On-board charger working process monitoring and fault warning analysis system and method

Abstract

The present application discloses a system and method for monitoring the working process of an on-board charger and its fault warning analysis. The system includes: a vehicle, which is used to obtain environmental data in real time and send it to a host computer; a voltage and power detection device, which is used to detect the electrical parameters of the on-board charger in real time and send them to the host computer, and generate an alarm signal to feed back to the host computer when the electrical parameters are abnormal; the host computer, which is used to receive environmental data and electrical parameters in real time, and store them as a ternary mapping relationship in combination with the time; the host computer, which is also used to respond to the alarm signal and determine the alarm time carried by the alarm signal; from the ternary mapping relationship, the original environmental data and original electrical parameters at each moment in a preset period before and after the alarm moment are obtained, and the alarm cause corresponding to the alarm signal is analyzed to obtain the analysis result. The use of the embodiments of the present application can improve the accuracy of OBC testing, and achieve an in-depth understanding and timely resolution of OBC performance issues.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle chargers, and in particular to a system and method for monitoring the working process of a vehicle charger and its fault early warning analysis. Background Art

[0002] In the field of modern automotive technology, the on-board charger (OBC) is a key power adapter for cars. Its performance and safety are crucial to ensuring driving safety and improving user experience. OBC testing is designed to evaluate its stability, compatibility, efficiency and environmental adaptability under various working conditions to ensure its reliability in practical applications.

[0003] In the related art, the OBC and the voltage and power detection device are installed in the vehicle during the test. During the test, the voltage and power detection device monitors the output parameters of the OBC. However, in the current test environment, the environmental parameters obtained by the vehicle and the power supply parameters obtained by the voltage and power detection device are often separated, which means that it may be difficult to control and monitor these two parameters at the same time during the test, thus affecting the accuracy and comprehensiveness of the test results. At the same time, when abnormal data is detected, the voltage and power detection device reminds the operator through an alarm mechanism. At this time, the operator needs to manually record the data and analyze the reasons. This process makes it difficult to determine the relevant data at the time of the alarm, and manual analysis is time-consuming and inaccurate, thereby reducing the accuracy of the OBC test and limiting the in-depth understanding and timely resolution of OBC performance issues. Summary of the invention

[0004] The embodiments of the present application provide a vehicle charger working process monitoring and fault warning analysis system. In order to have a basic understanding of some aspects of the disclosed embodiments, a simple summary is given below. This summary is not a general review, nor is it intended to identify key / important components or describe the scope of protection of these embodiments. Its only purpose is to present some concepts in a simple form as a preface to the detailed description that follows.

[0005] In a first aspect, an embodiment of the present application provides a vehicle charger working process monitoring and fault warning analysis system, the system comprising:

[0006] Vehicle, on-board charger, voltage and power detection device and host computer; wherein,

[0007] The on-board charger and the voltage and power detection device are arranged in the vehicle, the on-board charger is electrically connected to the voltage and power detection device, and the host computer is respectively connected to the vehicle and the voltage and power detection device for communication; wherein,

[0008] Vehicle, used to obtain environmental data in real time and send it to the host computer;

[0009] The voltage and power detection device is used to detect the electrical parameters of the on-board charger in real time, send them to the host computer, and generate an alarm signal to feed back to the host computer when the electrical parameters are abnormal;

[0010] The host computer is used to receive the environmental data sent by the vehicle and the electrical parameters sent by the voltage and power detection device in real time, and store the ternary mapping relationship between the environmental data, electrical parameters and timestamp at the same time;

[0011] The host computer is also used to respond to the alarm signal sent by the voltage and power detection device to determine the alarm time carried by the alarm signal; obtain the original environmental data and original electrical parameters at each moment in a preset period before and after the alarm moment from the ternary mapping relationship; analyze the alarm cause corresponding to the alarm signal according to the original environmental data and original electrical parameters at each moment to obtain the analysis result.

[0012] Optionally, the alarm cause corresponding to the alarm signal is analyzed based on the original environmental data and original electrical parameters at each moment, including:

[0013] From the original environmental data and original electrical parameters at each moment, obtain the original environmental data and original electrical parameters corresponding to the alarm moment;

[0014] The acquired original environmental data and original electrical parameters are used as environmental data to be analyzed and electrical parameters to be analyzed; the environmental data to be analyzed include temperature data to be analyzed, humidity data to be analyzed and pressure data to be analyzed, and the electrical parameters to be analyzed include voltage to be analyzed, current to be analyzed and power to be analyzed;

[0015] Determine whether the temperature data to be analyzed is greater than a preset threshold and determine whether an abnormal power drop occurs based on the power to be analyzed; if so, determine that the on-board charger is overheated, and use the overheating as the alarm cause corresponding to the alarm signal; or,

[0016] Determine whether the current to be analyzed or the power to be analyzed increases to a preset value within a preset time; if so, determine that the on-board charger is overloaded, and use the overload phenomenon as the alarm cause corresponding to the alarm signal;

[0017] Determine whether the humidity data to be analyzed and the pressure data to be analyzed are greater than the preset threshold value and determine whether the electrical parameters are unstable based on the voltage to be analyzed and the current to be analyzed; if so, determine that the on-board charger has an environmental adaptability problem, and use the environmental adaptability problem as the alarm cause corresponding to the alarm signal.

[0018] Optionally, the alarm cause corresponding to the alarm signal is analyzed based on the original environmental data and original electrical parameters at each moment, including:

[0019] Eliminate invalid or redundant parameter values ​​from the original environmental data and the original electrical parameters at each moment to obtain first environmental data and first electrical parameters; wherein the invalid or redundant parameter values ​​refer to information irrelevant to fault warning analysis;

[0020] By presetting a large language model, the parameter values ​​with semantic duplication in the first environment data and the first electrical parameter are merged to obtain the target environment data and the target electrical parameter; the preset large language model is ChatGPT;

[0021] Based on each target environment data, construct environment state information for characterizing the vehicle;

[0022] Based on each target electrical parameter, construct device status information for characterizing the on-board charger;

[0023] The environmental status information and the equipment status information are input into the pre-trained fault warning analysis model, and the alarm cause corresponding to the alarm signal is output.

[0024] Optionally, each target environment data includes temperature data, humidity data and pressure data;

[0025] Based on each target environment data, construct the environment status information used to characterize the vehicle, including:

[0026] Using the temperature data, humidity data and pressure data of each target environment data to construct an environment matrix;

[0027] According to the environmental matrix, calculate the covariance of temperature data, humidity data and pressure data;

[0028] Convert the covariance into eigenvalues ​​of temperature data, humidity data, and pressure data;

[0029] Sort by the size of the eigenvalues ​​and select the first K as the principal components;

[0030] Using the selected principal components, an environmental status index is constructed;

[0031] The constructed environmental state index is used as the environmental state information for characterizing the vehicle; wherein the environmental matrix is:

[0032] is the temperature data, is the humidity data, is the pressure data; is the total number of target environment data; the covariance calculation formula is:

[0033]

[0034] in, Represents the first Parameters and The covariance between the parameters, is the total amount of target environment data, and For the Parameters and The mean of the parameters, and For the The target environment data Parameters and The value of a parameter.

[0035] Optionally, each target electrical parameter includes voltage, current, and power;

[0036] Based on each target electrical parameter, construct device status information for characterizing the on-board charger, including:

[0037] From the voltage, current and power included in each target electrical parameter, obtain the voltage, current and power at the alarm moment;

[0038] Determine the power consumption of the on-board charger within a preset period based on the voltage, current and power at the time of the alarm;

[0039] According to the voltage, current and power of each target electrical parameter, a coordinate diagram of the power consumption of the on-board charger at each moment in a preset cycle is constructed;

[0040] Determine that the device power consumption of the on-board charger within a preset period is located at a target coordinate point in the power consumption coordinate graph;

[0041] According to the target coordinate point and the power consumption coordinate diagram, device status information for characterizing the on-board charger is generated.

[0042] Optionally, according to the target coordinate point and the power consumption coordinate diagram, device status information for characterizing the on-board charger is generated, including:

[0043] Taking the target coordinate point as the origin, a circular area within a preset radius is established in the power consumption coordinate diagram;

[0044] Obtain corresponding electrical information within the circular area;

[0045] Perform vector coding processing on the corresponding electrical information in the circular area to obtain the feature code corresponding to the target coordinate point;

[0046] Performing vector coding processing on all corresponding electrical information of the power consumption coordinate diagram to obtain a feature code corresponding to the power consumption coordinate diagram;

[0047] Calculate the degree of discreteness between the feature code corresponding to the target coordinate point and the feature code corresponding to the power consumption coordinate graph;

[0048] The discrete degree is used to characterize the device status information of the on-board charger; the calculation formula of the discrete degree is:

[0049]

[0050] in, is the degree of discreteness, is the feature code corresponding to the power consumption coordinate diagram feature codes, is the feature code corresponding to the target coordinate point, and p is the total number of feature codes corresponding to the power consumption coordinate diagram.

[0051] Optionally, a pre-trained fault warning analysis model is generated by following the steps below, including:

[0052] From the pre-stored ternary mapping relationships, a plurality of historical ternary mapping relationships corresponding to each historical alarm signal existing in a historical time period are obtained, each historical ternary mapping relationship including historical environmental data and historical electrical parameters at each historical moment;

[0053] For the historical environmental data and historical electrical parameters at each historical moment, invalid or redundant parameter values ​​are eliminated and parameter values ​​with semantic duplication are merged to obtain sample environmental data and sample electrical parameters at each historical moment;

[0054] Based on the sample environmental data at each historical moment, the sample environmental status information used to characterize the vehicle is constructed, and based on the sample electrical parameters at each historical moment, the sample device status information used to characterize the on-board charger is constructed, and the sample environmental status information and sample device status information corresponding to each historical alarm signal are obtained;

[0055] Determine the historical alarm cause corresponding to each historical alarm signal through sample environmental data and sample electrical parameters at each historical moment;

[0056] The historical alarm causes corresponding to each historical alarm signal are used as labels, and the sample environment status information and sample equipment status information corresponding to each historical alarm signal are annotated to obtain model training samples;

[0057] Machine learning is performed based on the model training samples to obtain a pre-trained fault warning analysis model.

[0058] Optionally, the historical alarm causes corresponding to each historical alarm signal are determined through sample environmental data and sample electrical parameters at each historical moment, including:

[0059] Display sample environmental data and sample electrical parameters at each historical moment;

[0060] Receiving the alarm reasons input for the displayed sample environmental data and sample electrical parameters as the historical alarm reasons corresponding to each historical alarm signal; or,

[0061] In the self-learning mode, the sample environmental data including historical temperature data, historical humidity data and historical pressure data are extracted, and the sample electrical parameters including historical voltage, historical current and historical power are extracted;

[0062] Determine whether the historical temperature data is greater than the preset threshold and determine whether an abnormal power drop occurs based on the historical power; if so, determine that the on-board charger is overheated, and use the overheating phenomenon as the historical alarm cause corresponding to each historical alarm signal; or, determine whether the historical current or historical power increases to the preset value within the preset time; if so, determine that the on-board charger is overloaded, and use the overload phenomenon as the historical alarm cause corresponding to each historical alarm signal; determine whether the historical humidity data and the historical pressure data are greater than the preset threshold and determine whether the electrical parameters are unstable based on the historical voltage and historical current; if so, determine that the on-board charger has an environmental adaptability problem, and use the environmental adaptability problem as the historical alarm cause corresponding to each historical alarm signal.

[0063] Optionally, machine learning is performed based on the model training samples to obtain a pre-trained fault warning analysis model, including

[0064] Use neural network to create fault warning analysis model;

[0065] Input the model training samples into the fault warning analysis model for machine learning and output the model loss value;

[0066] When the model loss value reaches the minimum, a pre-trained fault warning analysis model is generated; or, when the model loss value does not reach the minimum, the step of inputting the model training sample into the fault warning analysis model for machine learning is continued until the model loss value reaches the minimum; wherein the loss function of the fault warning analysis model is:

[0067]

[0068] in, is the model loss value, N is the number of historical warning signals, C is the number of alarm reasons, Indicates Is the historical alarm cause of the alarm signal Class (1 for yes, 0 for no), The first The warning signal is The probability of the class.

[0069] In a second aspect, a method for monitoring the working process of a vehicle charger and its fault early warning analysis is provided, the method comprising:

[0070] Obtain environmental data in real time through the vehicle and send it to the host computer;

[0071] The voltage and power detection device detects the electrical parameters of the on-board charger in real time and sends them to the host computer. When the electrical parameters are abnormal, an alarm signal is generated and fed back to the host computer.

[0072] The environmental data sent by the vehicle and the electrical parameters sent by the voltage and power detection device are received in real time by the host computer, and the ternary mapping relationship among the environmental data, electrical parameters and timestamp at the same time is stored; in response to the alarm signal sent by the voltage and power detection device, the alarm time carried by the alarm signal is determined; from the ternary mapping relationship, the original environmental data and original electrical parameters at each time within a preset period before and after the alarm time are obtained; according to the original environmental data and original electrical parameters at each time, the alarm cause corresponding to the alarm signal is analyzed to obtain the analysis result.

[0073] In the embodiment of the present application, on the one hand, the host computer can accurately integrate the environmental parameters and power supply parameters at the same time by storing the ternary mapping relationship between the environmental data, electrical parameters and timestamp at the same time, and analyze based on the integrated data, thereby improving the accuracy and comprehensiveness of the test results. At the same time, after receiving the alarm signal through the host computer, it can immediately respond and determine the alarm time. At this time, the system can extract the original environmental data and original electrical parameters within a preset period before and after the alarm time from the stored ternary mapping relationship. This rapid response mechanism enables the time and data of the problem to be quickly located, providing accurate data support for fault diagnosis and analysis. On the other hand, through the original environmental data and original electrical parameters at each moment, the alarm cause corresponding to the alarm signal can be automatically analyzed. The analysis process has a high degree of automation, thereby improving the efficiency and reliability of the vehicle charger test, reducing the risk of failure, and optimizing the overall performance of the product.

[0074] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0076] Figure 1 It is a system structure diagram of a vehicle charger working process monitoring and fault warning analysis system provided by an embodiment of the present application;

[0077] Figure 2It is a method flow chart of a method for monitoring the working process of an on-board charger and its fault early warning analysis method provided by an embodiment of the present application;

[0078] Figure 3 It is a method flow diagram of a training method of a fault warning analysis model provided in an embodiment of the present application;

[0079] Figure 4 It is a structural schematic diagram of a host computer provided in an embodiment of the present application;

[0080] Figure 5 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0081] The following description and the accompanying drawings sufficiently illustrate specific embodiments of the present application to enable those skilled in the art to practice them.

[0082] It should be clear that the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0083] When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Instead, they are only examples of systems and methods consistent with some aspects of the present application as detailed in the attached claims.

[0084] In the description of the present application, it should be understood that the terms "first", "second", etc. are used for descriptive purposes only and should not be understood as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to the specific circumstances. In addition, in the description of the present application, unless otherwise specified, "multiple" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects associated before and after are in an "or" relationship.

[0085] At present, the OBC and voltage and power detection devices are installed in the vehicle during the test. During the test, the voltage and power detection device monitors the output parameters of the OBC. At the same time, when abnormal data is detected, the voltage and power detection device reminds the operator through an alarm mechanism. At this time, the operator needs to manually record the data and analyze the cause.

[0086] The inventors realized that in the current test environment, the environmental parameters obtained by the vehicle and the power supply parameters obtained by the voltage and power detection device are often separated, which means that it may be difficult to simultaneously control and monitor these two parameters during the test, thereby affecting the accuracy and comprehensiveness of the test results. This process makes it difficult to determine the relevant data at the alarm time and manual analysis is time-consuming and inaccurate, thereby reducing the accuracy of the OBC test and limiting the in-depth understanding and timely resolution of OBC performance issues.

[0087] In the embodiment of the present application, in the embodiment of the present application, on the one hand, the host computer can accurately integrate the environmental parameters and power supply parameters at the same time by storing the ternary mapping relationship between the environmental data, electrical parameters and timestamp at the same time, and analyze based on the integrated data, thereby improving the accuracy and comprehensiveness of the test results. At the same time, after receiving the alarm signal through the host computer, it can immediately respond and determine the alarm time. At this time, the system can extract the original environmental data and original electrical parameters within the preset period before and after the alarm time from the stored ternary mapping relationship. This fast response mechanism enables the time and data of the problem to be quickly located, providing accurate data support for fault diagnosis and analysis. On the other hand, through the original environmental data and original electrical parameters at each moment, the alarm cause corresponding to the alarm signal can be automatically analyzed. The analysis process has a high degree of automation, thereby improving the efficiency and reliability of the vehicle charger test, reducing the risk of failure, and optimizing the overall performance of the product. The following exemplary embodiments are used for detailed description.

[0088] See also Figure 1 , Figure 1 This is a system structure diagram of a vehicle charger working process monitoring and fault warning analysis system provided in an embodiment of the present application, the system comprising: a vehicle, an on-board charger, a voltage and power detection device and a host computer; wherein the on-board charger and the voltage and power detection device are arranged in the vehicle, the on-board charger is electrically connected to the voltage and power detection device, and the host computer is respectively communicated with the vehicle and the voltage and power detection device.

[0089] Among them, the on-board charger is a device installed on an electric vehicle, which converts AC power into DC power to charge the battery of the electric vehicle. The on-board charger is placed inside the vehicle to test its performance under real environmental conditions. The voltage and power detection device is a device used to measure electrical parameters such as voltage, current, and power. During the operation of the on-board charger, the voltage and power detection device is used to monitor its electrical parameters in real time to ensure that it operates within a safe and expected range. If an abnormality is detected, the device can also generate an alarm signal. The host computer usually refers to the control computer in a system, which is responsible for receiving data from other devices and processing and analyzing them.

[0090] In some embodiments of the present application, the vehicle is used to obtain environmental data in real time and send it to a host computer; the voltage and power detection device is used to detect the electrical parameters of the on-board charger in real time, send them to the host computer, and generate an alarm signal to feed back to the host computer when the electrical parameters are abnormal; the host computer is used to receive the environmental data sent by the vehicle and the electrical parameters sent by the voltage and power detection device in real time, and store the ternary mapping relationship between the environmental data, electrical parameters and timestamp at the same time; the host computer is also used to respond to the alarm signal sent by the voltage and power detection device to determine the alarm time carried by the alarm signal; from the ternary mapping relationship, the original environmental data and original electrical parameters at each moment within a preset period before and after the alarm moment are obtained; according to the original environmental data and original electrical parameters at each moment, the alarm cause corresponding to the alarm signal is analyzed to obtain the analysis result.

[0091] Among them, environmental data refers to the data corresponding to the simulated climate conditions obtained by the vehicle in real time, including parameters such as temperature, humidity, and pressure. Electrical parameters refer to the key electrical characteristics of the on-board charger during operation, including voltage, current, and power. The ternary mapping relationship refers to a data structure that associates data in three dimensions: environmental data, electrical parameters, and time information (moment). This relationship allows the host computer to store and query environmental and electrical parameters at a specific time point. The alarm signal is a signal generated by the voltage and power detection device when an electrical parameter abnormality is detected. The alarm moment refers to the specific time point when the voltage and power detection device detects an electrical parameter abnormality and issues an alarm signal. The original environmental data and original electrical parameters refer to the unprocessed data collected directly from the vehicle and the voltage and power detection device. The analysis result refers to the specific alarm cause corresponding to the alarm signal obtained by the host computer after analyzing the original environmental data and original electrical parameters before and after the alarm moment.

[0092] For example, an on-board charger (OBC) is installed in a vehicle and is ready to undergo a series of performance tests and fault warning analysis. The vehicle begins to simulate an extreme climate condition, such as a high temperature of 40°C and a high humidity of 90%, to test the performance of the on-board charger under such conditions. The sensors built into the test chamber monitor and record temperature and humidity data in real time, which are sent to the host computer via a wireless module. The voltage and power detection device is connected to the on-board charger, monitors its voltage, current, and power output in real time, and sends these data to the host computer synchronously. During the test, the voltage and power detection device finds that the current reading suddenly rises and exceeds the preset safety threshold, and generates an alarm signal to feed back to the host computer. The host computer receives the environmental data from the vehicle and the electrical parameters of the voltage and power detection device in real time, and stores these data, including the timestamp of the recorded data. After receiving the alarm signal from the voltage and power detection device, the host computer immediately records the alarm time and retrieves the environmental data and electrical parameters within one minute before and after the alarm time from the database. The host computer extracts the data before and after the alarm time from the ternary mapping relationship, including the ambient temperature, humidity, and the voltage, current, and power of the on-board charger. The host computer analyzes these data and finds that the on-board charger has an overload fault. The host computer feeds back the analysis results to the test engineer, pointing out the possible cause of the fault and the recommended repair measures. The ternary mapping relationship is shown in Table 1.

[0093] Table 1

[0094]

[0095] In some embodiments of the present application, the specific process of analyzing the alarm cause corresponding to the alarm signal according to the original environmental data and original electrical parameters at each moment includes: obtaining the original environmental data and original electrical parameters corresponding to the alarm moment from the original environmental data and original electrical parameters at each moment; using the obtained original environmental data and original electrical parameters as the environmental data to be analyzed and the electrical parameters to be analyzed; the environmental data to be analyzed includes temperature data to be analyzed, humidity data to be analyzed and pressure data to be analyzed, and the electrical parameters to be analyzed include voltage to be analyzed, current to be analyzed and power to be analyzed; judging whether the temperature data to be analyzed is greater than a preset threshold and according to the data to be analyzed The power is used to determine whether there is an abnormal power drop; if so, it is determined that the on-board charger is overheated, and the overheating phenomenon is used as the alarm cause corresponding to the alarm signal; or, it is determined whether the current to be analyzed or the power to be analyzed increases to the preset value within the preset time; if so, it is determined that the on-board charger is overloaded, and the overload phenomenon is used as the alarm cause corresponding to the alarm signal; it is determined whether the humidity data to be analyzed and the pressure data to be analyzed are greater than the preset threshold and the electrical parameters are judged to be unstable based on the voltage to be analyzed and the current to be analyzed; if so, it is determined that the on-board charger has an environmental adaptability problem, and the environmental adaptability problem is used as the alarm cause corresponding to the alarm signal.

[0096] Among them, by real-time monitoring and evaluation of the original environmental data and electrical parameters of the on-board charger at the time of the alarm, and comparing them with the preset safety threshold, potential faults such as overheating, overload and environmental adaptability problems can be quickly identified. This rule-based method is simple and efficient, can respond to abnormal situations in a timely manner, reduce errors in human judgment, improve the accuracy and response speed of fault diagnosis, and thus enhance the reliability and safety of the on-board charger.

[0097] In other embodiments of the present application, the specific process of analyzing the alarm cause corresponding to the alarm signal according to the original environmental data and the original electrical parameters at each moment includes: eliminating the invalid or redundant parameter values ​​from the original environmental data and the original electrical parameters at each moment to obtain the first environmental data and the first electrical parameter; wherein the invalid or redundant parameter value refers to the information irrelevant to the fault warning analysis; by presetting a large language model, merging the semantically repeated parameter values ​​in the first environmental data and the first electrical parameter to obtain the target environmental data and the target electrical parameter; based on each target environmental data, constructing the environmental status information for characterizing the vehicle; based on each target electrical parameter, constructing the equipment status information for characterizing the on-board charger; inputting the environmental status information and the equipment status information into the pre-trained fault warning analysis model, and outputting the alarm cause corresponding to the alarm signal.

[0098] Among them, some alarm reasons are shown in Table 2.

[0099] Table 2

[0100]

[0101] Among them, invalid or redundant parameter values ​​refer to those data that are inaccurate, wrong, outdated or unnecessary for fault warning analysis. These data may be irrelevant to the analysis target due to measurement errors, duplicate data entry or other reasons. The processed data set obtained after eliminating invalid or redundant parameter values ​​is called the first environmental data and the first electrical parameter. The preset large language model refers to a pre-set large language model, such as ChatGPT, which is used to understand and process natural language data and help identify and merge semantically repeated parameter values. The pre-trained fault warning analysis model is a model that is pre-trained using historical data and machine learning technology, and can output possible alarm causes based on the input environmental status information and equipment status information.

[0102] In the embodiment of the present application, the accuracy and efficiency of fault diagnosis are effectively improved through precise data preprocessing, using a large language model to eliminate information redundancy, building key environmental and equipment status information, and applying a pre-trained fault warning analysis model. This method not only reduces the complexity of data processing, but also enhances the system's ability to predict potential faults of the on-board charger, thereby improving the safety and reliability of the test process and helping to take timely measures to prevent possible equipment failures.

[0103] Each target environment data includes temperature data, humidity data and pressure data.

[0104] In some embodiments of the present application, based on each target environmental data, a specific process of constructing environmental state information for characterizing a vehicle includes: constructing an environmental matrix using temperature data, humidity data, and pressure data included in each target environmental data; calculating the covariance of the temperature data, humidity data, and pressure data according to the environmental matrix; converting the covariance into eigenvalues ​​of the temperature data, humidity data, and pressure data; sorting according to the size of the eigenvalues, and selecting the first K as principal components; constructing an environmental state index using the selected principal components; and using the constructed environmental state index as environmental state information for characterizing the vehicle; wherein the environmental matrix is:

[0105] is the temperature data, is the humidity data, is the pressure data; is the total number of target environment data; the covariance calculation formula is:

[0106]

[0107] in, Represents the first Parameters and The covariance between the parameters, is the total amount of target environment data, and For the Parameters and The mean of the parameters, and For the The target environment data Parameters and The value of a parameter.

[0108] Among them, the environmental matrix is ​​a mathematical concept that refers to organizing the data of multiple variables (in this case, temperature, humidity, and pressure) into a matrix form, where each row represents an observation sample and each column represents a variable. Covariance is a statistic that measures the joint change trend of two variables. In this passage, the covariance of temperature, humidity, and pressure data is calculated to understand how these environmental parameters change with each other. The environmental state index is a comprehensive indicator constructed by combining the principal components of multiple environmental parameters such as temperature, humidity, and pressure. The environmental state information of the vehicle refers to the overall environmental condition of the vehicle expressed by the environmental state index.

[0109] Each target electrical parameter includes voltage, current and power.

[0110] In some embodiments of the present application, based on each target electrical parameter, the specific process of constructing the device status information for characterizing the on-board charger includes: obtaining the voltage, current and power at the alarm time from the voltage, current and power included in each target electrical parameter; determining the device power consumption of the on-board charger within a preset period according to the voltage, current and power at the alarm time; constructing a power consumption coordinate diagram of the on-board charger at each moment within the preset period according to the voltage, current and power included in each target electrical parameter; determining that the device power consumption of the on-board charger within the preset period is located at the target coordinate point in the power consumption coordinate diagram; generating the device status information for characterizing the on-board charger according to the target coordinate point and the power consumption coordinate diagram.

[0111] Among them, the power consumption of the device refers to the total amount of electric energy consumed by the on-board charger within a specific time period. This is usually calculated by multiplying the voltage, current and power, and can reflect the energy consumption of the device within a certain period of time. The power consumption coordinate graph is a graphical representation method used to show the changes in power consumption of the on-board charger at each moment within a preset cycle. The coordinate graph will use time as the horizontal axis and power consumption as the vertical axis to show the trend of the device's power consumption over time. The target coordinate point refers to the specific location in the power consumption coordinate graph that represents the power consumption of the on-board charger at a specific moment (such as the alarm moment). This point is determined by the power consumption value at that moment, and can provide specific information about the energy consumption status of the device at that moment.

[0112] In some embodiments of the present application, the specific process of generating device status information for characterizing the on-board charger based on the target coordinate point and the power consumption coordinate graph includes: taking the target coordinate point as the origin, establishing a circular area within a preset radius in the power consumption coordinate graph; obtaining the corresponding electrical information within the circular area; performing vector encoding processing on the corresponding electrical information within the circular area to obtain the feature code corresponding to the target coordinate point; performing vector encoding processing on all the corresponding electrical information of the power consumption coordinate graph to obtain the feature code corresponding to the power consumption coordinate graph; calculating the degree of discreteness between the feature code corresponding to the target coordinate point and the feature code corresponding to the power consumption coordinate graph; and using the degree of discreteness to characterize the device status information of the on-board charger.

[0113] The calculation formula of the discrete degree is:

[0114]

[0115] in, is the degree of discreteness, is the feature code corresponding to the power consumption coordinate diagram feature codes, is the feature code corresponding to the target coordinate point, and p is the total number of feature codes corresponding to the power consumption coordinate diagram.

[0116] In some embodiments of the present application, a pre-trained fault warning analysis model can be generated according to the following steps, specifically including: obtaining multiple historical ternary mapping relationships corresponding to each historical alarm signal existing in a historical time period from a pre-stored ternary mapping relationship, each historical ternary mapping relationship includes historical environmental data and historical electrical parameters at each historical moment; for the historical environmental data and historical electrical parameters at each historical moment, invalid or redundant parameter values ​​are eliminated and parameter values ​​with semantic duplication are merged to obtain sample environmental data and sample electrical parameters at each historical moment; based on the sample environmental data at each historical moment, a sample for characterizing the vehicle is constructed. Environmental status information, and according to the sample electrical parameters at each historical moment, construct the sample equipment status information for characterizing the on-board charger, and obtain the sample environmental status information and sample equipment status information corresponding to each historical alarm signal; determine the historical alarm cause corresponding to each historical alarm signal through the sample environmental data and sample electrical parameters at each historical moment; use the historical alarm cause corresponding to each historical alarm signal as a label, and annotate the sample environmental status information and sample equipment status information corresponding to each historical alarm signal to obtain model training samples; perform machine learning based on the model training samples to obtain a pre-trained fault warning analysis model.

[0117] Among them, historical alarm causes refer to the specific reasons that led to the generation of historical alarm signals. These reasons are conclusions drawn by operators, experts or automatic diagnosis systems based on historical data and alarm signal analysis. Data labeling refers to the process of associating historical alarm causes (labels) with corresponding sample environmental status information and sample equipment status information. This is an important step in machine learning and is used to train models to identify and predict alarm causes. Model training samples refer to the data set used to train fault warning analysis models, including sample environmental status information, sample equipment status information, and corresponding historical alarm cause labels.

[0118] In some embodiments, the specific process of determining the historical alarm cause corresponding to each historical alarm signal through the sample environmental data and sample electrical parameters at each historical moment includes: displaying the sample environmental data and sample electrical parameters at each historical moment; receiving the alarm cause input for the displayed sample environmental data and sample electrical parameters as the historical alarm cause corresponding to each historical alarm signal. The cause is summarized by the operator or expert.

[0119] In other embodiments, the specific process of determining the historical alarm cause corresponding to each historical alarm signal through the sample environmental data and sample electrical parameters at each historical moment includes: in the self-learning mode, extracting the historical temperature data, historical humidity data and historical pressure data included in the sample environmental data, extracting the historical voltage, historical current and historical power included in the sample electrical parameters; judging whether the historical temperature data is greater than the preset threshold and judging whether the power abnormally decreases according to the historical power; if so, determining that the on-board charger is overheated, and taking the overheating phenomenon as the historical alarm cause corresponding to each historical alarm signal; or, judging whether the historical current or historical power increases to the preset value within the preset time; if so, determining that the on-board charger is overloaded, and taking the overload phenomenon as the historical alarm cause corresponding to each historical alarm signal; judging whether the historical humidity data and the historical pressure data are greater than the preset threshold and judging whether the electrical parameters are unstable according to the historical voltage and historical current; if so, determining that the on-board charger has an environmental adaptability problem, and taking the environmental adaptability problem as the historical alarm cause corresponding to each historical alarm signal. This method is obtained by the automatic diagnosis system based on the analysis of historical data and alarm signals.

[0120] In some embodiments of the present application, the specific process of performing machine learning based on model training samples to obtain a pre-trained fault warning analysis model includes: using a neural network to create a fault warning analysis model; inputting the model training samples into the fault warning analysis model for machine learning, and outputting a model loss value; when the model loss value reaches the minimum, generating a pre-trained fault warning analysis model; or, when the model loss value does not reach the minimum, continuing to perform the step of inputting the model training samples into the fault warning analysis model for machine learning until the model loss value reaches the minimum. The neural network can be a random forest model or a decision tree model.

[0121] Among them, the loss function of the fault warning analysis model is:

[0122]

[0123] in, is the model loss value, N is the number of historical warning signals, C is the number of alarm reasons, Indicates Is the historical alarm cause of the alarm signal Class (1 for yes, 0 for no), The first The warning signal is The probability of the class.

[0124] In the embodiment of the present application, in the embodiment of the present application, on the one hand, the host computer can accurately integrate the environmental parameters and power supply parameters at the same time by storing the ternary mapping relationship between the environmental data, electrical parameters and timestamp at the same time, and analyze based on the integrated data, thereby improving the accuracy and comprehensiveness of the test results. At the same time, after receiving the alarm signal through the host computer, it can immediately respond and determine the alarm time. At this time, the system can extract the original environmental data and original electrical parameters within a preset period before and after the alarm time from the stored ternary mapping relationship. This rapid response mechanism enables the time and data of the problem to be quickly located, providing accurate data support for fault diagnosis and analysis. On the other hand, through the original environmental data and original electrical parameters at each moment, the alarm cause corresponding to the alarm signal can be automatically analyzed. The analysis process has a high degree of automation, thereby improving the efficiency and reliability of the on-board charger test, reducing the risk of failure, and optimizing the overall performance of the product.

[0125] See also Figure 2 , which is a flow chart of a method for monitoring the working process of a vehicle charger and its fault warning analysis in accordance with an embodiment of the present application. Figure 2 As shown, the detection method of the embodiment of the present application may include the following steps:

[0126] S101, real-time acquisition of environmental data through the vehicle and sending to the host computer;

[0127] S102, using a voltage and power detection device to detect electrical parameters of the on-board charger in real time, and sending the parameters to a host computer. When the electrical parameters are abnormal, an alarm signal is generated and fed back to the host computer;

[0128] S103, receiving the environmental data sent by the vehicle and the electrical parameters sent by the voltage and power detection device in real time through the host computer, and storing the ternary mapping relationship among the environmental data, electrical parameters and timestamp recorded at the same time; in response to the alarm signal sent by the voltage and power detection device, determining the alarm time carried by the alarm signal; obtaining the original environmental data and original electrical parameters at each moment within a preset period before and after the alarm moment from the ternary mapping relationship; analyzing the alarm cause corresponding to the alarm signal according to the original environmental data and original electrical parameters at each moment, and obtaining the analysis result.

[0129] In an embodiment of the present application, after the analysis result is obtained, the analysis result can be pushed to the client of the relevant personnel for display.

[0130] In the embodiment of the present application, in the embodiment of the present application, on the one hand, the host computer can accurately integrate the environmental parameters and power supply parameters at the same time by storing the ternary mapping relationship between the environmental data, electrical parameters and timestamp at the same time, and analyze based on the integrated data, thereby improving the accuracy and comprehensiveness of the test results. At the same time, after receiving the alarm signal through the host computer, it can immediately respond and determine the alarm time. At this time, the system can extract the original environmental data and original electrical parameters within a preset period before and after the alarm time from the stored ternary mapping relationship. This rapid response mechanism enables the time and data of the problem to be quickly located, providing accurate data support for fault diagnosis and analysis. On the other hand, through the original environmental data and original electrical parameters at each moment, the alarm cause corresponding to the alarm signal can be automatically analyzed. The analysis process has a high degree of automation, thereby improving the efficiency and reliability of the on-board charger test, reducing the risk of failure, and optimizing the overall performance of the product.

[0131] See also Figure 3 , which is a flow chart of a method for training a fault warning analysis model provided in the present application embodiment. Figure 3 As shown, the process includes the following steps:

[0132] S201, acquiring multiple historical ternary mapping relationships corresponding to each historical alarm signal existing in a historical time period from pre-stored ternary mapping relationships, each historical ternary mapping relationship including historical environmental data and historical electrical parameters at each historical moment;

[0133] S202, for the historical environmental data and historical electrical parameters at each historical moment, remove invalid or redundant parameter values ​​and merge parameter values ​​with semantic duplication to obtain sample environmental data and sample electrical parameters at each historical moment;

[0134] S203, constructing sample environmental status information for characterizing the vehicle based on the sample environmental data at each historical moment, and constructing sample device status information for characterizing the on-board charger based on the sample electrical parameters at each historical moment, and obtaining sample environmental status information and sample device status information corresponding to each historical alarm signal;

[0135] S204, determining the historical alarm cause corresponding to each historical alarm signal through the sample environmental data and sample electrical parameters at each historical moment;

[0136] S205, using the historical alarm causes corresponding to each historical alarm signal as labels, and performing data labeling on the sample environment status information and sample device status information corresponding to each historical alarm signal to obtain a model training sample;

[0137] S206, performing machine learning based on the model training samples to obtain a pre-trained fault warning analysis model.

[0138] In the embodiment of the present application, in the embodiment of the present application, on the one hand, the host computer can accurately integrate the environmental parameters and power supply parameters at the same time by storing the ternary mapping relationship between the environmental data, electrical parameters and timestamp at the same time, and analyze based on the integrated data, thereby improving the accuracy and comprehensiveness of the test results. At the same time, after receiving the alarm signal through the host computer, it can immediately respond and determine the alarm time. At this time, the system can extract the original environmental data and original electrical parameters within a preset period before and after the alarm time from the stored ternary mapping relationship. This rapid response mechanism enables the time and data of the problem to be quickly located, providing accurate data support for fault diagnosis and analysis. On the other hand, through the original environmental data and original electrical parameters at each moment, the alarm cause corresponding to the alarm signal can be automatically analyzed. The analysis process has a high degree of automation, thereby improving the efficiency and reliability of the on-board charger test, reducing the risk of failure, and optimizing the overall performance of the product.

[0139] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.

[0140] See also Figure 4, which shows a schematic diagram of the structure of a host computer provided by an exemplary embodiment of the present application. The host computer can be implemented as all or part of the electronic device through software, hardware or a combination of both. The host computer 1 includes a receiving module 10, a storage module 20, a response module 30, an acquisition module 40, and an analysis module 50.

[0141] The receiving module 10 is used to receive the environmental data sent by the vehicle and the electrical parameters sent by the voltage and power detection device in real time;

[0142] The storage module 20 is used to store the ternary mapping relationship between the environmental data, the electrical parameters and the timestamp at the same time;

[0143] A response module 30, configured to respond to an alarm signal sent by the voltage and power detection device and determine an alarm time carried by the alarm signal;

[0144] The acquisition module 40 is used to acquire the original environmental data and the original electrical parameters at each moment in a preset period before and after the alarm moment from the ternary mapping relationship;

[0145] The analysis module 50 is used to analyze the alarm cause corresponding to the alarm signal according to the original environmental data and the original electrical parameters at each moment to obtain the analysis result.

[0146] It should be noted that the on-board charger working process monitoring and fault warning analysis device provided in the above embodiment only uses the division of the above functional modules as an example when executing the on-board charger working process monitoring and fault warning analysis method. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the on-board charger working process monitoring and fault warning analysis device provided in the above embodiment and the on-board charger working process monitoring and fault warning analysis method embodiment belong to the same concept, and the implementation process thereof is detailed in the method embodiment, which will not be repeated here.

[0147] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0148] In the embodiment of the present application, in the embodiment of the present application, on the one hand, the host computer can accurately integrate the environmental parameters and power supply parameters at the same time by storing the ternary mapping relationship between the environmental data, electrical parameters and timestamp at the same time, and analyze based on the integrated data, thereby improving the accuracy and comprehensiveness of the test results. At the same time, after receiving the alarm signal through the host computer, it can immediately respond and determine the alarm time. At this time, the system can extract the original environmental data and original electrical parameters within a preset period before and after the alarm time from the stored ternary mapping relationship. This rapid response mechanism enables the time and data of the problem to be quickly located, providing accurate data support for fault diagnosis and analysis. On the other hand, through the original environmental data and original electrical parameters at each moment, the alarm cause corresponding to the alarm signal can be automatically analyzed. The analysis process has a high degree of automation, thereby improving the efficiency and reliability of the on-board charger test, reducing the risk of failure, and optimizing the overall performance of the product.

[0149] The present application also provides a computer-readable medium having program instructions stored thereon, which, when executed by a processor, implement the on-board charger working process monitoring and fault warning analysis methods provided in the above-mentioned various method embodiments.

[0150] The present application also provides a computer program product including instructions, which, when executed on a computer, enables the computer to execute the vehicle charger working process monitoring and fault warning analysis methods of the above-mentioned various method embodiments.

[0151] See also Figure 5 , is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 5 As shown, the electronic device 1000 may include: at least one processor 1001 , at least one network interface 1004 , a user interface 1003 , a memory 1005 , and at least one communication bus 1002 .

[0152] The communication bus 1002 is used to realize the connection and communication between these components.

[0153] The user interface 1003 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 1003 may also include a standard wired interface and a wireless interface.

[0154] The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0155] Among them, the processor 1001 may include one or more processing cores. The processor 1001 uses various interfaces and lines to connect various parts of the entire electronic device 1000, and executes various functions and processes data of the electronic device 1000 by running or executing instructions, programs, code sets or instruction sets stored in the memory 1005, and calling data stored in the memory 1005. Optionally, the processor 1001 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 1001 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 1001, and it can be implemented separately through a chip.

[0156] Among them, the memory 1005 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 1005 includes a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 1005 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 1005 may also be optionally at least one storage system located away from the aforementioned processor 1001. As Figure 5 As shown, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program for monitoring the working process of the on-board charger and its fault warning analysis.

[0157] exist Figure 5In the electronic device 1000 shown, the user interface 1003 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 1001 can be used to call the on-board charger working process monitoring and fault warning analysis application stored in the memory 1005, and specifically perform the following operations:

[0158] Receive the environmental data sent by the vehicle and the electrical parameters sent by the voltage and power detection device in real time; store the ternary mapping relationship between the environmental data, electrical parameters and timestamp at the same time;

[0159] In response to an alarm signal sent by the voltage and power detection device, determine an alarm time carried by the alarm signal;

[0160] From the ternary mapping relationship, the original environmental data and original electrical parameters at each moment in a preset period before and after the alarm moment are obtained;

[0161] According to the original environmental data and original electrical parameters at each moment, the alarm cause corresponding to the alarm signal is analyzed to obtain the analysis result.

[0162] In the embodiment of the present application, in the embodiment of the present application, on the one hand, the host computer can accurately integrate the environmental parameters and power supply parameters at the same time by storing the ternary mapping relationship between the environmental data, electrical parameters and timestamp at the same time, and analyze based on the integrated data, thereby improving the accuracy and comprehensiveness of the test results. At the same time, after receiving the alarm signal through the host computer, it can immediately respond and determine the alarm time. At this time, the system can extract the original environmental data and original electrical parameters within a preset period before and after the alarm time from the stored ternary mapping relationship. This rapid response mechanism enables the time and data of the problem to be quickly located, providing accurate data support for fault diagnosis and analysis. On the other hand, through the original environmental data and original electrical parameters at each moment, the alarm cause corresponding to the alarm signal can be automatically analyzed. The analysis process has a high degree of automation, thereby improving the efficiency and reliability of the on-board charger test, reducing the risk of failure, and optimizing the overall performance of the product.

[0163] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program for monitoring the working process of the on-board charger and its fault warning analysis can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium of the program for monitoring the working process of the on-board charger and its fault warning analysis can be a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0164] The above disclosure is only the preferred embodiment of the present application, which certainly cannot be used to limit the scope of rights of the present application. Therefore, equivalent changes made according to the claims of the present application are still within the scope covered by the present application.

Claims

1. A vehicle charger working process monitoring and fault warning analysis system, characterized in that: The system comprises: Vehicle, on-board charger, voltage and power detection device and host computer; wherein, The on-board charger and the voltage and power detection device are arranged in the vehicle, the on-board charger is electrically connected to the voltage and power detection device, and the host computer is respectively connected to the vehicle and the voltage and power detection device for communication; wherein, The vehicle is used to obtain environmental data in real time and send it to the host computer; The voltage and power detection device is used to detect the electrical parameters of the on-board charger in real time, send them to the host computer, and generate an alarm signal to feed back to the host computer when the electrical parameters are abnormal; The host computer is used to receive the environmental data sent by the vehicle and the electrical parameters sent by the voltage and power detection device in real time, and store the ternary mapping relationship between the environmental data, the electrical parameters and the timestamp at the same time; The host computer is further used to respond to the alarm signal sent by the voltage power detection device to determine the alarm time carried by the alarm signal; obtain the original environmental data and original electrical parameters at each moment in a preset period before and after the alarm moment from the ternary mapping relationship; analyze the alarm cause corresponding to the alarm signal according to the original environmental data and original electrical parameters at each moment to obtain the analysis result; The analyzing the alarm cause corresponding to the alarm signal according to the original environmental data and the original electrical parameters at each moment includes: Eliminating invalid or redundant parameter values ​​from the original environmental data and the original electrical parameters at each time to obtain first environmental data and first electrical parameters; wherein the invalid or redundant parameter values ​​refer to information irrelevant to the fault warning analysis; By presetting a large language model, the parameter values ​​with semantic duplication in the first environmental data and the first electrical parameters are merged to obtain target environmental data and target electrical parameters; Based on each target environment data, construct environment state information for characterizing the vehicle; Based on each target electrical parameter, construct device status information for characterizing the on-board charger; Inputting the environmental status information and the equipment status information into a pre-trained fault warning analysis model, and outputting the alarm cause corresponding to the alarm signal; Wherein, each target environment data includes temperature data, humidity data and pressure data; The step of constructing environmental state information for characterizing the vehicle based on each target environmental data includes: Using the temperature data, humidity data and pressure data included in each target environment data, construct an environment matrix; Calculating the covariance of the temperature data, humidity data, and pressure data according to the environmental matrix; Converting the covariance into characteristic values ​​of the temperature data, humidity data and pressure data; Sort by the size of the eigenvalues ​​and select the first K as the principal components; Using the selected principal components, an environmental status index is constructed; Using the constructed environment state index as the environment state information for characterizing the vehicle; Wherein, each target electrical parameter includes voltage, current and power; The device status information for characterizing the on-board charger is constructed based on each target electrical parameter, including: Acquire the voltage, current and power at the alarm moment from the voltage, current and power included in each target electrical parameter; Determine the device power consumption of the on-board charger within the preset period according to the voltage, current and power at the alarm time; Constructing a power consumption coordinate diagram of the on-board charger at each time within a preset period according to the voltage, current and power included in each target electrical parameter; Determine that the device power consumption of the on-board charger in the preset period is located at a target coordinate point in the power consumption coordinate diagram; According to the target coordinate point and the power consumption coordinate diagram, device status information for characterizing the on-board charger is generated.

2. The system according to claim 1, characterized in that The analyzing the alarm cause corresponding to the alarm signal according to the original environmental data and the original electrical parameters at each moment includes: From the original environmental data and original electrical parameters at each time, obtaining the original environmental data and original electrical parameters corresponding to the alarm time; The acquired original environmental data and original electrical parameters are used as environmental data to be analyzed and electrical parameters to be analyzed; the environmental data to be analyzed includes temperature data to be analyzed, humidity data to be analyzed and pressure data to be analyzed, and the electrical parameters to be analyzed include voltage to be analyzed, current to be analyzed and power to be analyzed; Determine whether the temperature data to be analyzed is greater than a preset threshold and determine whether an abnormal power drop occurs based on the power to be analyzed; if so, determine that the on-board charger is overheated, and use the overheating as the alarm cause corresponding to the alarm signal; or, Determine whether the current to be analyzed or the power to be analyzed increases to a preset value within a preset time; if so, determine that the on-board charger is overloaded, and use the overload as the alarm cause corresponding to the alarm signal; Determine whether the humidity data to be analyzed and the pressure data to be analyzed are greater than a preset threshold and determine whether the electrical parameters are unstable based on the voltage to be analyzed and the current to be analyzed; if so, determine that the on-board charger has an environmental adaptability problem, and use the environmental adaptability problem as the alarm cause corresponding to the alarm signal.

3. The system according to claim 1, characterized in that The environment matrix is: is the temperature data, is the humidity data, is the pressure data; is the total number of target environment data; wherein the calculation formula of the covariance is: in, Represents the first Parameters and The covariance between the parameters, is the total amount of target environment data, and For the Parameters and The mean of the parameters, and For the The target environment data Parameters and The value of a parameter.

4. The system according to claim 1, characterized in that The generating, according to the target coordinate point and the power consumption coordinate diagram, device status information for characterizing the on-board charger comprises: Taking the target coordinate point as the origin, establishing a circular area within a preset radius in the power consumption coordinate diagram; Acquiring corresponding electrical information within the circular area; Performing vector coding processing on the corresponding electrical information within the circular area to obtain a feature code corresponding to the target coordinate point; Performing vector coding processing on all corresponding electrical information of the power consumption coordinate diagram to obtain a feature code corresponding to the power consumption coordinate diagram; Calculating the degree of discreteness between the characteristic code corresponding to the target coordinate point and the characteristic code corresponding to the power consumption coordinate graph; The discrete degree is used to characterize the device status information of the on-board charger; the calculation formula of the discrete degree is: in, is the degree of discreteness, is the feature code corresponding to the power consumption coordinate diagram feature codes, is the feature code corresponding to the target coordinate point, and p is the total number of feature codes corresponding to the power consumption coordinate diagram.

5. The system according to claim 1, characterized in that Follow these steps to generate a pre-trained fault warning analysis model, including: From the pre-stored ternary mapping relationships, a plurality of historical ternary mapping relationships corresponding to each historical alarm signal existing in a historical time period are obtained, each historical ternary mapping relationship including historical environmental data and historical electrical parameters at each historical moment; For the historical environmental data and historical electrical parameters at each historical moment, invalid or redundant parameter values ​​are eliminated and parameter values ​​with semantic duplication are merged to obtain sample environmental data and sample electrical parameters at each historical moment; According to the sample environmental data at each historical moment, construct sample environmental status information for characterizing the vehicle, and according to the sample electrical parameters at each historical moment, construct sample device status information for characterizing the on-board charger, and obtain sample environmental status information and sample device status information corresponding to each historical alarm signal; Determining the historical alarm causes corresponding to the historical alarm signals through the sample environmental data and sample electrical parameters at the historical moments; Using the historical alarm causes corresponding to the historical alarm signals as labels, data annotation is performed on the sample environment status information and sample device status information corresponding to the historical alarm signals to obtain model training samples; Machine learning is performed based on the model training samples to obtain a pre-trained fault warning analysis model.

6. The system according to claim 5, characterized in that Determining the historical alarm causes corresponding to the historical alarm signals through the sample environmental data and sample electrical parameters at the historical moments includes: Displaying sample environmental data and sample electrical parameters at each historical moment; receiving alarm reasons input for displayed sample environmental data and sample electrical parameters as historical alarm reasons corresponding to each historical alarm signal; or, In the self-learning mode, extracting the historical temperature data, historical humidity data and historical pressure data included in the sample environmental data, and extracting the historical voltage, historical current and historical power included in the sample electrical parameters; Determine whether the historical temperature data is greater than a preset threshold and determine whether an abnormal power drop occurs based on the historical power; if so, determine that the on-board charger is overheated, and use the overheating phenomenon as the historical alarm cause corresponding to each of the historical alarm signals; or, determine whether the historical current or the historical power increases to a preset value within a preset time period; if so, determine that the on-board charger is overloaded, and use the overload phenomenon as the historical alarm cause corresponding to each of the historical alarm signals; determine whether the historical humidity data and the historical pressure data are greater than a preset threshold and determine whether the electrical parameters are unstable based on the historical voltage and historical current; if so, determine that the on-board charger has an environmental adaptability problem, and use the environmental adaptability problem as the historical alarm cause corresponding to each of the historical alarm signals.

7. The system according to claim 5, characterized in that The method of performing machine learning based on the model training samples to obtain a pre-trained fault warning analysis model includes: Use neural network to create fault warning analysis model; Inputting the model training samples into the fault warning analysis model for machine learning, and outputting the model loss value; When the model loss value reaches the minimum, a pre-trained fault warning analysis model is generated; or, when the model loss value does not reach the minimum, the step of inputting the model training sample into the fault warning analysis model for machine learning is continued until the model loss value reaches the minimum; wherein the loss function of the fault warning analysis model is: in, is the model loss value, N is the number of historical warning signals, C is the number of alarm reasons, Indicates Is the historical alarm cause of the alarm signal Class, 1 for yes, 0 for no, The first The warning signal is The probability of the class.

8. A method for monitoring the working process of an on-board charger and its fault early warning analysis implemented by the system according to any one of claims 1 to 7, characterized in that: The method comprises: Acquire environmental data in real time through the vehicle and send it to the host computer; The electrical parameters of the on-board charger are detected in real time by a voltage and power detection device, and sent to the host computer, and an alarm signal is generated and fed back to the host computer when the electrical parameters are abnormal; The environmental data sent by the vehicle and the electrical parameters sent by the voltage and power detection device are received in real time by a host computer, and a ternary mapping relationship among the environmental data, the electrical parameters and the timestamp at the same time is stored; in response to an alarm signal sent by the voltage and power detection device, an alarm time carried by the alarm signal is determined; from the ternary mapping relationship, the original environmental data and the original electrical parameters at each time within a preset period before and after the alarm time are obtained; according to the original environmental data and the original electrical parameters at each time, the alarm cause corresponding to the alarm signal is analyzed to obtain an analysis result.

Images