Intelligent vehicle fault diagnosis and fault-tolerant control method based on three-step method

Abstract

The present invention relates to the field of autonomous driving technology, and specifically discloses a method for intelligent vehicle fault diagnosis and fault-tolerant control based on a three-step method. The present invention establishes a vehicle path tracking model; establishes an execution motor fault model; establishes a three-step control module; establishes a fault diagnosis module; establishes a fault adjustment module; and establishes a controller reconstruction module. It has the characteristics of simple design and clear logical concepts, is suitable for intelligent vehicle controller design, can be effectively applied to autonomous driving vehicle path tracking control, realizes fault diagnosis and fault-tolerant control functions, and can effectively solve the problems of complex system architecture, fault diversity, immature fault-tolerant technology and data processing difficulty faced by existing autonomous driving fault diagnosis and fault-tolerant control.

Description

Technical Field

[0001] The present invention belongs to the technical field of autonomous driving, and in particular relates to a three-step method based intelligent vehicle fault diagnosis and fault-tolerant control method. Background Art

[0002] The significance of studying autonomous driving is to use artificial intelligence and machine learning technology to enable cars to drive autonomously, thereby improving driving safety and efficiency. The study of autonomous driving helps solve some problems in the driving process, such as driver fatigue, operating errors, road traffic congestion, etc. The technology of autonomous driving can eliminate the influence of the driver to a certain extent, and can make decisions faster and more accurately when encountering complex road conditions. In addition, the study of autonomous driving also helps to promote technological progress in the automotive industry and help solve global environmental problems, such as reducing pollution, reducing energy consumption, and improving urban traffic conditions. In general, autonomous driving not only helps to improve driving safety and efficiency, but also helps to promote technological progress in the automotive industry and improve environmental conditions.

[0003] Autonomous driving fault diagnosis and fault-tolerant control are key links in autonomous driving technology. Autonomous driving fault diagnosis refers to the diagnosis of the system, hardware and software of autonomous driving technology to determine the cause of the fault and to repair or take emergency measures. This is crucial to ensure the safety and reliability of autonomous driving technology. Fault-tolerant control refers to taking corresponding measures to ensure the safety of the vehicle when autonomous driving technology encounters a fault or abnormal situation. Fault-tolerant control includes two aspects: on the one hand, avoiding faults; on the other hand, taking emergency measures after a fault occurs. This is also crucial to ensure the safety and reliability of autonomous driving technology. In general, autonomous driving fault diagnosis and fault-tolerant control are key factors in ensuring the safety and reliability of vehicle autonomous driving technology, and are of great significance to improving the level of autonomous driving technology.

[0004] In the existing technology, autonomous driving fault diagnosis and fault-tolerant control still have the following defects:

[0005] 1. Complex system architecture: The system architecture of autonomous driving technology is complex, including multiple components such as sensors, computers, controllers, and lidar. It is a challenge to diagnose faults and determine the causes of faults.

[0006] 2. Fault diversity: Faults can be caused by hardware failure, software failure, environmental factors or human factors. It is difficult to diagnose the cause of the fault quickly and accurately.

[0007] 3. Immature fault-tolerant technology: Currently, fault-tolerant technology is not mature enough to cope with complex fault situations. For example, when a fault affects multiple systems, it is still a challenge to determine the emergency measures to be taken.

[0008] 4. Difficulty in data processing: Autonomous driving technology generates a large amount of data. How to quickly and accurately process this data to diagnose faults and take emergency measures is a difficult problem. Summary of the invention

[0009] The purpose of the embodiment of the present invention is to provide an intelligent automobile fault diagnosis and fault-tolerant control method based on a three-step method, aiming to solve the problems raised in the background technology.

[0010] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0011] A three-step method for intelligent vehicle fault diagnosis and fault-tolerant control, the method specifically comprising the following steps:

[0012] Establish a vehicle path tracking model;

[0013] Establish an actuator motor fault model;

[0014] Based on the vehicle path tracking model, a three-step control module is established;

[0015] Based on the actuator motor fault model, a fault diagnosis module is established;

[0016] Establishing a fault adjustment module based on the vehicle path tracking model, the three-step control module and the fault diagnosis module;

[0017] A controller reconstruction module is established based on the vehicle path tracking model and the fault adjustment module.

[0018] As a further limitation of the technical solution of the embodiment of the present invention, the establishment of the vehicle path tracking model is expressed as:

[0019]

[0020] In the formula,

[0021]

[0022]

[0023]

[0024] ω=[ω fl ω fr ω rl ω rr ] T

[0025]

[0026] Among them, the state x of the vehicle path tracking model is x = [x 1 , x 2 ] T =[V x ,Ω z ] T , V x is the vehicle longitudinal velocity, Ω z is the vehicle yaw rate, and the input of the vehicle path tracking model u=[T fl , T fr , T rl , T rr ] T , T ij Respectively represent the motor torques of the left front wheel (f1), the right front wheel (fr), the left rear wheel (r1) and the right rear wheel (rr);

[0027] Among them, V y is the lateral speed of the vehicle, M v is the vehicle mass, C a and C s is the drag coefficient, C f and C r is the stiffness coefficient of the front and rear wheels, l f and l r is the length from the front and rear wheels to the center of the vehicle, δ is the front wheel steering angle, I z is the vehicle moment of inertia, R e is the effective radius of the tire, l s is the distance between the left and right wheels, ω ij They represent the angular velocities of the left front wheel (f1), the right front wheel (fr), the left rear wheel (rl), and the right rear wheel (rr), respectively.

[0028] As a further limitation of the technical solution of the embodiment of the present invention, the motor fault model is expressed as:

[0029] u=Eu *

[0030] In the formula, u * is the desired output torque of the actuator motor, E = Diag ([θ 1 θ 2 ,θ 3 ,θ 4 ]) is the effective coefficient of the four motors, that is, θ i ∈[0,1],i={1,…,4}.

[0031] As a further limitation of the technical solution of the embodiment of the present invention, the three-step control module established based on the vehicle path tracking model specifically includes the following steps:

[0032] Based on the vehicle path tracking model, a steady-state control law is established

[0033] Based on the vehicle path tracking model, a reference feedforward control law is established

[0034] Based on the vehicle path tracking model, an error feedback control law is established

[0035] Combining the steady-state control law, the reference feedforward control law and the error feedback control law, a three-step control module is established.

[0036] As a further limitation of the technical solution of the embodiment of the present invention, the three-step control module is expressed as:

[0037]

[0038] As a further limitation of the technical solution of the embodiment of the present invention, the steady-state control law is expressed as: The reference feedforward control law is expressed as: The error feedback control law is expressed as:

[0039] As a further limitation of the technical solution of the embodiment of the present invention, the fault diagnosis module is represented as:

[0040]

[0041] In the formula, The fault diagnosis module estimates the actuator fault, and Δ is the fault estimation error of the diagnosis model.

[0042] As a further limitation of the technical solution of the embodiment of the present invention, the fault adjustment module is represented as:

[0043]

[0044]

[0045]

[0046] In the formula, v * (k) is the kth T of the system s The virtual control amount at the moment, Is the fault adjustment module kT s The virtual control amount at time Ts is the sampling period, ε is a positive number, I is the identity matrix,

[0047] As a further limitation of the technical solution of the embodiment of the present invention, the controller reconstruction module is represented as:

[0048]

[0049] Compared with the prior art, the present invention has the following beneficial effects:

[0050] The embodiment of the present invention establishes a vehicle path tracking model; establishes an execution motor fault model; establishes a three-step control module; establishes a fault diagnosis module; establishes a fault adjustment module; and establishes a controller reconstruction module. It has the characteristics of simple design and clear logical concepts, is suitable for intelligent vehicle controller design, can be effectively applied to autonomous driving vehicle path tracking control, realizes fault diagnosis and fault-tolerant control functions, and can effectively solve the problems of complex system architecture, fault diversity, immature fault-tolerant technology and data processing difficulty faced by existing autonomous driving fault diagnosis and fault-tolerant control. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention.

[0052] Figure 1 A flow chart of a method provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0054] It is understandable that in the existing technology, autonomous driving fault diagnosis and fault-tolerant control still have the following defects: 1. Complex system architecture: The system architecture of autonomous driving technology is complex, including multiple components such as sensors, computers, controllers and lidar. How to diagnose faults and determine the causes of faults is a challenge; 2. Fault diversity: Faults can be caused by many reasons such as hardware failures, software failures, environmental factors or human factors. How to quickly and accurately diagnose the causes of faults is difficult; 3. Immature fault-tolerant technology: Currently, fault-tolerant technology is not mature enough to cope with complex fault situations. For example, when a fault affects multiple systems, how to determine the emergency measures to be taken is still a challenge; 4. Data processing difficulty: Autonomous driving technology generates a large amount of data. How to quickly and accurately process this data to diagnose faults and take emergency measures is a difficult problem.

[0055] To solve the above problems, the embodiment of the present invention establishes a vehicle path tracking model; establishes an execution motor fault model; establishes a three-step control module; establishes a fault diagnosis module; establishes a fault adjustment module; and establishes a controller reconstruction module. It has the characteristics of simple design and clear logical concepts, is suitable for intelligent vehicle controller design, can be effectively applied to autonomous driving vehicle path tracking control, realizes fault diagnosis and fault-tolerant control functions, and can effectively solve the problems of complex system architecture, fault diversity, immature fault-tolerant technology and data processing difficulty faced by existing autonomous driving fault diagnosis and fault-tolerant control.

[0056] Figure 1 A flow chart of a method provided by an embodiment of the present invention is shown.

[0057] Specifically, in a preferred embodiment of the present invention, a fault diagnosis and fault-tolerant control method for an intelligent vehicle based on a three-step method comprises the following steps:

[0058] Step S101, establishing a vehicle path tracking model.

[0059] In the embodiment of the present invention, the state x of the vehicle path tracking model is defined as 1 , x 2 ] T =[V x ,Ω z ] T , where V x is the vehicle longitudinal velocity, Ω z is the vehicle yaw rate; define the model input u=[T fl , T fr , T rl , T rr ] T , where T ijThey represent the motor torques of the left front wheel (fl), the right front wheel (fr), the left rear wheel (rl) and the right rear wheel (rr) respectively. According to the vehicle dynamics and tire dynamics, the vehicle path tracking model is established as follows:

[0060]

[0061] In the formula,

[0062]

[0063]

[0064]

[0065] ω=[ω fl ω fr ω rl ω rr ] T

[0066]

[0067] Among them, V y is the lateral speed of the vehicle, M v is the vehicle mass, C a and C s is the drag coefficient, C f and C r is the stiffness coefficient of the front and rear wheels, l f and l r is the length from the front and rear wheels to the center of the vehicle, δ is the front wheel steering angle, I z is the vehicle moment of inertia, R e is the effective radius of the tire, l s is the distance between the left and right wheels, ω ij They represent the angular velocities of the left front wheel (f1), the right front wheel (fr), the left rear wheel (rl), and the right rear wheel (rr), respectively.

[0068] It can be understood that in the vehicle path tracking model, the input of the model is the virtual input v, and the output of the model is the vehicle state x.

[0069] Step S102, establishing an execution motor fault model.

[0070] In the embodiment of the present invention, considering the decrease in motor efficiency, a motor fault model is established according to the multiplicative rule and is expressed as:

[0071] u=Eu *

[0072] In the formula, u * is the desired output torque of the actuator motor, E = Diag ([θ1 θ 2 ,θ 3 ,θ 4 ]) is the effective coefficient of the four motors, that is, θ i ∈[0,1],i={1,…,4}.

[0073] It can be understood that the input of the motor fault model is the desired output torque u of the actuator motor. * , the output is the actual output torque u of the actuator motor.

[0074] Step S103: establishing a three-step control module based on the vehicle path tracking model.

[0075] In the embodiment of the present invention, first, use Replace υ and substitute into the vehicle path tracking model, while ignoring the system dynamics (let ) and disturbance term (let J = 0), the steady-state control law is obtained Second, use Replace v, replace Substituting both into the vehicle path tracking model and ignoring the influence of the interference term (let d = 0), the reference feedforward control law is obtained Again, use Replace v and define the tracking error e = x * -x, the steady-state control law and the reference feedforward control law Substitute into the vehicle path tracking model and get the error feedback control law In the formula, K p is the feedback gain; finally, according to steady-state control, reference feedforward control and error feedback control, the designed three-step control module is expressed as:

[0076]

[0077] It can be understood that the input of the three-step control module is the vehicle path tracking model and the reference signal x * , the output is It is the output of the three-step control model and can act on the subsequent fault adjustment module.

[0078] Step S104: establishing a fault diagnosis module based on the execution motor fault model.

[0079] In the embodiment of the present invention, according to the motor fault model, a fault diagnosis module is established as follows:

[0080]

[0081] In the formula, The fault diagnosis module estimates the actuator fault, and Δ is the fault estimation error of the diagnosis model.

[0082] It can be understood that the input of the fault diagnosis module is the actual motor torque u and the expected motor torque u of the four wheels. * , the output is an estimate of the actuator fault Used in subsequent fault adjustment modules and controller reconstruction modules.

[0083] Step S105: establishing a fault adjustment module based on the vehicle path tracking model, the three-step control module and the fault diagnosis module.

[0084] In the embodiment of the present invention, based on the vehicle path tracking model, the three-step control module and the fault diagnosis module, a fault adjustment module is further established and expressed as:

[0085]

[0086]

[0087]

[0088] In the formula, v * (k) is the kth T of the system s The virtual control amount at the moment, Is the fault adjustment module kT s The virtual control amount at time T s is the sampling period, ε is a positive number, I is the identity matrix,

[0089] It can be understood that the input of the fault adjustment module is the three-step control law The state parameters related to the vehicle path tracking model, the output is the virtual control signal v actually executed * , used for subsequent controller reconstruction module.

[0090] Step S106: establishing a controller reconstruction module based on the vehicle path tracking model and the fault adjustment module.

[0091] In the embodiment of the present invention, after the fault adjustment module, according to the optimal control theory, a controller reconstruction module is established and expressed as:

[0092] u=C T D -1 v * .

[0093] It can be understood that the input of the controller reconstruction module is the output of the fault adjustment module, and the relevant state parameters of the vehicle path tracking model need to be used; the output of the controller reconstruction module is the actual motor torque u of the four wheels, which acts on the smart car.

[0094] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0095] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0096] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0097] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0098] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. Intelligent vehicle fault diagnosis and fault-tolerant control method based on three-step method, It is characterized in that The method specifically comprises the following steps: Establish a vehicle path tracking model; Establish an actuator motor fault model; Based on the vehicle path tracking model, a three-step control module is established; Based on the actuator motor fault model, a fault diagnosis module is established; Establishing a fault adjustment module based on the vehicle path tracking model, the three-step control module and the fault diagnosis module; Establishing a controller reconstruction module based on the vehicle path tracking model and the fault adjustment module; Wherein, the establishment of the vehicle path tracking model is expressed as: In the formula, ω=[ω fl oh fr oh rl oh rr ] T Among them, the state x of the vehicle path tracking model is x = [x 1 ,x 2 ] T =[V x ,Ω z ] T , V x is the vehicle longitudinal velocity, Ω z is the vehicle yaw rate, and the input of the vehicle path tracking model u=[T fl , T fr , T rl , T rr ] T , T ij Represent the motor torques of the left front wheel (fl), right front wheel (fr), left rear wheel (rl) and right rear wheel (rr) respectively; Among them, V y is the lateral speed of the vehicle, M v is the vehicle mass, C a and C s is the drag coefficient, C f and C r is the stiffness coefficient of the front and rear wheels, l f and l r is the length from the front and rear wheels to the center of the vehicle, δ is the front wheel steering angle, I z is the vehicle moment of inertia, R e is the effective radius of the tire, l s is the distance between the left and right wheels, ω ij denote the angular velocities of the left front wheel (fl), the right front wheel (fr), the left rear wheel (rl), and the right rear wheel (rr), respectively; The motor fault model is expressed as: u=I * In the formula, u * is the desired output torque of the actuator motor, E = Diag (θ 1 ,θ 2 ,θ 3 ,θ 4 ]) is the effective coefficient of the four motors, that is, θ i∈[0,1], i={1,…,4}; The three-step control module established based on the vehicle path tracking model specifically includes the following steps: Based on the vehicle path tracking model, a steady-state control law is established Based on the vehicle path tracking model, a reference feedforward control law is established Based on the vehicle path tracking model, an error feedback control law is established Combining the steady-state control law, the reference feedforward control law and the error feedback control law, a three-step control module is established. The three-step control module is expressed as: The steady-state control law is expressed as: The reference feedforward control law is expressed as: The error feedback control law is expressed as: The fault diagnosis module is represented as: In the formula, The estimated value of the actuator fault by the fault diagnosis module, Δ is the estimated error of the fault by the diagnosis model; The fault adjustment module is represented as: In the formula, v * (k) is the kth T of the system s The virtual control amount at the moment, Is the fault adjustment module kT s The virtual control amount at time T s is the sampling period, ε is a positive number, I is the identity matrix, The controller reconstruction module is represented as: u=C T D -1 v * 。

Images