Drive motor reliability remote diagnosis and prediction system, method and automobile

Abstract

The application provides a kind of drive motor reliability remote diagnosis and prediction system, comprising: sensor on drive motor, with integrated motor controller MCU on-board quick diagnosis system connection, on-board quick diagnosis system and vehicle controller ECU communication connection, and through T-box and cloud communication connection;Sensor is used to monitor the state parameters of each component on drive motor, the state parameters of each component are input into on-board quick diagnosis system, on-board quick diagnosis system first carries out fault determination, after determining that the component is fault-free, then the abnormal determination of each component is carried out, if it is determined that there is an abnormal component, the state parameters of the abnormal component are sent to the cloud, the cloud assesses the health status of the corresponding component based on the abnormal signal, and returns to the vehicle controller VCU or mobile terminal. The performance degradation state and health state of the drive motor are evaluated and monitored, a scientific and effective health management strategy is developed, the degree of motor performance degradation is reduced, and the user vehicle experience is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of vehicle safety technology, and provides a driving motor reliability remote diagnosis and prediction system, method and automobile. BACKGROUND

[0002] The invention patent with the patent number CN202111241240.7 discloses a motor fault diagnosis method based on GRU network stator current analysis, which collects stator current variable data, wirelessly transmits and stores to a cloud database; models and trains the collected stator current variable data using a GRU neural network, uses test set data for final current signal fault diagnosis, and presets a fault probability threshold, when the fault probability is greater than the preset fault probability threshold, an alarm is issued and the motor is stopped.

[0003] The invention patent with the patent number CN201811125406.7 discloses a cloud computing-based electric vehicle permanent magnet synchronous motor fault diagnosis system and method, which collects characteristic information of the permanent magnet synchronous motor, then sends the characteristic information to the motor controller for preliminary fault diagnosis, continues to send the characteristic information to the vehicle controller through the CAN network, sends the characteristic information to the cloud reliability diagnosis and prediction system for intelligent diagnosis through the 4G network, and the cloud reliability diagnosis and prediction system sends the fault state to the vehicle controller and issues corresponding final instructions to the motor controller, and sends the fault information to the display screen to enable the driver to master the vehicle state in real time.

[0004] The above two patents both use various characteristic signals of the motor collected by the embedded sensor in the motor to perform fault diagnosis in the cloud, issue relevant execution instructions to the motor according to the fault type and level, and can only be diagnosed after the motor fails, without monitoring and predicting the performance degradation and aging state of the motor, and thus cannot realize safety monitoring and health management of the motor in the whole life cycle, thereby affecting the service life of the driving motor. SUMMARY

[0005] The present application provides a driving motor reliability remote diagnosis and prediction system, which aims to improve the above problems.

[0006] The present application is implemented as follows: a driving motor reliability remote diagnosis and prediction system, characterized in that the system comprises:

[0007] A sensor provided on the driving motor, the sensor being connected to a vehicle-mounted rapid diagnosis system integrated on a motor controller MCU, the vehicle-mounted rapid diagnosis system being communicatively connected to a vehicle control unit VCU and communicatively connected to a cloud through a T-box;

[0008] The sensor on the drive motor is used to monitor the state parameters of each component on the drive motor, and the state parameters of each component are input into the on-board rapid diagnosis system. The on-board rapid diagnosis system first determines the fault of the component based on the state parameters, and then determines the abnormality of each component after determining that the component is fault-free. If an abnormal component is determined, the state parameters of the abnormal component are sent to the cloud, and the cloud evaluates the health status of the corresponding component based on the abnormal signal and returns to the vehicle controller.

[0009] Further, the key components affecting the performance degradation of the drive motor include: motor controller, insulated winding, bearing and permanent magnet.

[0010] Further, the motor controller is provided with a temperature sensor I, an electric current sensor I and a pressure sensor for detecting the temperature of the power component in the motor controller, the motor controller current and the motor back electromotive force;

[0011] The current sensor II and the temperature sensor II are arranged on the insulated winding for detecting the current and the temperature of the insulated winding;

[0012] The temperature sensor III and the impact pulse sensor are arranged on the bearing for detecting the bearing temperature and the impact pulse signal, and the acceleration sensor is arranged on the bearing seat for detecting the acceleration signal of the bearing.

[0013] Further, the on-board rapid diagnosis system includes: a motor controller fault determination model, the temperature sensor I, the current sensor I and the motor controller fault determination model are in communication connection;

[0014] The collected motor controller temperature and current are sent to the motor controller fault determination model, and the motor controller fault determination model detects whether the current of the motor controller exceeds the fault current threshold I2 or the temperature exceeds the fault temperature threshold T2. If the detection result is yes, it is determined that the motor controller is faulty. If the detection result is no, it is detected whether the current exceeds the aging current threshold I1 or the temperature exceeds the aging temperature threshold T1. If it exceeds, the motor controller is abnormal, and the current and temperature of the motor controller are uploaded to the cloud.

[0015] Further, the on-board rapid diagnosis system includes: an insulated winding fault determination model, the current sensor II, the temperature sensor II and the insulated winding fault determination model are in communication connection;

[0016] The collected insulation winding temperature and current are sent to the insulation winding fault determination model. The insulation winding fault determination model detects whether the current of the insulation winding exceeds the fault current threshold I4 or the temperature exceeds the fault temperature threshold T4. If the detection result is yes, it is determined that the insulation winding is faulty. If the detection result is no, it is detected whether the current exceeds the aging current threshold I3 or the temperature exceeds the aging temperature threshold T3. If it exceeds, it is determined that the insulation winding is abnormal. The current and temperature of the insulation winding are uploaded to the cloud.

[0017] Further, the on-board rapid diagnosis system comprises a bearing fault determination model, and the temperature sensor III, the impact pulse sensor and the acceleration sensor are in communication connection with the bearing fault determination model.

[0018] The collected bearing temperature, impact pulse and acceleration of the bearing are sent to the bearing fault determination model. The bearing fault determination model first detects whether the temperature of the insulation winding exceeds the fault temperature threshold T6, whether the impact pulse exceeds the fault impact pulse threshold M2 or whether the acceleration exceeds the fault acceleration threshold A2. If the detection result is yes, it is determined that the bearing is faulty. If the detection result is no, it is detected whether the bearing temperature exceeds the aging temperature threshold T5, whether the bearing acceleration exceeds the aging acceleration threshold A1 or whether the impact pulse of the bearing exceeds the aging impact pulse threshold M1. If it exceeds, it is determined that the bearing is abnormal. The temperature, impact pulse signal and acceleration information of the bearing are uploaded to the cloud.

[0019] Further, the on-board rapid diagnosis system comprises a permanent magnet fault determination model, and the voltage sensor and the temperature sensor II are in communication connection with the permanent magnet fault determination model.

[0020] The back electromotive force of the motor and the temperature of the insulation winding are input into the permanent magnet fault determination model. The permanent magnet fault determination model first detects whether the current of the insulation winding exceeds the fault current threshold I8 or whether the back electromotive force of the motor exceeds the fault back electromotive force threshold V2. If the detection result is yes, it is determined that the permanent magnet is faulty. If the detection result is no, it is detected whether the back electromotive force of the motor exceeds the aging back electromotive force threshold V1 or whether the temperature of the insulation winding exceeds the aging temperature threshold T7. If it exceeds, it is determined that the permanent magnet is abnormal. The back electromotive force of the motor and the temperature of the insulation winding are uploaded to the cloud.

[0021] Further, the cloud is integrated with a health state estimation system, which comprises:

[0022] Based on the deep learning model, a motor controller health state estimation model, an insulation winding health state estimation model, a bearing health state estimation model and a permanent magnet health state estimation model are constructed.

[0023] The motor controller temperature and current of the motor controller in an abnormal state are input into a motor controller health state estimation model, and the motor controller health state estimation model outputs a current health state value of the motor controller.

[0024] The insulation winding temperature and current of the insulation winding in an abnormal state are input into a motor controller health state estimation model, and the motor controller health state estimation model outputs a health state value of the insulation winding.

[0025] The bearing temperature, impact pulse and acceleration of the bearing in an abnormal state are input into a bearing health state estimation model, and the bearing health state estimation model outputs a health state value of the bearing.

[0026] The back electromotive force of the motor and the temperature of the insulation winding in an abnormal state of the permanent magnet are input into a permanent magnet health state estimation model, and the permanent magnet health state estimation model outputs a health state value of the permanent magnet.

[0027] The present application is realized in a kind of driving motor reliability remote diagnosis and prediction method, the method includes the following steps:

[0028] The state parameters when driving motor is operated are monitored;

[0029] Whether the relevant components on driving motor are failure is judged based on state parameters, if the determination result is yes, corresponding fault handling is carried out for different faults, if the determination result is no, whether corresponding component is abnormal is detected;

[0030] If it is judged that there is abnormal relevant component, the state parameters of abnormal component are input into cloud, and cloud carries out the evaluation of health state to abnormal component, and the evaluation result is returned to vehicle controller ECU or is sent to mobile terminal by 4G / 5G network.

[0031] The present application is realized in a kind of automobile, and the above-mentioned driving motor reliability remote diagnosis and prediction system is integrated on the automobile.

[0032] The driving motor reliability remote diagnosis and prediction system provided by the present application has the following beneficial technical effects:

[0033] (1) the performance degradation state and health state of driving motor are evaluated and monitored, scientific and effective health management strategy is formulated, the degree of motor performance degradation is reduced, and user vehicle experience is improved;

[0034] (2) the health state of driving motor is evaluated, and fault diagnosis and prediction are carried out, realize the safety monitoring of whole life cycle, for more serious fault, can be judged by vehicle controller fault grade, and control instruction is sent to motor controller, finally by actuator executes corresponding operation, so as to reach the purpose of guaranteeing user personal safety and protecting important parts of vehicle, and improve user vehicle safety. BRIEF DESCRIPTION OF DRAWINGS

[0035] Figure 1 A schematic structural diagram of a driving motor reliability remote diagnosis and prediction system provided by an embodiment of the present application is shown in the figure.

[0036] Figure 2 A flowchart of a driving motor reliability remote diagnosis and prediction method provided by an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0037] The specific embodiments of the present application are further described in detail below with reference to the accompanying drawings.

[0038] Figure 1 A schematic structural diagram of a driving motor reliability remote diagnosis and prediction system provided by an embodiment of the present application is shown in the figure. For the convenience of description, only the parts related to the embodiment of the present application are shown. The system comprises:

[0039] The sensor provided on the driving motor is connected with the on-board rapid diagnosis system integrated on the motor controller MCU. The on-board rapid diagnosis system is in communication connection with the vehicle controller ECU and is in communication connection with the cloud through the T-box.

[0040] The sensor on the driving motor is used to monitor the state parameters of each component on the driving motor. The state parameters of each component are input to the on-board rapid diagnosis system. The on-board rapid diagnosis system first determines the fault of the component based on the state parameters. When a faulty component is determined, the vehicle controller performs corresponding fault processing according to different faults. After determining that the component is not faulty, the abnormality of each component is determined. If an abnormal component is determined, the state parameters of the abnormal component are sent to the cloud. The cloud evaluates the health state of the corresponding component based on the abnormal signal and returns to the vehicle controller. The component state includes normal state, fault state, and abnormal state between normal state and fault state.

[0041] In the embodiment of the present application, the key components affecting the performance degradation of the driving motor include the motor controller, the insulated winding, the bearing and the permanent magnet. The following sensors are arranged for the above key components:

[0042] The temperature sensor I, the current sensor I and the pressure sensor are used to detect the temperature of the power component in the motor controller, the current of the motor controller and the back electromotive force of the motor. The current sensor II and the temperature sensor II are used to detect the current and the temperature of the insulated winding. The temperature sensor III and the impact pulse sensor are used to detect the temperature and the impact pulse signal of the bearing. The acceleration sensor is used to detect the acceleration signal of the bearing and is provided on the bearing seat.

[0043] The on-board rapid diagnosis system comprises a motor controller fault determination model, an insulation winding fault determination model, a bearing fault determination model and a permanent magnet fault determination model, and the working method is as follows:

[0044] (1) Motor controller fault determination model

[0045] The temperature sensor I and the current sensor I are in communication connection with the motor controller fault determination model, and the collected motor controller temperature and current are sent to the motor controller fault determination model. The motor controller fault determination model first determines whether the motor controller is faulty based on the motor controller current and temperature, that is, when the current of the motor controller exceeds the fault current threshold I2 or the temperature exceeds the fault temperature threshold T2, it is determined that the motor controller is faulty. If the temperature and current of the motor controller do not exceed the corresponding fault threshold, it is detected whether the temperature and current of the motor controller are abnormal, that is, whether the current exceeds the aging current threshold I1 or whether the temperature exceeds the aging temperature threshold T1. If so, the motor controller is abnormal, and the current and temperature of the motor controller are uploaded to the cloud,

[0046] The motor controller fault determination model is provided with an aging temperature threshold T1 and a fault temperature threshold T2 of the motor controller temperature, an aging current threshold I1 and a fault current threshold I2. The aging temperature threshold T1 and the aging current threshold I1 are the temperature value and the current value corresponding to the aging speed mutation point (the aging speed is slow in the early stage, and the aging speed suddenly becomes large after aging to a certain extent, which is the aging speed mutation point) of the motor controller aging curve measured by the bench test. The fault temperature threshold T2 and the fault current threshold I2 are the minimum temperature and minimum current value of the motor controller at the time of failure measured by the bench test.

[0047] (2) Insulation winding fault determination model

[0048] The current sensor II and the temperature sensor II are in communication connection with the insulation winding fault determination model, and the collected insulation winding temperature and current are sent to the insulation winding fault determination model. The insulation winding fault determination model first determines whether the insulation winding is faulty based on the insulation winding current and temperature, that is, when the current of the insulation winding exceeds the fault current threshold I4 or the temperature exceeds the fault temperature threshold T4, it is determined that the insulation winding is faulty. If the temperature and current of the insulation winding do not exceed the corresponding fault threshold, it is detected whether the temperature and current of the insulation winding are abnormal, that is, whether the current exceeds the aging current threshold I3 or whether the temperature exceeds the aging temperature threshold T3. If so, it is determined that the insulation winding is abnormal, and the current and temperature of the insulation winding are uploaded to the cloud.

[0049] The insulation winding fault determination model is provided with an aging temperature threshold T3 and a fault temperature threshold T4 of the insulation winding, an aging current threshold I3 and a fault current threshold I4, wherein the aging temperature threshold T3 and the aging current threshold I3 are temperature values and current values corresponding to the mutation points of the aging speed in the aging curve of the insulation winding measured through the bench test, and the fault temperature threshold T4 and the fault current threshold I4 are the minimum temperature value and the minimum current value when the insulation winding is in fault measured through the bench test.

[0050] (3) Bearing fault determination model

[0051] The temperature sensor III, the impact pulse sensor and the acceleration sensor are in communication connection with the bearing fault determination model, and the collected bearing temperature, impact pulse and acceleration of the bearing are sent to the bearing fault determination model. The bearing fault determination model first determines whether the bearing is in fault based on the bearing temperature, the impact pulse and the acceleration of the bearing, that is, when the temperature of the insulation winding exceeds the fault temperature threshold T6, the impact pulse exceeds the fault impact pulse threshold M2 or the acceleration exceeds the fault acceleration threshold A2, it is determined that the bearing is in fault. If the temperature, the impact pulse and the acceleration of the bearing do not exceed the corresponding fault threshold, it is determined whether the temperature, the impact pulse and the acceleration of the bearing are abnormal, that is, whether the temperature exceeds the aging temperature threshold T5, whether the acceleration exceeds the aging acceleration threshold A1 or whether the impact pulse exceeds the aging impact pulse threshold M1. If yes, it is determined that the bearing is abnormal, and the temperature, the impact pulse signal and the acceleration information of the bearing are uploaded to the cloud.

[0052] The bearing fault determination model is provided with an aging temperature threshold T5 and a fault temperature threshold T6 of the bearing, an aging acceleration threshold A1 and a fault acceleration threshold A2, and an aging impact pulse threshold M1 and a fault impact pulse threshold M2. The aging temperature threshold T5, the aging acceleration threshold A1 and the aging impact pulse threshold M1 are temperature values, acceleration values and impact pulse thresholds corresponding to the mutation points of the aging speed in the aging curve of the bearing measured through the bench test. The fault temperature threshold T6, the fault acceleration threshold A2 and the fault impact pulse threshold M2 are the minimum temperature value, the minimum acceleration value and the minimum impact pulse when the bearing is in fault measured through the bench test.

[0053] (4) Permanent magnet fault determination model

[0054] The voltage sensor, the temperature sensor II and the permanent magnet fault determination model are in communication connection, the back electromotive force of the motor and the temperature of the insulated winding are input into the permanent magnet fault determination model, the permanent magnet fault determination model first determines whether the permanent magnet is faulty based on the back electromotive force of the motor and the temperature of the insulated winding, that is, when the current of the insulated winding exceeds the fault current threshold I8 or the back electromotive force of the motor exceeds the fault back electromotive force threshold V2, it is determined that the permanent magnet is faulty, if the back electromotive force of the motor and the temperature of the insulated winding do not exceed the corresponding fault threshold, then the back electromotive force of the motor and the temperature of the insulated winding are detected whether they are abnormal, that is, whether the back electromotive force exceeds the aging back electromotive force threshold V1 or whether the temperature exceeds the aging temperature threshold T7, if so, it is determined that the permanent magnet is abnormal, and the back electromotive force of the motor and the temperature of the insulated winding are uploaded to the cloud;

[0055] The aging temperature threshold T7 and the fault temperature threshold T8 of the insulated winding, the aging back electromotive force threshold V1 and the fault back electromotive force threshold V2 are set in the permanent magnet fault determination model, wherein the aging temperature threshold T7 and the aging back electromotive force threshold V1 are the temperature value of the insulated winding and the back electromotive force value of the motor corresponding to the aging speed mutation point in the permanent magnet aging curve measured by the bench test, and the fault temperature threshold T8 and the fault back electromotive force threshold V2 are the minimum temperature value of the insulated winding and the minimum back electromotive force of the motor when the permanent magnet is faulty.

[0056] When it is detected that there is a driving motor fault based on the above motor controller fault determination model, the insulated winding fault determination model, the bearing fault determination model and the permanent magnet fault determination model, the fault processing includes motor power, limiting motor torque and power.

[0057] In the embodiment of the application, the motor controller health state estimation model, the insulated winding health state estimation model, the bearing health state estimation model and the permanent magnet health state estimation model are integrated on the cloud, the above four health state estimation models are constructed by using a deep learning model, and the corresponding model is trained in the early stage, and the training of the corresponding model is completed when the accurate recognition degree of the training reaches the requirement, the trained motor controller health state estimation model, the insulated winding health state estimation model, the bearing health state estimation model and the permanent magnet health state estimation model are integrated on the cloud, and the health state estimation of the motor controller, the insulated winding, the bearing and the permanent magnet is realized, and the health state estimation method of the above components is as follows:

[0058] (1) Motor controller health state estimation model

[0059] The motor controller temperature and current when the motor controller is abnormal are input into the motor controller health state estimation model, and the motor controller health state estimation model outputs the current health state value of the motor controller.

[0060] (2) Insulated winding health state estimation model

[0061] The temperature and current of the insulated winding when the insulated winding is abnormal are input into the motor controller health state estimation model, and the motor controller health state estimation model outputs the health state value of the insulated winding.

[0062] (3) Bearing health state estimation model

[0063] The bearing temperature, impact pulse and acceleration of the bearing when the bearing is abnormal are input into the bearing health state estimation model, and the bearing health state estimation model outputs the health state value of the bearing.

[0064] (4) Permanent magnet health state estimation model

[0065] The back electromotive force of the motor and the temperature of the insulated winding when the permanent magnet is abnormal are input into the permanent magnet health state estimation model, and the permanent magnet health state estimation model outputs the health state value of the permanent magnet.

[0066] The health state and the aging state are inversely related, the higher the aging state, the worse the health state, and the health state is represented by a numerical value of 0-1, 0 represents a fault state, and 1 represents a normal device at the time of production.

[0067] The health states of the motor controller, the insulated winding, the bearing and the permanent magnet are returned to the vehicle controller VCU through the T-box, and the vehicle controller VCU displays or reminds through the vehicle display unit, or sends to the mobile terminal through the 4G / 5G network.

[0068] Figure 2 The driving motor reliability remote diagnosis and prediction method flowchart provided for the embodiments of the application, the method specifically comprises the following steps:

[0069] The state parameters of the driving motor during operation are monitored based on the sensors on the driving motor;

[0070] It is determined whether the related components on the driving motor are faulty based on the state parameters, if the determination result is yes, corresponding fault handling is performed for different faults, and if the determination result is no, it is detected whether the corresponding components are abnormal;

[0071] If it is determined that there is an abnormal related component, the state parameters of the abnormal component are input into the cloud, the cloud evaluates the health state of the abnormal component, and the evaluation result is returned to the vehicle controller VCU, or is sent to the mobile terminal through the 4G / 5G network.

[0072] The application also provides an automobile, and the automobile is integrated with the health state remote diagnosis system of the driving motor.

[0073] The driving motor reliability remote diagnosis and prediction system has the following beneficial technical effects.

[0074] (1) The driving motor performance attenuation state and health state are evaluated and monitored, a scientific and effective health management strategy is formulated, the motor performance attenuation degree is reduced, and the user vehicle experience is improved.

[0075] (2) The health state of the driving motor is evaluated, and the fault diagnosis and prediction are performed, the whole life cycle safety monitoring is realized, for more serious faults, the fault level can be judged by the vehicle controller, control instructions are sent to the motor controller, and finally the corresponding operation is performed by the actuator, so that the user's personal safety and the protection of important vehicle parts are achieved, and the user's vehicle safety is improved.

[0076] The application is described exemplarily, and it is obvious that the specific implementation of the application is not limited by the above method, as long as various non-essential improvements are adopted, or the concept and technical scheme of the application are directly applied to other occasions without improvement, all of which are within the protection scope of the application.

Claims

1. A system for driving motor reliability remote diagnosis and prediction, characterized by, The system comprises: A sensor arranged on the drive motor, the sensor being connected with a vehicle-mounted rapid diagnosis system integrated on a motor controller MCU, the vehicle-mounted rapid diagnosis system being in communication connection with a vehicle control unit VCU and in communication connection with a cloud through a T-box; The sensor on the drive motor is used to monitor the state parameters of each component on the drive motor, and the state parameters of each component are input into the vehicle-mounted rapid diagnosis system, the vehicle-mounted rapid diagnosis system first performs fault determination on the components based on the state parameters, and after determining that the components have no faults, performs abnormality determination on each component, if it is determined that there is an abnormal component, the state parameters of the abnormal component are sent to the cloud, the cloud evaluates the health state of the corresponding component based on the abnormal signal, and returns to the vehicle control unit VCU or a mobile terminal; The vehicle-mounted rapid diagnosis system comprises: a motor controller fault determination model, a temperature sensor I, a current sensor I and the motor controller fault determination model in communication connection; The collected motor controller temperature and current are sent to the motor controller fault determination model, the motor controller fault determination model detects whether the current of the motor controller exceeds a fault current threshold I2 or the temperature exceeds a fault temperature threshold T2, if the detection result is yes, it is determined that the motor controller is faulty, if the detection result is no, it is detected whether the current exceeds an aging current threshold I1 or the temperature exceeds an aging temperature threshold T1, if yes, the motor controller is abnormal, and the current and temperature of the motor controller are uploaded to the cloud; The vehicle-mounted rapid diagnosis system comprises: an insulation winding fault determination model, a current sensor II, a temperature sensor II and the insulation winding fault determination model in communication connection; The collected insulation winding temperature and current are sent to the insulation winding fault determination model, the insulation winding fault determination model detects whether the current of the insulation winding exceeds a fault current threshold I4 or the temperature exceeds a fault temperature threshold T4, if the detection result is yes, it is determined that the insulation winding is faulty, if the detection result is no, it is detected whether the current exceeds an aging current threshold I3 or the temperature exceeds an aging temperature threshold T3, if yes, it is determined that the insulation winding is abnormal, and the current and temperature of the insulation winding are uploaded to the cloud; The vehicle-mounted rapid diagnosis system comprises: a bearing fault determination model, a temperature sensor III, an impact pulse sensor and an acceleration sensor and the bearing fault determination model in communication connection; The collected bearing temperature, impact pulse and bearing acceleration are sent to the bearing fault determination model, the bearing fault determination model first detects whether the temperature of the insulation winding exceeds a fault temperature threshold T6, whether the impact pulse exceeds a fault impact pulse threshold M2 or whether the acceleration exceeds a fault acceleration threshold A2, if the detection result is yes, it is determined that the bearing is faulty, if the detection result is no, it is detected whether the bearing temperature exceeds an aging temperature threshold T5, whether the bearing acceleration exceeds an aging acceleration threshold A1 or whether the impact pulse of the bearing exceeds an aging impact pulse threshold M1, if yes, it is determined that the bearing is abnormal, and the temperature, impact pulse signal and acceleration information of the bearing are uploaded to the cloud; The on-board rapid diagnosis system comprises a permanent magnet fault determination model, a voltage sensor, and a temperature sensor II, which are in communication connection with the permanent magnet fault determination model; The back electromotive force of the motor and the temperature of the insulated winding are input into the permanent magnet fault determination model. The permanent magnet fault determination model first detects whether the current of the insulated winding exceeds a fault current threshold I8 or whether the back electromotive force of the motor exceeds a fault back electromotive force threshold V2. If the detection result is yes, it is determined that the permanent magnet is faulty. If the detection result is no, it is detected whether the back electromotive force of the motor exceeds an aging back electromotive force threshold V1 or whether the temperature of the insulated winding exceeds an aging temperature threshold T7. If yes, it is determined that the permanent magnet is abnormal. The back electromotive force of the motor and the temperature of the insulated winding are uploaded to the cloud.

2. The system for reliable remote diagnosis and prognosis of the drive motor according to claim 1, wherein, The components affecting the performance of the driving motor include a motor controller, an insulated winding, a bearing, and a permanent magnet.

3. The system for reliable remote diagnosis and prognosis of the drive motor according to claim 2, wherein, The motor controller is provided with a temperature sensor I, a current sensor I, and a voltage sensor for detecting the temperature of the power component in the motor controller, the current of the motor controller, and the back electromotive force of the motor. The current sensor II and the temperature sensor II are arranged on the insulated winding for detecting the current and the temperature of the insulated winding. The temperature sensor III and the impact pulse sensor are arranged on the bearing for detecting the temperature and the impact pulse signal of the bearing, and the acceleration sensor is arranged on the bearing seat for detecting the acceleration signal of the bearing.

4. The system for reliable remote diagnosis and prognosis of electric motor drive according to claim 1, characterized in that, The cloud is integrated with: The motor controller health state estimation model, the insulated winding health state estimation model, the bearing health state estimation model, and the permanent magnet health state estimation model are constructed based on a deep learning model; The motor controller temperature and the current of the motor controller when the motor controller is abnormal are input into the motor controller health state estimation model, and the motor controller health state estimation model outputs the current health state value of the motor controller; The insulated winding temperature and the current of the insulated winding when the insulated winding is abnormal are input into the motor controller health state estimation model, and the motor controller health state estimation model outputs the health state value of the insulated winding; The bearing temperature, the impact pulse, and the acceleration of the bearing when the bearing is abnormal are input into the bearing health state estimation model, and the bearing health state estimation model outputs the health state value of the bearing; The back electromotive force of the motor and the temperature of the insulated winding when the permanent magnet is abnormal are input into the permanent magnet health state estimation model, and the permanent magnet health state estimation model outputs the health state value of the permanent magnet.

5. A method of remotely diagnosing and predicting reliability of a drive motor based on the system of remotely diagnosing and predicting reliability of a drive motor according to any one of claims 1 to 4, characterized in that, The method comprises the following steps: Monitoring the state parameters of the driving motor during operation; Determining whether the related components on the driving motor are faulty based on the state parameters. If the determination result is yes, corresponding fault handling is performed for different faults. If the determination result is no, it is detected whether the corresponding components are abnormal; If it is determined that there is an abnormal related component, the state parameters of the abnormal component are input into the cloud, the cloud performs health state evaluation on the abnormal component, and the evaluation result is returned to the vehicle control unit VCU or the mobile terminal.

6. An automobile characterized by comprising: The automobile is integrated with the driving motor reliability remote diagnosis and prediction system according to any one of claims 1 to 4.

Images