption of the software operation; the software vulnerability detection result refers to the static analysis result of the software program file.

[0062] Optionally, the AI ​​module can analyze the current operating status of the smart charging pile's software components based on real-time software operating status information. Furthermore, the AI ​​module can perform static analysis of software program information to determine whether the software program has software vulnerabilities and the results of the software vulnerability detection.

[0063] S403: Determine the database detection result and log file detection result of the smart charging pile according to the disk information, where the disk information includes: database files and log files.

[0064] Optionally, the database detection result is used to indicate the integrity and consistency detection result of the database file stored in the controller; the log file detection result refers to the text analysis result of the log file stored in the controller.

[0065] Optionally, the artificial intelligence module scans the disk in real time and uses corresponding tools to perform intelligent analysis on the database files and log files to obtain corresponding database detection results and log file detection results.

[0066] In an optional embodiment, see Figure 5 The operation of step S401 may specifically be: S501: Determine the hardware status monitoring result of the smart charging pile according to the hardware operating parameter information and the preset threshold value.

[0067] Optionally, the preset threshold is a parameter limit pre-set by the user, such as a temperature limit, an overcurrent limit, etc., which is not specifically limited in this application.

[0068] Optionally, a hardware operation failure of each hardware component in the smart charging pile is determined based on a comparison result between each hardware parameter in the hardware operation parameter information and its corresponding parameter threshold.

[0069] For example, if the temperature threshold of the key hardware component A in the smart charging pile is pre-set to 30℃-60℃, and the artificial intelligence module obtains the current temperature of the hardware component A as 65℃ through the temperature sensor, it is determined that there is a temperature abnormality in the hardware component A. The artificial intelligence module records the abnormal information and reports it to the cloud server.

[0070] S502. Input the hardware operating parameter information into a hardware fault prediction model to obtain a hardware fault prediction result of the smart charging pile, wherein the hardware fault prediction model is trained based on historical hardware operating data and historical hardware fault types of multiple smart charging piles.

[0071] Optionally, hardware operating parameter information can be input into a pre-trained hardware failure prediction model. This model can then predict hardware failures that may occur in various hardware components within the smart charging pile within a certain period of time. For example, by inputting hardware operating parameter information such as the current usage time, current ambient temperature, and current operating power of the charging module within the smart charging pile into the hardware failure prediction model, the model could predict that the charging module is likely to fail due to controller overheating within the next week and send this warning information to the cloud server.

[0072] In an optional embodiment, see Figure 6 The operation of step S402 may specifically be: S601. Based on a preset software process tool, monitor the software running status information of the smart charging pile in real time.

[0073] Optionally, the preset software process tool is mainly used to monitor the dynamic running process of the controller running software components in real time. The preset software process tool can be implemented by the ps command under the Linux system combined with the script, and this application does not make specific limitations on this.

[0074] Optionally, the software running status information refers to process status data generated when the controller runs the software component. The software running status information includes: whether the software component is running normally, the CPU occupancy rate of the software component running, the memory occupancy of the software component running, etc.

[0075] Optionally, when it is found that the software component exits abnormally or the resource usage is too high during operation, the artificial intelligence module records the abnormal information and reports it to the cloud server to trigger an early warning mechanism.

[0076] S602: Determine a software operation status detection result of the smart charging pile according to the software operation status information and the preset software standard process.

[0077] Optionally, the preset software standard process refers to a standard process for normal operation of the software component. Based on the comparison result of the software operation status information with the preset software standard process, it is determined whether there is a software program operation abnormality when the controller runs the software component.

[0078] S603. Perform static analysis on the software program information according to a second preset period to determine vulnerability information of the software program, and determine the software vulnerability detection result of the smart charging pile based on the vulnerability information. The software vulnerability detection result includes: vulnerability location, vulnerability occurrence time, vulnerability type, and vulnerability impact.

[0079] Optionally, the second preset period is a software program inspection period preset by the user. The second preset period may be 12 hours, one day, two days, etc., and this application does not make any specific limitation on this.

[0080] Optionally, the artificial intelligence module periodically performs static analysis on the software program code of the software component according to a second preset period to check whether the software program has vulnerabilities, and records the location of the vulnerability, the event at which the vulnerability occurred, the type of vulnerability, and the potential impact of the vulnerability on the operation of the software component, etc., and uploads the recorded exception information to the cloud server. The software program static analysis tool can be a tool such as Clang-Static-Analyzer, or other software vulnerability detection tool, which is not specifically limited in this application.

[0081] Furthermore, common software vulnerabilities include buffer overflow, SQL injection and other risk points, which are not specifically limited in this application.

[0082] Optionally, the vulnerability location refers to the location of the software vulnerability in the software program, the vulnerability occurrence time refers to the time when the software vulnerability exists in the software program or the time when the software vulnerability is discovered to exist in the software program, the vulnerability type refers to the category of the software vulnerability, and the vulnerability impact refers to the degree of impact of the software vulnerability on the normal operation of the software component.

[0083] In an optional embodiment, see Figure 7 The operation of step S403 may specifically be: S701: Call a preset database management tool to check a database file according to a third preset period to obtain a database detection result of the smart charging pile, where the database detection result includes at least one of an abnormal table name, an abnormal field name, and an abnormal data example.

[0084] Optionally, the third preset period is a regular database check period preset by the user. The third preset period may be 1 day, 3 days, 5 days, etc., and this application does not make any specific limitation on this.

[0085] Optionally, a preset database management tool is used to check the integrity and consistency of the database file. The preset database management tool can be implemented by the sqlite3 command line tool combined with a script, or it can be other database checking tools. This application does not make specific restrictions on this.

[0086] Optionally, the database file stored in the disk of the controller may be an SQLite data file or other types of database files, which is not specifically limited in this application.

[0087] Optionally, the artificial intelligence module periodically calls a preset database management tool to check the integrity and consistency of the database files in the controller according to a third preset period. For example, by executing SQL statements to check whether the database table structure is complete and whether there are any anomalies in the data records (such as duplicate records, missing key fields, etc.), the artificial intelligence module records any anomalies and sends them to the cloud server.

[0088] Among them, the data monitoring results include: one or more of abnormal table names, abnormal field names, and abnormal data examples. The abnormal table name refers to the name of the data table with data anomalies, the abnormal field name refers to the name of the field with data anomalies, and the abnormal data example refers to specific abnormal data with duplicate records and lack of keywords.

[0089] S702: Extract keyword information from the log file and determine the log file detection result based on the keyword information. The keyword information includes error information, operation information, and system status change information.

[0090] Optionally, the artificial intelligence module scans the controller's disk to obtain the controller's log files, extracts keyword information from the log files using text analysis techniques and regular expression matching, and analyzes and compiles keyword information from the log text to determine the operating status of the smart charging pile, such as whether the smart charging pile frequently encounters specific types of errors, thereby determining whether the smart charging pile has potential problems. Keyword information includes error information, operation information, and system status change information. Error information refers to keywords indicating errors in the smart charging pile's operation; operation information refers to information about charging operations performed by the smart charging pile; and system status change information refers to information about changes in the state of the smart charging pile during operation.

[0091] For example, if it is found that the smart charging pile frequently records the error message of "charging connection timeout", it is analyzed that it may be caused by charging interface hardware failure or network instability, and the relevant analysis results are sent to the cloud server.

[0092] In an optional implementation, the artificial intelligence module summarizes the hardware status monitoring results, software operation status detection results, and disk information analysis results, and organizes them into a structured data format (such as JSON format) according to data type and time sequence, and performs intelligent analysis on the smart charging pile based on the structured data format.

[0093] The AI ​​module uses local machine learning algorithms (such as decision trees and random forests) to perform preliminary analysis on the aggregated data in JSON format, identifying anomalies and their characteristics. For example, it can determine whether the smart charging pile is operating normally by analyzing the changing trends of hardware operating parameters such as temperature, current, and voltage. For more complex analysis tasks, the aggregated data in JSON format is uploaded to a cloud server for in-depth analysis.

[0094] In an optional embodiment, see Figure 8 After step S203, the charging pile intelligent analysis method further includes: S801. Determine whether the abnormal phenomenon corresponding to the analysis result can be self-repaired based on the abnormality level corresponding to the analysis result.

[0095] Optionally, the abnormality level is a fault level pre-classified by the user, and the abnormality level is divided into mild, moderate, severe, etc., which is not specifically limited in this application.

[0096] Optionally, based on the abnormality level corresponding to the analysis result, determine whether the artificial intelligence module can automatically repair the abnormal phenomenon indicated by the analysis result. The abnormal phenomenon may be that the controller temperature is too high, the CPU memory usage is too high, etc. This application does not make specific limitations on this.

[0097] S802: If yes, automatically execute the preset script file to automatically repair the abnormal phenomenon.

[0098] Optionally, if the AI ​​module determines that the abnormality indicated by the analysis result is a mild abnormality, such as when the controller temperature is slightly above a preset temperature range, the AI ​​module can automatically trigger a preset script file to perform a simple process to address the abnormality. The preset script file may be a cooling program, a fan control program, or the like, which is not specifically limited in this application.

[0099] For example, if the artificial intelligence module identifies that the controller temperature is slightly higher than a preset temperature threshold, the artificial intelligence module can trigger a fan control program to adjust the speed of the cooling fan to reduce the temperature of the hardware device.

[0100] S803: If not, generate corresponding alarm information according to the abnormal phenomenon.

[0101] Optionally, if the artificial intelligence module determines that the abnormal phenomenon indicated by the analysis result is a severe abnormality, such as a software program crash, the analysis result needs to be fed back to the cloud server in a timely manner.

[0102] Figure 9 This is a schematic diagram of the structure of a smart charging system provided by this application, see Figure 9 The embodiment of the present application provides a smart charging system 10, comprising: a cloud server 102 and a plurality of the above-mentioned smart charging piles 101, wherein each smart charging pile 101 is in communication with the cloud server 102. The cloud server 102 is configured to receive analysis results and historical operating data sent by each smart charging pile 101, and generate a performance evaluation report corresponding to each smart charging pile based on the analysis results, historical operating data, and preset scoring criteria.

[0103] Optionally, the preset scoring criteria are performance evaluation criteria for smart charging piles pre-written by the user into the cloud server, and the historical operation data refers to historical hardware operation parameter information, historical software operation status information, and disk information of each smart charging pile.

[0104] Optionally, the cloud server receives analysis results sent from the artificial intelligence module deployed in the controller of each smart charging pile under its jurisdiction, stores them in a dedicated database (such as a MySQL database), and classifies and manages them according to multiple dimensions such as the ID and time of the smart charging pile.

[0105] Optionally, based on the current and historical analysis results of the smart charging pile, a neural network model (convolutional neural network (CNN) or recurrent neural network (RNN)) is used to assess the overall health of the smart charging pile 101. The neural network model inputs include multi-dimensional feature data such as hardware operating parameters, software operating status, and historical fault records, and outputs a performance evaluation report for the smart charging pile 101 (e.g., good, fair, warning, fault, etc.).

[0106] Furthermore, the performance evaluation report includes an overview of the current status of the smart charging pile 101, potential risk analysis, historical fault records, processing suggestions, and current performance scores, providing maintenance personnel with comprehensive and reliable equipment health information to facilitate maintenance personnel to formulate reasonable maintenance plans, thereby extending the service life of the smart charging pile 101.

[0107] The above are only specific embodiments of the present application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0108] The above description is merely a preferred embodiment of the present application and is not intended to limit the present application. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

Claims

1. A charging pile intelligent analysis method, characterized in that: The method is applied to an artificial intelligence module, which runs in the controller of a smart charging pile in the form of an independent software program, and includes: The artificial intelligence module collects hardware operating parameter information of the smart charging pile in real time based on the sensors in the smart charging pile; and obtains software operating status information and software program information of the smart charging pile; Collecting disk information of the smart charging pile in real time; Based on a neural network model, the hardware operating parameter information, the software operating status information, the software program information and the disk information are trained to generate an analysis result of the smart charging pile.

2. The charging pile intelligent analysis method according to claim 1, characterized in that: The artificial intelligence module has an independent resource space, and the resource space is allocated to the artificial intelligence module based on a process management mechanism provided by the operating system of the smart charging pile.

3. The charging pile intelligent analysis method according to claim 1, characterized in that: The method further comprises: The artificial intelligence module sends a version query request to the cloud server according to a first preset period, wherein the version query request includes: an identifier of the current version; The artificial intelligence module receives the response information sent by the cloud server; If the response information indicates that there is a new version, the artificial intelligence module automatically downloads the data package to be updated from the cloud server and performs data integrity verification on the data package to be updated. After the verification passes, the data package to be updated is installed to complete the version upgrade.

4. The charging pile intelligent analysis method according to claim 1, characterized in that: The neural network model includes: a hardware fault prediction model, which is based on the neural network model and trains the hardware operating parameter information, the software operating status information, the software program information, and the disk information to generate an analysis result of the smart charging pile, including: Determining a hardware status monitoring result and a hardware fault prediction result of the smart charging pile according to the hardware operating parameter information and the hardware fault prediction model; Determine a software detection result of the smart charging pile according to the software running status information and the software program information, wherein the software detection result includes: a software running status detection result and a software vulnerability detection result; According to the disk information, a database detection result and a log file detection result of the smart charging pile are determined, and the disk information includes: a database file and a log file.

5. The charging pile intelligent analysis method according to claim 4, characterized in that: The determining of the hardware status monitoring result and the hardware fault prediction result of the smart charging pile according to the hardware operating parameter information and the hardware fault prediction model includes: Determine the hardware status monitoring result of the smart charging pile according to the hardware operating parameter information and the preset threshold; The hardware operating parameter information is input into a hardware fault prediction model to obtain a hardware fault prediction result of the smart charging pile, wherein the hardware fault prediction model is trained based on historical hardware operating data of multiple smart charging piles and historical hardware fault types of multiple smart charging piles.

6. The charging pile intelligent analysis method according to claim 4, characterized in that: The determining, based on the software running status information and the software program information, a software detection result of the smart charging pile includes: Based on a preset software process tool, real-time monitoring of the software running status information of the smart charging pile; Determine the software running status detection result of the smart charging pile according to the software running status information and the preset software standard process; The software program information is statically analyzed according to a second preset period to determine vulnerability information of the software program, and a software vulnerability detection result of the smart charging pile is determined based on the vulnerability information. The software vulnerability detection result includes: vulnerability location, vulnerability occurrence time, vulnerability type, and vulnerability impact.

7. The charging pile intelligent analysis method according to claim 4, characterized in that: The step of determining the database detection result and the log file detection result of the smart charging pile according to the disk information includes: Invoking a preset database management tool to check the database file according to a third preset period to obtain a database detection result of the smart charging pile, wherein the database detection result includes at least one of an abnormal table name, an abnormal field name, and an abnormal data example; Keyword information is extracted from the log file, and the log file detection result is determined according to the keyword information, where the keyword information includes error information, operation information, and system status change information.

8. The charging pile intelligent analysis method according to claim 1, characterized in that: After training the hardware operating parameter information, the software operating status information, the software program information, and the disk information based on the neural network model to generate an analysis result of the smart charging pile, the method further includes: Determining whether the abnormal phenomenon corresponding to the analysis result can be self-repaired according to the abnormality level corresponding to the analysis result; If so, the preset script file is automatically executed to automatically repair the abnormal phenomenon; If not, corresponding alarm information is generated according to the abnormal phenomenon.

9. A smart charging pile, characterized in that: The smart charging pile includes: a charging pile body and a controller deployed inside the charging pile body, wherein an artificial intelligence module is deployed in the controller, and the controller executes the steps of the charging pile intelligent analysis method according to any one of claims 1 to 8 based on the artificial intelligence module.

10. An intelligent charging system, characterized in that: The smart charging system comprises: a cloud server and a plurality of smart charging piles according to claim 9, each of the smart charging piles being communicatively connected to the cloud server; The cloud server is used to receive the analysis results and historical operation data sent by each smart charging pile, and generate a performance evaluation report corresponding to each smart charging pile according to the analysis results, the historical operation data and a preset scoring standard.

Images