Multi-source heterogeneous fault diagnosis method and device for drive-by-wire chassis of electric carrying equipment

Abstract

The invention discloses a multi-source heterogeneous fault diagnosis method and device for a drive-by-wire chassis of electric carrying equipment. The method comprises the following steps: step 1, constructing a multi-source signal acquisition and preprocessing method; step 2, on the basis of the preprocessed multi-source signal preprocessed in the step 1, a heterogeneous system of the electric carrying equipment is processed; 3, on the basis of the step 2, multi-source heterogeneous information fusion is carried out, and the preprocessed data of different sensors and systems are integrated into unified diagnosis information; and 4, based on the fault features extracted in the step 3, performing fault diagnosis and judgment on the fusion information by using a decision tree, and identifying whether the vehicle has a functional fault or not. According to the invention, by effectively integrating the multi-source signals, the limitation of only depending on a single signal source in the prior art is solved, the function state of the vehicle can be more comprehensively judged, and the accuracy and reliability of fault diagnosis are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of fault diagnosis of a wire-controlled chassis of an electric vehicle, and in particular to a multi-source heterogeneous fault diagnosis method and device for a wire-controlled chassis of an electric vehicle. Background Art

[0002] Existing fault diagnosis methods for chassis systems of electric vehicles usually judge whether there is a fault in the system based on the status of a single signal source or a single system. This method has limitations, especially in the case of complex interaction of multi-source information, it is difficult to accurately reflect the actual working status of the system, and it is easy to cause misjudgment or missed judgment. In addition, under heterogeneous system architecture, such as the coexistence of three-axis steering system and differential steering system, and the coordinated work of braking system and regenerative braking system, the complexity of fault diagnosis is increased. At present, there is no effective method that can integrate multi-source heterogeneous information to accurately diagnose the fault status of the overall functional level of the vehicle. In the existing research on fault diagnosis methods for chassis systems of electric transportation equipment, for example: Chinese invention patent application number CN201510516435.6, entitled “Automobile Electronic Stability Control System Sensor Fault Diagnosis and Fault-Tolerant Control Method” diagnoses the faults of each sensor, but cannot achieve the expected fault diagnosis goal when multi-level faults occur; Chinese invention patent application number CN202110170344.7, entitled “A Digital Twin Driven Intelligent Wire-Controlled Chassis System and Its Fault Diagnosis Method” completes fault prediction, evaluation and diagnosis through the interaction of real-time simulation data of the digital twin system and real-time sensor data of the wire-controlled chassis device, but does not involve sensor data fusion and collaborative fault diagnosis of complex heterogeneous systems.

[0003] However, the above existing fault diagnosis methods have the following two potential problems: First, in terms of fault diagnosis, existing research mainly focuses on the redundant design of a single system or signal source, ignoring the comprehensive processing of multi-source information and system-level fault status diagnosis. Under the complex interaction of heterogeneous systems, diagnostic methods that rely solely on a single signal source often find it difficult to accurately judge the overall functional status of the system, which can easily lead to misjudgment or missed judgment. Second, in terms of collaborative fault diagnosis, existing research lacks comprehensive analysis and processing of multi-source heterogeneous systems, and fails to effectively establish a cross-system collaborative diagnosis model, which makes it difficult to ensure the accuracy and reliability of diagnosis when the system faces complex working conditions.

[0004] Therefore, how to comprehensively utilize multi-source heterogeneous information and develop a fault diagnosis method that can handle complex system architectures has become an important technical bottleneck that currently restricts the large-scale application of wire-controlled chassis systems for electric transportation equipment. Summary of the invention

[0005] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0006] In view of the problems existing in the above-mentioned existing multi-source heterogeneous fault diagnosis method of the wire-controlled chassis of electric transportation equipment, the present invention is proposed.

[0007] Therefore, the purpose of the present invention is to provide a multi-source heterogeneous fault diagnosis method for the wire-controlled chassis of electric vehicles, which accurately determines the actual fault state of the vehicle function level by integrating multi-source signals (such as angle sensors, pressure sensors, road roughness information, cloud data, etc.) and processing diagnostic information of heterogeneous system architectures (such as three-axis steering, differential steering, braking system and regenerative braking, etc.), thereby improving the accuracy and reliability of fault diagnosis. This will provide important technical support for the safe and reliable operation of electric vehicles and promote its promotion and application in more industries.

[0008] In order to solve the above technical problems, the present invention provides the following technical solutions: a multi-source heterogeneous fault diagnosis method for a wire-controlled chassis of an electric vehicle, comprising the following steps: Step 1: Construct a multi-source signal acquisition and preprocessing method to acquire multi-source signals from the chassis steering system, braking system, road surface and road status sensors in the intelligent driving domain, and cloud databases; perform preprocessing on the acquired signals, including signal denoising, normalization, and time synchronization, to ensure data accuracy and consistency; Step 2: Based on the preprocessed multi-source signals preprocessed in step 1, the heterogeneous systems of the electric vehicle equipment, including the three-axis steering system, differential steering system, braking system and regenerative braking system, are modeled, and the behavioral characteristics of the system under normal and fault conditions are described to provide an accurate model basis for subsequent fault diagnosis; Step 3: Based on step 2, multi-source heterogeneous information is fused to integrate the pre-processed data from different sensors and systems into unified diagnostic information. The Bayesian network is used to perform fusion analysis on the data to extract key fault features, and a corresponding fault mode library is established based on the characteristics of the heterogeneous system. Step 4: Based on the fault features extracted in step 3, use the decision tree to diagnose and judge the fused information, identify whether the vehicle has functional faults, and adjust other redundant systems through the coordinated control algorithm of the redundant system to ensure that the vehicle functionality is not affected and maintain the normal operation of the vehicle.

[0009] As a preferred solution of the multi-source heterogeneous fault diagnosis method for the wire-controlled chassis of electric vehicle equipment of the present invention, the step 1 specifically includes: 1.1) Multi-source signal acquisition: Collect multi-source signals from the chassis steering system including the three-axis steering system and the differential steering system, the braking system including the mechanical braking system and the regenerative braking system, the road state sensor of the intelligent driving domain, and the cloud database. Suppose the collected signals are: ,in, Collect signals for each sensor and system, , is the signal acquisition time; 1.2) Preprocess the collected signals in 1.1): preprocess the multi-source signals collected in 1.1) Perform denoising, normalization and time synchronization processing; assume that the denoised signal is , the normalized signal is , the signal after time synchronization processing is , the preprocessing formula is: , where Sync, Norm, and Denoise represent time synchronization, normalization, and denoising operations, respectively. It is the signal after time synchronization processing; 1.3) Data consistency and accuracy guarantee: Based on 1.2), by analyzing the characteristic vector F of the preprocessed signal sync , ensuring the consistency of data on the time axis and the error between signals The control formula is: ,in, is the error tolerance, For an ideal signal, is the error between the signals.

[0010] As a preferred solution of the multi-source heterogeneous fault diagnosis method for the wire-controlled chassis of electric vehicle equipment of the present invention, the step 2 specifically includes: 2.1) Based on the signals in 1.3), a two-degree-of-freedom vehicle dynamics model and a behavioral model of the three-axis steering system and the differential steering system are established: the preprocessed steering system signal S steer (t) Modeling to describe the behavior characteristics of three-axis steering and differential steering under normal and fault conditions, respectively. The two-degree-of-freedom vehicle dynamics model is expressed as: , where a, b, and c are the distances from the center of mass to the first, second, and third axes, respectively. , , are the front, middle and rear wheel turning angles respectively. , , are the cornering stiffness of the front, middle and rear axles respectively, is the vehicle longitudinal velocity, is the vehicle lateral velocity, is the vehicle yaw angular velocity, is the vehicle mass, is the vehicle yaw inertia; is the vehicle lateral acceleration, is the vehicle yaw angular acceleration; The behavioral model of the steering system is expressed as: ,in, Indicates that the steering system mode is three-axis steering. Indicates that the steering system mode is differential steering. represents the steering system behavior model; 2.2) Modeling of mechanical braking and regenerative braking of the braking system: Based on the signals in step 1.3), a behavioral characteristic model of the mechanical braking and regenerative braking system is established to describe the dynamic characteristics of the system under different working modes. The behavioral model of the braking system is: ,in, and is the weight coefficient corresponding to the braking mode, is the behavior model of the mechanical brake system, is the regenerative braking system behavior model, Represents the brake system behavior model; 2.3) Fault state description of behavioral model: Based on 2.1) and 2.2), by analyzing the deviation characteristics of system signals under fault conditions , describing the failure behavior of heterogeneous systems, the failure deviation model is: ,in, is the behavior model under normal conditions, is the behavior model under fault conditions, is the deviation characteristic of the system signal.

[0011] As a preferred solution of the multi-source heterogeneous fault diagnosis method for the wire-controlled chassis of electric vehicle equipment of the present invention, the step three specifically includes: 3.1) Based on the behavior model in 2.3), the pre-processed multi-source signals are fused: the Bayesian network is used to fuse the data of different sensors and systems, and the signals of three-axis steering, differential steering, mechanical braking and regenerative braking are integrated into unified diagnostic information. , the fusion formula is: ,in, It is a three-axis turn signal. is the differential turn signal, Is the mechanical brake signal, is the regenerative braking signal, To unify diagnostic information; 3.2) Extraction of key fault features: Based on the fused signal in 3.1), extract key fault features by analyzing the change rate and amplitude of the signal , the fault feature extraction formula is: ,in, Respectively represent the fault characteristics of each system, Indicates key fault characteristics of the system; 3.3) Establishment of fault mode library: Based on the fault characteristics in 3.2), combined with the characteristics of heterogeneous systems, establish the corresponding fault mode library , the mode library is expressed by the failure mode matrix as: M f a u l t l i b r a r y = [ F f a u l t ( 1 ) , F f a u l t ( 2 ) … F f a u l t ( m ) ] ,in, , They represent the key fault characteristics of the system, It is a system failure mode library.

[0012] As a preferred solution of the multi-source heterogeneous fault diagnosis method for the wire-controlled chassis of electric vehicle equipment of the present invention, the step 4 specifically includes: 4.1) Based on the fault mode library in 3.3), perform fault diagnosis: Use the decision tree to perform fault diagnosis and judgment on the fusion information extracted in 3.2) to identify whether the vehicle has functional faults. The judgment rules of the decision tree are: ,in, That is, determine whether the fault feature belongs to the fault mode library; 4.2) Coordinated control of redundant systems: According to the fault diagnosis results in 4.1), the allocation strategy of three-axis steering and differential steering, mechanical braking and regenerative braking is adjusted through the coordinated control algorithm of the redundant system. , the coordinated control formula is: ,in, , , , They are the coordination distribution coefficients of three-axis steering, differential steering, mechanical braking, and regenerative braking systems. For allocation strategies; 4.3) Function maintenance under fault conditions: When a fault occurs, the redundant system control strategy in 4.2) is adjusted to ensure that the functionality of the vehicle is not affected and the normal operation of the vehicle is maintained. The objective function of function maintenance is: ,in, represents the fault-tolerant behavior model, The statement represents the minimum value of the fault-tolerant behavior model deviating from the normal behavior model.

[0013] As a preferred solution of the multi-source heterogeneous fault diagnosis device for the wire-controlled chassis of the electric vehicle equipment of the present invention, it includes: a central controller, a three-axis steering system, a hub motor drive system, an EMB braking system, a wheel angle sensor, a brake wheel cylinder pressure sensor, a road surface roughness information visual sensor, a frame, an energy storage unit and a multi-source signal; Wherein, each steering shaft of the three-axis steering system includes a steering motor, a steering motor controller and a steering kingpin column; The wheel hub motor drive system includes a wheel hub motor, a wheel hub motor controller and a high voltage power supply; The EMB brake system includes a brake motor, a brake motor controller and a brake disc assembly, and the brake disc assembly includes a brake wheel cylinder and a brake pad; The road surface roughness information visual sensor is installed at the front end of the vehicle, collects road surface information and transmits it to the central controller in real time to adjust the response of the steering system, braking system and driving system, thereby improving the adaptability of the vehicle under complex road conditions; The frame is used to support and connect the above systems and is made of high-strength and lightweight materials to ensure the stability and safety of the overall structure; Among them, the energy storage unit is connected to the hub motor, steering motor and brake motor through the power management module to provide the required electrical energy and monitor and manage the energy usage of each system.

[0014] As a preferred solution of the multi-source heterogeneous fault diagnosis device for the wire-controlled chassis of the electric transport equipment described in the present invention, wherein: the steering motor receives the steering command through the steering motor controller, the output shaft of the steering motor is connected to a worm gear reduction mechanism, the output end of the worm gear reduction mechanism transmits the torque to the wheel through the steering kingpin column to achieve vehicle steering, the steering kingpin column is rigidly connected to the frame to ensure the effective transmission of the steering torque, the wheel angle sensor is installed on the steering kingpin column, and is used to monitor the angle signal in real time, and send the signal to the steering motor controller to achieve precise steering control.

[0015] As a preferred solution of the multi-source heterogeneous fault diagnosis device for the wire-controlled chassis of the electric transport equipment described in the present invention, wherein: the wheel hub motor is connected to the high-voltage power supply through a high-voltage wire harness, the wheel hub motor controller is responsible for controlling the rotation of the wheel hub motor, and communicates with the central controller through the CAN bus to realize the power output of the vehicle, the wheel hub motor is integrated in the wheel, and directly drives the wheel to rotate through the output shaft to provide driving power for the vehicle; the brake motor receives the brake signal through the brake motor controller, the output shaft of the brake motor is connected to a ball screw reduction mechanism, the ball screw reduction mechanism converts the rotational motion into linear motion, and transmits the torque to the brake disc assembly through the ball screw to realize the braking function of the vehicle, and the brake wheel cylinder pressure sensor is installed near the output shaft of the brake motor, which is used to detect the actual output of the braking force, and feed back the data to the brake motor controller to ensure the stability and reliability of the braking effect.

[0016] As a preferred solution of the multi-source heterogeneous fault diagnosis device for the wire-controlled chassis of electric transport equipment described in the present invention, the energy storage unit adopts a high-density lithium battery pack and is integrated with a power management system, which can monitor the working status of the battery in real time and perform active protection in abnormal situations; the frame adopts a modular design and can be flexibly adjusted according to different needs to adapt to various types of electric transport equipment.

[0017] As a preferred solution of the multi-source heterogeneous fault diagnosis device for the wire-controlled chassis of the electric vehicle equipment described in the present invention, the multi-source signals include a steering angle sensor, a pressure sensor and a visual sensor, which communicate with the central controller through the CAN bus. The central controller performs data processing and comprehensive analysis based on the received signals, and outputs control commands to each actuator, so as to realize precise control and fault diagnosis of the steering, drive and braking systems.

[0018] Beneficial effects of the present invention: 1. The present invention solves the limitation of the prior art that only relies on a single signal source by effectively integrating multi-source signals (such as steering angle sensors, pressure sensors, road roughness information, etc.), and can more comprehensively judge the functional status of the vehicle, significantly improving the accuracy and reliability of fault diagnosis; 2. The present invention not only diagnoses a single system or signal source, but also establishes a collaborative diagnosis model for multi-source heterogeneous systems, which can realize comprehensive diagnosis of multiple subsystems (such as three-axis steering, differential steering, braking system, regenerative braking system) under a complex system architecture, avoiding the occurrence of missed judgments and misjudgments; 3. Through the multi-source information fusion analysis of the Bayesian network, the present invention can effectively extract the fault characteristics of the system and establish a fault mode library. In this way, faults can be quickly identified and countermeasures can be taken, which improves the fault identification speed and accuracy of the system; 4. After diagnosing a functional fault, the present invention can adjust the operation of other redundant systems through the coordinated control of the redundant systems to ensure that the vehicle can still maintain normal operation when a partial fault occurs, thereby enhancing the stability and fault tolerance of the system; 5. Through the real-time collection and processing of road roughness information visual sensors and other multi-source signals, the present invention can dynamically adjust the steering, braking and driving systems according to complex road conditions, further improving the adaptability of electric transport equipment in complex environments; 6. The present invention performs preprocessing on multi-source signals, including signal denoising, normalization processing and time synchronization processing, which ensures the accuracy and consistency of data, reduces data interference in the diagnosis process, and improves the accuracy of fault diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them: Figure 1 A top view of a multi-source heterogeneous fault diagnosis device for a wire-controlled chassis of an electric vehicle; Figure 2 A structural diagram of a multi-source heterogeneous fault diagnosis device for a wire-controlled chassis of an electric vehicle; Numbers in the figure: 1. Frame; 2. Visual sensor for road roughness information; 3. Central controller; 4. Steering motor controller; 5. Steering motor; 6. Worm gear reduction mechanism; 7. Steering kingpin column; 8. Wheel angle sensor; 9. Brake motor; 10. Brake wheel cylinder pressure sensor; 11. Ball screw reduction mechanism; 12. Ball screw; 13. Hub motor; 14. Brake wheel cylinder; 15. Brake pad; 16. High-voltage wiring harness; 17. Hub motor controller; 18. High-voltage power supply; 19. Brake motor controller. DETAILED DESCRIPTION

[0020] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0021] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0022] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0023] Secondly, the present invention is described in detail with reference to the schematic diagram. When describing the embodiments of the present invention in detail, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0024] Reference Figure 1-Figure 2 , provides a multi-source heterogeneous fault diagnosis method for a wire-controlled chassis of an electric vehicle, comprising the following steps: Step 1: Construct a multi-source signal acquisition and preprocessing method to acquire multi-source signals from the chassis steering system, braking system, road surface and road status sensors in the intelligent driving domain, and cloud databases; perform preprocessing on the acquired signals, including signal denoising, normalization, and time synchronization, to ensure data accuracy and consistency; Step 2: Based on the preprocessed multi-source signals preprocessed in step 1, the heterogeneous systems of the electric vehicle equipment, including the three-axis steering system, differential steering system, braking system and regenerative braking system, are modeled, and the behavioral characteristics of the system under normal and fault conditions are described to provide an accurate model basis for subsequent fault diagnosis; Step 3: Based on step 2, multi-source heterogeneous information is fused to integrate the pre-processed data from different sensors and systems into unified diagnostic information. The Bayesian network is used to perform fusion analysis on the data to extract key fault features, and a corresponding fault mode library is established based on the characteristics of the heterogeneous system. Step 4: Based on the fault features extracted in step 3, use the decision tree to diagnose and judge the fused information, identify whether the vehicle has functional faults, and adjust other redundant systems through the coordinated control algorithm of the redundant system to ensure that the vehicle functionality is not affected and maintain the normal operation of the vehicle.

[0025] Wherein, the step 1 specifically includes: 1.1) Multi-source signal acquisition: Collect multi-source signals from the chassis steering system including the three-axis steering system and the differential steering system, the braking system including the mechanical braking system and the regenerative braking system, the road state sensor of the intelligent driving domain, and the cloud database. Suppose the collected signals are: ,in, Collect signals for each sensor and system, , is the signal acquisition time; 1.2) Preprocess the collected signals in 1.1): preprocess the multi-source signals collected in 1.1) Perform denoising, normalization and time synchronization processing; assume that the denoised signal is , the normalized signal is , the signal after time synchronization processing is , the preprocessing formula is: , where Sync, Norm, and Denoise represent time synchronization, normalization, and denoising operations, respectively. It is the signal after time synchronization processing; 1.3) Data consistency and accuracy guarantee: Based on 1.2), by analyzing the characteristic vector F of the preprocessed signal sync , ensuring the consistency of data on the time axis and the error between signals The control formula is: , in, is the error tolerance, For an ideal signal, is the error between the signals.

[0026] Wherein, the step 2 specifically includes: 2.1) Based on the signals in 1.3), a two-degree-of-freedom vehicle dynamics model and a behavioral model of the three-axis steering system and the differential steering system are established: the preprocessed steering system signal S steer (t) Modeling to describe the behavior characteristics of three-axis steering and differential steering under normal and fault conditions, respectively. The two-degree-of-freedom vehicle dynamics model is expressed as: , where a, b, and c are the distances from the center of mass to the first, second, and third axes, respectively. , , are the front, middle and rear wheel turning angles respectively. , , are the cornering stiffness of the front, middle and rear axles respectively, is the vehicle longitudinal velocity, is the vehicle lateral velocity, is the vehicle yaw angular velocity, is the vehicle mass, is the vehicle yaw inertia; is the vehicle lateral acceleration, is the vehicle yaw angular acceleration; The behavioral model of the steering system is expressed as: ,in, Indicates that the steering system mode is three-axis steering. Indicates that the steering system mode is differential steering. represents the steering system behavior model; 2.2) Modeling of mechanical braking and regenerative braking of the braking system: Based on the signals in step 1.3), a behavioral characteristic model of the mechanical braking and regenerative braking system is established to describe the dynamic characteristics of the system under different working modes. The behavioral model of the braking system is: ,in, and is the weight coefficient corresponding to the braking mode, is the behavior model of the mechanical brake system, is the regenerative braking system behavior model, Represents the brake system behavior model; 2.3) Fault state description of behavioral model: Based on 2.1) and 2.2), by analyzing the deviation characteristics of system signals under fault conditions , describing the failure behavior of heterogeneous systems, the failure deviation model is: ,in, is the behavior model under normal conditions, is the behavior model under fault conditions, is the deviation characteristic of the system signal.

[0027] Furthermore, the step three specifically includes: 3.1) Based on the behavior model in 2.3), the pre-processed multi-source signals are fused: the Bayesian network is used to fuse the data of different sensors and systems, and the signals of three-axis steering, differential steering, mechanical braking and regenerative braking are integrated. Integrate into unified diagnostic information, the fusion formula is: ,in, It is a three-axis turn signal. is the differential turn signal, Is the mechanical brake signal, is the regenerative braking signal, To unify diagnostic information; 3.2) Extraction of key fault features: Based on the fused signal in 3.1), extract key fault features by analyzing the change rate and amplitude of the signal , the fault feature extraction formula is: ,in, Respectively represent the fault characteristics of each system, Indicates key fault characteristics of the system; 3.3) Establishment of fault mode library: Based on the fault characteristics in 3.2), combined with the characteristics of heterogeneous systems, establish the corresponding fault mode library , the mode library is expressed by the failure mode matrix as: M f a u l t l i b r a r y = [ F f a u l t ( 1 ) , F f a u l t ( 2 ) … F f a u l t ( m ) ] ,in, , They represent the key fault characteristics of the system, It is a system failure mode library.

[0028] Wherein, the step 4 specifically includes: 4.1) Based on the fault mode library in 3.3), perform fault diagnosis: Use the decision tree to perform fault diagnosis and judgment on the fusion information extracted in 3.2) to identify whether the vehicle has functional faults. The judgment rules of the decision tree are: ,in, That is, determine whether the fault feature belongs to the fault mode library; 4.2) Coordinated control of redundant systems: According to the fault diagnosis results in 4.1), the allocation strategy of three-axis steering and differential steering, mechanical braking and regenerative braking is adjusted through the coordinated control algorithm of the redundant system. , the coordinated control formula is: ,in, , , , They are the coordination distribution coefficients of three-axis steering, differential steering, mechanical braking, and regenerative braking systems. For allocation strategies; 4.3) Function maintenance under fault conditions: When a fault occurs, the redundant system control strategy in 4.2) is adjusted to ensure that the functionality of the vehicle is not affected and the normal operation of the vehicle is maintained. The objective function of function maintenance is: ,in, represents the fault-tolerant behavior model, The statement represents the minimum value of the fault-tolerant behavior model deviating from the normal behavior model.

[0029] Furthermore, the multi-source heterogeneous fault diagnosis device for the wire-controlled chassis of electric transport equipment includes: a central controller 3, a three-axis steering system, a hub motor drive system, an EMB brake system, a wheel angle sensor 8, a brake wheel cylinder pressure sensor 10, a road surface roughness information visual sensor 2, a frame 1, an energy storage unit and multi-source signals; Wherein, each steering shaft of the three-axis steering system includes a steering motor 5, a steering motor controller 4 and a steering kingpin column 7; The wheel hub motor drive system includes a wheel hub motor 13, a wheel hub motor controller 17 and a high voltage power supply 18; The EMB brake system includes a brake motor 9, a brake motor controller 19 and a brake disc assembly, and the brake disc assembly includes a brake wheel cylinder 14 and a brake pad 15; The road surface roughness information visual sensor 2 is installed at the front end of the vehicle, and collects road surface information and transmits it to the central controller 3 in real time to adjust the response of the steering system, braking system and driving system, thereby improving the adaptability of the vehicle under complex road conditions; The frame 1 is used to support and connect the above-mentioned systems and is made of high-strength and lightweight materials to ensure the stability and safety of the overall structure; The energy storage unit is connected to the wheel hub motor 13, the steering motor 5 and the brake motor 9 through the power management module to provide the required electrical energy and monitor and manage the energy usage of each system.

[0030] Among them, the steering motor 5 receives the steering command through the steering motor controller 4, the output shaft of the steering motor is connected to the worm gear reduction mechanism 6, the output end of the worm gear reduction mechanism 6 transmits the torque to the wheel through the steering kingpin column 7 to realize vehicle steering, the steering kingpin column 7 is rigidly connected to the frame 1 to ensure the effective transmission of the steering torque, and the wheel angle sensor 8 is installed on the steering kingpin column 7 for real-time monitoring of the angle signal and sending the signal to the steering motor controller 4 to achieve precise steering control.

[0031] Specifically, the wheel hub motor 13 is connected to the high-voltage power supply 18 through a high-voltage wiring harness 16, and the wheel hub motor controller 17 is responsible for controlling the rotation of the wheel hub motor 13, and communicates with the central controller 3 through the CAN bus to realize the power output of the vehicle. The wheel hub motor 13 is integrated in the wheel, and directly drives the wheel to rotate through the output shaft to provide driving power for the vehicle; the brake motor 9 receives the brake signal through the brake motor controller 19, and the output shaft of the brake motor 9 is connected to the ball screw reduction mechanism 11, and the ball screw reduction mechanism 11 converts the rotational motion into linear motion, and transmits the torque to the brake disc assembly through the ball screw 12 to realize the braking function of the vehicle. The brake wheel cylinder pressure sensor 10 is installed near the output shaft of the brake motor 9, which is used to detect the actual output of the braking force and feed back the data to the brake motor controller 19 to ensure the stability and reliability of the braking effect.

[0032] Furthermore, the energy storage unit adopts a high-density lithium battery pack and is integrated with a power management system, which can monitor the working status of the battery in real time and perform active protection in case of abnormalities; the frame 1 adopts a modular design and can be flexibly adjusted according to different needs to adapt to various types of electric transportation equipment. The multi-source signal includes an angle sensor, a pressure sensor and a visual sensor, which communicate with the central controller 3 through the CAN bus. The central controller 3 performs data processing and comprehensive analysis based on the received signals, and outputs control commands to each actuator to achieve precise control and fault diagnosis of the steering, drive and braking systems.

[0033] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A multi-source heterogeneous fault diagnosis method for a wire-controlled chassis of an electric vehicle, characterized in that: The following steps are involved: Step 1: Construct a multi-source signal acquisition and preprocessing method to acquire multi-source signals from the chassis steering system, braking system, road surface and road status sensors in the intelligent driving domain, and cloud databases; Preprocess the collected signals, including signal denoising, normalization and time synchronization, to ensure the accuracy and consistency of the data; Step 2: Based on the preprocessed multi-source signals preprocessed in step 1, the heterogeneous systems of the electric vehicle equipment, including the three-axis steering system, differential steering system, braking system and regenerative braking system, are modeled, and the behavioral characteristics of the system under normal and fault conditions are described to provide an accurate model basis for subsequent fault diagnosis; Step 3: Based on step 2, multi-source heterogeneous information is fused to integrate the pre-processed data from different sensors and systems into unified diagnostic information. The Bayesian network is used to perform fusion analysis on the data to extract key fault features, and a corresponding fault mode library is established based on the characteristics of the heterogeneous system. Step 4: Based on the fault features extracted in step 3, use the decision tree to diagnose and judge the fused information, identify whether the vehicle has functional faults, and adjust other redundant systems through the coordinated control algorithm of the redundant system to ensure that the vehicle functionality is not affected and maintain the normal operation of the vehicle.

2. The multi-source heterogeneous fault diagnosis method for a wire-controlled chassis of an electric vehicle according to claim 1 is characterized by: The step 1 specifically includes: 1.1) Multi-source signal acquisition: Collect multi-source signals from the chassis steering system including the three-axis steering system and the differential steering system, the braking system including the mechanical braking system and the regenerative braking system, the road state sensor of the intelligent driving domain, and the cloud database. Suppose the collected signals are: ,in, Collect signals for each sensor and system, , is the signal acquisition time; 1.2) Preprocess the collected signals in 1.1): preprocess the multi-source signals collected in 1.1) Perform denoising, normalization and time synchronization processing; assume that the denoised signal is , the normalized signal is , the signal after time synchronization processing is , the preprocessing formula is: , where Sync, Norm, and Denoise represent time synchronization, normalization, and denoising operations, respectively. It is the signal after time synchronization processing; 1.3) Data consistency and accuracy guarantee: Based on 1.2), by analyzing the characteristic vector F of the preprocessed signal sync , ensuring the consistency of data on the time axis and the error between signals The control formula is: ,in, is the error tolerance, For an ideal signal, is the error between the signals.

3. The multi-source heterogeneous fault diagnosis method for a wire-controlled chassis of an electric vehicle according to claim 2 is characterized by: The step 2 specifically includes: 2.1) Based on the signals in 1.3), a two-degree-of-freedom vehicle dynamics model and a behavioral model of the three-axis steering system and the differential steering system are established: the preprocessed steering system signal S steer (t) Modeling to describe the behavior characteristics of three-axis steering and differential steering under normal and fault conditions, respectively. The two-degree-of-freedom vehicle dynamics model is expressed as: , where a, b, and c are the distances from the center of mass to the first, second, and third axes, respectively. , , are the front, middle and rear wheel turning angles respectively. , , are the cornering stiffness of the front, middle and rear axles respectively, is the vehicle longitudinal velocity, is the vehicle lateral velocity, is the vehicle yaw angular velocity, is the vehicle mass, is the vehicle's lateral inertia, is the vehicle lateral acceleration, is the vehicle yaw angular acceleration; The behavioral model of the steering system is expressed as: , in, Indicates that the steering system mode is three-axis steering. Indicates that the steering system mode is differential steering. represents the steering system behavior model; 2.2) Modeling of mechanical braking and regenerative braking of the braking system: Based on the signals in step 1.3), a behavioral characteristic model of the mechanical braking and regenerative braking system is established to describe the dynamic characteristics of the system under different working modes. The behavioral model of the braking system is: ,in, and is the weight coefficient corresponding to the braking mode, is the behavior model of the mechanical brake system, is the regenerative braking system behavior model, Represents the brake system behavior model; 2.3) Fault state description of behavioral model: Based on 2.1) and 2.2), by analyzing the deviation characteristics of system signals under fault conditions , describing the failure behavior of heterogeneous systems, the failure deviation model is: ,in, is the behavior model under normal conditions, is the behavior model under fault conditions, is the deviation characteristic of the system signal.

4. The multi-source heterogeneous fault diagnosis method for a wire-controlled chassis of an electric vehicle according to claim 3 is characterized by: The step three specifically includes: 3.1) Based on the behavior model in 2.3), the pre-processed multi-source signals are fused: the Bayesian network is used to fuse the data of different sensors and systems, and the signals of three-axis steering, differential steering, mechanical braking and regenerative braking are integrated into unified diagnostic information. , the fusion formula is: ,in, It is a three-axis turn signal. is the differential turn signal, Is the mechanical brake signal, is the regenerative braking signal, To unify diagnostic information; 3.2) Extraction of key fault features: Based on the fused signal in 3.1), extract key fault features by analyzing the change rate and amplitude of the signal , the fault feature extraction formula is: ,in, Respectively represent the fault characteristics of each system, Indicates key fault characteristics of the system; 3.3) Establishment of fault mode library: Based on the fault characteristics in 3.2), combined with the characteristics of heterogeneous systems, establish the corresponding fault mode library , the mode library is expressed by the failure mode matrix as: ,in, , They represent the key fault characteristics of the system, It is a system failure mode library.

5. The multi-source heterogeneous fault diagnosis method for a wire-controlled chassis of an electric vehicle according to claim 4 is characterized in that: The step 4 specifically includes: 4.1) Based on the fault mode library in 3.3), perform fault diagnosis: Use the decision tree to perform fault diagnosis and judgment on the fusion information extracted in 3.2) to identify whether the vehicle has functional faults. The judgment rules of the decision tree are: ,in, That is, determine whether the fault feature belongs to the fault mode library; 4.2) Coordinated control of redundant systems: According to the fault diagnosis results in 4.1), the allocation strategy of three-axis steering and differential steering, mechanical braking and regenerative braking is adjusted through the coordinated control algorithm of the redundant system. , the coordinated control formula is: ,in, , , , They are the coordination distribution coefficients of three-axis steering, differential steering, mechanical braking, and regenerative braking systems. For allocation strategies; 4.3) Function maintenance under fault conditions: When a fault occurs, the redundant system control strategy in 4.2) is adjusted to ensure that the functionality of the vehicle is not affected and the normal operation of the vehicle is maintained. The objective function of function maintenance is: ,in, represents the fault-tolerant behavior model, The statement represents the minimum value of the fault-tolerant behavior model deviating from the normal behavior model.

6. A device for diagnosing multi-source heterogeneous faults of a wire-controlled chassis of an electric vehicle, adopting the method for diagnosing multi-source heterogeneous faults of a wire-controlled chassis of an electric vehicle as claimed in any one of claims 1 to 5, characterized in that: include: Central controller (3), three-axis steering system, wheel hub motor drive system, EMB brake system, wheel angle sensor (8), brake wheel cylinder pressure sensor (10), road surface roughness information visual sensor (2), vehicle frame (1), energy storage unit and multi-source signal; Wherein, each steering axis of the three-axis steering system comprises a steering motor (5), a steering motor controller (4) and a steering kingpin column (7); The wheel hub motor drive system comprises a wheel hub motor (13), a wheel hub motor controller (17) and a high voltage power supply (18); The EMB brake system comprises a brake motor (9), a brake motor controller (19) and a brake disc assembly, wherein the brake disc assembly comprises a brake wheel cylinder (14) and a brake pad (15); The road surface roughness information visual sensor (2) is installed at the front end of the vehicle, collects road surface information, and transmits it to the central controller (3) in real time, so as to adjust the response of the steering system, the braking system and the driving system, thereby improving the adaptability of the vehicle under complex road conditions; The frame (1) is used to support and connect the above-mentioned systems and is made of high-strength lightweight materials to ensure the stability and safety of the overall structure; The energy storage unit is connected to the wheel hub motor (13), the steering motor (5) and the brake motor (9) through the power management module, provides the required electric energy, and monitors and manages the energy use of each system.

7. The multi-source heterogeneous fault diagnosis device for a wire-controlled chassis of an electric vehicle according to claim 6 is characterized by: The steering motor (5) receives a steering command via a steering motor controller (4); the output shaft of the steering motor is connected to a worm gear reduction mechanism (6); the output end of the worm gear reduction mechanism (6) transmits torque to the wheel via a steering kingpin column (7) to achieve vehicle steering; the steering kingpin column (7) is rigidly connected to the vehicle frame (1) to ensure effective transmission of the steering torque; the wheel angle sensor (8) is mounted on the steering kingpin column (7) to monitor the angle signal in real time and send the signal to the steering motor controller (4) to achieve precise steering control.

8. The multi-source heterogeneous fault diagnosis device for a wire-controlled chassis of an electric vehicle according to claim 7, characterized in that: The wheel hub motor (13) is connected to a high-voltage power supply (18) via a high-voltage wire harness (16); the wheel hub motor controller (17) is responsible for controlling the rotation of the wheel hub motor (13) and communicating with the central controller (3) via a CAN bus to achieve power output of the vehicle; the wheel hub motor (13) is integrated in the wheel and directly drives the wheel to rotate via an output shaft to provide driving power for the vehicle; the brake motor (9) receives a brake signal via a brake motor controller (19); the output shaft of the brake motor (9) is connected to a ball screw reduction mechanism (11); the ball screw reduction mechanism (11) converts rotational motion into linear motion and transmits torque to a brake disc assembly via a ball screw (12) to achieve a braking function of the vehicle; a brake wheel cylinder pressure sensor (10) is installed near the output shaft of the brake motor (9) to detect the actual output of the braking force and feed back data to the brake motor controller (19) to ensure the stability and reliability of the braking effect.

9. The multi-source heterogeneous fault diagnosis device for a wire-controlled chassis of an electric vehicle according to claim 8, characterized in that: The energy storage unit adopts a high-density lithium battery pack and is integrated with a power management system, which can monitor the working status of the battery in real time and perform active protection in the event of an abnormality; the frame (1) adopts a modular design and can be flexibly adjusted according to different needs to adapt to various types of electric transport equipment.

10. The multi-source heterogeneous fault diagnosis device for a wire-controlled chassis of an electric vehicle according to claim 9, characterized in that: The multi-source signals include a rotation angle sensor, a pressure sensor and a visual sensor, which communicate with a central controller (3) via a CAN bus. The central controller (3) performs data processing and comprehensive analysis based on the received signals, and outputs control commands to each actuator, thereby achieving precise control and fault diagnosis of the steering, drive and braking systems.

Images