Fault handling method and system for automobile motor drive system

By monitoring and analyzing the voltage and temperature difference data of the battery cells in the automotive motor drive system in real time, and evaluating the status equalization index using a fault prediction model, the problems of passiveness in fault processing and difficulty in analyzing the status difference of battery cells in the prior art are solved, and the problem of passiveness in fault processing and difficulty in analyzing the status difference of battery cells is realized. The efficient monitoring and preventive maintenance of the battery system improve the stability and user experience of the system.

CN118528791BActive Publication Date: 2024-11-29深圳市杰恒芯科技有限公司
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202410765966.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-06-14
Publication Date
2024-11-29
Estimated Expiration
2044-06-14

AI Technical Summary

Technical Problem

The fault handling methods of existing automotive motor drive systems lack the ability to monitor and predict the battery system status in a timely manner, resulting in failures that may only be discovered after occurrence or deterioration, increasing maintenance costs and risks, and it is difficult to carefully analyze the status differences between battery cells. , affects system performance and lifespan.

Method used

By monitoring the voltage conditions of each battery cell in the battery compartment in real time, calculating the voltage deviation coefficient, combining temperature differences and self-discharge data, the state equalization index is obtained using the trained fault prediction model to achieve prediction and evaluation of the state between the battery cells, and According to the evaluation results, it will be processed accordingly, including fault warning and preventive maintenance.

Benefits of technology

It realizes timely early warning and rapid response to potential faults, improves the reliability and performance of the system, reduces maintenance costs and risks, and improves user trust and driving experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118528791B_ABST
    Figure CN118528791B_ABST
Patent Text Reader

Abstract

The present invention discloses a fault handling method and system for an automobile motor drive system, which relates to the technical field of automobile faults. By real-time monitoring of the voltage conditions of each battery cell in the battery compartment, the voltage deviation between the battery cells can be discovered in time. Once the voltage deviation exceeds the set threshold, a fault monitoring command can be issued to the outside to achieve early warning and rapid response to potential faults. After receiving the corresponding command, the temperature difference data and self-discharge data of each battery cell in the automobile are monitored to construct a fault monitoring set, so that the working state of the battery cell can be fully understood and potential faults or abnormal conditions can be discovered. After preprocessing, feature extraction and training of the relevant data information in the fault monitoring set, the temperature difference variation coefficient Wbxs and the self-discharge fluctuation coefficient Zbxs are calculated and obtained, and the state balance index Zjzs is obtained by fitting, so that the state balance degree between the battery cells can be predicted and evaluated, providing a scientific basis for fault handling.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of automobile failures, and in particular to a failure processing method and system for an automobile motor drive system. Background Art

[0002] In the field of modern science and technology, electric vehicles, as a clean and efficient means of transportation, are gradually becoming the mainstream trend of the automotive industry. As one of the core components of electric vehicles, the stable operation of the automotive motor drive system directly affects the performance and safety of the vehicle. Specifically, the automotive motor drive system refers to a system that converts electrical energy into mechanical energy through an electric motor to drive the vehicle. In this system, the battery is a crucial component, which provides the electrical energy required to drive the motor. The capacity and charge and discharge performance of the battery cell directly affect the vehicle's cruising range and power performance. When the automotive motor drive system receives the electrical energy provided by the battery cell, it converts it into mechanical energy to drive the vehicle.

[0003] In a Chinese invention patent with application publication number CN116539980A, a method for analyzing overcurrent faults in an electric drive system is disclosed, including: determining whether an overcurrent fault occurs in the d-axis current and the q-axis current of the electric drive system; in the case where an overcurrent fault occurs in the d-axis current or the q-axis current of the electric drive system, judging whether a software fault occurs in the current electric drive system; in the case where a software fault occurs in the electric drive system, judging whether a current current loop control parameter is abnormal.

[0004] In the technical solutions recorded in the above applications, on the one hand, key fault information can be better obtained, and more efficient analysis of occasional overcurrent problems in motor controllers can be achieved. On the other hand, it does not occupy more resources, which improves the efficiency of fault analysis. However, in combination with the existing technology and the above applications, there are still some defects and deficiencies in the current monitoring and fault handling of automotive batteries. Traditional fault handling methods can often only be handled passively after the fault occurs, and lack the ability to monitor and predict the status of the battery system in a timely manner. This leads to the fact that in some cases, the fault may have occurred or worsened before it can be discovered and handled in time, increasing the maintenance cost and risk of the vehicle. Secondly, the traditional method of realizing simple monitoring of the overall state of the battery has been fully analyzed, and the state differences between each battery cell still need further detailed analysis, because when there are obvious inconsistent changes between the battery cells, unbalanced charging and discharging problems may occur during the operation of the battery, thereby affecting the performance and life of the entire battery system, which makes it difficult for the existing optimization methods to play a practical role. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides a fault handling method and system for an automobile motor drive system, which solves the problems in the above-mentioned background technology.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: A method for troubleshooting a motor drive system of an automobile comprises the following steps:

[0007] S1. Obtain the battery compartment status in the automobile motor drive system in advance, build a battery operation platform, monitor the voltage of each battery unit in the battery compartment to obtain the voltage deviation set between the battery cells, generate the voltage deviation coefficient Dpxs based on the voltage deviation set between the battery cells, and issue a fault monitoring command if the voltage deviation coefficient Dpxs exceeds the deviation threshold;

[0008] S2. After receiving the fault monitoring command, analyze whether the voltage and current distribution of the battery cell during the charging and discharging process is uneven, monitor the temperature difference data and self-discharge data of each battery cell in the car, and build a fault monitoring set;

[0009] S3, preprocessing the relevant data information in the fault monitoring set, and performing feature extraction to respectively obtain the temperature value Wz of each battery cell, the thermal conductivity Rdc between battery cells, and the self-discharge rate Zfz in each battery cell during the monitoring period, and calculating and obtaining the temperature difference variation coefficient Wbxs and the self-discharge fluctuation coefficient Zbxs through the trained fault prediction model, and obtaining the state equilibrium index Zjzs by fitting by associating the temperature difference variation coefficient Wbxs with the self-discharge fluctuation coefficient Zbxs;

[0010] S4. Preset an evaluation threshold value P, and compare and analyze it with the state balance index Zjzs, comprehensively judge the working state of each battery unit in the current automobile motor drive system, and make corresponding processing measures.

[0011] Preferably, several groups of monitoring equipment are used to continuously monitor the voltage of each battery cell in the battery compartment, and the voltage of each battery cell in the battery compartment is monitored and compared to obtain a set of voltage deviations between battery cells, and then the set of voltage deviations between battery cells is transmitted to the battery operation status platform in real time, wherein the set of voltage deviations between battery cells includes the voltage value Dy of each battery cell at each time node in the monitoring period, and the maximum value of the voltage value Dy at each time node and the voltage mean value in the monitoring period are obtained. , and based on the voltage average value during the monitoring period , calculate and obtain the voltage standard deviation Dbc within the monitoring period.

[0012] Preferably, the voltage mean value within the monitoring period is calculated based on the voltage deviation set between the cells. The voltage standard deviation Dbc is dimensionless, and the voltage deviation coefficient Dpxs is calculated as follows:

[0013]

[0014] The significance of this formula is to: evaluate the relative strength of the voltage fluctuation differences of each battery cell in the car;

[0015] At the same time, a deviation threshold is preset, and the deviation threshold is compared and analyzed with the voltage deviation coefficient Dpxs. The specific contents are as follows:

[0016] If the voltage deviation coefficient Dpxs exceeds the deviation threshold, a fault monitoring command will be issued externally;

[0017] If the voltage deviation coefficient Dpxs does not exceed the deviation threshold, no fault monitoring command will be issued temporarily.

[0018] Preferably, after receiving the fault monitoring command from step S1, the fault monitoring mode is turned on and entered, and the voltage and current distribution of each battery cell during the charging and discharging process is analyzed to determine whether there is an uneven phenomenon; in the fault monitoring mode, the temperature difference data and self-discharge data of each battery cell in the car are monitored respectively to construct a fault monitoring set;

[0019] The temperature difference data of each battery cell in the vehicle includes the temperature value Wz of each battery cell and the thermal conductivity Rdc between battery cells during the monitoring period;

[0020] The self-discharge data includes the self-discharge rate Zfz of each battery cell at different monitoring time nodes, and the self-discharge rate Zfz of each battery cell at the same monitoring time node is differentially analyzed to obtain the self-discharge rate difference value of the corresponding monitoring time node.

[0021] Preferably, a convolutional neural network is used to construct a basic model, and the basic model is trained and tested using the temperature difference data and self-discharge data of each battery cell in the car. At the same time, the trained basic model is used as a fault recognition model, and the feature information therein is obtained. The fault recognition model is trained and tested using the acquired feature information, and the trained fault recognition model is used as a fault prediction model in combination with the fault monitoring command triggered in the battery operation platform.

[0022] Preferably, the trained fault prediction model is used to perform fault prediction on the temperature fluctuation of the vehicle drive battery and the battery self-discharge difference, respectively, to obtain the temperature difference variation coefficient Wbxs and the self-discharge fluctuation coefficient Zbxs, wherein the temperature difference variation coefficient Wbxs is obtained by the following formula:

[0023]

[0024] The significance of this formula is to describe the difference in temperature rate change between battery cells; where k represents the number of monitoring time nodes, i=1, 2, 3, ..., k, It is represented as the temperature value of the jth battery cell at the i+1th time node; It is represented as the temperature value of the jth battery cell at the i-th time node; R is represented as the first correction constant; Expressed as the thermal conductivity between the jth battery cell and the nth battery cell, It is represented by the temperature value of the j+nth battery cell at the i+1th time node; It is represented by the temperature value of the j+nth battery cell at the i-th time node.

[0025] When the temperature difference variation coefficient Wbxs exceeds the control threshold, the battery operation platform will simultaneously send a temperature abnormality voice prompt to the user terminal and the corresponding repair shop, requiring targeted monitoring and maintenance measures for the car battery.

[0026] Preferably, the self-release fluctuation coefficient Zbxs is obtained by the following formula:

[0027]

[0028] In the formula, They are respectively represented as the maximum and minimum values ​​of the self-discharge rate of the battery cell at the i-th time node, It is expressed as the average value of the self-discharge rate of the battery cells during the monitoring period.

[0029] Preferably, by correlating the temperature difference variation coefficient Wbxs with the self-release fluctuation coefficient Zbxs, a state equilibrium index Zjzs is obtained by fitting, and the state equilibrium index Zjzs is obtained by the following formula:

[0030]

[0031] Wherein, Nz represents the internal resistance value, and V represents the second correction constant.

[0032] Preferably, the state balance index Zjzs is compared and analyzed with the evaluation threshold value P, the working state of each battery unit in the current automobile motor drive system is comprehensively judged, and corresponding processing measures are taken:

[0033] When the state balance index Zjzs is greater than the evaluation threshold value P, it indicates that the working state of the battery cells of the current vehicle is normal, and the current monitoring state is continued while maintaining normal operation;

[0034] When the state balance index Zjzs is equal to the evaluation threshold P, it means that the working state of the battery cells of the current vehicle has reached the standard of the evaluation threshold, and preventive measures will be taken at this time, including increasing the monitoring frequency and optimizing the SOC control strategy;

[0035] When the state balance index Zjzs is less than the evaluation threshold value P, it means that the current working state of each battery unit is lower than the expected level and an abnormal state exists. At this time, an alarm notification will be issued to the user terminal and the corresponding repair shop, notifying the user to go to the corresponding repair shop within the specified time period for fault diagnosis and repair. According to the diagnosis results, corresponding repair measures are taken, including adjusting the battery charge and discharge control strategy and replacing the faulty battery unit to restore the stability of the system and normal working state.

[0036] A fault handling system for an automobile motor drive system, comprising a preliminary monitoring module, a preliminary analysis module, a fault monitoring module, a fault analysis module and a processing module;

[0037] The preliminary monitoring module is used to obtain the battery compartment status in the automobile motor drive system in advance, and to build a battery operation platform to monitor the voltage of each battery unit in the battery compartment to obtain a voltage deviation set between battery cells;

[0038] The preliminary analysis module is used to generate a voltage deviation coefficient Dpxs according to the voltage deviation set between the cells, and if the voltage deviation coefficient Dpxs exceeds the deviation threshold, a fault monitoring command is issued externally;

[0039] The fault monitoring module is used to analyze whether the voltage and current distribution of the battery unit during the charging and discharging process is uneven after receiving the fault monitoring command, monitor the temperature difference data and self-discharge data of each battery unit in the car, and build a fault monitoring set;

[0040] The fault analysis module is used to pre-process the relevant data information in the fault monitoring set and perform feature extraction to respectively obtain the temperature value Wz of each battery cell, the thermal conductivity Rdc between battery cells and the self-discharge rate Zfz in each battery cell during the monitoring period, and calculate the temperature difference variation coefficient Wbxs and the self-discharge fluctuation coefficient Zbxs through the trained fault prediction model, and obtain the state equilibrium index Zjzs by fitting by associating the temperature difference variation coefficient Wbxs with the self-discharge fluctuation coefficient Zbxs;

[0041] The processing module is used to pre-set an evaluation threshold value P, and compare and analyze it with the state balance index Zjzs, comprehensively judge the working state of each battery unit in the current automobile motor drive system, and make corresponding processing measures.

[0042] The present invention provides a method and system for handling a fault of an automobile motor drive system, which has the following beneficial effects:

[0043] (1) By real-time monitoring of the voltage of each battery cell in the battery compartment, the voltage deviation between cells can be discovered in time. Once the voltage deviation exceeds the set threshold, a fault monitoring command can be issued to the outside to achieve early warning and rapid response to potential faults. After receiving the corresponding command, the temperature difference data and self-discharge data of each battery cell in the car are monitored to build a fault monitoring set. In this way, the working state of the battery cell can be fully understood and potential faults or abnormal conditions can be discovered. After preprocessing, feature extraction and training of the relevant data information in the fault monitoring set, the temperature difference variation coefficient Wbxs and the self-discharge fluctuation coefficient Zbxs are calculated and fitted to obtain the state balance index Zjzs. In this way, the state balance degree between battery cells can be predicted and evaluated, providing a scientific basis for fault handling. The evaluation threshold is set in advance and compared with the state balance index to comprehensively judge the working state degree between each battery cell in the current automobile motor drive system. According to the evaluation results, corresponding fault handling measures can be formulated, which further realizes the comprehensive optimization and management of the battery system state and improves the reliability and performance of the system. Through functions such as real-time monitoring and early warning, fault prediction and evaluation, users' trust and sense of security in the automotive motor drive system can be enhanced, improving their overall driving experience.

[0044] (2) Continuously monitoring the voltage of battery cells can capture the working status of the battery system in real time and promptly detect voltage deviations between battery cells. This helps to issue fault monitoring commands in a timely manner and provide early warning of potential battery failures or abnormal conditions to ensure the stable and safe operation of the vehicle's motor drive system.

[0045] (3) Through dynamic status assessment and intelligent preventive maintenance measures, the system ensures the stability and reliability of the battery system, while improving the user experience and trust. The system's adaptability and flexibility enable it to make corresponding treatment measures in a timely manner according to actual conditions, effectively prevent the occurrence of potential faults, and provide timely alarm notifications and automatic diagnosis and repair functions when faults occur, thereby minimizing the user's maintenance costs and risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A schematic diagram of the steps of a method for troubleshooting a motor drive system of an automobile according to the present invention;

[0047] Figure 2 The figure is a flow chart of a fault handling system of an automobile motor drive system of the present invention. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] Example 1

[0050] See also Figure 1 The present invention provides a method for troubleshooting a motor drive system of an automobile, comprising the following steps:

[0051] S1. Obtain the battery compartment status in the automobile motor drive system in advance, build a battery operation platform, monitor the voltage of each battery unit in the battery compartment to obtain the voltage deviation set between the battery cells, generate the voltage deviation coefficient Dpxs based on the voltage deviation set between the battery cells, and issue a fault monitoring command if the voltage deviation coefficient Dpxs exceeds the deviation threshold;

[0052] S2. After receiving the fault monitoring command, analyze whether the voltage and current distribution of the battery cell during the charging and discharging process is uneven, monitor the temperature difference data and self-discharge data of each battery cell in the car, and build a fault monitoring set;

[0053] S3, preprocessing the relevant data information in the fault monitoring set, and performing feature extraction to respectively obtain the temperature value Wz of each battery cell, the thermal conductivity Rdc between battery cells, and the self-discharge rate Zfz in each battery cell during the monitoring period, and calculating and obtaining the temperature difference variation coefficient Wbxs and the self-discharge fluctuation coefficient Zbxs through the trained fault prediction model, and obtaining the state equilibrium index Zjzs by fitting by associating the temperature difference variation coefficient Wbxs with the self-discharge fluctuation coefficient Zbxs;

[0054] S4. Preset an evaluation threshold value P, and compare and analyze it with the state balance index Zjzs, comprehensively judge the working state of each battery unit in the current automobile motor drive system, and make corresponding processing measures.

[0055] In this embodiment, by obtaining the battery compartment status in the automobile motor drive system in advance and building a battery operation platform, the voltage conditions of each battery cell in the battery compartment are monitored in real time, so that the voltage deviation between the battery cells can be discovered in time, and the voltage deviation coefficient Dpxs can be generated, so as to warn of potential fault problems in advance. By analyzing the voltage and current distribution of the battery cell during the charging and discharging process, monitoring temperature difference data and self-discharge data and other information, a fault monitoring set is constructed, so that the working status of the battery cell can be fully understood, and the accuracy and reliability of monitoring system faults can be further improved; by preprocessing and feature extraction of relevant data information in the fault monitoring set, and through the trained fault prediction model, the temperature difference variation coefficient Wbxs and the self-discharge fluctuation coefficient Zbxs are calculated, so that more representative and distinguishing features can be extracted for further fault diagnosis and prediction; the state equilibrium index Zjzs is obtained by fitting. The evaluation threshold P is set in advance, and compared with the state balance index Zjzs, to comprehensively judge the working state of each battery unit in the current automobile motor drive system, so that the imbalance or fault of the system can be discovered in time, and corresponding processing measures can be taken to ensure the stability and reliability of the system. In summary, this fault handling method further improves the monitoring and judgment capabilities of the working state of the battery unit in the automobile motor drive system through multi-faceted data acquisition, analysis and evaluation, which helps to timely discover and handle potential fault problems, thereby improving the safety and stability of the system.

[0056] Example 2

[0057] Please refer to Figure 1 Specifically: use several groups of monitoring equipment to continuously monitor the voltage of each battery cell in the battery compartment, monitor and compare the voltage of each battery cell in the battery compartment to obtain a set of voltage deviations between battery cells, and then transmit the set of voltage deviations between battery cells to the battery operation status platform in real time, wherein the set of voltage deviations between battery cells includes the voltage value Dy of each battery cell at each time node in the monitoring period, and obtains the maximum value of the voltage value Dy at each time node and the voltage average value in the monitoring period , and based on the voltage average value during the monitoring period , calculate and obtain the voltage standard deviation Dbc within the monitoring period.

[0058] The voltage standard deviation Dbc is obtained by the following formula:

[0059] ;

[0060] in, , ,..., It is represented by the voltage value in the first monitoring time node, the voltage value in the second monitoring time node, ..., the voltage value in the kth monitoring time node, where k represents the number of monitoring time nodes.

[0061] According to the voltage deviation set between cells, the voltage mean value within the monitoring period is calculated. The voltage standard deviation Dbc is dimensionless, and the voltage deviation coefficient Dpxs is calculated as follows:

[0062]

[0063] The significance of this formula is to: evaluate the relative strength of the voltage fluctuation differences of each battery cell in the car;

[0064] At the same time, a deviation threshold is preset, and the deviation threshold is compared and analyzed with the voltage deviation coefficient Dpxs. The specific contents are as follows:

[0065] If the voltage deviation coefficient Dpxs exceeds the deviation threshold, a fault monitoring command will be issued externally;

[0066] If the voltage deviation coefficient Dpxs does not exceed the deviation threshold, no fault monitoring command will be issued temporarily.

[0067] In this embodiment, by real-time monitoring and comparison of the voltage deviation set between battery cells, the voltage conditions of each battery cell can be obtained, the mean and standard deviation within the monitoring period can be calculated, and the voltage deviation coefficient Dpxs can be obtained. This multi-dimensional data analysis can fully understand the voltage fluctuations between battery cells and provide a reliable basis for fault prediction and diagnosis. By pre-setting the deviation threshold and comparing it with the voltage deviation coefficient Dpxs, the automation of fault monitoring can be achieved. Once the voltage deviation coefficient Dpxs exceeds the set threshold, a fault monitoring command can be automatically issued without manual intervention, further improving the response speed and efficiency of the system. In summary, by continuously monitoring the voltage conditions of the battery cells and performing fault monitoring and early warning based on the voltage deviation coefficient Dpxs, this method can effectively improve the fault detection accuracy and response capability of the automotive motor drive system, and ensure the stable operation of the system and user safety.

[0068] Example 3

[0069] Please refer to Figure 1 Specifically: after receiving the fault monitoring command from step S1, the fault monitoring mode is turned on and entered, and the voltage and current distribution of each battery cell during the charging and discharging process is analyzed to determine whether there is an uneven phenomenon; in the fault monitoring mode, the temperature difference data and self-discharge data of each battery cell in the car are monitored respectively to construct a fault monitoring set;

[0070] Among them, the temperature difference data of each battery cell in the car includes the temperature value Wz of each battery cell during the monitoring period and the thermal conductivity Rdc between the battery cells, which can help analyze the temperature difference and thermal conductivity characteristics between the battery cells. This helps to discover the possible temperature unevenness and heat dissipation imbalance problems in the battery system, and provides an important basis for the system's temperature management and fault prevention.

[0071] The self-discharge data includes the self-discharge rate Zfz of each battery cell at different monitoring time nodes, and the self-discharge rate Zfz of each battery cell at the same monitoring time node is differentially analyzed to obtain the self-discharge rate difference value of the corresponding monitoring time node.

[0072] In this embodiment, by turning on the fault monitoring mode, key parameters such as the temperature fluctuation and self-discharge rate Zfz of the battery cell can be monitored and analyzed in real time, which helps to timely discover the unevenness and potential faults of the battery system, further improve the reliability and safety of the system, and monitor and record the temperature value Wz of each battery cell in the car and the thermal conductivity Rdc between the battery cells, which can provide an important basis for fault diagnosis. At the same time, differential analysis of self-discharge data and obtaining the difference value of self-discharge rate can help further evaluate the health of the battery cell and the stability of the system; by constructing a fault monitoring set, the working state of the battery system can be fully understood, and potential faults and abnormal conditions can be discovered in time. This helps to perform fault diagnosis and preventive maintenance in time, and improves the reliability and sustainability of the system. Based on the analysis of monitoring data, a more accurate and effective fault handling strategy can be formulated. According to data such as temperature difference and self-discharge rate difference, targeted measures can be taken to reduce the risk of battery system failure and extend the service life of the battery. In summary, by real-time monitoring and analysis of multi-dimensional data of automotive battery cells, this method can fully understand the working state of the battery system, timely discover potential faults and abnormal conditions, and provide reliable protection for the safe and stable operation of the system.

[0073] Example 4

[0074] Please refer to Figure 1 Specifically: a convolutional neural network is used to build a basic model, and the temperature difference data and self-discharge data of each battery cell in the car are used to train and test the basic model. At the same time, the trained basic model is used as a fault recognition model, and the feature information therein is obtained. The fault recognition model is trained and tested with the acquired feature information. Combined with the fault monitoring command triggered in the battery operation platform, the trained fault recognition model is used as a fault prediction model.

[0075] The trained fault prediction model is used to predict the temperature fluctuation of the vehicle drive battery and the battery self-discharge difference, respectively, to obtain the temperature difference variation coefficient Wbxs and the self-discharge fluctuation coefficient Zbxs. The temperature difference variation coefficient Wbxs is obtained by the following formula:

[0076]

[0077] The significance of this formula is to describe the difference in temperature rate change between battery cells; where k represents the number of monitoring time nodes, i=1, 2, 3, ..., k, It is represented as the temperature value of the jth battery cell at the i+1th time node; It is represented as the temperature value of the jth battery cell at the i-th time node; R is represented as the first correction constant; Expressed as the thermal conductivity between the jth battery cell and the nth battery cell, It is represented by the temperature value of the j+nth battery cell at the i+1th time node; It is represented by the temperature value of the j+nth battery cell at the i-th time node.

[0078] The thermal conductivity mentioned above can be obtained by the heat flow meter method, which uses a heat flow meter to measure the temperature difference and heat flux density on both sides of the material to calculate the thermal conductivity.

[0079] When the temperature difference variation coefficient Wbxs exceeds the control threshold, the battery operation platform will simultaneously send a temperature abnormality voice prompt to the user terminal and the corresponding repair shop, requiring targeted monitoring and maintenance measures for the vehicle battery. This intelligent alarm and maintenance guidance can guide users and maintenance personnel to deal with the fault in a timely manner and reduce the impact of the fault on vehicle safety and performance.

[0080] In this embodiment, based on the trained convolutional neural network model, abnormal conditions such as battery cell temperature difference and self-discharge can be effectively identified. Through training and testing of data, the model can learn and capture the characteristic information of temperature and self-discharge, thereby realizing accurate identification of battery status. The trained basic model is used as a fault identification model, and combined with the fault monitoring command triggered in the battery operation platform, a model with fault prediction capability can be constructed. In this way, when temperature difference or self-discharge abnormality is detected, possible fault conditions can be predicted in time, and maintenance measures can be taken in advance to further avoid accidents. The fault identification model is trained and tested using the characteristic information obtained by the convolutional neural network model, and data-driven fault diagnosis can be realized. The model can automatically analyze and identify the abnormal conditions of each battery cell, providing a scientific basis for fault prediction and maintenance. When the temperature difference variation coefficient Wbxs exceeds the control threshold, a temperature abnormality voice prompt is issued to the user terminal and the repair shop through the battery operation platform, realizing intelligent fault prompts and alarms, which helps users and maintenance personnel to understand the abnormal battery status in time and take corresponding measures to ensure the safety and stable operation of the automotive battery system. In summary, the fault prediction and diagnosis method based on the convolutional neural network model can improve the ability to identify and predict automotive battery system faults, provide users and maintenance personnel with timely and effective fault prompts and handling suggestions, and ensure the safety and stable operation of the vehicle.

[0081] Example 5

[0082] Please refer to Figure 1 Specifically, the self-release fluctuation coefficient Zbxs is obtained by the following formula:

[0083]

[0084] In the formula, They are respectively represented as the maximum and minimum values ​​of the self-discharge rate of the battery cell at the i-th time node, It is expressed as the average value of the self-discharge rate of the battery cells during the monitoring period.

[0085] The self-discharge rate Zfz is obtained by monitoring the open circuit voltage of the battery through a voltage monitor, and the self-discharge rate is calculated by the rate at which the voltage decreases over time.

[0086] By correlating the temperature difference variation coefficient Wbxs with the self-release fluctuation coefficient Zbxs, a state equilibrium index Zjzs is obtained by fitting. The state equilibrium index Zjzs is obtained by the following formula:

[0087]

[0088] Wherein, Nz represents the internal resistance value, and V represents the second correction constant. The internal resistance value Nz can be monitored and obtained by a DC internal resistance tester.

[0089] In this embodiment, by calculating the self-discharge fluctuation coefficient Zbxs, the fluctuation degree of the self-discharge rate of the battery cell can be evaluated, which helps to discover abnormal changes in the self-discharge rate between battery cells, timely identify possible faults or abnormal conditions, and provide an important basis for fault diagnosis and prediction. By fitting to obtain the state balance index Zjzs, the influence of the temperature influence coefficient Wbxs and the self-discharge fluctuation coefficient Zbxs on the state of the battery system can be comprehensively considered. This index can reflect the state balance degree inside the battery system, help evaluate the overall health and working state of the battery system, and provide guidance for system maintenance and optimization. Based on the calculation results of the state balance index Zjzs, the possible future failure risks of the battery system can be predicted. When the state balance index Zjzs is lower than a certain threshold, it may mean that the battery system is seriously unbalanced or abnormal, and corresponding preventive measures need to be taken to avoid the occurrence or further deterioration of the fault. According to the evaluation results of the state balance index Zjzs, targeted battery maintenance strategies and decisions can be formulated. For example, when the state balance index Zjzs is low, the monitoring and maintenance of the battery system can be strengthened, and the battery pack configuration can be adjusted or the battery can be replaced in time to ensure the safety and stable operation of the system.

[0090] Example 6

[0091] Please refer to Figure 1 Specifically: the state balance index Zjzs is compared and analyzed with the evaluation threshold value P, the working state of each battery unit in the current automobile motor drive system is comprehensively judged, and corresponding processing measures are taken:

[0092] When the state balance index Zjzs is greater than the evaluation threshold value P, it means that the working state of the battery cells of the current vehicle is normal and the system is in a relatively stable and balanced state. At this time, the current monitoring state is continued while maintaining normal operation to ensure the stability of the system;

[0093] When the state balance index Zjzs is equal to the evaluation threshold P, it means that the working state of the battery cells of the current vehicle has reached the standard of the evaluation threshold, and the system is in a relatively balanced state. At this time, preventive measures will be taken, including increasing the monitoring frequency and optimizing the SOC control strategy to maintain the stability of the system and prevent the occurrence of potential faults;

[0094] When the state balance index Zjzs is less than the evaluation threshold value P, it means that the current working state of each battery unit is lower than the expected level and an abnormal state exists. At this time, an alarm notification will be issued to the user terminal and the corresponding repair shop, notifying the user to go to the corresponding repair shop for fault diagnosis within the specified time period, conduct detailed fault diagnosis on the system, find out the root cause of the imbalance or fault, and repair the fault. According to the diagnosis results, take corresponding repair measures, which include adjusting the battery charge and discharge control strategy and replacing the faulty battery unit to restore the stability of the system and normal working state.

[0095] In this embodiment, when the state balance index Zjzs is greater than the evaluation threshold value P, the system determines that the working state between each battery unit is within the normal range and the system stability is high. At this time, the system will continue to maintain the current monitoring state to ensure the stability and balance state of the system, thereby ensuring the normal operation of the automobile motor drive system. When the state balance index Zjzs is equal to the evaluation threshold value P, the system realizes that the working state between each battery unit is close to the critical point and there are certain unstable factors. In order to prevent the occurrence of potential faults, the system will take preventive measures, including increasing the monitoring frequency and optimizing the SOC (State of Charge) control strategy, to maintain the stability of the system and prevent the occurrence of faults, and ensure the reliability and continuous operation of the automobile motor drive system. When the state balance index Zjzs is less than the evaluation threshold value P, the system realizes that the working state between each battery unit is lower than the expected level, and there is a serious abnormal situation, which may affect the safety and stability of the system. At this time, the system will immediately issue an alarm notification to notify the user to go to the corresponding repair shop for fault diagnosis and repair to ensure the safe operation of the automobile motor drive system. Through the above measures, the system can timely evaluate and respond to the working status of each battery unit according to the changes in the state balance index Zjzs, ensuring the safety, stability and reliability of the automobile motor drive system.

[0096] Example 7

[0097] Please refer to Figure 2 , specifically: a fault handling system for an automobile motor drive system, comprising a fault handling method for an automobile motor drive system as claimed in any one of claims 1 to 9, characterized in that: it comprises a preliminary monitoring module, a preliminary analysis module, a fault monitoring module, a fault analysis module and a processing module;

[0098] The preliminary monitoring module is used to obtain the battery compartment status in the automobile motor drive system in advance, and to build a battery operation platform to monitor the voltage of each battery unit in the battery compartment to obtain a voltage deviation set between battery cells;

[0099] The preliminary analysis module is used to generate a voltage deviation coefficient Dpxs according to the voltage deviation set between the cells, and if the voltage deviation coefficient Dpxs exceeds the deviation threshold, a fault monitoring command is issued externally;

[0100] The fault monitoring module is used to analyze whether the voltage and current distribution of the battery unit during the charging and discharging process is uneven after receiving the fault monitoring command, monitor the temperature difference data and self-discharge data of each battery unit in the car, and build a fault monitoring set;

[0101] The fault analysis module is used to pre-process the relevant data information in the fault monitoring set and perform feature extraction to respectively obtain the temperature value Wz of each battery cell, the thermal conductivity Rdc between battery cells and the self-discharge rate Zfz in each battery cell during the monitoring period, and calculate the temperature difference variation coefficient Wbxs and the self-discharge fluctuation coefficient Zbxs through the trained fault prediction model, and obtain the state equilibrium index Zjzs by fitting by associating the temperature difference variation coefficient Wbxs with the self-discharge fluctuation coefficient Zbxs;

[0102] The processing module is used to pre-set an evaluation threshold value P, and compare and analyze it with the state balance index Zjzs, comprehensively judge the working state of each battery unit in the current automobile motor drive system, and make corresponding processing measures.

[0103] 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. Troubleshooting methods for automobile motor drive systems, Features: The following steps are included: S1. Obtain the battery compartment status in the automobile motor drive system in advance, build a battery operation platform, monitor the voltage of each battery unit in the battery compartment to obtain the voltage deviation set between the battery cells, generate the voltage deviation coefficient Dpxs based on the voltage deviation set between the battery cells, and issue a fault monitoring command if the voltage deviation coefficient Dpxs exceeds the deviation threshold; S2. After receiving the fault monitoring command, analyze whether the voltage and current distribution of the battery cell during the charging and discharging process is uneven, monitor the temperature difference data and self-discharge data of each battery cell in the car, and build a fault monitoring set; S3, preprocessing the relevant data information in the fault monitoring set, and performing feature extraction to respectively obtain the temperature value Wz of each battery cell, the thermal conductivity Rdc between battery cells, and the self-discharge rate Zfz in each battery cell during the monitoring period, and calculating and obtaining the temperature difference variation coefficient Wbxs and the self-discharge fluctuation coefficient Zbxs through the trained fault prediction model, and obtaining the state equilibrium index Zjzs by fitting by associating the temperature difference variation coefficient Wbxs with the self-discharge fluctuation coefficient Zbxs; A convolutional neural network is used to build a basic model, and the basic model is trained and tested with the temperature difference data and self-discharge data of each battery cell in the car. The trained basic model is used as a fault recognition model, and the feature information in it is obtained. The fault recognition model is trained and tested with the acquired feature information. Combined with the fault monitoring command triggered in the battery operation platform, the trained fault recognition model is used as a fault prediction model. The trained fault prediction model is used to predict the temperature fluctuation of the vehicle drive battery and the battery self-discharge difference, respectively, to obtain the temperature difference variation coefficient Wbxs and the self-discharge fluctuation coefficient Zbxs. The temperature difference variation coefficient Wbxs is obtained by the following formula: ; The significance of this formula is to describe the difference in temperature rate change between battery cells; where k represents the number of monitoring time nodes, i=1, 2, 3, ..., k, It is represented as the temperature value of the jth battery cell at the i+1th time node; It is represented as the temperature value of the jth battery cell at the i-th time node; R is represented as the first correction constant; Expressed as the thermal conductivity between the jth battery cell and the nth battery cell, It is represented by the temperature value of the j+nth battery cell at the i+1th time node; It is represented as the temperature value of the j+nth battery cell at the i-th time node; When the temperature difference variation coefficient Wbxs exceeds the control threshold, the battery operation platform will send a temperature abnormality voice prompt to the user terminal and the corresponding repair shop at the same time, requiring targeted monitoring and maintenance measures for the car battery; The self-release fluctuation coefficient Zbxs is obtained by the following formula: ; In the formula, They are respectively represented as the maximum and minimum values ​​of the self-discharge rate of the battery cell at the i-th time node, It is expressed as the mean value of the self-discharge rate of the battery cell during the monitoring period; By correlating the temperature difference variation coefficient Wbxs with the self-release fluctuation coefficient Zbxs, a state equilibrium index Zjzs is obtained by fitting. The state equilibrium index Zjzs is obtained by the following formula: ; In the formula, Nz represents the internal resistance value, and V represents the second correction constant; S4. Preset an evaluation threshold value P, and compare and analyze it with the state balance index Zjzs, comprehensively judge the working state of each battery unit in the current automobile motor drive system, and make corresponding processing measures.

2. The method for troubleshooting a motor drive system for an automobile according to claim 1, Features: Use several groups of monitoring equipment to continuously monitor the voltage of each battery cell in the battery compartment. By monitoring and comparing the voltage of each battery cell in the battery compartment, a set of voltage deviations between battery cells is obtained, and then the set of voltage deviations between battery cells is transmitted to the battery operation status platform in real time. The set of voltage deviations between battery cells includes the voltage value Dy of each battery cell at each time node in the monitoring period, and the maximum value of the voltage value Dy at each time node and the voltage mean value in the monitoring period are obtained. , and based on the voltage average value during the monitoring period , calculate and obtain the voltage standard deviation Dbc within the monitoring period.

3. The method for troubleshooting a motor drive system for an automobile according to claim 2, Features: According to the voltage deviation set between cells, the voltage mean value within the monitoring period is calculated. The voltage standard deviation Dbc is dimensionless, and the voltage deviation coefficient Dpxs is calculated as follows: ; The significance of this formula is to: evaluate the relative strength of the voltage fluctuation differences of each battery cell in the car; At the same time, a deviation threshold is preset, and the deviation threshold is compared and analyzed with the voltage deviation coefficient Dpxs. The specific contents are as follows: If the voltage deviation coefficient Dpxs exceeds the deviation threshold, a fault monitoring command will be issued externally; If the voltage deviation coefficient Dpxs does not exceed the deviation threshold, no fault monitoring command will be issued temporarily.

4. The method for troubleshooting a motor drive system for an automobile according to claim 3, Features: After receiving the fault monitoring command from step S1, the fault monitoring mode is turned on and entered to analyze the voltage and current distribution of each battery cell during the charging and discharging process to determine whether there is an uneven phenomenon; in the fault monitoring mode, the temperature difference data and self-discharge data of each battery cell in the car are monitored respectively to construct a fault monitoring set; The temperature difference data of each battery cell in the vehicle includes the temperature value Wz of each battery cell and the thermal conductivity Rdc between battery cells during the monitoring period; The self-discharge data includes the self-discharge rate Zfz of each battery cell at different monitoring time nodes, and the self-discharge rate Zfz of each battery cell at the same monitoring time node is differentially analyzed to obtain the self-discharge rate difference value of the corresponding monitoring time node.

5. The method for troubleshooting a motor drive system for an automobile according to claim 1, Features: The state balance index Zjzs is compared and analyzed with the evaluation threshold value P, and the working state of each battery unit in the current automobile motor drive system is comprehensively judged, and corresponding processing measures are taken: When the state balance index Zjzs is greater than the evaluation threshold value P, it indicates that the working state of the battery cells of the current vehicle is normal, and the current monitoring state is continued while maintaining normal operation; When the state balance index Zjzs is equal to the evaluation threshold P, it means that the working state of the battery cells of the current vehicle has reached the standard of the evaluation threshold, and preventive measures will be taken at this time, including increasing the monitoring frequency and optimizing the SOC control strategy; When the state balance index Zjzs is less than the evaluation threshold value P, it means that the current working state of each battery unit is lower than the expected level and an abnormal state exists. At this time, an alarm notification will be issued to the user terminal and the corresponding repair shop, notifying the user to go to the corresponding repair shop within the specified time period for fault diagnosis and repair. According to the diagnosis results, corresponding repair measures are taken, including adjusting the battery charge and discharge control strategy and replacing the faulty battery unit to restore the stability of the system and normal working state.

6. A fault handling system for an automobile motor drive system, comprising the fault handling method for an automobile motor drive system according to any one of claims 1 to 5, Features: It includes a preliminary monitoring module, a preliminary analysis module, a fault monitoring module, a fault analysis module and a processing module; The preliminary monitoring module is used to obtain the battery compartment status in the automobile motor drive system in advance, and to build a battery operation platform to monitor the voltage of each battery unit in the battery compartment to obtain a voltage deviation set between battery cells; The preliminary analysis module is used to generate a voltage deviation coefficient Dpxs according to the voltage deviation set between the cells, and if the voltage deviation coefficient Dpxs exceeds the deviation threshold, a fault monitoring command is issued externally; The fault monitoring module is used to analyze whether the voltage and current distribution of the battery unit during the charging and discharging process is uneven after receiving the fault monitoring command, monitor the temperature difference data and self-discharge data of each battery unit in the car, and build a fault monitoring set; The fault analysis module is used to pre-process the relevant data information in the fault monitoring set and perform feature extraction to respectively obtain the temperature value Wz of each battery cell, the thermal conductivity Rdc between battery cells and the self-discharge rate Zfz in each battery cell during the monitoring period, and calculate the temperature difference variation coefficient Wbxs and the self-discharge fluctuation coefficient Zbxs through the trained fault prediction model, and obtain the state equilibrium index Zjzs by fitting by associating the temperature difference variation coefficient Wbxs with the self-discharge fluctuation coefficient Zbxs; The processing module is used to pre-set an evaluation threshold value P, and compare and analyze it with the state balance index Zjzs, comprehensively judge the working state of each battery unit in the current automobile motor drive system, and make corresponding processing measures.

Citation Information

Patent Citations

  • Overcurrent fault analysis method for electric drive system

    CN116539980A

  • Electric vehicle charging method and electric vehicle charging device based on storage battery monitoring and fault diagnosis

    CN106058987A

  • New energy vehicle maintenance and fault monitoring diagnosis method based on machine learning

    CN116973782A