Three-axis distributed electric drive vehicle fault diagnosis processing method and system

Abstract

The invention belongs to the technical field of vehicle driving monitoring, and particularly discloses a three-axis distributed electric drive vehicle fault diagnosis processing method and system, and the method comprises the steps: collecting the motor operation state information of a three-axis 6 * 6 distributed electric drive vehicle in real time, the fault level of each motor is analyzed and evaluated based on the collected data; receiving the output fault level information of each motor in real time, and transmitting an optimal fault-tolerant control instruction to a vehicle motor controller based on a diagnosis result and a motor distribution condition so as to regulate and control the running state of the fault motor; wherein the fault levels comprise zero level, first level, second level and third level, which are respectively corresponding to no fault, prompt fault, slight fault and serious fault. According to the fault diagnosis processing method, the fault processing decision is accurately made according to the detailed fault condition of the vehicle motor, the vehicle safety is guaranteed, and meanwhile the dynamic property for continuous driving is provided for the vehicle as much as possible.

Description

Technical Field

[0001] This invention belongs to the field of vehicle drive monitoring technology, and more specifically, relates to a fault diagnosis and processing method and system for a three-axis distributed electric drive vehicle. Background Technology

[0002] With increasing global emphasis on environmental protection and a reduction in reliance on traditional gasoline-powered vehicles, the development of new energy vehicles has made significant progress worldwide. Among these advancements, the electric drive system, as the core powertrain of new energy vehicles, has undergone rapid iteration and development. In particular, the application of distributed electric drive technology has not only been widely adopted in traditional four-wheel drive vehicles but is also beginning to emerge in the field of special vehicles such as off-road vehicles, including six-wheel drive (6×6) vehicles. For three-axle, six-wheel drive 6×6 distributed drive vehicles, their unique structural design—two motors per axle, for a total of six drive motors—makes them an ideal choice for traversing complex terrain. Compared to traditional vehicles, their system complexity is significantly increased, involving multiple aspects such as the coordinated control of multiple motors, optimization of power transmission paths, and power distribution strategies between axles.

[0003] Currently, existing technologies for fault diagnosis and handling of distributed electric drive systems have been researched and applied to some extent in both single-motor two-wheel drive and four-wheel drive vehicles. For two-wheel drive vehicles, key parameters such as motor current, voltage, and speed are monitored, and simple fault diagnosis algorithms are used to determine if the motor has common faults such as overload, short circuit, or phase loss. Once a fault is detected, basic measures such as cutting off the motor power and issuing a fault alarm are typically taken to protect the motor and vehicle. For four-wheel drive vehicles, existing technologies consider the power distribution and coordination between more axles in fault diagnosis. By installing sensors at each wheel to monitor wheel speed, torque, and other information in real time, and combining this with the vehicle's driving status and driver intent, more complex control algorithms are used to analyze the operating status of each motor. When a motor fails or a wheel slips, the vehicle's basic driving functions can be maintained by adjusting the output power of other motors and controlling the braking system, guiding the driver to take appropriate actions, such as reducing speed or switching drive modes.

[0004] However, existing fault diagnosis and handling methods for distributed electric drive systems have significant limitations and cannot effectively solve the complex fault diagnosis and handling problems faced by 6×6 distributed drive vehicles. For example, in terms of fault diagnosis, existing technologies are mostly designed for two-wheel or four-wheel drive vehicles, and their diagnostic algorithms are mainly based on a smaller number of motors and relatively simple power transmission paths. However, 6×6 vehicles have six drive motors distributed on three different axles. Secondly, in terms of fault handling strategies, existing technologies for two-wheel or four-wheel drive vehicles are often not directly applicable to 6×6 vehicles. For example, in a four-wheel drive vehicle, when one wheel slips, the vehicle's driving stability can be restored by adjusting the driving force of the other three wheels. However, for a 6×6 vehicle, due to its special three-axle, six-wheel layout, power distribution and vehicle stability control become more complex. In addition, existing technologies lack a comprehensive analysis and systematic organization of various possible fault scenarios for 6×6 vehicles, resulting in an inability to provide effective solutions when facing complex and diverse fault scenarios. This affects the reliability and safety of 6×6 distributed drive vehicles and limits their widespread application and further development in complex environments such as off-road driving. Summary of the Invention

[0005] In view of the above-mentioned defects or improvement needs of the existing technology, the present invention provides a fault diagnosis and processing method and system for a three-axis distributed electric drive vehicle. Based on the detailed fault conditions of the vehicle motor, the system can make accurate fault handling decisions, ensuring vehicle safety while providing the vehicle with as much power as possible to continue driving.

[0006] To achieve the above objectives, the present invention provides a fault diagnosis and processing method for a three-axle distributed electric drive vehicle, comprising:

[0007] S1: Real-time acquisition of motor operating status information of a three-axis 6×6 distributed electric drive vehicle, and analysis and evaluation of the fault level of each motor based on the acquired data;

[0008] S2: Receives fault level information of each motor in real time, and based on the diagnostic results and motor distribution, sends the optimal fault-tolerant control command to the vehicle motor controller to regulate the operating status of the faulty motor.

[0009] The fault levels include: Level 0, Level 1, Level 2, and Level 3, which correspond to no fault, indicative fault, minor fault, and serious fault, respectively.

[0010] Further, step S1 includes:

[0011] S101: Using preset engineering experience, physical laws, basic parameter thresholds and dynamic thresholds under multiple working conditions, perform preliminary anomaly detection and rough fault classification on the real-time collected data.

[0012] S102: Identify potential failure modes from large amounts of operational data using data mining and machine learning algorithms.

[0013] Further, step S101 includes:

[0014] S1011: Based on historical operating data, combined with the distribution range of key indicators of typical roads and typical driving scenarios, establish a scenario-specific threshold set, and switch the applicable threshold in real time according to the current CAN bus upload signal.

[0015] S1012: Integrates a timing event recognition framework, linking information from motor drivers, power management units, and sensor nodes to achieve cross-module linkage fault symptom detection;

[0016] S1013: If the uploaded data of a certain indicator exceeds the threshold range of the current working condition, it is marked as an abnormal signal; if multiple indicators exceed the limit together, it is judged as a high-risk event through a complex event handling mechanism; at the same time, sudden anomalies are judged by the data change rate to prevent misjudgment caused by steady drift.

[0017] Further, step S102 includes:

[0018] S1021: Using the dataset from step S101, match the dataset with the fault type labels, and train different machine learning models to achieve efficient fault identification and classification. At the same time, ensemble learning is used to further improve the robustness and accuracy of diagnosis.

[0019] S1022: Cluster and detect anomalies in the operational data to further capture unknown fault modes;

[0020] S1023: When there is insufficient data on the target motor or vehicle model, the model pre-trained on similar motor models or historical vehicle model data will be fine-tuned with a small amount of target domain data and then applied to the target task. At the same time, through meta-learning or metric-based learning methods, the model can quickly adapt and accurately diagnose new fault types even when it has only seen a very small number of fault samples.

[0021] Furthermore, in step S2, when the fault level of the motor is level three, a command is sent to the vehicle motor controller to set the torque of the two motors on the shaft where the motor is located to 0 Nm, and the vehicle enters limp mode.

[0022] Furthermore, in step S2, when a first-level and / or second-level fault occurs in any motor on any axle of the vehicle, it includes: if the fault level is first-level, sending an alarm prompt to the vehicle's main control console.

[0023] If a motor experiences a level 2 fault, when a single motor experiences a level 2 fault, torque limiting control is applied to both motors on that shaft with a torque limiting coefficient of a1; when both motors experience a level 2 fault, torque limiting control is applied to both motors on that shaft with a torque limiting coefficient of a2.

[0024] Furthermore, in step S2, when a first-level and / or second-level fault occurs in any two motors on the vehicle's axles, it includes: if both fault levels are first-level, sending an alarm notification to the vehicle's main control console.

[0025] If a motor experiences a level 2 fault, when one motor experiences a level 2 fault, torque limiting control is applied to both motors on that shaft with a torque limiting coefficient of a1.

[0026] When two motors experience a level 2 fault, if they are on the same shaft, torque limiting control is applied to both motors on that shaft with a torque limiting coefficient of a2; if they are on different shafts but on the same side, torque limiting control is applied to both motors on both shafts with a torque limiting coefficient of a2; if they are on different shafts and on different sides, torque limiting control is applied to both motors on both shafts with a torque limiting coefficient of a1.

[0027] When three motors experience a level 2 fault, the two coaxial motors with level 2 faults are both subject to torque limiting control with a torque limiting coefficient of a2, and the motors on the other shaft are both subject to torque limiting control with a torque limiting coefficient of a1.

[0028] When all four motors experience a level 2 fault, torque limiting control is applied to both shaft motors with a torque limiting coefficient of a2.

[0029] Furthermore, in step S2, when the motors on the three axles of the vehicle experience a first-level and / or second-level fault, it includes: if all fault levels are first-level, sending an alarm prompt to the vehicle's main control console;

[0030] If a motor experiences a level 2 fault, when one motor experiences a level 2 fault, torque limiting control is applied to both motors on that shaft with a torque limiting coefficient of a1.

[0031] When two motors experience a level 2 fault, if they are on the same shaft, torque limiting control is applied to both motors on that shaft with a torque limiting coefficient of a2; if they are on different shafts but on the same side, torque limiting control is applied to both motors on both shafts with a torque limiting coefficient of a2; if they are on different shafts and on different sides, torque limiting control is applied to both motors on both shafts with a torque limiting coefficient of a1.

[0032] When three motors have a level 2 fault, such as two level 2 fault motors on the same shaft, torque limiting control is applied to the two motors on that shaft with a torque limiting coefficient of a2, and torque limiting control is applied to all motors on the shaft of the other level 2 fault motor with a torque limiting coefficient of a1.

[0033] If the three motors are not coaxial and are located on the same side, torque limiting control is applied to all three motors with a torque limiting coefficient of a2.

[0034] If the three motors are not coaxial, two motors are located on the same side, and one motor is located on the opposite side, torque limiting control is applied to the two shaft motors where the faulty motor is located on the same side, and the torque limiting coefficient is a2. Torque limiting control is applied to the other shaft motor, and the torque limiting coefficient is a1.

[0035] When four motors experience a level two fault, such as when the four motors are distributed on two shafts, torque limiting control is applied to both shaft motors with a torque limiting coefficient of a2.

[0036] If four motors are distributed on three axes, torque limiting control is applied to the motors on the axes where two motors have level two faults, and the torque limiting coefficient is a2. For the other two axes, if the level two fault motors are on the same side, torque limiting control is applied to the motors on both axes, and the torque limiting coefficient is a2. If the level two fault motors are on different sides, torque limiting control is applied to the motors on both axes, and the torque limiting coefficient is a1.

[0037] When five motors have a level 2 fault, torque limiting control is applied to the motors on the shafts where two motors have a level 2 fault, with a torque limiting coefficient of a2. Torque limiting control is applied to the motors on the other shaft, with a torque limiting coefficient of a1.

[0038] When six motors experience a level-two fault, torque limiting control is applied to all three-axis motors with a torque limiting coefficient of a2.

[0039] Furthermore, the values ​​of the torque limiting coefficients a1 and a2 are both in the range of 0 to 1, and a1 is greater than a2. At the same time, when the vehicle stability or dynamism is insufficient, the values ​​of the torque limiting coefficients a1 and a2 are reduced simultaneously.

[0040] Another aspect of the present invention provides a fault diagnosis and processing system for a three-axis distributed electric drive vehicle, applied to the above-mentioned fault diagnosis and processing method, comprising:

[0041] The fault diagnosis module is used to collect real-time motor operating status information of the three-axle 6×6 distributed electric drive vehicle, and analyze and evaluate the fault level of each motor based on the collected data.

[0042] The fault handling module is used to receive the fault level information of each motor output by the fault diagnosis module in real time, and based on the diagnosis results and motor distribution, send the optimal fault-tolerant control command to the vehicle motor controller to regulate the operating status of the faulty motor.

[0043] In summary, compared with the prior art, the above-described technical solutions conceived by this invention can achieve the following beneficial effects:

[0044] 1. The fault diagnosis and handling method of the present invention makes accurate fault handling decisions based on the detailed fault conditions of the vehicle motor, ensuring vehicle safety while providing the vehicle with as much power as possible to continue driving.

[0045] 2. The fault diagnosis and processing method of the present invention combines rule-based and threshold-based rapid screening with data-driven intelligent identification, which can leverage the complementary advantages of the two. By first using a rule layer to remove the vast majority of normal data and then handing over the remaining anomalies to the model for in-depth analysis, the false alarm rate and false negative rate can be significantly reduced. Secondly, rule judgment has low computational load and low latency, and can run at high speed on edge computing units. Furthermore, the more computationally intensive machine learning module is only invoked when a potential anomaly is detected, which effectively alleviates the real-time computing pressure, improves the comprehensiveness and accuracy of fault detection, and can also balance real-time performance and computational efficiency, providing a fast and accurate hybrid solution for vehicle fault diagnosis.

[0046] 3. The fault diagnosis and handling method of the present invention can implement differentiated control strategies by accurately analyzing the fault type, level and motor spatial distribution information, thereby effectively preventing the spread of faults, maximizing the continuous controllable operation of the power system and the symmetrical power distribution on both sides of the vehicle, and providing drivers and passengers with a safer and more reliable travel experience. Attached Figure Description

[0047] Figure 1 This is a schematic diagram of the workflow of the fault diagnosis and processing system according to an embodiment of the present invention;

[0048] Figure 2 This is a flowchart illustrating the steps of a fault diagnosis and processing method for a three-axle distributed electric drive vehicle according to an embodiment of the present invention.

[0049] Figure 3 This is a flowchart illustrating step S1 of an embodiment of the present invention;

[0050] Figure 4 This is a flowchart illustrating step S101 of an embodiment of the present invention.

[0051] Figure 5 This is a flowchart illustrating step S102 of an embodiment of the present invention.

[0052] Figure 6 This is a schematic diagram of the fault diagnosis and processing flow for any axle motor failure in a vehicle according to an embodiment of the present invention.

[0053] Figure 7 This is a schematic diagram of the fault diagnosis and processing flow for any two-axle motor fault in a vehicle according to an embodiment of the present invention.

[0054] Figure 8 This is a schematic diagram of the fault diagnosis and handling process for a vehicle three-axis motor fault according to an embodiment of the present invention. Detailed Implementation

[0055] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only intended to illustrate the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.

[0056] Example 1

[0057] like Figure 1 , Figures 6 to 8 As shown, Embodiment 1 of the present invention provides a fault diagnosis and processing system for a three-axle distributed electric drive vehicle, comprising: a fault diagnosis module, which is used to collect the motor operating status information of the three-axle 6×6 distributed electric drive vehicle in real time, and analyze and evaluate the fault level of each motor based on the collected data; and a fault processing module, which is used to receive the fault level information of each motor output by the fault diagnosis module in real time, and based on the diagnosis results and motor distribution, send the optimal fault-tolerant control command to the vehicle motor controller to regulate the operating status of the faulty motor. The fault diagnosis and processing system of the present invention makes accurate fault handling decisions based on the detailed fault conditions of the vehicle motors, ensuring vehicle safety while providing the vehicle with as much power as possible for continued driving.

[0058] It should be noted that the distributed electric drive vehicle includes wheel-side distributed and centrally distributed vehicles, characterized in that there is no mechanical connection such as a differential between the vehicle wheels or motors, and one motor controls the rotation of one wheel.

[0059] like Figure 1 As shown, the fault diagnosis module also includes a fault database, which contains various fault information, including preset motor operating parameter threshold data, and supports iterative data updates. The fault diagnosis module determines the actual fault level of the motor by matching the information in the fault database with real-time motor operating status information. It is understood that the motor operating status information is obtained from various sensors, including but not limited to: motor operating temperature, phase current, bus current, bus voltage, relative position signals of the rotor and stator, and motor rotation speed, etc., to clearly classify and list numerous motor fault conditions, ensuring that the fault database can fully cover all faults and further ensuring vehicle safety and stability.

[0060] Furthermore, the fault levels include: Level 0, Level 1, Level 2, and Level 3, which correspond to no fault, warning fault, minor fault, and serious fault, respectively. It can be understood that "no fault" indicates that the motor is operating normally, i.e., no fault has occurred, and no fault information is sent to the fault processing unit; "warning fault" is a warning level, indicating that the motor status does not affect current driving safety, but the driver needs to be alerted to potential risks or performance degradation, requiring attention or subsequent maintenance. Examples include: motor winding / bearing temperature approaching the design threshold without triggering protection, motor efficiency decreasing by 5% to 10%, and transient noise in the speed or position sensor output; "minor fault" is a degraded operation level, indicating that the fault may cause localized performance degradation. The motor output needs to be limited, but basic driving functions can still be maintained. These include: the temperature of one phase winding exceeds the limit but does not reach the hardware damage threshold, the difference between the three phase currents is greater than 15%, and the sensor communication packet loss rate increases by 10% to 20%. The serious faults are emergency protection level, which means that the motor status at this time directly threatens hardware safety or causes the vehicle to lose control. The vehicle needs to be stopped and repaired as soon as possible and safety protection should be activated immediately. These include: short circuit causing the current to instantly exceed twice the peak value, power module breakdown causing direct conduction of the DC bus, winding temperature exceeding 140°C, and motor shaft jamming causing a surge in stall current.

[0061] Furthermore, the fault diagnosis module numbers the motors according to their distribution, designating them as left first motor, right first motor, left second motor, right second motor, left third motor, and right third motor. The left first motor and right first motor belong to the first axis, the left second motor and right second motor belong to the second axis, and the left third motor and right third motor belong to the third axis. The fault diagnosis module matches the fault level of each motor with its corresponding axis and sends the corresponding fault information to the fault processing module.

[0062] Understandably, through the above design, the fault diagnosis module significantly improves the accuracy and response efficiency of fault identification by integrating a fault database containing various fault information and matching it with the real-time operating status information of the motor. Simultaneously, by structurally numbering each motor in the six-wheel distributed drive system, it achieves logical management of the motor spatial layout, providing a clear physical hierarchy for subsequent fault location and analysis. Furthermore, the fault diagnosis module can correlate the fault level detected by each motor with the axle system to which the motor belongs, comprehensively judging the degree of impact of the fault on the vehicle's power distribution and driving safety. This realizes a multi-level fault assessment system from point to axle and from axle to the entire vehicle system, providing reliable data support for formulating differentiated control strategies and emergency response measures. This significantly improves the pertinence and timeliness of fault handling, enhances the intelligence level and fault tolerance of the vehicle control system, and is of great significance for improving the operational stability and safety of three-axle six-wheel distributed electric drive vehicles under complex working conditions.

[0063] like Figure 1 , Figures 6 to 8 As shown, the fault handling module outputs corresponding execution information to the vehicle motor controller based on the fault information issued by the fault diagnosis module, and sends warning information to the vehicle's main control panel. It is understood that when any motor experiences a level one, two, or three fault, the fault handling module will send a warning message to the vehicle's main control panel or relevant display devices to remind the driver to pay attention to vehicle motor safety.

[0064] In an optional embodiment, when the fault level is zero, the instrument panel displays normally without alarms; when the fault level is one, the instrument panel displays non-emergency warning information; when the fault level is two, the instrument panel displays a yellow warning light and pops up specific fault information, while the vehicle voice system broadcasts fault information and handling suggestions, such as please slow down and go to a service station as soon as possible; when the fault level is three, the instrument panel displays a red warning light and emits an emergency beep, while the vehicle voice system broadcasts fault information and handling suggestions, and forcibly pops up fault details and emergency handling suggestions, such as immediately pulling over and seeking help.

[0065] It is understandable that, since the vehicle is in a non-faulty state when the fault level is zero, the subsequent description of the vehicle motor failure refers to a level one, two, and / or three fault in the motor.

[0066] Furthermore, when the motor's fault level is level three, the fault handling module sends an instruction to the vehicle motor controller to set the torque of the two motors on the shaft where the motor is located to 0 Nm, and the vehicle enters limp mode.

[0067] Furthermore, when a first-level and / or second-level fault occurs on any axle motor of the three-axle 6×6 distributed electric drive vehicle, if the fault level is first-level, an alarm prompt is sent to the vehicle's main control console.

[0068] If a motor experiences a level 2 fault, when a single motor experiences a level 2 fault, torque limiting control is applied to both motors on that shaft with a torque limiting coefficient of a1; when both motors experience a level 2 fault, torque limiting control is applied to both motors on that shaft with a torque limiting coefficient of a2.

[0069] Furthermore, when any two motors on any two axles of the three-axle 6×6 distributed electric drive vehicle experience a first-level and / or second-level fault, if both faults are at the first-level, an alarm prompt is sent to the vehicle's main control console.

[0070] If a motor experiences a level 2 fault, when one motor experiences a level 2 fault, torque limiting control is applied to both motors on that shaft with a torque limiting coefficient of a1.

[0071] When two motors experience a level 2 fault, if they are on the same shaft, torque limiting control is applied to both motors on that shaft with a torque limiting coefficient of a2; if they are on different shafts but on the same side, torque limiting control is applied to both motors on both shafts with a torque limiting coefficient of a2; if they are on different shafts and on different sides, torque limiting control is applied to both motors on both shafts with a torque limiting coefficient of a1.

[0072] When three motors experience a level 2 fault, the two coaxial motors with level 2 faults are both subject to torque limiting control with a torque limiting coefficient of a2, and the motors on the other shaft are both subject to torque limiting control with a torque limiting coefficient of a1.

[0073] When all four motors experience a level 2 fault, torque limiting control is applied to both shaft motors with a torque limiting coefficient of a2.

[0074] Furthermore, when a level 1 or level 2 fault occurs in the motors on the three axles of the three-axle 6×6 distributed electric drive vehicle, if the fault level is level 1, an alarm prompt is sent to the vehicle's main control console.

[0075] If a motor experiences a level 2 fault, when one motor experiences a level 2 fault, torque limiting control is applied to both motors on that shaft with a torque limiting coefficient of a1.

[0076] When two motors experience a level 2 fault, if they are on the same shaft, torque limiting control is applied to both motors on that shaft with a torque limiting coefficient of a2; if they are on different shafts but on the same side, torque limiting control is applied to both motors on both shafts with a torque limiting coefficient of a2; if they are on different shafts and on different sides, torque limiting control is applied to both motors on both shafts with a torque limiting coefficient of a1.

[0077] When three motors have a level 2 fault, such as two level 2 fault motors on the same shaft, torque limiting control is applied to the two motors on that shaft with a torque limiting coefficient of a2, and torque limiting control is applied to all motors on the shaft of the other level 2 fault motor with a torque limiting coefficient of a1.

[0078] If the three motors are not coaxial and are located on the same side, torque limiting control is applied to all three motors with a torque limiting coefficient of a2.

[0079] If the three motors are not coaxial, two motors are located on the same side, and one motor is located on the opposite side, torque limiting control is applied to the two shaft motors where the faulty motor is located on the same side, and the torque limiting coefficient is a2. Torque limiting control is applied to the other shaft motor, and the torque limiting coefficient is a1.

[0080] When four motors experience a level two fault, such as when the four motors are distributed on two shafts, torque limiting control is applied to both shaft motors with a torque limiting coefficient of a2.

[0081] If four motors are distributed on three axes, torque limiting control is applied to the motors on the axes where two motors have level two faults, and the torque limiting coefficient is a2. For the other two axes, if the level two fault motors are on the same side, torque limiting control is applied to the motors on both axes, and the torque limiting coefficient is a2. If the level two fault motors are on different sides, torque limiting control is applied to the motors on both axes, and the torque limiting coefficient is a1.

[0082] When five motors have a level 2 fault, torque limiting control is applied to the motors on the shafts where two motors have a level 2 fault, with a torque limiting coefficient of a2. Torque limiting control is applied to the motors on the other shaft, with a torque limiting coefficient of a1.

[0083] When six motors experience a level-two fault, torque limiting control is applied to all three-axis motors with a torque limiting coefficient of a2.

[0084] It is understandable that the aforementioned single-sided faults and same-sided faults include the left or right side of the vehicle. When a motor on one axle experiences a level two fault, and the other motor on that axle experiences a level zero or level one fault, the aforementioned torque limiting control must also be followed to ensure that the torque on both sides of the vehicle is the same, thereby further ensuring the vehicle's driving stability and safety.

[0085] Table 1. Fault Levels of Motors in Three-Axle 6×6 Distributed Electric Drive Vehicles

[0086]

[0087]

[0088] Furthermore, the torque limiting coefficients a1 and a2 both range from 0 to 1, with a1 being greater than a2. Simultaneously, when vehicle stability or responsiveness is insufficient, the values ​​of torque limiting coefficients a1 and a2 are reduced. Preferably, the initial values ​​of torque limiting coefficients a1 and a2 are 0.7 and 0.5, respectively.

[0089] In an optional embodiment, the response cycle of the fault diagnosis module and the fault processing module is 15ms to 25ms, in order to meet the high-speed requirements of the distributed electric drive system for fault identification and processing, and to ensure that the vehicle control system has a rapid response capability when faced with sudden or transient faults.

[0090] Understandably, through the above design, by accurately analyzing the fault type, level, and motor spatial distribution information provided by the fault diagnosis module, the fault handling module can implement differentiated control strategies, thereby effectively preventing the spread of faults, maximizing the continuous and controllable operation of the power system and the symmetrical power distribution on both sides of the vehicle, and providing drivers and passengers with a safer and more reliable travel experience.

[0091] Example 2

[0092] like Figures 2 to 8 As shown, Embodiment 2 of the present invention provides a fault diagnosis and processing method for a three-axle distributed electric drive vehicle, comprising the following steps:

[0093] S1: Real-time acquisition of motor operating status information of a three-axis 6×6 distributed electric drive vehicle, and analysis and evaluation of the fault level of each motor based on the acquired data;

[0094] S2: Receives fault level information of each motor in real time, and based on the diagnostic results and motor distribution, sends the optimal fault-tolerant control command to the vehicle motor controller to regulate the operating status of the faulty motor.

[0095] The fault levels include: Level 0, Level 1, Level 2, and Level 3, which correspond to no fault, indicative fault, minor fault, and serious fault, respectively.

[0096] Further, step S1 includes:

[0097] S101: Using preset engineering experience, physical laws, basic parameter thresholds and dynamic thresholds under multiple working conditions, perform preliminary anomaly detection and rough fault classification on the real-time collected data.

[0098] S102: Identify potential failure modes from large amounts of operational data using data mining and machine learning algorithms.

[0099] Further, step S101 includes:

[0100] S1011: Based on historical operating data, combined with the distribution range of key indicators of typical roads and typical driving scenarios, establish a scenario-specific threshold set, and switch the applicable threshold in real time according to the current CAN bus (Controller Area Network) uploaded signal;

[0101] S1012: Integrates a timing event recognition framework, linking information from motor drivers, power management units, and sensor nodes to achieve cross-module linkage fault symptom detection;

[0102] S1013: If the uploaded data of a certain indicator exceeds the threshold range of the current working condition, it is marked as an abnormal signal; if multiple indicators exceed the limit together, it is judged as a high-risk event through a complex event handling mechanism; at the same time, sudden anomalies are judged by the data change rate to prevent misjudgment caused by steady drift.

[0103] Typical roads include highways, roads, and urban driving conditions; typical driving scenarios include acceleration, deceleration, hill climbing, and sharp turns; key indicators include core parameters such as current, voltage, speed, temperature, and torque output by the motor controller, key state parameters output by the battery BMS, and speed and acceleration in vehicle dynamics; scenario-specific threshold sets are set by expert experience and experimental data.

[0104] Further, step S102 includes:

[0105] S1021: Using the dataset from step S101, match the dataset with the fault type labels, and train different machine learning models to achieve efficient fault identification and classification. At the same time, ensemble learning is used to further improve the robustness and accuracy of diagnosis.

[0106] It should be noted that this machine learning model includes supervised learning models such as support vector machines, random forests, and deep neural networks, thereby effectively utilizing historical data for model training. This improves the accuracy of fault classification based on known fault types and data, thereby helping to identify different fault types and make corresponding diagnostic decisions.

[0107] S1022: Cluster and detect anomalies in the operational data to further capture unknown fault modes;

[0108] It should be noted that the clustering algorithms include: incremental K-Means and DBSCAN (Density-Based Spatial Clustering of Applications with Noise), which are used to continuously track changes in data patterns and, when new cluster centers are formed, infer unknown fault modes and trigger the labeling mechanism; anomaly detection uses a deep autoencoder, which learns the characteristics of normal data and judges it as an anomaly when the reconstruction error is too large.

[0109] S1023: When there is insufficient data on the target motor or vehicle model, the model pre-trained on similar motor models or historical vehicle model data will be fine-tuned with a small amount of target domain data and then applied to the target task. At the same time, through meta-learning or metric-based learning methods, the model can quickly adapt and accurately diagnose new fault types even when it has only seen a very small number of fault samples.

[0110] It should be noted that step S1023 is based on transfer learning and few-shot learning, which enables the model to quickly adapt and generalize even with limited data and insufficient annotations. Compared with traditional models that rely entirely on large-scale data training, it has engineering advantages such as low deployment cost and strong adaptability. Furthermore, in practical applications, it is often difficult to obtain sufficient labeled samples in a timely manner for the running data of different platform models or new hardware batches, and the data distribution is different. Traditional supervised learning methods are difficult to reuse. Therefore, it is necessary to introduce transfer learning and few-shot learning methods to enable the model to have the ability to "quickly adapt" and maintain the accuracy of fault identification even under new models or edge conditions.

[0111] Understandably, by combining the rule-based and threshold-based rapid screening in step S101 with the data-driven intelligent recognition in step S102 through the above design, the complementary advantages of the two can be leveraged. By first using the rule layer to remove the vast majority of normal data and then handing over the remaining anomalies to the model for in-depth analysis, the false alarm rate and false negative rate can be significantly reduced. Secondly, rule judgment has low computational load and low latency, and can run at high speed on edge computing units. Furthermore, the more computationally intensive machine learning module is only invoked when a potential anomaly is detected, effectively alleviating the real-time computing pressure, improving the comprehensiveness and accuracy of fault detection, and balancing real-time performance with computational efficiency, providing a fast and accurate hybrid solution for vehicle fault diagnosis.

[0112] Furthermore, in step S2, when the fault level of the motor is level three, a command is sent to the vehicle motor controller to set the torque of the two motors on the shaft where the motor is located to 0 Nm, and the vehicle enters limp mode.

[0113] Furthermore, such as Figure 6 As shown, in step S2, when a first-level and / or second-level fault occurs in any motor on any axle of the vehicle, it includes: if the fault level is first-level, sending an alarm prompt to the vehicle's main control console.

[0114] If a motor experiences a level 2 fault, when a single motor experiences a level 2 fault, torque limiting control is applied to both motors on that shaft with a torque limiting coefficient of a1; when both motors experience a level 2 fault, torque limiting control is applied to both motors on that shaft with a torque limiting coefficient of a2.

[0115] Furthermore, such as Figure 7As shown, in step S2, when a first-level and / or second-level fault occurs on any two motors on the vehicle's axles, it includes: if the fault level is first-level, sending an alarm prompt to the vehicle's main control console.

[0116] If a motor experiences a level 2 fault, when one motor experiences a level 2 fault, torque limiting control is applied to both motors on that shaft with a torque limiting coefficient of a1.

[0117] When two motors experience a level 2 fault, if they are on the same shaft, torque limiting control is applied to both motors on that shaft with a torque limiting coefficient of a2; if they are on different shafts but on the same side, torque limiting control is applied to both motors on both shafts with a torque limiting coefficient of a2; if they are on different shafts and on different sides, torque limiting control is applied to both motors on both shafts with a torque limiting coefficient of a1.

[0118] When three motors experience a level 2 fault, the two coaxial motors with level 2 faults are both subject to torque limiting control with a torque limiting coefficient of a2, and the motors on the other shaft are both subject to torque limiting control with a torque limiting coefficient of a1.

[0119] When all four motors experience a level 2 fault, torque limiting control is applied to both shaft motors with a torque limiting coefficient of a2.

[0120] Furthermore, such as Figure 8 As shown, in step S2, when the motors on the three axles of the vehicle experience a first-level and / or second-level fault, it includes: if the fault level is first-level, sending an alarm prompt to the vehicle's main control console.

[0121] If a motor experiences a level 2 fault, when one motor experiences a level 2 fault, torque limiting control is applied to both motors on that shaft with a torque limiting coefficient of a1.

[0122] When two motors experience a level 2 fault, if they are on the same shaft, torque limiting control is applied to both motors on that shaft with a torque limiting coefficient of a2; if they are on different shafts but on the same side, torque limiting control is applied to both motors on both shafts with a torque limiting coefficient of a2; if they are on different shafts and on different sides, torque limiting control is applied to both motors on both shafts with a torque limiting coefficient of a1.

[0123] When three motors have a level 2 fault, such as two level 2 fault motors on the same shaft, torque limiting control is applied to the two motors on that shaft with a torque limiting coefficient of a2, and torque limiting control is applied to all motors on the shaft of the other level 2 fault motor with a torque limiting coefficient of a1.

[0124] If the three motors are not coaxial and are located on the same side, torque limiting control is applied to all three motors with a torque limiting coefficient of a2.

[0125] If the three motors are not coaxial, two motors are located on the same side, and one motor is located on the opposite side, torque limiting control is applied to the two shaft motors where the faulty motor is located on the same side, and the torque limiting coefficient is a2. Torque limiting control is applied to the other shaft motor, and the torque limiting coefficient is a1.

[0126] When four motors experience a level two fault, such as when the four motors are distributed on two shafts, torque limiting control is applied to both shaft motors with a torque limiting coefficient of a2.

[0127] If four motors are distributed on three axes, torque limiting control is applied to the motors on the axes where two motors have level two faults, and the torque limiting coefficient is a2. For the other two axes, if the level two fault motors are on the same side, torque limiting control is applied to the motors on both axes, and the torque limiting coefficient is a2. If the level two fault motors are on different sides, torque limiting control is applied to the motors on both axes, and the torque limiting coefficient is a1.

[0128] When five motors have a level 2 fault, torque limiting control is applied to the motors on the shafts where two motors have a level 2 fault, with a torque limiting coefficient of a2. Torque limiting control is applied to the motors on the other shaft, with a torque limiting coefficient of a1.

[0129] When six motors experience a level-two fault, torque limiting control is applied to all three-axis motors with a torque limiting coefficient of a2.

[0130] It should be noted that the filler wheel in the attached diagram represents a level two motor fault, and represents only one example.

[0131] Furthermore, the torque limiting coefficients a1 and a2 both range from 0 to 1, with a1 being greater than a2. Simultaneously, when vehicle stability or responsiveness is insufficient, the values ​​of torque limiting coefficients a1 and a2 are reduced. Preferably, the initial values ​​of torque limiting coefficients a1 and a2 are 0.7 and 0.5, respectively.

[0132] It should be noted that if the embodiments of the present invention involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of the components in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.

[0133] Furthermore, if the embodiments of this invention involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by this invention.

[0134] In this invention, the terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0135] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit it; those skilled in the art will readily understand that the above descriptions are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A fault diagnosis and processing method for a three-axle distributed electric drive vehicle, characterized in that, include: S1: Real-time acquisition of motor operating status information of a three-axis 6×6 distributed electric drive vehicle, and analysis and evaluation of the fault level of each motor based on the acquired data; S2: Receives fault level information of each motor in real time, and based on the diagnostic results and motor distribution, sends the optimal fault-tolerant control command to the vehicle motor controller to regulate the operating status of the faulty motor. The fault levels include: Level 0, Level 1, Level 2, and Level 3, which correspond to no fault, indicative fault, minor fault, and serious fault, respectively.

2. The fault diagnosis and processing method according to claim 1, characterized in that, Step S1 includes: S101: Using preset engineering experience, physical laws, basic parameter thresholds and dynamic thresholds under multiple working conditions, perform preliminary anomaly detection and rough fault classification on the real-time collected data. S102: Identify potential failure modes from large amounts of operational data using data mining and machine learning algorithms.

3. The fault diagnosis and processing method according to claim 2, characterized in that, Step S101 includes: S1011: Based on historical operating data, combined with the distribution range of key indicators of typical roads and typical driving scenarios, establish a scenario-specific threshold set, and switch the applicable threshold in real time according to the current CAN bus upload signal. S1012: Integrates a timing event recognition framework, linking information from motor drivers, power management units, and sensor nodes to achieve cross-module linkage fault symptom detection; S1013: If the uploaded data of a certain indicator exceeds the threshold range of the current working condition, it is marked as an abnormal signal; if multiple indicators exceed the limit together, it is judged as a high-risk event through a complex event handling mechanism; at the same time, sudden anomalies are judged by the data change rate to prevent misjudgment caused by steady drift.

4. The fault diagnosis and processing method according to claim 2, characterized in that, Step S102 includes: S1021: Using the dataset from step S101, match the dataset with the fault type labels, and train different machine learning models to achieve efficient fault identification and classification. At the same time, ensemble learning is used to further improve the robustness and accuracy of diagnosis. S1022: Cluster and detect anomalies in the operational data to further capture unknown fault modes; S1023: When there is insufficient data on the target motor or vehicle model, the model pre-trained on similar motor models or historical vehicle model data will be fine-tuned with a small amount of target domain data and then applied to the target task. At the same time, through meta-learning or metric-based learning methods, the model can quickly adapt and accurately diagnose new fault types even when it has only seen a very small number of fault samples.

5. The fault diagnosis and processing method according to any one of claims 1-4, characterized in that, In step S2, when the motor fault level is level three, a command is sent to the vehicle motor controller to set the torque of the two motors on the shaft where the motor is located to 0 Nm, and the vehicle enters limp mode.

6. The fault diagnosis and processing method according to claim 5, characterized in that, In step S2, when a first-level and / or second-level fault occurs in any motor on any axle of the vehicle, it includes: if the fault level is first-level, sending an alarm prompt to the vehicle's main control console. If a motor experiences a level 2 fault, when a single motor experiences a level 2 fault, torque limiting control is applied to both motors on that shaft with a torque limiting coefficient of a1; when both motors experience a level 2 fault, torque limiting control is applied to both motors on that shaft with a torque limiting coefficient of a2.

7. The fault diagnosis and processing method according to claim 6, characterized in that, In step S2, when a first-level and / or second-level fault occurs on any two motors on the vehicle's axles, it includes: if both fault levels are first-level, sending an alarm notification to the vehicle's main control console. If a motor experiences a level 2 fault, when one motor experiences a level 2 fault, torque limiting control is applied to both motors on that shaft with a torque limiting coefficient of a1. When two motors experience a level 2 fault, if they are on the same shaft, torque limiting control is applied to both motors on that shaft with a torque limiting coefficient of a2; if they are on different shafts but on the same side, torque limiting control is applied to both motors on both shafts with a torque limiting coefficient of a2; if they are on different shafts and on different sides, torque limiting control is applied to both motors on both shafts with a torque limiting coefficient of a1. When three motors experience a level 2 fault, the two coaxial motors with level 2 faults are both subject to torque limiting control with a torque limiting coefficient of a2, and the motors on the other shaft are both subject to torque limiting control with a torque limiting coefficient of a1. When all four motors experience a level 2 fault, torque limiting control is applied to both shaft motors with a torque limiting coefficient of a2.

8. The fault diagnosis and processing method according to claim 7, characterized in that, In step S2, when a first-level and / or second-level fault occurs in the motors on the three axles of the vehicle, it includes: if the fault level is first-level, sending an alarm prompt to the vehicle's main control console; If a motor experiences a level 2 fault, when one motor experiences a level 2 fault, torque limiting control is applied to both motors on that shaft with a torque limiting coefficient of a1. When two motors experience a level 2 fault, if they are on the same shaft, torque limiting control is applied to both motors on that shaft with a torque limiting coefficient of a2; if they are on different shafts but on the same side, torque limiting control is applied to both motors on both shafts with a torque limiting coefficient of a2; if they are on different shafts and on different sides, torque limiting control is applied to both motors on both shafts with a torque limiting coefficient of a1. When three motors have a level 2 fault, such as two level 2 fault motors on the same shaft, torque limiting control is applied to the two motors on that shaft with a torque limiting coefficient of a2, and torque limiting control is applied to all motors on the shaft of the other level 2 fault motor with a torque limiting coefficient of a1. If the three motors are not coaxial and are located on the same side, torque limiting control is applied to all three motors with a torque limiting coefficient of a2. If the three motors are not coaxial, two motors are located on the same side, and one motor is located on the opposite side, torque limiting control is applied to the two shaft motors where the faulty motor is located on the same side, and the torque limiting coefficient is a2. Torque limiting control is applied to the other shaft motor, and the torque limiting coefficient is a1. When four motors experience a level two fault, such as when the four motors are distributed on two shafts, torque limiting control is applied to both shaft motors with a torque limiting coefficient of a2. If four motors are distributed on three axes, torque limiting control is applied to the motors on the axes where two motors have level two faults, and the torque limiting coefficient is a2. For the other two axes, if the level two fault motors are on the same side, torque limiting control is applied to the motors on both axes, and the torque limiting coefficient is a2. If the level two fault motors are on different sides, torque limiting control is applied to the motors on both axes, and the torque limiting coefficient is a1. When five motors have a level 2 fault, torque limiting control is applied to the motors on the shafts where two motors have a level 2 fault, with a torque limiting coefficient of a2. Torque limiting control is applied to the motors on the other shaft, with a torque limiting coefficient of a1. When six motors experience a level-two fault, torque limiting control is applied to all three-axis motors with a torque limiting coefficient of a2.

9. The fault diagnosis and processing method according to claim 8, characterized in that, The torque limiting coefficients a1 and a2 both range from 0 to 1, with a1 being greater than a2. Simultaneously, when the vehicle's stability or dynamism is insufficient, the values ​​of the torque limiting coefficients a1 and a2 are reduced.

10. A fault diagnosis and processing system for a three-axle distributed electric drive vehicle, applied to the fault diagnosis and processing method according to any one of claims 1-9, characterized in that, include: The fault diagnosis module is used to collect real-time motor operating status information of the three-axle 6×6 distributed electric drive vehicle, and analyze and evaluate the fault level of each motor based on the collected data. The fault handling module is used to receive the fault level information of each motor output by the fault diagnosis module in real time, and based on the diagnosis results and motor distribution, send the optimal fault-tolerant control command to the vehicle motor controller to regulate the operating status of the faulty motor.

Images