WO2024114512A1 - Procédé et dispositif de détection de panne de système d'entraînement électrique, et véhicule et support de stockage - Google Patents

Procédé et dispositif de détection de panne de système d'entraînement électrique, et véhicule et support de stockage Download PDF

Info

Publication number
WO2024114512A1
WO2024114512A1 PCT/CN2023/133849 CN2023133849W WO2024114512A1 WO 2024114512 A1 WO2024114512 A1 WO 2024114512A1 CN 2023133849 W CN2023133849 W CN 2023133849W WO 2024114512 A1 WO2024114512 A1 WO 2024114512A1
Authority
WO
WIPO (PCT)
Prior art keywords
drive system
electric drive
fault
motor
signal
Prior art date
Application number
PCT/CN2023/133849
Other languages
English (en)
Chinese (zh)
Inventor
王蓓
孙永朝
王凯
Original Assignee
蔚来动力科技(合肥)有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 蔚来动力科技(合肥)有限公司 filed Critical 蔚来动力科技(合肥)有限公司
Publication of WO2024114512A1 publication Critical patent/WO2024114512A1/fr

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
    • B60L3/00—Electric devices on electrically-propelled vehicles for safety purposes; Monitoring operating variables, e.g. speed, deceleration or energy consumption
    • B60L3/0023—Detecting, eliminating, remedying or compensating for drive train abnormalities, e.g. failures within the drive train
    • B60L3/0061—Detecting, eliminating, remedying or compensating for drive train abnormalities, e.g. failures within the drive train relating to electrical machines
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
    • B60L3/00—Electric devices on electrically-propelled vehicles for safety purposes; Monitoring operating variables, e.g. speed, deceleration or energy consumption
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
    • G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M17/00—Testing of vehicles
    • G01M17/007—Wheeled or endless-tracked vehicles
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M7/00—Vibration-testing of structures; Shock-testing of structures
    • G01M7/02—Vibration-testing by means of a shake table
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/34—Testing dynamo-electric machines

Definitions

  • the present application relates to the field of vehicle fault detection, and more specifically, to a method and device for detecting electric drive system faults, a vehicle, and a storage medium.
  • Embodiments of the present application provide a method and apparatus for detecting electric drive system faults, a vehicle, and a storage medium for determining whether the electric drive system of the vehicle has a fault or a potential fault hazard.
  • a method for detecting faults in an electric drive system comprising the following steps: receiving an environmental signal about the electric drive system, and determining whether a predetermined operating condition for detecting faults is entered based on the environmental signal; in the case of determining that the predetermined operating condition is entered, extracting a vibration signal from a vibration sensor, wherein the vibration sensor is coupled to a predetermined position of the electric drive system; and determining whether the electric drive system has a fault based on the vibration signal.
  • the predetermined position includes at least one of the following: on the motor housing in the electric drive system and located near the axial center of the motor rotor; near the input shaft of the gearbox in the electric drive system; near the intermediate shaft of the gearbox; and on the motor controller housing in the electric drive system.
  • the vibration signal is an acceleration signal in a direction perpendicular to the ground.
  • whether to enter the predetermined operating condition is determined by a discriminant model generated by the following steps: obtaining a first data set in which a fault exists and a second data set in which no fault exists in the electric drive system, wherein the first data set and the second data set are respectively constructed based on the environmental signal; and training a classification model based on the first data set and the second data set to generate the discriminant model for determining whether to enter the predetermined operating condition.
  • the classification model includes: a classification model based on machine learning and deep learning.
  • the environmental signal includes at least one of the following: vehicle speed, rotation speed of the motor in the electric drive system, torque of the motor, temperature in the electric drive system, current and voltage of the motor.
  • determining whether the electric drive system has a fault based on the vibration signal includes: low-pass filtering the vibration signal, and converting the low-pass filtered signal to the frequency domain to generate frequency domain data; extracting the amplitude at a predetermined frequency where a fault is expected to exist in the frequency domain data; constructing an analysis model based on the amplitude at a predetermined frequency in the vibration signal where no fault exists a priori; extracting a monitoring indicator through the analysis model and based on the amplitude at the predetermined frequency; and determining whether there is a fault based on the comparison of the monitoring indicator with a preset threshold.
  • the electric drive system fault includes at least one of the following: abnormal noise of the motor rotor in the electric drive system, motor bearing failure in the electric drive system, and gearbox bearing failure in the electric drive system.
  • a fault detection device for an electric drive system, the device comprising: a receiving unit configured to receive an environmental signal about the electric drive system; and a processing unit configured to: determine whether a predetermined operating condition for detecting a fault is entered based on the environmental signal, and instruct the receiving unit to extract a vibration signal from a vibration sensor when it is determined that the predetermined operating condition is entered, wherein the vibration sensor is coupled to a predetermined position of the electric drive system; and determine whether the electric drive system has a fault based on the vibration signal.
  • the predetermined position includes at least one of the following: on the motor housing in the electric drive system and located near the axial center of the motor rotor; near the input shaft of the gearbox in the electric drive system; near the intermediate shaft of the gearbox; and on the motor controller housing in the electric drive system.
  • the vibration signal is an acceleration signal in a direction perpendicular to the ground.
  • the processing unit is configured to determine whether to enter the predetermined operating condition by a discriminant model generated by the following steps: obtaining a first data set in which a fault exists and a second data set in which no fault exists in the electric drive system, wherein the first data set and the second data set are respectively constructed based on the environmental signal; and training a classification model based on the first data set and the second data set to generate the discriminant model for determining whether to enter the predetermined operating condition.
  • the classification model includes: a classification model based on machine learning and deep learning.
  • the environmental signal includes at least one of the following: vehicle speed, rotation speed of a motor in the electric drive system, torque of the motor, temperature in the electric drive system, current and voltage of the motor.
  • the processing unit is configured to: perform low-pass filtering on the vibration signal, and convert the low-pass filtered signal to the frequency domain to generate frequency domain data; extract the amplitude at a predetermined frequency where a fault is expected to exist in the frequency domain data; construct an analysis model based on the amplitude at a predetermined frequency in the vibration signal where no fault exists a priori; extract a monitoring indicator through the analysis model and based on the amplitude at the predetermined frequency; and determine whether a fault exists based on a comparison between the monitoring indicator and a preset threshold.
  • the electric drive system fault includes at least one of the following: abnormal noise of the motor rotor in the electric drive system, motor bearing failure in the electric drive system, and gearbox bearing failure in the electric drive system.
  • a fault detection device for an electric drive system comprises: a memory configured to store instructions; and a processor configured to execute the instructions so as to perform any one of the methods described above.
  • a vehicle comprising any one of the systems described above.
  • a computer-readable storage medium wherein instructions are stored in the computer-readable storage medium, and wherein when the instructions are executed by a processor, the processor is caused to execute any one of the methods described above.
  • the methods and devices, vehicles, and storage media for detecting electric drive system faults provided in some embodiments of the present application can determine whether the vehicle's electric drive system has a fault or potential fault hazard, thereby facilitating users or maintenance units to eliminate the fault or hazard as soon as possible.
  • FIG1 shows an electric drive system according to an embodiment of the present application
  • FIG2 shows the working principle of a discriminant model according to an embodiment of the present application
  • FIG3 shows the working principle of the analysis model according to an embodiment of the present application
  • FIG4 shows a method for detecting an electric drive system fault according to an embodiment of the present application
  • FIG5 shows a method for detecting an electric drive system fault according to an embodiment of the present application
  • FIG6 shows a device for detecting faults in an electric drive system according to an embodiment of the present application.
  • a method 50 for detecting an electric drive system fault includes the following steps: receiving an environmental signal about the electric drive system in step S502, and determining whether to enter a predetermined operating condition for detecting a fault according to the environmental signal; in the case of determining to enter the predetermined operating condition, extracting a vibration signal from a vibration sensor under the predetermined operating condition in step S504; and determining whether the electric drive system has a fault according to the vibration signal in step S506.
  • Method 50 can determine whether the electric drive system of the vehicle has a fault or a potential fault through the above steps, so that the user of the vehicle or the vehicle maintenance unit is informed of the existence of the fault or the potential fault, and can intervene in the electric drive system of the vehicle at an early stage to prevent the expansion of the damage.
  • the working principle of each step of method 50 will be described in detail below.
  • step S502 method 50 receives an environmental signal about the electric drive system, and determines whether to enter a predetermined working condition for detecting a fault according to the environmental signal.
  • a predetermined working condition for detecting a fault The following will take the rotor abnormal fault as an example to illustrate the influence of the predetermined working condition on fault diagnosis. Since the deterioration speed of the rotor abnormal noise fault is slow, it will not pose a safety threat to the normal driving of the vehicle, and the real-time requirement for its diagnosis is not high, so this type of problem can be handled by state detection under predetermined working conditions.
  • the rotor abnormal noise fault Through the study of the performance of the rotor abnormal noise fault, it is found that when the vehicle is driving in the low-speed section, the rotor abnormal noise is not obvious; in the high-speed section, the motor rotor abnormal noise has a small degree of distinction in the vibration signal, so the abnormal noise is only more obvious under the predetermined working condition (for example, the medium and low speed section). Therefore, the detection of the fault can be carried out under the predetermined working condition. Due to the different diagnostic objects, the working conditions where the fault performance is prominent are different, so the predetermined working conditions in this article may not be easy to summarize in language or through empirical structures, but can be reflected in certain mathematical features, or a certain algorithm or classification method can be formed to determine whether it belongs to the predetermined working condition.
  • a discriminant model generated by the following steps can be used to determine whether the predetermined operating condition has been entered: (1) First, a first data set with a fault in the electric drive system and a second data set without a fault are obtained. The first data set and the second data set can be constructed based on environmental signals respectively. (2) Secondly, a classification model is trained based on the first data set and the second data set to generate a discriminant model for determining whether the predetermined operating condition has been entered.
  • the first data set and the second data set here are referred to as training data, which can be obtained by sorting out component data with known faults and without faults.
  • the classification model can be trained by taking the environmental signals in the first data set and the second data set as inputs and the known classification results (faults present, faults not present) of the first data set and the second data set as expected outputs.
  • a discriminant model will be obtained through the above steps.
  • the model can be a binary classification model.
  • the model can also give the probability of each classification. When using the model, the classification with a larger discriminant probability can be used as the discriminant result of the model.
  • the discriminant model determines that the probability of "entering the predetermined operating condition” is 70% and the probability of "not entering the predetermined operating condition” is 30%, it can be determined that the discriminant model determines that the predetermined operating condition has been entered.
  • the model may also include more than two classification results, but the classification results should at least include two categories: "entering the predetermined operating condition” and "not entering the predetermined operating condition”.
  • the classification model may be a classification model based on machine learning and deep learning.
  • the classification model may be trained by inputting a first data set (forward) and a second data set (reverse) including various environmental signals.
  • the training may be considered complete.
  • the trained classification model will be used as a discriminant model in method 50 to determine whether to enter a predetermined operating condition for detecting a fault.
  • the environmental signal may be vehicle speed, rotation speed of the motor in the electric drive system, torque of the motor, temperature of the electric drive system (specifically, the temperature of each component therein), current and voltage of the motor, etc.
  • the environmental signals listed above may be added or deleted, so as to facilitate the formation of more effective environmental signals that are more closely associated with the predetermined working conditions.
  • the following will take the decision tree model as an example to illustrate how to form a discriminant model, and further use the model in step S502 to determine whether a predetermined operating condition has been entered according to the received environmental signal. It should be noted that the following uses abnormal noise of a motor as an example to illustrate the working principle, and those skilled in the art will be able to apply the relevant principles to other types of fault detection processes after reading this application.
  • Method 20 first obtains normal environmental signals under working conditions where the rotor abnormal noise is obvious (faults exist) and other working conditions (no faults exist) in step S202.
  • the environmental signal under the working condition where the abnormal noise is obvious can be marked as 1
  • the environmental signal under other working conditions can be marked as 0.
  • a classification model is used to construct a predetermined working condition discrimination model based on the marked environmental signals. Specifically, the classification model is trained with these marked data to eventually obtain a stable structure. That is, the parameters of each part of the model tend to a stable value.
  • step S206 the vehicle can be made to regularly trigger the motor rotor abnormal noise detection, and the environmental signal can be input into the predetermined working condition discrimination model, and in step S208, the classification tree model can be used to determine whether the vehicle is in the predetermined working condition for rotor abnormal noise judgment.
  • step S504 extracts a vibration signal from a vibration sensor under a predetermined operating condition when it is determined that the predetermined operating condition has been entered.
  • the vibration sensor is coupled to a predetermined position of the electric drive system.
  • the predetermined position may be on a motor housing in the electric drive system and located near the axis center of the motor rotor, near the input shaft of a gearbox in the electric drive system, near the intermediate shaft of a gearbox, on a motor controller housing in the electric drive system, or other positions coupled to the housing.
  • FIG1 schematically depicts a possible configuration of an electric drive system 10.
  • the electric drive system 10 is composed of a motor 101, a motor controller 102, a gearbox 103 and a differential 104.
  • the mechanical rotating parts in the electric drive system 10 include a motor rotor, a motor internal bearing, a shaft, a gearbox internal bearing, a gear, a differential, etc.
  • the vibration of the mechanical rotating parts during movement can be transmitted to the mechanical housing thereof through the shaft teeth and the bearings.
  • the motor 101 plays an important role in the mutual conversion between high-voltage current and the torque of vehicle driving/braking.
  • the uneven temperature inside and outside the rotor of the motor 101 increases during operation, causing uneven release of internal stress, which will cause dynamic imbalance of the rotor, and may produce abnormal noise at a certain vehicle speed, which may bring a bad driving experience to the user.
  • the operation of the rotor of the vehicle's electric drive system can be modeled and monitored by collecting the vibration signal of the electric drive system 10 and combining it with other operating condition information collected by the vehicle.
  • maintenance reminder information can be sent to the user or after-sales service at the beginning of the dynamic imbalance of the rotor and before the human ear detects the abnormal noise, so as to ensure that the vehicle can be maintained in time, thereby improving the customer's vehicle comfort and satisfaction.
  • the sensitive direction of the acceleration sensor can be arranged in the Z-axis height direction of the vehicle (that is, the direction perpendicular to the ground); if the acceleration sensor is equally sensitive to all directions, the direction does not need to be emphasized during the arrangement process.
  • the acceleration sensor is equally sensitive to all directions, the direction does not need to be emphasized during the arrangement process.
  • omnidirectional acceleration signals only the component perpendicular to the ground can be extracted for analysis in the subsequent analysis process to reduce the difficulty of fault analysis due to vehicle movement, etc.
  • the optimal arrangement point of the acceleration sensor can be the motor housing measuring point 111 in Figure 1, which is close to the center of the rotor axis.
  • Such a layout is the closest to the rotor, which will be conducive to transmitting various mechanical vibration information from the rotor.
  • the motor controller 102, the motor 101 and the gear box 103 are often designed with a common housing, and the vibration of a certain point on the housing can be transmitted to other positions of the housing without distortion.
  • Such a feasible vibration measuring point can also be any one or more of the motor controller measuring point 112, the gear box input shaft measuring point 113, and the gear box intermediate shaft measuring point 114 in Figure 1.
  • the vibration measuring point can also be other measuring point positions on the housing.
  • the vibration sensor can be arranged on the outer wall of the housing or on the inner wall of the housing.
  • the difficulty of arranging different measuring points of the electric drive system 10, the sensor fixing method, the sensor harness distance, the sensor signal communication method, etc. can be comprehensively considered to select one or more simple, reliable and economical measuring points.
  • step S506 determines whether there is a fault in the electric drive system according to the vibration signal in step S506. Further referring to FIG. 3 , in some embodiments of the present application, in step S506, the following steps can be used to determine whether there is a fault in the electric drive system.
  • method 30 first performs low-pass filtering on the vibration signal in step S302, and converts the low-pass filtered signal to the frequency domain to generate frequency domain data; in step S304, the amplitude at a predetermined frequency at which a fault is expected to exist in the frequency domain data is extracted; in step S306, an analysis model is constructed based on the amplitude at a predetermined frequency in the vibration signal that does not have a fault a priori; in step S308, a monitoring index is extracted based on the analysis model and the amplitude at a predetermined frequency; in step S310, it is determined whether there is a fault according to the comparison between the monitoring index and the preset threshold.
  • the frequency at which the fault is expected to exist here refers to the frequency component obtained according to theoretical analysis or actual experience. If there is a fault in the electric drive system of the vehicle, it will be reflected in this series of predetermined frequencies.
  • step S302 the high-frequency vibration signal of a normal vehicle under a predetermined working condition can be obtained.
  • the vibration signal such as low-pass filtering and Fourier transform
  • the high-frequency vibration signal can be converted to the frequency domain space.
  • step S304 the amplitude information of the vibration signal at a specific speed order can be extracted in combination with the environmental signal.
  • an analysis model can be constructed to analyze whether the amplitude signal obtained in step S304 corresponds to a fault such as an abnormal noise, and an abnormal monitoring algorithm can be used to monitor and diagnose whether an abnormality occurs.
  • Independent principal component analysis is used to illustrate that an independent principal component analysis model is constructed by the amplitude of a vibration signal without a fault (for example, a vibration signal collected for a normal component) at a specific speed order.
  • the independent principal component analysis model can be used to reduce the dimensionality of the input data to reduce the difficulty of subsequent analysis.
  • various amplitude information can be converted into monitoring indicators.
  • step S308 the amplitude information extracted in step S304 can be input into the independent principal component analysis model to generate a monitoring indicator.
  • a judgment can be made based on the previously set risk threshold. If the monitoring indicator exceeds the threshold, it is considered that the electric drive motor rotor has a risk of abnormal noise; otherwise, it is considered that there is no abnormal noise or hidden danger of abnormal noise.
  • the electric drive system faults that can be detected by method 50 include abnormal noise of the motor rotor in the electric drive system, motor bearing failure in the electric drive system, gearbox bearing failure in the electric drive system, etc.
  • FIG4 takes rotor abnormal noise as an example to describe in detail the working principle of method 40 (hereinafter referred to as method 40) for detecting faults of electric drive system.
  • the vehicle will be able to enter the periodic triggering of the motor rotor abnormal noise diagnosis mechanism.
  • method 40 can be triggered at predetermined time intervals (for example, 10 minutes, 1 hour, etc.) and enter step S402.
  • the environmental signal is used as the input of the predetermined working condition discrimination model to obtain the vehicle operating condition information.
  • step S406 it can be determined whether the vehicle lasts for t seconds (for example, 5 seconds, 10 seconds, 20 seconds, etc.) under the predetermined working condition according to the output of the predetermined working condition discrimination model. If so, the high-frequency vibration signal of the electric drive system corresponding to this period is extracted and the step is entered into step S408; if it is not maintained for t seconds, it returns to step S404 until the working condition meets the requirement of t seconds.
  • step S408 the electric drive high-frequency data corresponding to the t-second time can be obtained as the input of the motor rotor abnormal noise analysis model, and the motor rotor abnormal noise analysis model is run in step S410 to output the motor rotor abnormal noise monitoring index.
  • step S412 it can be determined whether the motor rotor abnormal noise monitoring index exceeds the threshold value. If it exceeds the threshold value, step S414 is entered and a rotor abnormal noise warning message can be remotely sent to the user or after-sales service; if it does not exceed the threshold value, step S416 is entered and no operation is performed. According to the method 40 described above, the user or the vehicle maintenance organization can obtain an early warning of the rotor abnormal noise and can take timely measures to prevent the damage of the fault from expanding.
  • a fault detection device 60 for an electric drive system includes a receiving unit 602 and a processing unit 604.
  • Device 60 can determine whether there is a fault or a potential fault in the electric drive system of the vehicle, so that the user of the vehicle or the vehicle maintenance unit is informed of the existence of the fault or the potential fault, and can perform early intervention on the electric drive system of the vehicle to prevent the expansion of damage.
  • the working principles of the various parts of device 60 can be carried out with reference to the various steps of the fault detection method for the electric drive system described above, and the relevant contents are quoted here together. Due to space limitations, this article will not elaborate on them here.
  • the receiving unit of device 60 is configured to receive an environmental signal about the electric drive system, and the processing unit of device 60 is configured to: determine whether a predetermined operating condition for detecting a fault is entered based on the environmental signal, and if it is determined that the predetermined operating condition is entered, further instruct the receiving unit to extract a vibration signal from a vibration sensor, wherein the vibration sensor is coupled to a predetermined position of the electric drive system; and determine whether there is a fault in the electric drive system based on the vibration signal.
  • the predetermined position includes at least one of the following: on the motor housing in the electric drive system and located near the axial center of the motor rotor; near the input shaft of the gearbox in the electric drive system; near the intermediate shaft of the gearbox; and on the motor controller housing in the electric drive system.
  • the vibration signal is an acceleration signal in a direction perpendicular to the ground (the height direction of the vehicle, ie, the Z-axis direction of the vehicle in engineering).
  • the processing unit is configured to determine whether to enter a predetermined operating condition through a discriminant model generated by the following steps: obtaining a first data set in which a fault exists and a second data set in which no fault exists in the electric drive system, wherein the first data set and the second data set are constructed based on environmental signals, respectively; and training a classification model based on the first data set and the second data set to generate a discriminant model for determining whether to enter a predetermined operating condition.
  • the classification model includes: a decision tree model and a neural network model.
  • the environmental signal includes at least one of the following: vehicle speed, speed of the motor in the electric drive system, torque of the motor, temperature in the electric drive system (specifically, the temperature of each component therein), current and voltage of the motor.
  • the processing unit is configured to: perform low-pass filtering on the vibration signal, and convert the low-pass filtered signal to the frequency domain to generate frequency domain data; extract the amplitude at a predetermined frequency where a fault is expected to exist in the frequency domain data; construct an analysis model based on the amplitude at a predetermined frequency in the vibration signal where no fault exists a priori; extract a monitoring indicator quantity based on the amplitude at a predetermined frequency through the analysis model; and determine whether a fault exists based on the comparison between the monitoring indicator quantity and a preset threshold value.
  • the electric drive system fault includes at least one of the following: abnormal noise of a motor rotor in the electric drive system, a motor bearing fault in the electric drive system, and a gearbox bearing fault in the electric drive system.
  • Another aspect of the present application provides a fault detection device for an electric drive system, wherein the system comprises: a memory configured to store instructions; and a processor configured to execute the instructions so as to perform any one of the methods described above.
  • Another aspect of the present application provides a vehicle, the vehicle comprising any one of the systems described above.
  • a computer-readable storage medium in which instructions are stored, and when the instructions are executed by a processor, the processor is caused to execute any method for detecting an electric drive system fault as described above.
  • the computer-readable medium referred to in the present application includes various types of computer storage media, which can be any available medium that can be accessed by a general or special computer.
  • the computer-readable medium may include RAM, ROM, EPROM, E2PROM , register, hard disk, removable disk, CD-ROM or other optical disk storage, disk storage or other magnetic storage device, or any other temporary or non-temporary medium that can be used to carry or store a desired program code unit in the form of an instruction or data structure and can be accessed by a general or special computer, or a general or special processor.
  • the disk usually copies data magnetically, while the disc uses a laser to optically copy data.
  • the above combination should also be included in the scope of protection of the computer-readable medium.
  • the exemplary storage medium is coupled to the processor so that the processor can read and write information from/to the storage medium.
  • the storage medium can be integrated into the processor.
  • the processor and the storage medium can reside in an ASIC.
  • the ASIC can reside in a user terminal.
  • the processor and the storage medium may reside as discrete components in a user terminal.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Sustainable Development (AREA)
  • Sustainable Energy (AREA)
  • Power Engineering (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Electric Propulsion And Braking For Vehicles (AREA)

Abstract

L'invention concerne un procédé (50) et un dispositif (60) pour détecter une panne d'un système d'entraînement électrique, et un véhicule et un support de stockage. Le procédé (50) de détection de la panne du système d'entraînement électrique comprend les étapes suivantes : recevoir un signal d'environnement pour un système d'entraînement électrique (10) et, en fonction du signal d'environnement, déterminer s'il faut entrer dans un état de fonctionnement prédéfini pour détecter une panne ; extraire un signal de vibration d'un capteur de vibrations lorsqu'il est déterminé d'entrer dans l'état de fonctionnement prédéfini, le capteur de vibrations étant couplé à une position prédéfinie du système d'entraînement électrique (10) ; et en fonction du signal de vibration, déterminer la présence d'une panne dans le système d'entraînement électrique (10).
PCT/CN2023/133849 2022-11-29 2023-11-24 Procédé et dispositif de détection de panne de système d'entraînement électrique, et véhicule et support de stockage WO2024114512A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211507963.1A CN118107389A (zh) 2022-11-29 2022-11-29 检测电驱动系统故障的方法和装置、车辆、存储介质
CN202211507963.1 2022-11-29

Publications (1)

Publication Number Publication Date
WO2024114512A1 true WO2024114512A1 (fr) 2024-06-06

Family

ID=91207356

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/133849 WO2024114512A1 (fr) 2022-11-29 2023-11-24 Procédé et dispositif de détection de panne de système d'entraînement électrique, et véhicule et support de stockage

Country Status (2)

Country Link
CN (1) CN118107389A (fr)
WO (1) WO2024114512A1 (fr)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20190072165A (ko) * 2017-12-15 2019-06-25 주식회사 에이스이앤티 모터 고장 진단 시스템
CN112285561A (zh) * 2020-11-13 2021-01-29 烟台杰瑞石油装备技术有限公司 电机故障监测装置、驱动电机系统和电机故障监测方法
US20210356361A1 (en) * 2020-05-15 2021-11-18 Deere & Company Fault detection technique for a bearing
CN114216640A (zh) * 2022-02-21 2022-03-22 蘑菇物联技术（深圳）有限公司 用于检测工业设备故障状态的方法、设备和介质
US20220155373A1 (en) * 2020-11-13 2022-05-19 Yantai Jereh Petroleum Equipment & Technologies Co., Ltd. Motor malfunction monitoring device, drive motor system and motor malfunction monitoring method
CN114636554A (zh) * 2022-03-15 2022-06-17 联合汽车电子有限公司 电驱动系统轴承故障监测方法和装置
CN115169385A (zh) * 2022-06-16 2022-10-11 蔚来动力科技(合肥)有限公司 拟合车辆用目标传感器的方法和系统、存储介质

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20190072165A (ko) * 2017-12-15 2019-06-25 주식회사 에이스이앤티 모터 고장 진단 시스템
US20210356361A1 (en) * 2020-05-15 2021-11-18 Deere & Company Fault detection technique for a bearing
CN112285561A (zh) * 2020-11-13 2021-01-29 烟台杰瑞石油装备技术有限公司 电机故障监测装置、驱动电机系统和电机故障监测方法
US20220155373A1 (en) * 2020-11-13 2022-05-19 Yantai Jereh Petroleum Equipment & Technologies Co., Ltd. Motor malfunction monitoring device, drive motor system and motor malfunction monitoring method
CN114216640A (zh) * 2022-02-21 2022-03-22 蘑菇物联技术（深圳）有限公司 用于检测工业设备故障状态的方法、设备和介质
CN114636554A (zh) * 2022-03-15 2022-06-17 联合汽车电子有限公司 电驱动系统轴承故障监测方法和装置
CN115169385A (zh) * 2022-06-16 2022-10-11 蔚来动力科技(合肥)有限公司 拟合车辆用目标传感器的方法和系统、存储介质

Also Published As

Publication number Publication date
CN118107389A (zh) 2024-05-31

Similar Documents

Publication Publication Date Title
Mohd Ghazali et al. Vibration analysis for machine monitoring and diagnosis: a systematic review
KR102166649B1 (ko) 기계학습을 이용한 회전기계 고장 진단 및 예측시스템
CN109901537B (zh) 用于边缘计算侧的机械设备运行状态监测方法和系统
CN116842423A (zh) 基于多模态深度学习的航空发动机故障诊断方法及系统
CN111509847A (zh) 一种电网机组状态的智能检测系统及方法
EP3913453B1 (fr) Système et procédé de détection de défaillance pour un véhicule
Liu et al. Technology development and commercial applications of industrial fault diagnosis system: a review
CN103998775A (zh) 用于确定风能源设备的转子叶片的机械损坏的方法
CN105318959A (zh) 用于监测蒸汽涡轮的轴线的次同步扭转振荡的方法和系统
KR20110131411A (ko) 허브 베어링 검사 방법
CN114565006A (zh) 一种基于深度学习的风力发电机叶片损伤检测方法及系统
WO2022147684A1 (fr) Procédé et appareil d'identification d'anomalies dans un appareil mécanique ou un composant mécanique
KR102545672B1 (ko) 기계고장 진단 방법 및 장치
CN116383633A (zh) 一种多因素综合分析的机制砂振动筛故障检测方法及系统
JP4412306B2 (ja) 異常判定方法および異常判定装置
CN113516023B (zh) 设备振动异常诊断方法和系统
Khamidov et al. Locomotive asynchronous traction motor rolling bearing fault detection based on current intelligent methods
WO2024114512A1 (fr) Procédé et dispositif de détection de panne de système d'entraînement électrique, et véhicule et support de stockage
Choudhary et al. Fault diagnosis of induction motor under varying operating condition
Kavitha et al. Magnetoresistance sensor-based rotor fault detection in induction motor using non-decimated wavelet and streaming data
Yu et al. Distributed real time compressor blade health monitoring system
US20230260332A1 (en) Prognostic and health monitoring system for a device with a rotating component
GB2579786A (en) Device and method of integrity monitoring and failure predicting for a vehicle system
CN105651512A (zh) 一种汽车驱动桥主减齿轮包块检测方法
CN205449521U (zh) 基于emd降噪的吸油烟机故障诊断的系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23896663

Country of ref document: EP

Kind code of ref document: A1