An intelligent test system for the response time of motor control of new energy vehicles

Abstract

The invention discloses an intelligent test system for the response time of a motor control of a new energy vehicle, and relates to the technical field of motor control of a new energy vehicle. A data acquisition and preprocessing module collects voltage data, current data and electromagnetic data through sensors, and performs normalization preprocessing on the data to ensure the accuracy and consistency of the data. A feature extraction and analysis module extracts key features, current transient response time #imgabs0# and magnetic field change rate #imgabs1#, from the preprocessed data, and further calculates the standard deviation #imgabs2# and mean #imgabs3# of these features to provide basic data for subsequent analysis. By normalizing the filtered data, the differences between different signals are eliminated, and a historical data training module uses the collected fault operation data and non-fault operation data to obtain the response time range #imgabs4# of the fault data set and the response time range #imgabs5# of the non-fault data set, which provides strong support for real-time monitoring and prediction of the system.

Description

Technical Field

[0001] The present invention relates to the technical field of new energy vehicle motor control, and in particular to an intelligent test system for response time of new energy vehicle motor control. Background Art

[0002] Motor control response time is an important indicator of motor performance. It reflects the time required for the motor to reach the target position or speed from the time it receives the command signal. The length of this time depends on factors such as the motor's mechanical structure, control system, and load characteristics. As a commonly used type of motor, the servo motor's speed range and response time are two key performance parameters that determine the servo motor's adjustment ability and speed in the control system.

[0003] In the patent with application publication number CN202210806673.0, a new type of new energy vehicle motor control response time test system is disclosed. By setting a control device that can control the motor during use, it can stably control the start and shutdown, speed increase and decrease, and steering and shifting of the motor. At the same time, it can detect the time interval between when the motor reaches a certain speed, so as to stably detect the time required for the motor to respond.

[0004] However, the functions implemented above cannot fully utilize the multi-dimensional data in the operation of the motor, such as the interaction between electrical and magnetic variables. Due to the lack of comprehensive analysis of these key variables, the existing response time evaluation is prone to inaccuracies, especially when dealing with complex and extreme working conditions. In addition, inadequate evaluation may cause the motor to respond lagging or too fast, resulting in fluctuations in driving experience and even affecting the stability and safety of the vehicle. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides an intelligent testing system for the control response time of a new energy vehicle motor, which solves the problems mentioned in the background technology.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent test system for the control response time of a new energy vehicle motor, including a data acquisition and preprocessing module, a feature extraction and analysis module, a real-time monitoring and prediction module, a historical data training module and an early warning and feedback module;

[0007] The data acquisition and preprocessing module acquires voltage data, current data and electromagnetic data through sensors to form a data group, and preprocesses the data group to obtain a characteristic data group C, including normalization preprocessing;

[0008] The feature extraction and analysis module extracts features from the feature data group C to obtain the current transient response time and the rate of change of magnetic field ; Response time to current transient and the rate of change of magnetic field Analyze and get the standard deviation and mean ;

[0009] The real-time monitoring and prediction module detects the feature data group C through a machine learning model and calculates and predicts the real-time feature vector , and predict the real-time feature vector Make predictions and identify the state of motor control operation; obtain predicted real-time response time ;

[0010] The historical data training module collects and stores operation data, extracts fault operation data and non-fault operation data to form a fault data set and a non-fault data set, and statistically obtains the response time range of the fault data set and the response time range of the non-faulty data set ;

[0011] The early warning and feedback module predicts the real-time response time Conduct judgment and early warning, obtain judgment and early warning evaluation plan, and carry out specific implementation and notification according to the content of the judgment and early warning evaluation plan.

[0012] Preferably, the data acquisition and preprocessing module includes a data acquisition unit and a data processing unit;

[0013] The data acquisition unit collects data in the data group through a sensor, and the frequency of the collection is 10KHz;

[0014] Among them, the sensors include voltage sensors, current sensors and electromagnetic sensors;

[0015] The data processing unit includes noise filtering and normalization processing, wherein the noise filtering uses a filter to remove high-frequency noise and interference in the data group, and the data group after the noise filtering processing is normalized to eliminate magnitude differences;

[0016] Obtain the filtered voltage signal through filtering and normalization , current signal and electromagnetic signals , forming a processed feature data group C;

[0017] The voltage signal , current signal and electromagnetic signals Obtained by the following formula:

[0018] ;

[0019] ;

[0020] ;

[0021] In the formula, Represents the original voltage signal, represents the original current signal, represents the original electromagnetic signal, represents the impulse response function of the filter.

[0022] Preferably, the feature extraction and analysis module includes a feature extraction unit and a feature analysis unit;

[0023] The feature extraction unit extracts the current transient response time from the feature data group C. and the rate of change of magnetic field , current transient response time It indicates the time it takes for the current to rise from the initial value to the steady-state value. It is calculated from the time between 10% and 90% of the response time and is obtained using the following formula:

[0024] ;

[0025] In the formula, Indicates the moment when the current reaches 90% of the steady-state value. Indicates the moment when the current reaches 10% of the steady-state value;

[0026] Magnetic field change rate It reflects the degree of change of the magnetic field of the motor during the dynamic process and is obtained through the following formula:

[0027] ;

[0028] In the formula, Indicates a time interval;

[0029] The feature analysis unit analyzes the correlation of the feature data group C to obtain the mean and standard deviation ;

[0030] The mean Obtained through the following calculation formula:

[0031] ;

[0032] In the formula, N represents the number of sampling points of the signal, Represents a characteristic data set, including voltage signals , current signal and electromagnetic signals ;

[0033] The standard deviation Obtained through the following calculation formula:

[0034] ;

[0035] In the formula, Represents the mean of feature data set C.

[0036] Preferably, the real-time monitoring and prediction module includes a real-time monitoring unit and a prediction unit;

[0037] The real-time monitoring unit reorganizes the feature data group C after feature extraction and feature analysis to obtain a predicted real-time feature vector :

[0038] ;

[0039] In the formula, represents the current transient response time, Reflects the intensity of the change in the magnetic field of the motor during the dynamic process. represents the mean of the feature data set C, Represents the standard deviation of feature data set C.

[0040] Preferably, the prediction unit predicts the real-time feature vector by establishing a machine learning model. Prognostics, identifies the state of motor control operation, and predicts the motor's predicted real-time response time , obtained by the following formula:

[0041] ;

[0042] In the formula, represents the weight value, , Represents the predicted real-time feature vector The nonlinear transformation function is Represents the predicted real-time feature vector The interaction function, n represents the predicted real-time feature vector The number of

[0043] Preferably, the historical data training module includes a historical data collection unit and a data model unit;

[0044] The historical data collection unit and the data model unit investigate, integrate and classify historical data to form a fault data set and a non-fault data set, and integrate and analyze the fault data set and the non-fault data set to obtain the response time range of the fault data set. Response time range for non-faulty data sets , will predict the real-time response time Response time range for fault datasets in historical data and the response time range of the non-faulty data set Compare and judge abnormalities and potential failures.

[0045] Among them, the fault data set includes the time range of transient fluctuations of voltage and current before and after the fault occurs, and the time range of changes in magnetic field strength before and after the fault occurs; the non-fault data set includes the time range of voltage data and current data when the motor is running without fault, and the time range of changes in the electromagnetic field when the motor is running without fault.

[0046] Preferably, the response time range of the fault data set is Obtained by the following formula:

[0047] ;

[0048] In the formula, represents the shortest response time in the fault data set, represents the longest response time among the response times in the fault dataset;

[0049] , extract the minimum response time from the fault dataset;

[0050] , extract the maximum response time from the fault dataset.

[0051] Preferably, the response time range of the non-fault data set is Obtained by the following formula:

[0052] ;

[0053] In the formula, represents the shortest response time in the non-faulty data set, represents the longest response time among the response times in the non-faulty data set;

[0054] , extract the minimum response time from the non-faulty data set;

[0055] , extract the maximum response time from the non-faulty dataset.

[0056] Preferably, the early warning and feedback module includes an early warning comparison unit and a feedback unit;

[0057] The early warning comparison unit predicts the real-time response time Compare the results with the historical response time to determine the abnormal situation:

[0058] If you predict real-time response time In response time range If the alarm is within the range of 1000, no alarm will be issued;

[0059] If you predict real-time response time In response time range If the alarm is triggered, the feedback module will adjust the next test parameters or stop the test according to the alarm.

[0060] Preferably, after triggering the warning, the feedback unit records detailed information of the warning event, including the warning time and the predicted real-time response time. and feed the information back to the system database.

[0061] The present invention provides an intelligent test system for the control response time of a new energy vehicle motor, which has the following beneficial effects:

[0062] (1) When the system is running, the coordinated work of the five modules realizes comprehensive monitoring, analysis and prediction of the motor control response time. The data acquisition and preprocessing module collects voltage data, current data and electromagnetic data in real time through sensors, and normalizes and preprocesses the data to ensure the accuracy and consistency of the data. The feature extraction and analysis module extracts key features from the preprocessed data, and the current transient response time and the rate of change of magnetic field , and further calculate the standard deviation of the feature and mean , providing basic data for subsequent analysis. The historical data training module uses the collected fault operation data and non-fault operation data to train the machine learning model and obtain the response time range of the fault data set. and the response time range of the non-faulty data set , which provides strong support for the real-time monitoring and prediction of the system.

[0063] (2) Use filters to filter the collected data to remove high-frequency noise and electromagnetic interference. This improvement effectively improves data quality and ensures that the system can still obtain reliable signals in complex electromagnetic environments. By normalizing the filtered data, the magnitude differences between different signals are eliminated, allowing voltage, current and electromagnetic signals to be analyzed and compared within the same numerical range.

[0064] (3) By calculating the standard deviation of the signal and mean , the system can quantify the performance of the motor under stable conditions. These statistical features not only help identify abnormal fluctuations, but also provide key inputs for subsequent fault prediction models. The design of this embodiment enables the system to complete the entire process of data collection, feature extraction and analysis, simplifying the operation process while improving the consistency and accuracy of the analysis. This integrated functional implementation helps to improve the efficiency and reliability of the system. The system can accurately judge the operating status of the motor under different working conditions, warn of potential faults in real time, and adjust the test parameters in time through an automated feedback mechanism to ensure the stable operation of the motor.

[0065] (4) Through real-time collection and intelligent analysis of multi-dimensional data, the system can more accurately evaluate the response time of the motor and maintain efficient performance under complex working conditions; the introduction of machine learning models enables the system to have the ability of self-learning and self-optimization, which can continuously improve the accuracy of prediction and response speed. This intelligent testing system significantly improves the safety and stability of motor control, optimizes the driving experience, and provides a solid guarantee for the efficient operation of new energy vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 This is a schematic diagram of the flow chart of an intelligent testing system for the control response time of a new energy vehicle motor according to the present invention. DETAILED DESCRIPTION

[0067] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0068] Example 1

[0069] The present invention provides an intelligent test system for the control response time of a new energy vehicle motor. Figure 1 , including data collection and preprocessing module, feature extraction and analysis module, real-time monitoring and prediction module, historical data training module and early warning and feedback module;

[0070] The data acquisition and preprocessing module acquires voltage data, current data and electromagnetic data through sensors to form a data group, and preprocesses the data group to obtain a characteristic data group C, including normalization preprocessing;

[0071] The feature extraction and analysis module extracts features from the feature data group C to obtain the current transient response time and the rate of change of magnetic field ; Response time to current transient and the rate of change of magnetic field Analyze and get the standard deviation and mean ;

[0072] The real-time monitoring and prediction module detects the feature data group C through a machine learning model and calculates and predicts the real-time feature vector , and predict the real-time feature vector Make predictions and identify the state of motor control operation; obtain predicted real-time response time ;

[0073] The historical data training module collects and stores operation data, extracts fault operation data and non-fault operation data to form a fault data set and a non-fault data set, and statistically obtains the response time range of the fault data set and the response time range of the non-faulty data set ;

[0074] The early warning and feedback module predicts the real-time response time Conduct judgment and early warning, obtain judgment and early warning evaluation plan, and carry out specific implementation and notification according to the content of the judgment and early warning evaluation plan.

[0075] In this embodiment, the coordinated work of five modules realizes comprehensive monitoring, analysis and prediction of the motor control response time. First, the data acquisition and preprocessing module collects voltage data, current data and electromagnetic data in real time through sensors, and normalizes and preprocesses the data to ensure the accuracy and consistency of the data. Then, the feature extraction and analysis module extracts key features from the preprocessed data, and the current transient response time is calculated. and the rate of change of magnetic field , and further calculate the standard deviation of the feature and mean , providing basic data for subsequent analysis. The historical data training module uses the collected fault operation data and non-fault operation data to train the machine learning model and obtain the response time range of the fault data set. and the response time range of the non-faulty data set , which provides strong support for the real-time monitoring and prediction of the system.

[0076] Example 2

[0077] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the data acquisition and preprocessing module includes a data acquisition unit and a data processing unit;

[0078] The data acquisition and preprocessing module includes a data acquisition unit and a data processing unit;

[0079] The data acquisition unit collects data in the data group through a sensor, and the frequency of the collection is 10KHz;

[0080] Among them, the sensors include voltage sensors, current sensors and electromagnetic sensors;

[0081] The data processing unit includes noise filtering and normalization processing, wherein the noise filtering uses a filter to remove high-frequency noise and interference in the data group, and the data group after the noise filtering processing is normalized to eliminate magnitude differences;

[0082] Obtain the filtered voltage signal through filtering and normalization , current signal and electromagnetic signals , forming a processed feature data group C;

[0083] The voltage signal , current signal and electromagnetic signals Obtained by the following formula:

[0084] ;

[0085] ;

[0086] ;

[0087] In the formula, Represents the original voltage signal, represents the original current signal, represents the original electromagnetic signal, represents the impulse response function of the filter.

[0088] In this embodiment, the voltage, current and electromagnetic data are collected at a high frequency of 10KHz by sensors, ensuring detailed monitoring of the motor operation status. Compared with the traditional system with a lower sampling frequency, this embodiment can capture transient changes during the operation of the motor and provide higher signal resolution, thereby improving the accuracy of the data and the response speed of the system; the collected data is filtered by a filter to remove high-frequency noise and electromagnetic interference. This improvement effectively improves the data quality and ensures that the system can still obtain reliable signals in a complex electromagnetic environment. By normalizing the filtered data, the magnitude differences between different signals are eliminated, so that the voltage, current and electromagnetic signals can be analyzed and compared within the same numerical range. This improvement makes the subsequent data analysis more intuitive and consistent, avoids calculation errors caused by different magnitudes, and thus improves the overall stability and analysis accuracy of the system.

[0089] Example 3

[0090] This embodiment is explained in Example 2. Please refer to Figure 1 ,Specifically: the feature extraction and analysis module includes a feature extraction unit and a feature analysis unit;

[0091] The feature extraction unit extracts the current transient response time from the feature data group C. and the rate of change of magnetic field , current transient response time It indicates the time it takes for the current to rise from the initial value to the steady-state value. It is calculated from the time between 10% and 90% of the response time and is obtained using the following formula:

[0092] ;

[0093] In the formula, Indicates the moment when the current reaches 90% of the steady-state value. Indicates the moment when the current reaches 10% of the steady-state value;

[0094] Magnetic field change rate It reflects the degree of change of the magnetic field of the motor during the dynamic process and is obtained through the following formula:

[0095] ;

[0096] In the formula, Indicates a time interval;

[0097] The feature analysis unit analyzes the correlation of the feature data group C to obtain the mean and standard deviation ;

[0098] The mean Obtained through the following calculation formula:

[0099] ;

[0100] Where N is the number of sampling points of the signal. Represents a characteristic data set, including voltage signals , current signal and electromagnetic signals ;

[0101] The standard deviation Obtained through the following calculation formula:

[0102] ;

[0103] In the formula, Represents the mean of feature data set C.

[0104] In this embodiment, through high-frequency acquisition and accurate feature extraction, this embodiment can monitor the transient response of the motor in real time. and the rate of change of magnetic field This process relies on high-precision data collection and processing to ensure that the system can capture subtle motor dynamic changes and provide more sensitive indicators for fault detection. and standard deviation , the system can quantify the performance of the motor under stable working conditions. These statistical features not only help identify abnormal fluctuations, but also provide key inputs for subsequent fault prediction models. The design of this embodiment enables the system to complete the entire process of data collection, feature extraction and analysis, simplifies the operation process, and improves the consistency and accuracy of the analysis. This integrated functional implementation helps to improve the efficiency and reliability of the system.

[0105] Example 4

[0106] This embodiment is explained in Example 3, please refer to Figure 1 ,Specifically: the real-time monitoring and prediction module includes a real-time monitoring unit and a prediction unit;

[0107] The real-time monitoring unit reorganizes the feature data group C after feature extraction and feature analysis to obtain a predicted real-time feature vector :

[0108] ;

[0109] In the formula, represents the current transient response time, Reflects the intensity of the change in the magnetic field of the motor during the dynamic process. represents the mean of the feature data set C, Represents the standard deviation of feature data set C.

[0110] Specific, Indicates voltage signal , current signal and electromagnetic signals The mean of Indicates voltage signal , current signal and electromagnetic signals The standard deviation of .

[0111] The prediction unit predicts the real-time feature vector by establishing a machine learning model. Prognostics, identifies the state of motor control operation, and predicts the motor's predicted real-time response time , obtained by the following formula:

[0112] ;

[0113] In the formula, represents the weight value, , Represents the predicted real-time feature vector The nonlinear transformation function is Represents the predicted real-time feature vector The interaction function, n represents the predicted real-time feature vector The number of

[0114] The historical data training module includes a historical data collection unit and a data model unit;

[0115] The historical data collection unit and the data model unit investigate, integrate and classify historical data to form a fault data set and a non-fault data set, and integrate and analyze the fault data set and the non-fault data set to obtain the response time range of the fault data set. Response time range for non-faulty data sets , will predict the real-time response time Response time range for fault datasets in historical data and the response time range of the non-faulty data set Compare and judge abnormalities and potential failures.

[0116] The specific, historical data collection unit systematically constructs fault data sets and non-fault data sets by investigating, integrating and classifying a large amount of historical data. This systematic data management method ensures the integrity and accuracy of the data, making data analysis more in-depth.

[0117] By integrating and analyzing the fault data set and the non-fault data set, the system can derive the response time range of the fault data set. and the response time range of the non-faulty data set , providing more accurate training data for machine learning models. This data-driven approach greatly improves the learning efficiency and prediction accuracy of the model.

[0118] Example 5

[0119] An intelligent test system for the response time of motor control of new energy vehicles, please refer to Figure 1 , specifically: the response time range of the fault data set Obtained by the following formula:

[0120] ;

[0121] In the formula, represents the shortest response time in the fault data set, represents the longest response time among the response times in the fault dataset;

[0122] , extract the minimum response time from the fault dataset;

[0123] , extract the maximum response time from the fault dataset.

[0124] The response time range of the non-faulty data set Obtained by the following formula:

[0125] ;

[0126] In the formula, represents the shortest response time in the non-faulty data set, represents the longest response time among the response times in the non-faulty data set;

[0127] , extract the minimum response time from the non-faulty data set;

[0128] , extract the maximum response time from the non-faulty dataset.

[0129] Specifically, by explicitly calculating the response time range of the fault data set and the non-fault data set, the minimum and maximum response times are extracted from the historical data using formulas to determine the response time range under fault and non-fault conditions, respectively. This precise range definition provides a reliable benchmark for subsequent real-time monitoring and abnormal judgment of the system.

[0130] By defining the response time range, the system can more accurately determine the motor's operating status and avoid false alarms or missed alarms. This precise monitoring method improves the system's reliability and effectiveness in practical applications, ensuring that correct judgments can be made under different working conditions.

[0131] The early warning and feedback module includes an early warning comparison unit and a feedback unit;

[0132] The early warning comparison unit predicts the real-time response time Compare the results with the historical response time to determine the abnormal situation:

[0133] If you predict real-time response time In response time range If the alarm is within the range of 1000, no alarm will be issued;

[0134] If you predict real-time response time In response time range If the alarm is triggered, the feedback module will adjust the next test parameters or stop the test according to the alarm.

[0135] Specifically, the operator can be informed of the abnormal state of the motor at the first time and take timely countermeasures, thereby reducing the potential safety hazards or equipment damage caused by motor failure. This real-time early warning mechanism makes the system more efficient and proactive in fault detection.

[0136] After the warning is triggered, the feedback unit records the detailed information of the warning event, including the warning time and the predicted real-time response time. and feed the information back to the system database.

[0137] In this embodiment, high-frequency data collection and real-time monitoring are used to achieve rapid response and high-precision analysis of the motor's operating status. This not only significantly improves the system's real-time performance and prediction accuracy, but also ensures that potential anomalies can be detected at an early stage. The system combines historical data and real-time data and uses machine learning models for intelligent analysis and prediction. This data-driven approach not only improves the accuracy of fault detection, but also continuously optimizes the system's judgment ability through continuous learning and model updating.

[0138] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent test system for the control response time of a new energy vehicle motor, characterized in that: It includes data collection and preprocessing module, feature extraction and analysis module, real-time monitoring and prediction module, historical data training module and early warning and feedback module; The data acquisition and preprocessing module acquires voltage data, current data and electromagnetic data through sensors to form a data group, and preprocesses the data group to obtain a characteristic data group C, including normalization preprocessing; The data acquisition and preprocessing module includes a data acquisition unit and a data processing unit; The data acquisition unit collects data in the data group through a sensor, and the frequency of the collection is 10KHz; Among them, the sensors include voltage sensors, current sensors and electromagnetic sensors; The data processing unit includes noise filtering and normalization processing, wherein the noise filtering uses a filter to remove high-frequency noise and interference in the data group, and the data group after the noise filtering processing is normalized to eliminate magnitude differences; Obtain the filtered voltage signal through filtering and normalization , current signal and electromagnetic signals , forming a processed feature data group C; The voltage signal , current signal and electromagnetic signals Obtained by the following formula: ； ； ； In the formula, Represents the original voltage signal, represents the original current signal, represents the original electromagnetic signal, represents the impulse response function of the filter; The feature extraction and analysis module extracts features from the feature data group C to obtain the current transient response time and the rate of change of magnetic field ; Response time to current transient and the rate of change of magnetic field Analyze and get the standard deviation and mean ; The feature extraction and analysis module includes a feature extraction unit and a feature analysis unit; The feature extraction unit extracts the current transient response time from the feature data group C. and the rate of change of magnetic field , current transient response time It indicates the time it takes for the current to rise from the initial value to the steady-state value. It is calculated from the time between 10% and 90% of the response time and is obtained using the following formula: ； In the formula, Indicates the moment when the current reaches 90% of the steady-state value. Indicates the moment when the current reaches 10% of the steady-state value; Magnetic field change rate It reflects the degree of change of the magnetic field of the motor during the dynamic process and is obtained through the following formula: ； In the formula, Indicates a time interval; The feature analysis unit analyzes the correlation of the feature data group C to obtain the mean and standard deviation ; The mean Obtained through the following calculation formula: ； In the formula, N represents the number of sampling points of the signal, Represents a characteristic data set, including voltage signals , current signal and electromagnetic signals ; The standard deviation Obtained through the following calculation formula: ； In the formula, represents the mean of feature data set C; The real-time monitoring and prediction module detects the feature data group C through a machine learning model and calculates and predicts the real-time feature vector , and predict the real-time feature vector Make predictions and identify the state of motor control operation; obtain predicted real-time response time ; The real-time monitoring and prediction module includes a real-time monitoring unit and a prediction unit; The real-time monitoring unit reorganizes the feature data group C after feature extraction and feature analysis to obtain a predicted real-time feature vector : ； In the formula, represents the current transient response time, Reflects the intensity of the change in the magnetic field of the motor during the dynamic process. represents the mean of the feature data set C, represents the standard deviation of the feature data set C; The prediction unit predicts the real-time feature vector by establishing a machine learning model. Prognostics, identifies the state of motor control operation, and predicts the motor's predicted real-time response time , obtained by the following formula: ； In the formula, represents the weight value, , Represents the predicted real-time feature vector The nonlinear transformation function is Represents the predicted real-time feature vector The interaction function, n represents the predicted real-time feature vector the number of The historical data training module collects and stores operation data, extracts fault operation data and non-fault operation data to form a fault data set and a non-fault data set, and statistically obtains the response time range of the fault data set and the response time range of the non-faulty data set ; The early warning and feedback module predicts the real-time response time Conduct judgment and early warning, obtain judgment and early warning evaluation plan, and carry out specific implementation and notification according to the content of the judgment and early warning evaluation plan.

2. According to claim 1, a new energy vehicle motor control response time intelligent test system is characterized by: The historical data training module includes a historical data collection unit and a data model unit; The historical data collection unit and the data model unit investigate, integrate and classify historical data to form a fault data set and a non-fault data set, and integrate and analyze the fault data set and the non-fault data set to obtain the response time range of the fault data set. Response time range for non-faulty data sets , will predict the real-time response time Response time range for the fault dataset in historical data and the response time range of the non-faulty data set Compare and judge abnormalities and potential failures.

3. According to claim 2, a new energy vehicle motor control response time intelligent test system is characterized in that: The response time range of the fault data set Obtained by the following formula: ； In the formula, represents the shortest response time in the fault data set, represents the longest response time among the response times in the fault dataset; , extract the minimum response time from the fault dataset; , extract the maximum response time from the fault dataset.

4. According to claim 2, a new energy vehicle motor control response time intelligent test system is characterized by: The response time range of the non-faulty data set Obtained by the following formula: ； In the formula, represents the shortest response time in the non-faulty data set, represents the longest response time among the response times in the non-faulty data set; , extract the minimum response time from the non-faulty data set; , extract the maximum response time from the non-faulty dataset.

5. According to claim 1, a new energy vehicle motor control response time intelligent test system is characterized by: The early warning and feedback module includes an early warning comparison unit and a feedback unit; The early warning comparison unit predicts the real-time response time Compare the results with the historical response time to determine the abnormal situation: If you predict real-time response time In response time range If the alarm is within the range of 1000, no alarm will be issued; If you predict real-time response time In response time range If the alarm is triggered, the feedback module will adjust the next test parameters or stop the test according to the alarm.

6. The intelligent test system for the control response time of a new energy vehicle motor according to claim 5 is characterized in that: After the warning is triggered, the feedback unit records the detailed information of the warning event, including the warning time and the predicted real-time response time. and feed the information back to the system database.

Images