A multi-source heterogeneous fault diagnosis method and device for a by-wire chassis of an electric transportation equipment

Abstract

The present invention discloses a method and device for multi-source heterogeneous fault diagnosis of a drive-by-wire chassis of an electric transportation equipment, including the following steps: Step 1: Construct a method for acquisition and preprocessing of multi-source signals; Step 2: Based on the preprocessed multi-source signals in Step 1, for the heterogeneous systems of the electric transportation equipment; Step 3: On the basis of Step 2, perform fusion of multi-source heterogeneous information, and integrate the data of different sensors and systems after preprocessing into unified diagnostic information; Step 4: Based on the fault features extracted in Step 3, use a decision tree to perform fault diagnosis and determination on the fused information to identify whether there are functional faults in the vehicle. By effectively integrating multi-source signals, the present invention solves the limitation of relying only on a single signal source in the prior art, can more comprehensively judge the functional state of the vehicle, and significantly improves the accuracy and reliability of fault diagnosis.

Description

Technical Field

[0001] The present invention relates to the technical field of fault diagnosis for the steer-by-wire chassis of electric transportation equipment, and particularly to a multi-source heterogeneous fault diagnosis method and device for the steer-by-wire chassis of electric transportation equipment. Background Art

[0002] Existing fault diagnosis methods for the chassis system of electric transportation equipment usually judge whether the system has faults based on the state 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 true working state of the system, and it is easy to cause misjudgment or missed judgment. In addition, in a heterogeneous system architecture, such as the coexistence of a three-axis steering system and a differential steering system, and the collaborative work of a braking system and a regenerative braking system, the complexity of fault diagnosis is increased. At present, there is no effective method to comprehensively integrate multi-source heterogeneous information and accurately diagnose the fault state at the overall vehicle function level.

[0003] In the existing research on fault diagnosis methods for the chassis system of electric transportation equipment, for example: in the Chinese invention patent application No. CN201510516435.6, titled "Sensor Fault Diagnosis and Fault Tolerant Control Method for Automotive Electronic Stability Control System", the faults of each sensor are diagnosed, but the expected fault diagnosis goal cannot be achieved when multi-level faults occur; in the Chinese invention patent application No. CN202110170344.7, titled "A Digital Twin-Driven Intelligent Steer-by-Wire Chassis System and Its Fault Diagnosis Method", the prediction, evaluation, and diagnosis of faults are completed through the interaction between the real-time simulation data of the digital twin system and the real-time sensor data of the steer-by-wire chassis device, but it does not involve sensor data fusion and collaborative fault diagnosis of complex heterogeneous systems.

[0004] However, the above existing fault diagnosis methods have the following two potential problems:

[0005] 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 the diagnosis of system-level fault states. Under the complex interaction of heterogeneous systems, the diagnosis method relying solely on a single signal source often has difficulty accurately judging the overall function state of the system, thus easily leading to misjudgment or missed judgment.

[0006] 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. This makes it difficult for the system to ensure the accuracy and reliability of diagnosis when facing complex working conditions.

[0007] 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 restricting the large-scale application of the steer-by-wire chassis system of electric transportation equipment. Summary of the Invention

[0008] The purpose of this section is to outline some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Simplifications or omissions may be made in this section, as well as in the abstract and title of the present application, to avoid obscuring the purpose of this section, the abstract, and the title. However, such simplifications or omissions shall not be used to limit the scope of the present invention.

[0009] In view of the problems existing in the above-mentioned prior multi-source heterogeneous fault diagnosis method for the drive-by-wire chassis of electric transportation equipment, the present invention is proposed.

[0010] Therefore, the object of the present invention is to provide a multi-source heterogeneous fault diagnosis method and device for the drive-by-wire chassis of electric transportation equipment, which integrates multi-source signals (such as steering angle sensors, pressure sensors, road surface unevenness information, cloud data, etc.) and processes the diagnostic information of heterogeneous system architectures (such as three-axis steering, differential steering, braking systems, and regenerative braking, etc.), accurately judges the actual fault state at the vehicle function level, thereby improving the accuracy and reliability of fault diagnosis. This will provide important technical support for the safe and reliable operation of electric transportation equipment and promote its popularization and application in more industries.

[0011] To solve the above technical problems, the present invention provides the following technical solutions: A multi-source heterogeneous fault diagnosis method for the drive-by-wire chassis of electric transportation equipment, comprising the following steps:

[0012] Step 1: Construct a method for collecting and preprocessing multi-source signals, collect multi-source signals obtained from the chassis steering system, braking system, road surface and road state sensors in the intelligent driving domain, and the cloud database; perform preprocessing on the collected signals, including signal denoising, normalization processing, and time synchronization processing, to ensure the accuracy and consistency of the data;

[0013] Step 2: Based on the preprocessed multi-source signals in Step 1, model the heterogeneous systems of the electric transportation equipment, including the three-axis steering system, differential steering system, braking system, and regenerative braking system, and describe the behavioral characteristics of the systems in normal and fault states, providing an accurate model basis for subsequent fault diagnosis;

[0014] Step 3: On the basis of Step 2, perform the fusion of multi-source heterogeneous information, integrate the data of different sensors and systems after preprocessing into unified diagnostic information, use Bayesian networks to perform fusion analysis on the data, thereby extracting key fault features, and establish a corresponding fault mode library according to the characteristics of the heterogeneous systems;

[0015] Step 4: Based on the fault features extracted in Step 3, use a decision tree to perform fault diagnosis and determination on the fused information, identify whether there are functional faults in the vehicle, and adjust other redundant systems through the coordinated control algorithm of the redundant system to ensure that the functionality of the vehicle is not affected and maintain the normal operation of the vehicle.

[0016] As a preferred solution of the multi-source heterogeneous fault diagnosis method for the steer-by-wire chassis of the electric transport equipment described in the present invention, wherein: the specific content of Step 1 includes:

[0017] 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 and regenerative braking systems, the road surface state sensors in the intelligent driving domain, and the cloud database. Let the collected signals be:

[0018]

[0019] Among them, is the acquisition signal of each sensor and system, , is the signal acquisition time;

[0020] 1.2) Preprocess the acquisition signals based on 1.1): Perform denoising processing, normalization processing, and time synchronization processing on the multi-source signals collected in 1.1) . Assume that the signal after denoising is , the signal after normalization processing is , and the signal after time synchronization processing is . The preprocessing formula is:

[0021]

[0022] Among them, Sync, Norm, and Denoise respectively represent time synchronization, normalization, and denoising operations, is the signal after time synchronization processing;

[0023] 1.3) Ensure data consistency and accuracy: On the basis of 1.2), by analyzing the feature vector F sync of the preprocessed signal, ensure the consistency of the data on the time axis, and the error between signals is controlled by the formula:

[0024]

[0025] Among them, is the error tolerance, is the ideal signal, is the error between signals.

[0026] As a preferred solution of the multi-source heterogeneous fault diagnosis method for the by-wire chassis of the electric transportation equipment described in the present invention, wherein: the specific steps of step two include:

[0027] 2.1) Based on the signals in 1.3), establish a two-degree-of-freedom vehicle dynamics model and the behavior models of the three-axis steering system and the differential steering system: Model the preprocessed steering system signal S steer (t) to describe the behavioral characteristics of the three-axis steering and differential steering in normal and fault states respectively,

[0028] The two-degree-of-freedom vehicle dynamics model is expressed as:

[0029]

[0030] where a, b, and c are the distances from the center of mass to the first, second, and third axles respectively, 、 、 are the front, middle, and rear wheel angles respectively, 、 、 are the cornering stiffnesses of the front, middle, and rear axles respectively, is the longitudinal vehicle speed, is the lateral vehicle speed, is the yaw rate of the vehicle, is the vehicle mass, is the yaw inertia of the vehicle, is the lateral acceleration of the vehicle, is the yaw angular acceleration of the vehicle;

[0031] The behavior model of the steering system is expressed as:

[0032]

[0033] where, indicates that the steering system mode is three-axis steering, indicates that the steering system mode is differential steering, indicates the behavior model of the steering system;

[0034] 2.2) Model the mechanical braking and regenerative braking of the braking system: Based on the signals in step 1.3), establish the behavior characteristic models of the mechanical braking and regenerative braking systems to describe the dynamic characteristics of the system under different working modes. The behavior model of the braking system is:

[0035]

[0036] where, and are the weight coefficients corresponding to the braking modes, is the behavior model of the mechanical braking system, For the regenerative braking system behavior model, representing the braking system behavior model;

[0037] 2.3) Fault state description of the behavior model: Based on 2.1) and 2.2), by analyzing the deviation characteristics of system signals in the fault state , describe the fault behavior of the heterogeneous system. The fault deviation model is:

[0038]

[0039] Among them, is the behavior model in the normal state, is the behavior model in the fault state, is the deviation characteristic of the system signal.

[0040] As a preferred solution of the multi-source heterogeneous fault diagnosis method for the by-wire chassis of the electric transport equipment described in the present invention, among them: The specific steps of step three include:

[0041] 3.1) Based on the behavior model in 2.3), fuse the preprocessed multi-source signals: Use the Bayesian network to perform fusion analysis on the data of different sensors and systems, and integrate the signals of three-axis steering, differential steering, mechanical braking, and regenerative braking into unified diagnostic information , and the fusion formula is:

[0042]

[0043] Among them, is the three-axis steering signal, is the differential steering signal, is the mechanical braking signal, is the regenerative braking signal, is the unified diagnostic information;

[0044] 3.2) Extract key fault features: Based on the fused signals in 3.1), extract key fault features by analyzing the change rate and amplitude of the signals , and the extraction formula for the fault features is:

[0045]

[0046] Among them, respectively represent the fault features of each system, represents the key fault feature of the system;

[0047] 3.3) Establish a fault mode library: Based on the fault features in 3.2), combined with the characteristics of the heterogeneous system, establish a corresponding fault mode library , and the mode library is represented by a fault mode matrix as:

[0048] 。

[0049] Among them, , respectively represent the key fault characteristics of the system, is the system fault mode library;

[0050] As a preferred solution of the multi-source heterogeneous fault diagnosis method for the by-wire chassis of the electric transportation equipment described in the present invention, wherein: Step 4 specifically includes:

[0051] 4.1) Based on the fault mode library in 3.3), perform fault diagnosis: Use the decision tree to perform fault diagnosis and determination on the fusion information extracted in 3.2), and identify whether the vehicle has functional faults. The determination rule of the decision tree is:

[0052]

[0053] Among them, that is, judge whether the fault characteristic belongs to the fault mode library;

[0054] 4.2) Coordinated control of the redundant system: According to the fault diagnosis result in 4.1), through the coordinated control algorithm of the redundant system, adjust the distribution strategies of three-axis steering and differential steering, mechanical braking and regenerative braking , and the coordinated control formula is:

[0055]

[0056] Among them, , , , are the coordinated distribution coefficients of the three-axis steering, differential steering, mechanical braking, and regenerative braking systems respectively, is the distribution strategy;

[0057] 4.3) Function maintenance under fault conditions: When a fault occurs, by adjusting the control strategy of the redundant system in 4.2), ensure that the functionality of the vehicle is not affected and maintain the normal operation of the vehicle. The objective function of function maintenance is:

[0058] 。

[0059] Among them, represents the behavior model under fault tolerance, The statement represents the minimum value of the deviation of the behavior model under fault tolerance from the normal state behavior model.

[0060] As a preferred embodiment of the multi-source heterogeneous fault diagnosis device for the steer-by-wire chassis of the electric transport equipment according to 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 vision sensor for road surface unevenness information, a vehicle frame, an energy storage unit, and multi-source signals;

[0061] Among them, each steering axis of the three-axis steering system includes a steering motor, a steering motor controller, and a kingpin column;

[0062] The hub motor drive system includes a hub motor, a hub motor controller, and a high-voltage power supply;

[0063] The EMB braking system includes a braking motor, a braking motor controller, and a brake disc assembly, and the brake disc assembly includes a brake wheel cylinder and brake pads;

[0064] The vision sensor for road surface unevenness information is installed at the front end of the vehicle. By collecting road surface information and transmitting it to the central controller in real time, it is used to adjust the responses of the steering system, braking system, and drive system, thereby improving the adaptability of the vehicle under complex road conditions;

[0065] The vehicle frame 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;

[0066] Among them, the energy storage unit is connected to the hub motor, steering motor, and braking motor through a power management module, provides the required electric energy, and monitors and manages the energy usage of each system.

[0067] As a preferred embodiment of the multi-source heterogeneous fault diagnosis device for the steer-by-wire chassis of the electric transport equipment according to the present invention, among them: the steering motor receives a steering command through the steering motor controller. The output shaft of the steering motor is connected with a worm and gear reduction mechanism. The output end of the worm and gear reduction mechanism transmits the torque to the wheel through the kingpin column to realize vehicle steering. The kingpin column is rigidly connected to the vehicle frame to ensure the effective transmission of the steering torque. The wheel angle sensor is installed on the 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.

[0068] As a preferred solution of the multi-source heterogeneous fault diagnosis device for the by-wire chassis of the electric transport equipment according to the present invention, the following is provided: The hub motor is connected to a high-voltage power source through a high-voltage wire harness. The hub motor controller is responsible for controlling the rotation of the hub motor and communicating with the central controller through the CAN bus to achieve the power output of the vehicle. The hub motor is integrated within the wheel and directly drives the wheel to rotate through an output shaft, providing the driving force for the vehicle to travel; The braking motor receives a braking signal through the braking motor controller. A ball screw reduction mechanism is connected to the output shaft of the braking motor. The ball screw reduction mechanism converts the rotational motion into a linear motion and transmits the torque to the brake disc assembly through the ball screw to achieve the braking function of the vehicle. A brake wheel cylinder pressure sensor is installed near the output shaft of the braking motor to detect the actual output of the braking force and feedback the data to the braking motor controller to ensure the stability and reliability of the braking effect.

[0069] As a preferred solution of the multi-source heterogeneous fault diagnosis device for the by-wire chassis of the electric transport equipment according to the present invention, the following is provided: The energy storage unit uses a high-density lithium battery pack and is integrated with a power management system, which can monitor the working state of the battery in real time and perform active protection in case of abnormalities; The vehicle frame adopts a modular design and can be flexibly adjusted according to different requirements to adapt to various types of electric transport equipment.

[0070] Advantages of the present invention:

[0071] 1. By effectively integrating multi-source signals (such as angle sensors, pressure sensors, road surface roughness information, etc.), the present invention solves the limitations of relying only on a single signal source in the prior art, can more comprehensively judge the functional state of the vehicle, and significantly improves the accuracy and reliability of fault diagnosis.

[0072] 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 the 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.

[0073] 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, improving the fault identification speed and accuracy of the system.

[0074] 4. After diagnosing a functional fault, the present invention can, through the coordinated control of the redundant system, adjust the operation of other redundant systems to ensure that the vehicle can still maintain normal operation when some faults occur, enhancing the stability and fault tolerance of the system.

[0075] 5. Through the real-time acquisition and processing of road surface unevenness 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 transportation equipment in complex environments.

[0076] 6. The present invention preprocesses multi-source signals, including signal denoising, normalization processing, and time synchronization processing, ensuring the accuracy and consistency of data, reducing data interference during the diagnosis process, and improving the accuracy of fault diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings. Among them:

[0078] Figure 1 It is a top view of the multi-source heterogeneous fault diagnosis device for the drive-by-wire chassis of electric transportation equipment;

[0079] Figure 2 It is a structural diagram of the multi-source heterogeneous fault diagnosis device for the drive-by-wire chassis of electric transportation equipment.

[0080] Reference numerals in the figure: 1. Frame; 2. Road surface unevenness information visual sensor; 3. Central controller; 4. Steering motor controller; 5. Steering motor; 6. Worm and gear reduction mechanism; 7. Steering kingpin column; 8. Wheel angle sensor; 9. Braking motor; 10. Brake wheel cylinder pressure sensor; 11. Ball screw reduction mechanism; 12. Ball screw; 13. In-wheel motor; 14. Brake wheel cylinder; 15. Brake pad; 16. High-voltage wire harness; 17. In-wheel motor controller; 18. High-voltage power supply; 19. Braking motor controller. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0081] In order to make the above-mentioned objects, features, and advantages of the present invention more obvious and understandable, the following will give a detailed description of the specific embodiments of the present invention with reference to the accompanying drawings of the specification.

[0082] Many specific details are set forth in the following description in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0083] Second, the so-called "one embodiment" or "embodiment" herein refers to specific features, structures, or characteristics that may be included in at least one implementation manner of the present invention. The appearances of "in one embodiment" in different places in this specification do not all refer to the same embodiment, nor are they separate or selectively exclusive embodiments from other embodiments.

[0084] Thirdly, the present invention is described in detail in conjunction with schematic diagrams. When detailing the embodiments of the present invention, for the convenience of explanation, the cross-sectional views showing the device structure will be enlarged locally not in accordance with the general scale, and the schematic diagrams are only examples and should not limit the scope of protection of the present invention herein. In addition, in actual production, three-dimensional spatial dimensions including length, width, and depth should be included.

[0085] Referring to Figure 1 - Figure 2 , a multi-source heterogeneous fault diagnosis method for the by-wire chassis of an electric transportation equipment is provided, including the following steps:

[0086] Step 1: Construct a method for collecting and preprocessing multi-source signals, collect multi-source signals obtained from the chassis steering system, braking system, road surface and road condition sensors in the intelligent driving domain, and the cloud database; preprocess the collected signals, including signal denoising, normalization processing, and time synchronization processing, to ensure the accuracy and consistency of the data;

[0087] Step 2: Based on the preprocessed multi-source signals in Step 1, model the heterogeneous systems of the electric transportation equipment, including the three-axis steering system, differential steering system, braking system, and regenerative braking system, and describe the behavioral characteristics of the systems in normal and faulty states, providing an accurate model basis for subsequent fault diagnosis;

[0088] Step 3: On the basis of Step 2, perform the fusion of multi-source heterogeneous information, integrate the data of different sensors and systems after preprocessing into unified diagnostic information, use the Bayesian network to perform fusion analysis on the data, thereby extracting key fault features, and establish a corresponding fault mode library according to the characteristics of the heterogeneous systems;

[0089] Step 4: Based on the fault features extracted in Step 3, use the decision tree to perform fault diagnosis and determination on the fused information, identify whether the vehicle has functional faults, and through the coordinated control algorithm of the redundant system, adjust other redundant systems to ensure that the vehicle's functionality is not affected and maintain the normal operation of the vehicle.

[0090] Among them, Step 1 specifically includes:

[0091] 1.1) Multi-source signal collection: Collect multi-source signals from the chassis steering system including the three-axis steering system and the differential steering system, the braking system including mechanical braking and regenerative braking systems, the road surface condition sensors in the intelligent driving domain, and the cloud database. Let the collected signals be:

[0092]

[0093] Among them, is the acquisition signal of each sensor and system, , is the signal acquisition time;

[0094] 1.2) Perform preprocessing based on the acquisition signal in 1.1): Perform denoising processing, normalization processing, and time synchronization processing on the multi-source signals collected in 1.1); Assume the signal after denoising is , the signal after normalization processing is , and the signal after time synchronization processing is , and the preprocessing formula is:

[0095]

[0096] Among them, Sync, Norm, and Denoise respectively represent time synchronization, normalization, and denoising operations, is the signal after time synchronization processing;

[0097] 1.3) Ensure data consistency and accuracy: Based on 1.2), by analyzing the eigenvector F of the preprocessed signal sync , ensure the consistency of data on the time axis, and the error between signals. The control formula is:

[0098]

[0099] Among them, is the error tolerance, is the ideal signal, is the error between signals.

[0100] Among them, step two specifically includes:

[0101] 2.1) Based on the signal in 1.3), establish a two-degree-of-freedom vehicle dynamics model and the behavior models of the three-axis steering system and the differential steering system: Model the preprocessed steering system signal S steer (t) to respectively describe the behavior characteristics of the three-axis steering and differential steering in normal and fault states,

[0102] The two-degree-of-freedom vehicle dynamics model is expressed as:

[0103]

[0104] Among them, 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 steering angles respectively, , , are the cornering stiffnesses of the front, middle, and rear axles respectively, is the longitudinal vehicle speed, is the lateral vehicle speed, is the yaw rate of the vehicle, is the vehicle mass, is the yaw moment of inertia of the vehicle, is the lateral acceleration of the vehicle, is the yaw angular acceleration of the vehicle;

[0105] The behavioral model of the steering system is expressed as:

[0106]

[0107] where, indicates that the steering system mode is three-axle steering, indicates that the steering system mode is differential steering, indicates the behavioral model of the steering system;

[0108] 2.2) Modeling the mechanical braking and regenerative braking of the braking system: Based on the signals in step 1.3), establish the behavioral characteristic model of the mechanical braking and regenerative braking systems to describe the dynamic characteristics of the system under different working modes. The behavioral model of the braking system is:

[0109]

[0110] where, and are the weight coefficients corresponding to the braking modes, is the behavioral model of the mechanical braking system, is the behavioral model of the regenerative braking system, indicates the behavioral model of the braking system;

[0111] 2.3) Description of the fault state of the behavioral model: On the basis of 2.1) and 2.2), by analyzing the deviation characteristics of the system signals in the fault state , describe the fault behavior of the heterogeneous system. The fault deviation model is:

[0112]

[0113] where, is the behavioral model in the normal state, is the behavioral model in the fault state, is the deviation characteristic of the system signal.

[0114] Further, Step 3 specifically includes:

[0115] 3.1) Based on the behavior model in 2.3), fuse the preprocessed multi-source signals: Use Bayesian network to perform fusion analysis on the data of different sensors and systems, and integrate the signals of three-axis steering, differential steering, mechanical braking, and regenerative braking into unified diagnostic information. The fusion formula is:

[0116]

[0117] where, is the three-axis steering signal, is the differential steering signal, is the mechanical braking signal, is the regenerative braking signal, is the unified diagnostic information;

[0118] 3.2) Extract key fault features: Based on the signals fused in 3.1), extract key fault features by analyzing the change rate and amplitude of the signals , and the extraction formula for fault features is:

[0119]

[0120] where, respectively represent the fault features of each system, represents the key fault feature of the system;

[0121] 3.3) Establish a fault mode library: Based on the fault features in 3.2), combined with the characteristics of heterogeneous systems, establish the corresponding fault mode library , and the mode library is represented by a fault mode matrix as:

[0122] .

[0123] where, , respectively represent the key fault features of the system, is the system fault mode library;

[0124] Among them, Step 4 specifically includes:

[0125] 4.1) Based on the fault mode library in 3.3), perform fault diagnosis: Use a decision tree to perform fault diagnosis and determination on the fusion information extracted in 3.2) to identify whether the vehicle has functional faults. The determination rules of the decision tree are:

[0126]

[0127] where, That is, to determine whether the fault feature belongs to the fault mode library;

[0128] 4.2) Coordinated control of the redundant system: According to the fault diagnosis results in 4.1), through the coordinated control algorithm of the redundant system, adjust the distribution strategies of the three-axis steering and differential steering, and the mechanical braking and regenerative braking , and the coordinated control formula is:

[0129]

[0130] Among them, , , , are the coordinated distribution coefficients of the three-axis steering, differential steering, mechanical braking, and regenerative braking systems respectively, is the distribution strategy;

[0131] 4.3) Function maintenance under fault conditions: When a fault occurs, by adjusting the control strategy of the redundant system in 4.2), ensure that the functionality of the vehicle is not affected and maintain the normal operation of the vehicle. The objective function of function maintenance is:

[0132] .

[0133] Among them, represents the behavior model under fault tolerance, The statement represents the minimum value of the deviation of the behavior model under fault tolerance from the normal state behavior model;

[0134] Furthermore, the multi-source heterogeneous fault diagnosis device for the by-wire chassis of the electric transport equipment includes: a central controller 3, a three-axis steering system, a hub motor drive system, an EMB braking system, a wheel angle sensor 8, a brake wheel cylinder pressure sensor 10, a road surface unevenness information vision sensor 2, a vehicle frame 1, an energy storage unit, and multi-source signals;

[0135] Among them, each steering axis of the three-axis steering system includes a steering motor 5, a steering motor controller 4, and a steering kingpin column 7;

[0136] The hub motor drive system includes a hub motor 13, a hub motor controller 17, and a high-voltage power supply 18;

[0137] The EMB braking system includes a braking motor 9, a braking motor controller 19, and a brake disc assembly. The brake disc assembly includes a brake wheel cylinder 14 and brake pads 15;

[0138] The road surface unevenness information vision sensor 2 is installed at the front end of the vehicle. By collecting road surface information, it is transmitted to the central controller 3 in real time, which is used to adjust the responses of the steering system, braking system, and drive system, so as to improve the adaptability of the vehicle under complex road conditions;

[0139] The vehicle 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;

[0140] Among them, the energy storage unit is connected to the hub motor 13, the steering motor 5 and the braking motor 9 through the power management module, provides the required electric energy, and monitors and manages the energy use of each system.

[0141] 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 with a worm and worm gear reduction mechanism 6. The output end of the worm and worm gear reduction mechanism 6 transmits the torque to the wheel through the kingpin column 7 to realize vehicle steering. The kingpin column 7 is rigidly connected to the vehicle frame 1 to ensure the effective transmission of the steering torque. The wheel angle sensor 8 is installed on the 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.

[0142] Specifically, the hub motor 13 is connected to the high-voltage power supply 18 through the high-voltage wire harness 16. The hub motor controller 17 is responsible for controlling the rotation of the hub motor 13 and communicates with the central controller 3 through the CAN bus to achieve the power output of the vehicle. The hub motor 13 is integrated in the wheel and directly drives the wheel to rotate through the output shaft to provide the driving force for the vehicle to travel; the braking motor 9 receives the braking signal through the braking motor controller 19. The output shaft of the braking motor 9 is connected with a ball screw reduction mechanism 11. The ball screw reduction mechanism 11 converts the rotary motion into a linear motion and transmits the torque to the brake disc assembly through the ball screw 12 to achieve the braking function of the vehicle. The brake wheel cylinder pressure sensor 10 is installed near the output shaft of the braking motor 9 to detect the actual output of the braking force and feedback the data to the braking motor controller 19 to ensure the stability and reliability of the braking effect.

[0143] 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 state of the battery in real time and perform active protection in case of anomalies; the vehicle frame 1 adopts a modular design and can be flexibly adjusted according to different requirements to adapt to various types of electric transportation equipment.

[0144] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A multi-source heterogeneous fault diagnosis method for the drive-by-wire chassis of an electric transportation equipment, characterized in that It includes the following steps: Step 1: Construct a multi-source signal acquisition and preprocessing method to collect multi-source signals from the chassis steering system, braking system, road surface condition sensors in the intelligent driving domain, and the cloud database; preprocess the collected signals, including signal denoising, normalization processing, and time synchronization processing, to ensure the accuracy and consistency of the data; Step 2: Based on the preprocessed multi-source signals in Step 1, model the heterogeneous systems of the electric transportation equipment, including the three-axis steering system, differential steering system, and braking system, and describe the behavioral characteristics of the systems in normal and faulty states, providing an accurate model basis for subsequent fault diagnosis; Step 3: On the basis of Step 2, perform the fusion of multi-source heterogeneous information, integrate the data of different sensors and systems after preprocessing into unified diagnostic information, use the Bayesian network to perform fusion analysis on the data, thereby extracting key fault characteristics, and establish a corresponding fault mode library according to the characteristics of the heterogeneous systems; Step 4: Based on the fault characteristics extracted in Step 3, use the decision tree to perform fault diagnosis and determination on the fused information, identify whether the vehicle has functional faults, and through the coordinated control algorithm of the redundant system, adjust other redundant systems to ensure that the functionality of the vehicle is not affected and maintain the normal operation of the vehicle.

2. The multi-source heterogeneous fault diagnosis method for the drive-by-wire chassis of an electric transportation equipment according to claim 1, wherein: The specific content of Step 1 includes: 1.1) Multi-source signal acquisition: Collect multi-source signals from the chassis steering system, braking system, road surface condition sensors in the intelligent driving domain, and the cloud database. Let the collected signals be: Among them, is the acquisition signal of each sensor and system, , is the signal acquisition time; The chassis steering system includes a three-axis steering system and a differential steering system; The braking system includes mechanical braking and regenerative braking systems; 1.2) Preprocess the collected signals in 1.1): For the multi-source signals collected in 1.1) perform denoising, normalization, and time synchronization processing; assume the signal after denoising is , the signal after normalization processing is , and the signal after time synchronization processing is , and the preprocessing formula is: Among them, Sync, Norm, and Denoise represent time synchronization, normalization, and denoising operations respectively, is the signal after time synchronization processing; 1.3) Data Consistency and Accuracy Assurance: On the basis of 1.2), by analyzing the eigenvector F of the preprocessed signal, sync , ensure the consistency of data on the time axis and the error between signals The control formula is: wherein, is the error tolerance, is the ideal signal, is the error between signals.

3. The multi-source heterogeneous fault diagnosis method for the by-wire chassis of an electric transport equipment according to claim 2, characterized in that: The specific content of Step 2 includes: 2.1) Based on the signals in 1.3), establish a two-degree-of-freedom vehicle dynamics model and the behavior models of the three-axle steering system and the differential steering system: Model the preprocessed steering system signal S steer (t), and respectively describe the behavior characteristics of the three-axle steering and differential steering in normal and fault states. The two-degree-of-freedom vehicle dynamics model is expressed as: where a, b, and c are the distances from the centroid to the first, second, and third axes, respectively, , , are the front, middle, and rear wheel steering angles, respectively, , , are the cornering stiffnesses of the front, middle, and rear axles, respectively, is the longitudinal velocity of the vehicle, is the lateral velocity of the vehicle, is the yaw rate of the vehicle, is the mass of the vehicle, is the yaw moment of inertia of the vehicle, is the lateral acceleration of the vehicle, is the yaw angular acceleration of the vehicle; The behavioral model of the steering system is expressed as: Among them, indicates that the steering system mode is three-axis steering, indicates that the steering system mode is differential steering, indicates the steering system behavior model; 2.2) Model the mechanical braking and regenerative braking of the braking system: Based on the signals in Step 1.3), establish a behavioral characteristic model of the mechanical braking and regenerative braking systems, describe the dynamic characteristics of the systems in different working modes, and the behavioral model of the braking system is: Among them, and are the weight coefficients corresponding to the braking modes, is the mechanical braking system behavior model, is the regenerative braking system behavior model, represents the braking system behavior model; 2.3) Fault state description of the behavior model: Based on 2.1) and 2.2), by analyzing the deviation characteristics of system signals in the fault state , the fault behavior of the heterogeneous system is described, and the fault deviation model is: Among them, 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 the drive-by-wire chassis of an electric vehicle according to claim 3, characterized in that: The specific content of Step 3 includes: 3.1) Based on the behavior model in 2.3), fuse the preprocessed multi-source signals: Use a Bayesian network to perform fusion analysis on the data of different sensors and systems, and integrate the signals of three-axis steering, differential steering, mechanical braking, and regenerative braking into unified diagnostic information , and the fusion formula is: Among them, is a three-axis steering signal, is a differential steering signal, is a mechanical braking signal, is a regenerative braking signal, is unified diagnostic information; 3.2) Extraction of key fault features: Based on the fused signal in 3.1), key fault features are extracted by analyzing the change rate and amplitude of the signal , and the extraction formula for fault features is as follows: Among them, respectively represent the fault characteristics of each system, represents the key fault characteristic of the system; 3.3) Establishment of the fault mode library: Based on the fault characteristics in 3.2) and combined with the characteristics of heterogeneous systems, establish the corresponding fault mode library , and the mode library is represented by a fault mode matrix as follows: Among them, , respectively represent the key fault characteristics of the system, is the system fault mode library.

5. The multi-source heterogeneous fault diagnosis method for the drive-by-wire chassis of an electric vehicle according to claim 4, characterized in that: The specific content of Step 4 includes: 4.1) Based on the fault mode library in 3.3), perform fault diagnosis: Use the decision tree to perform fault diagnosis and determination on the fused information extracted in 3.2), identify whether the vehicle has functional faults, and the determination rule of the decision tree is: Among them, that is, to determine whether the fault feature belongs to the fault mode library; 4.2) Coordinated control of the redundant system: Based on the fault diagnosis results in 4.1), adjust the distribution strategies of the three-axis steering and differential steering, mechanical braking and regenerative braking through the coordinated control algorithm of the redundant system , and the coordinated control formula is as follows: Among them, , , , are the coordination distribution coefficients of the three-axis steering, differential steering, mechanical braking, and regenerative braking systems respectively, is the distribution strategy; 4.3) Function maintenance under fault conditions: When a fault occurs, ensure that the functionality of the vehicle is not affected and maintain the normal operation of the vehicle by adjusting the control strategy of the redundant system in 4.2). The objective function of function maintenance is: Among them, represents the fault tolerance downlink behavior model, The statement represents the minimum value of the deviation of the fault tolerance downlink behavior model from the normal state behavior model.

6. A multi-source heterogeneous fault diagnosis device for a drive-by-wire chassis of an electric transportation equipment, adopting the diagnosis method according to any one of claims 1 to 5, characterized in that: It includes: Central controller (3), three-axis steering system, in-wheel motor drive system, EMB braking system, wheel angle sensor (8), brake wheel cylinder pressure sensor (10), road surface roughness information vision sensor (2), frame (1), energy storage unit, and multi-source signals; Among them, each steering axis of the three-axis steering system includes a steering motor (5), a steering motor controller (4), and a steering kingpin column (7); The in-wheel motor drive system includes in-wheel motors (13), in-wheel motor controllers (17), and high-voltage power supplies (18); The described EMB braking system includes a braking motor (9), a braking motor controller (19), and a brake disc assembly. The brake disc assembly includes a brake wheel cylinder (14) and brake pads (15). The road surface unevenness information vision sensor (2) is installed at the front end of the vehicle. By collecting road surface information, it is transmitted to the central controller (3) in real time, and is used to adjust the responses of the steering system, braking system, and drive system, thereby improving the adaptability of the vehicle under complex road conditions. The vehicle frame (1) is used to support and connect the above-mentioned systems. It is made of high-strength lightweight materials to ensure the stability and safety of the overall structure. Among them, the energy storage unit is connected to the hub motor (13), steering motor (5), and braking motor (9) through a power management module, provides the required electrical energy, and monitors and manages the energy usage of each system.

7. The multi-source heterogeneous fault diagnosis device for the by-wire chassis of an electric vehicle carrier according to claim 6, characterized in that: The steering motor (5) receives steering commands through the steering motor controller (4). The output shaft of the steering motor is connected to a worm and worm gear reduction mechanism (6). The output end of the worm and worm gear reduction mechanism (6) transmits the torque to the wheel through the steering kingpin column (7) to achieve vehicle steering. The steering kingpin column (7) is rigidly connected to the vehicle frame (1) to ensure the effective transmission of the steering torque. The wheel angle sensor (8) is installed on the steering kingpin column (7) and is used 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 the drive-by-wire chassis of an electric transportation equipment according to claim 7, characterized in that: The hub motor (13) is connected to the high-voltage power supply (18) through a high-voltage wire harness (16). The hub motor controller (17) is responsible for controlling the rotation of the hub motor (13) and communicates with the central controller (3) through the CAN bus to achieve the power output of the vehicle. The hub motor (13) is integrated in the wheel and directly drives the wheel to rotate through the output shaft to provide the driving force for the vehicle to travel. The braking motor (9) receives braking signals through the braking motor controller (19). The output shaft of the braking motor (9) is connected to a ball screw reduction mechanism (11). The ball screw reduction mechanism (11) converts the rotational motion into a linear motion and transmits the torque to the brake disc assembly through the ball screw (12) to achieve the braking function of the vehicle. The brake wheel cylinder pressure sensor (10) is installed near the output shaft of the braking motor (9) and is used to detect the actual output of the braking force and feedback the data to the braking motor controller (19) to ensure the stability and reliability of the braking effect.

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

Images