Distributed electric drive vehicle state parameter observation method and device and readable medium

Abstract

The application discloses a kind of distributed electric drive car state parameter observation method, device and readable medium, by obtaining the first longitudinal velocity of current time of car, lateral acceleration, wheel longitudinal force, wheel rotation angle and wheel lateral force, wheel longitudinal force, wheel rotation angle and wheel lateral force of current time are input nonlinear vehicle model, obtain yaw angular velocity;Wheel rotation angle, lateral acceleration, yaw angular velocity, the first longitudinal velocity input state parameter observation model, obtain the first mass side slip angle, and state parameter observation model uses adaptive fuzzy neural network model;With yaw angular velocity and the first mass side slip angle as observation vector constructs the first sliding mode observer;Wheel rotation angle, wheel longitudinal force, wheel lateral force are input the first sliding mode observer, obtain the second longitudinal velocity and second lateral velocity, according to the second longitudinal velocity and second lateral velocity obtain the second mass side slip angle, effectively improve the precision of car state parameter estimation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of distributed electric drive vehicles, and particularly relates to a distributed electric drive vehicle state parameter observation method, device and readable medium. BACKGROUND

[0002] With the progress of information technology, the development of intelligent vehicles has also made great progress. In the field of passenger vehicles, the trend of electrification and intelligentization is also becoming more and more obvious. The biggest advantage of distributed electric drive passenger vehicles compared with traditional centralized drive passenger vehicles is that it can flexibly distribute the torque of the four wheels, expand the application range of vehicle dynamics control, and improve the control accuracy and response speed. Safety is one of the core problems in the driving process of passenger vehicles. The working conditions of passenger vehicles are complex and changeable. Therefore, vehicle dynamics control is needed for passenger vehicles. Vehicle dynamics control is a key technology for active safety control of vehicles, and the first problem is to accurately obtain the current state and other important parameters of the passenger vehicle.

[0003] In some state parameters of traditional vehicles can be directly measured by sensors, but the cost of some sensors is very high, and the requirements for the environment are also relatively high, which seriously affects the accurate acquisition of the state parameters of the vehicle, which will inevitably affect the control effect of the control system. Moreover, some key parameters cannot be directly measured and can only be obtained by some prediction methods. For example, the vehicle mass center side slip angle. The vehicle state parameter estimation method is to minimize the residual error between the measured value and the estimated value of the easily measured state as the target to achieve optimal estimation of the estimated state. Some commonly used estimation algorithms include Kalman filter algorithm, sliding mode observer, etc. Each has its own defects. For example, the noise of Kalman filter is greatly affected by external factors. The error of sliding mode observer is prone to chattering. These shortcomings have a great impact on the accuracy of the observer.

[0004] Through the analysis of the existing research results, it is known that how to further improve the estimation accuracy while ensuring the stability of the estimation method is a key problem that needs to be solved. Therefore, it is necessary to develop an estimation method that can accurately estimate the state parameters of the passenger vehicle during driving. SUMMARY

[0005] In view of the problem that the observation accuracy of the previous vehicle state observer is not high and is easily disturbed by external factors, the purpose of the embodiments of the present application is to propose a distributed electric drive vehicle state parameter observation method, device and readable medium to solve the technical problems mentioned in the background technology part.

[0006] In a first aspect, the present application provides a distributed electric drive vehicle state parameter observation method, comprising the following steps:

[0007] S1, acquiring a first longitudinal speed, a lateral acceleration, a wheel longitudinal force, a wheel steering angle and a wheel lateral force of the vehicle at a current time, inputting the wheel longitudinal force, the wheel steering angle and the wheel lateral force at the current time into a nonlinear vehicle model to obtain a yaw rate;

[0008] S2, inputting the wheel steering angle, the lateral acceleration, the yaw rate and the first longitudinal speed into a state parameter observation model to obtain a first mass center side slip angle, the state parameter observation model adopting an adaptive fuzzy neural network model;

[0009] S3, taking the yaw rate and the first mass center side slip angle as an observation vector to construct a first sliding mode observer;

[0010] S4, inputting the wheel steering angle, the wheel longitudinal force and the wheel lateral force into the first sliding mode observer to obtain a second longitudinal speed and a second lateral speed, and obtaining a second mass center side slip angle according to the second longitudinal speed and the second lateral speed.

[0011] As preferred, the adaptive fuzzy neural network model comprises an input node layer, a rule node layer, an average node layer, a conclusion node layer and an output node layer, the input node layer is used for fuzzifying input variables, each node is an adaptive node with a specific node function, and the node function is:

[0012]

[0013] Wherein, x is a node input, {a, b, c} is a variable parameter set, referred to as a premise part parameter of a rule, and capable of reflecting different membership functions in a fuzzy set;

[0014] The node output function of the input node layer is represented as:

[0015]

[0016] Wherein, x1, x2, …, x n are node inputs, and the node output is a membership function value of fuzzy variables A i , B j and C k , and represents the membership degree of the node inputs x1, x2, …, x n to A i , B j and C k ;

[0017] The node of the rule node layer is a fixed node represented by a multiplication symbol (Π), and the node output function of the input node layer is taken as an input signal of the rule node layer, and the input of the rule node layer is the product of all input signals in the rule node layer:

[0018]

[0019] The nodes of the average node layer are fixed nodes labeled N, and the output of the nodes is the ratio of the excitation strength to the sum of the excitation strengths in the rule base, which represents the normalization of the rule strength:

[0020]

[0021] The nodes of the conclusion node layer are adaptive nodes with a node function, and the output of the nodes of the conclusion node layer is represented as:

[0022]

[0023] where p i , q i and r i are the consequent parameters, and f i is a symbol representing the product of the consequent parameters and the system input;

[0024] The nodes of the output node layer are adaptive nodes with a node function, and the output of the nodes of the output node layer is represented as:

[0025]

[0026] The input of the adaptive fuzzy neural network model is the wheel angle, lateral acceleration, yaw rate, first longitudinal velocity input state parameter observation model, and the output of the adaptive fuzzy neural network model is the first mass side slip angle β ANFIS .

[0027] As preferred, the training process of the adaptive fuzzy neural network model specifically includes:

[0028] A second sliding mode observer is constructed with the yaw rate as the observation vector:

[0029] The second sliding mode observer is described by the following formula:

[0030]

[0031] where x is the state vector, u is the input variable, z is the observation vector, and K is the robust control term matrix;

[0032] The nonlinear form expression of the second sliding mode observer is:

[0033]

[0034] where the input variable is:

[0035] u = [δ F x F y ];

[0036] where δ is the wheel angle, Fx F is the longitudinal force acting on the wheel. y The lateral force acting on the wheel; the state vector and observation vector are respectively:

[0037] x = [v x v y r];

[0038] y = [r];

[0039] Where, ν x For the third longitudinal velocity, ν y The third lateral velocity is r, and the yaw rate is r.

[0040] The second sliding mode observer is constructed based on the sliding mode variable structure theory as follows:

[0041]

[0042] I s =sgn(s);

[0043]

[0044] H is the damping coefficient matrix, I s This is the switching function;

[0045] The damping coefficient matrix H of the second sliding mode observer is:

[0046] H = [h1 h2 h3];

[0047] Where h1, h2, and h3 are the damping coefficients obtained during the simulation process;

[0048] The robust control term matrix K of the second sliding mode observer is:

[0049] K = [k1 k2 k3];

[0050] Wherein, k1, k2, and k3 are the robust control terms obtained during the simulation process;

[0051] Choosing the saturation function as the switching function for the second sliding mode observer is equivalent to setting a boundary layer near the sliding surface, thus:

[0052] I s =sat(s / λ);

[0053] Where λ is the thickness of the boundary layer;

[0054] The third longitudinal velocity v is estimated using the second sliding mode observer. x and the third lateral velocity v y Then, the first centroid sideslip angle is estimated using the following formula:

[0055]

[0056] Collect the wheel angle, lateral acceleration, yaw rate and first longitudinal velocity in the process of automobile running, and constitute the training data of the wheel angle, lateral acceleration, yaw rate and first longitudinal velocity and the first mass center side slip angle. The adaptive fuzzy neural network model is trained by using the training data, and a state parameter observation model is obtained.

[0057] As preferred, step S1 specifically comprises:

[0058] A three-degree-of-freedom dynamic model is selected as a nonlinear vehicle model of a distributed electric drive vehicle:

[0059]

[0060] Wherein, m is the mass of the vehicle, v 0 x is the first longitudinal velocity, v 0 y is the first lateral velocity, r is the yaw rate, δ is the wheel angle, d is the wheelbase of the front and rear axles, a is the distance from the vehicle mass center to the front axle, b is the distance from the vehicle mass center to the rear axle, I z is the yaw moment of inertia, F x is the wheel longitudinal force acting on the wheel, F y is the wheel lateral force acting on the wheel, F xij and F yij ij=fl、fr、rl、rr, respectively, represent the front left wheel, the front right wheel, the rear left wheel and the rear right wheel.

[0061] As preferred, the calculation formula of the wheel longitudinal force F x is as follows:

[0062]

[0063] Wherein, J w is the wheel moment of inertia, r w is the effective radius of the wheel, w ij and T ij represent the angular velocity and the wheel torque of each wheel, respectively.

[0064] As preferred, step S3 specifically comprises:

[0065] The nonlinear form expression of the first sliding mode observer is:

[0066]

[0067] Wherein, the state vector is:

[0068] x = [v' x v' y r];

[0069] The observation vector is

[0070] y = [r β ANFIS ];

[0071] wherein β ANFIS is a first center of mass side slip angle estimated by an adaptive fuzzy neural network;

[0072] The input vector is

[0073] u = [δ F x F y ];

[0074] Therefore, the first sliding mode observer is constructed as follows:

[0075]

[0076] I s = sat(s / λ);

[0077]

[0078] As preferred, the step S4 specifically comprises:

[0079] The second longitudinal speed v' x and the second lateral speed v' y of the automobile are estimated by the first sliding mode observer, and the second center of mass side slip angle is estimated according to the following formula:

[0080]

[0081] In a second aspect, the present application provides a distributed electric drive automobile state parameter observation device, comprising:

[0082] The yaw rate calculation module is configured to obtain the first longitudinal speed, the lateral acceleration, the wheel longitudinal force, the wheel rotation angle and the wheel lateral force of the automobile at the current time, input the wheel longitudinal force, the wheel rotation angle and the wheel lateral force at the current time into the nonlinear vehicle model, and obtain the yaw rate;

[0083] The first center of mass side slip angle calculation module is configured to input the wheel rotation angle, the lateral acceleration, the yaw rate and the first longitudinal speed into the state parameter observation model, and obtain the first center of mass side slip angle, wherein the state parameter observation model adopts an adaptive fuzzy neural network model;

[0084] The first sliding mode observer construction module is configured to construct the first sliding mode observer by taking the yaw rate and the first center of mass side slip angle as the observation vector;

[0085] The second center-of-mass side slip angle calculation module is configured to input the wheel rotation angle, the wheel longitudinal force and the wheel lateral force into the first sliding mode observer to obtain a second longitudinal velocity and a second lateral velocity, and obtain a second center-of-mass side slip angle according to the second longitudinal velocity and the second lateral velocity.

[0086] In a third aspect, the present application provides an electronic device, comprising one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any of the implementation manners of the first aspect.

[0087] In a fourth aspect, the present application provides a computer readable storage medium, which stores a computer program, when the computer program is executed by a processor, the method described in any of the implementation manners of the first aspect is implemented.

[0088] Compared with the prior art, the present application has the following beneficial effects:

[0089] (1) The distributed electric drive vehicle state parameter observation method provided by the present application can effectively solve the problem of poor estimation accuracy caused by chattering of the sliding mode observer due to the sliding mode surface, by designing a second sliding mode observer to estimate the vehicle state parameters, and introducing an adaptive fuzzy neural network model based on the estimation, and using the first center-of-mass side slip angle estimated by the second sliding mode observer, the wheel rotation angle, the lateral acceleration, the yaw rate and the first longitudinal velocity as training data to train the adaptive fuzzy neural network model, and obtaining a state parameter observation model.

[0090] (2) The distributed electric drive vehicle state parameter observation method provided by the present application can finally obtain a second center-of-mass side slip angle close to the true value, with high estimation accuracy and small error.

[0091] (3) The distributed electric drive vehicle state parameter observation method provided by the present application overcomes the shortcomings of the existing vehicle observer, improves the estimation accuracy of the vehicle state parameters, and is suitable for state parameter estimation of passenger cars. BRIEF DESCRIPTION OF DRAWINGS

[0092] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0093] Figure 1 is an exemplary device architecture diagram to which an embodiment of the present application can be applied;

[0094] Figure 2 This is a flowchart illustrating the distributed electric drive vehicle state parameter observation method according to an embodiment of this application.

[0095] Figure 3 This is a flowchart illustrating a distributed electric drive vehicle state parameter observation method according to an embodiment of this application.

[0096] Figure 4 This is a schematic diagram illustrating the data processing between the adaptive fuzzy neural network model and the first sliding mode observer in the distributed electric drive vehicle state parameter observation method of an embodiment of this application.

[0097] Figure 5 This is a comparison chart of the results of the distributed electric drive vehicle state parameter observation method according to an embodiment of this application with the original method and the actual values;

[0098] Figure 6 This is a schematic diagram of a distributed electric drive vehicle state parameter observation device according to an embodiment of this application;

[0099] Figure 7 This is a schematic diagram of the structure of a computer device suitable for implementing electronic devices according to the embodiments of this application. Detailed Implementation

[0100] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0101] Figure 1 An exemplary device architecture 100 is shown that can be applied to the distributed electric vehicle state parameter observation method or distributed electric vehicle state parameter observation device according to the embodiments of this application.

[0102] like Figure 1 As shown, the device architecture 100 may include terminal devices 101, 102, and 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, and 103 and the server 105. The network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0103] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various applications, such as data processing applications and file processing applications, can be installed on terminal devices 101, 102, and 103.

[0104] The terminal device 101, 102, 103 can be hardware or software. When the terminal device 101, 102, 103 is hardware, it can be various electronic devices including but not limited to a smart phone, a tablet computer, a laptop computer, a desktop computer, and the like. When the terminal device 101, 102, 103 is software, it can be installed in the above-mentioned electronic devices. It can be implemented as multiple software or software modules (for example, software or software modules for providing distributed services) or as a single software or software module. No specific limitation is made herein.

[0105] The server 105 can be a server providing various services, for example, a background data processing server processing files or data uploaded by the terminal device 101, 102, 103. The background data processing server can process the obtained files or data to generate a processing result.

[0106] It should be noted that the distributed electric drive vehicle state parameter observation method provided by the embodiments of the present application can be executed by the server 105 or the terminal device 101, 102, 103, and correspondingly, the distributed electric drive vehicle state parameter observation apparatus can be arranged in the server 105 or the terminal device 101, 102, 103.

[0107] It should be understood that Figure 1 The number of terminal devices, networks, and servers in the above-mentioned apparatus architecture is only illustrative. According to the implementation needs, there can be any number of terminal devices, networks, and servers. In the case that the processed data does not need to be obtained from a remote place, the above-mentioned apparatus architecture can not include a network, but only a server or a terminal device.

[0108] Figure 2 A distributed electric drive vehicle state parameter observation method provided by an embodiment of the present application is shown, which includes the following steps:

[0109] S1, obtaining a first longitudinal speed, a lateral acceleration, a wheel longitudinal force, a wheel rotation angle, and a wheel lateral force of the vehicle at a current time, inputting the wheel longitudinal force, the wheel rotation angle, and the wheel lateral force at the current time into a nonlinear vehicle model to obtain a yaw angular speed.

[0110] In a specific embodiment, step S1 specifically includes:

[0111] A three-degree-of-freedom dynamic model is selected as the nonlinear vehicle model of the distributed electric drive vehicle:

[0112]

[0113] wherein m is the mass of the vehicle, v 0x is the first longitudinal velocity, v 0 y is the first lateral velocity, r is the yaw rate, δ is the wheel angle, d is the wheel base of the front and rear axles, a is the distance from the vehicle mass center to the front axle, b is the distance from the vehicle mass center to the rear axle, I z is the yaw moment of inertia, F x is the wheel longitudinal force acting on the wheel, F y is the wheel lateral force acting on the wheel, F xij and F yij in which ij = fl, fr, rl, rr, respectively represent the front left wheel, the front right wheel, the rear left wheel, and the rear right wheel.

[0114] In specific embodiments, the wheel longitudinal force F x is calculated according to the following formula:

[0115]

[0116] in which J w is the wheel moment of inertia, r w is the wheel effective radius, w ij and T ij respectively represent the angular velocity and the wheel torque of each wheel.

[0117] Specifically, referring to Figure 3 , the wheel longitudinal force, the wheel lateral force, and the wheel angle of the vehicle are obtained by directly acquiring the wheel longitudinal force, the wheel lateral force, and the wheel angle through a GPS system, a gyroscope, a tire force sensor, a front wheel angle sensor, or a vehicle CAN installed on the passenger car, and the wheel angle is preferably a front wheel angle. The wheel longitudinal force is calculated by the above formula, and the wheel lateral force can be directly measured. The wheel longitudinal force, the wheel angle, and the wheel lateral force at the current time are input into a nonlinear vehicle model of the distributed electric drive vehicle to obtain the yaw rate r.

[0118] S2, the wheel angle, the lateral acceleration, the yaw rate, and the first longitudinal velocity are input into a state parameter observation model to obtain the first mass side slip angle, and the state parameter observation model adopts an adaptive fuzzy neural network model.

[0119] Specifically, referring to Figure 4 , the adaptive fuzzy neural network model is an intelligent system combining a fuzzy inference system and a neural network. The system covers a five-layer structure network with multiple inputs, single output, and multiple rules.

[0120] In specific embodiments, the adaptive fuzzy neural network model includes an input node layer, a rule node layer, an average node layer, a conclusion node layer, and an output node layer. The input node layer is used for fuzzifying the input variables, each node is an adaptive node with a specific node function, and the node function is:

[0121]

[0122] Where x is the node input, and {a,b,c} is a set of variable parameters, called the premise parameters of the rule, which can reflect the different membership functions in the fuzzy set;

[0123] The node output function of the input node layer is represented as:

[0124]

[0125] Where x1, x2, ..., x n The node output is the fuzzy variable A. i B j and C k The membership function values ​​represent the node inputs x1, x2, ..., x3. n For A i B j and C k The degree of membership;

[0126] The nodes in the rule node layer are fixed nodes denoted by the cumulative multiplication symbol (∏). The output function of the nodes in the input node layer serves as the input signal for the rule node layer. The input of the rule node layer is the product of all input signals in the rule node layer.

[0127]

[0128] The nodes in the average node layer are fixed nodes labeled N. The output of each node is the ratio of the excitation intensity to the sum of the excitation intensities in the rule base. This ratio represents the normalization of the rule intensity.

[0129]

[0130] The nodes in the conclusion node layer are adaptive nodes with node functions, and the output of the nodes in the conclusion node layer is represented as follows:

[0131]

[0132] Where, p i q i and r i For the consequent parameter, f i It is a symbol representing the product of the consequent parameter and the system input;

[0133] The nodes in the output node layer are adaptive nodes with node functions, and the output representation of the nodes in the output node layer is as follows:

[0134]

[0135] The input of the adaptive fuzzy neural network model is wheel angle, lateral acceleration, yaw rate, first longitudinal velocity v° x The output of the adaptive fuzzy neural network model is first mass side slip angle β ANFIS .

[0136] Specifically, the selection criteria of the adaptive fuzzy neural network model input parameters are: selecting the minimum number of inputs and selecting signals measurable by vehicle sensors. After comprehensive consideration, the following parameters are selected as inputs: wheel angle, lateral acceleration, yaw rate and first longitudinal velocity, and the output is the first mass side slip angle β ANFIS . The first mass side slip angle is calculated from the constructed second sliding mode observer.

[0137] Finally, the data of the above input and output parameters are extracted from a large amount of data generated during vehicle operation, and are arranged to form state input and state output data sets to constitute training data. The adaptive fuzzy neural network model is trained using the training data to obtain a state parameter observation model.

[0138] In a specific embodiment, the training process of the adaptive fuzzy neural network model specifically includes:

[0139] The second sliding mode observer is constructed with the yaw rate as the observation vector:

[0140] The second sliding mode observer is described by the following formula:

[0141]

[0142] Wherein, x is the state vector, u is the input variable, z is the observation vector, and K is the robust control item matrix;

[0143] The nonlinear form expression of the second sliding mode observer is:

[0144]

[0145] Wherein, the input variable is:

[0146] u = [δ F x F y ];

[0147] Wherein, δ is the wheel angle, F x is the wheel longitudinal force acting on the wheel, and F y is the wheel lateral force acting on the wheel; the state vector and the observation vector are respectively:

[0148] x = [v x v y r];

[0149] y = [r];

[0150] wherein v x is the third longitudinal velocity, v y is the third lateral velocity, and r is the yaw rate;

[0151] The second sliding mode observer is constructed based on the sliding mode variable structure theory as follows:

[0152]

[0153] I s = sgn(s);

[0154]

[0155] H is a damping coefficient matrix, I s is a switching function;

[0156] The damping coefficient matrix H of the second sliding mode observer is:

[0157] H = [h1 h2 h3];

[0158] wherein h1, h2, and h3 are damping coefficients obtained in the simulation process;

[0159] The robust control term matrix K of the second sliding mode observer is:

[0160] K = [k1 k2 k3];

[0161] wherein k1, k2, and k3 are robust control terms obtained in the simulation process;

[0162] The saturation function is selected as the switching function of the second sliding mode observer, which is equivalent to setting a boundary layer near the sliding surface, and then:

[0163] I s = sat(s / λ);

[0164] wherein λ is the thickness of the boundary layer;

[0165] The third longitudinal velocity v x and the third lateral velocity v y of the vehicle are estimated by the second sliding mode observer, and then the first mass side slip angle is estimated according to the following formula:

[0166]

[0167] The wheel rotation angle, lateral acceleration, yaw rate and first longitudinal velocity in the running process of the automobile are collected, the wheel rotation angle, lateral acceleration, yaw rate and first longitudinal velocity and the first mass center side slip angle constitute training data, the adaptive fuzzy neural network model is trained by using the training data, and a state parameter observation model is obtained. The first longitudinal velocity is actually measured data, and the third longitudinal velocity is estimated data obtained by the second sliding mode observer.

[0168] Specifically, adjusting the gain matrix K can eliminate the uncertain terms of the system, and the switching function I s The high-speed switching in the vicinity of the sliding surface reaches the sliding condition. When designing the second sliding mode observer, in order to eliminate chattering, a saturation function is selected as the switching function of the second sliding mode observer, which is equivalent to setting a boundary layer in the vicinity of the sliding surface. The thickness λ of the boundary layer can be reasonably selected to obtain satisfactory performance of the second sliding mode observer. The yaw rate is taken as an observation vector to construct a second sliding mode observer. The wheel rotation angle, wheel longitudinal force and wheel lateral force are input into the second sliding mode observer to estimate the first mass center side slip angle. The first mass center side slip angle is combined with the wheel rotation angle, lateral acceleration, yaw rate and first longitudinal velocity in the running process of the automobile to constitute training data of an adaptive fuzzy neural network model, the adaptive fuzzy neural network model is trained, and a state parameter observation model is obtained.

[0169] S3, the yaw rate and the first mass center side slip angle are taken as observation vectors to construct a first sliding mode observer.

[0170] In a specific embodiment, step S3 specifically includes:

[0171] The nonlinear form expression of the first sliding mode observer is:

[0172]

[0173] The state vector is:

[0174] x=[v' x v' y r];

[0175] The observation vector is

[0176] y=[r β ANFIS ];

[0177] Wherein, β ANFIS is the first mass center side slip angle estimated by the adaptive fuzzy neural network;

[0178] The input vector is

[0179] u=[δ F x F y ];

[0180] Therefore, the first sliding mode observer is constructed as follows:

[0181]

[0182] I s = sat(s / λ);

[0183]

[0184] S4, inputting the wheel rotation angle, the wheel longitudinal force, and the wheel lateral force into the first sliding mode observer to obtain a second longitudinal velocity and a second lateral velocity, and obtaining a second mass center side slip angle according to the second longitudinal velocity and the second lateral velocity.

[0185] In specific embodiments, the step S4 specifically comprises:

[0186] The second longitudinal velocity v' and the second lateral velocity v' of the automobile are estimated by the first sliding mode observer. x y The second mass center side slip angle is estimated according to the following formula:

[0187]

[0188] Figure 5 FIG. 6 is a result comparison diagram of the state parameter observation method of the distributed electric drive automobile and the original method according to an embodiment of the present application, from which Figure 5 It can be seen that the estimation result of the mass center side slip angle reflecting the state of the automobile obtained by the state parameter observation method of the distributed electric drive automobile according to the embodiment of the present application is better than that of the original method, and is very close to the true value.

[0189] Further referring to Figure 6 As an implementation of the method shown in the above figures, the present application provides an embodiment of a distributed electric drive automobile state parameter observation device, which corresponds to the method embodiment shown in Figure 2 The device can be specifically applied to various electronic devices.

[0190] The present application provides a distributed electric drive automobile state parameter observation device, which comprises:

[0191] The yaw rate calculation module 1 is configured to obtain the first longitudinal velocity, the lateral acceleration, the wheel longitudinal force, the wheel rotation angle, and the wheel lateral force of the automobile at the current time, input the wheel longitudinal force, the wheel rotation angle, and the wheel lateral force at the current time into the nonlinear vehicle model to obtain the yaw rate.

[0192] ​The first centroid side slip angle calculation module 2 is configured to input the wheel angle, the lateral acceleration, the yaw rate, and the first longitudinal velocity into a state parameter observation model to obtain the first centroid side slip angle, and the state parameter observation model adopts an adaptive fuzzy neural network model.

[0193] The first sliding mode observer configuration module 3 is configured to configure a first sliding mode observer with the yaw rate and the first centroid side slip angle as an observation vector.

[0194] The second centroid side slip angle calculation module 4 is configured to input the wheel angle, the wheel longitudinal force, and the wheel lateral force into the first sliding mode observer to obtain the second longitudinal velocity and the second lateral velocity, and obtain the second centroid side slip angle according to the second longitudinal velocity and the second lateral velocity.

[0195] Reference will now be made to the following description Figure 7 which shows a structural schematic diagram of a computer device 700 of an electronic device (for example Figure 1 a server or a terminal device) suitable for being used to implement the embodiments of the present application. Figure 7 The electronic device shown is merely an example, and should not bring any limitation to the functions and use range of the embodiments of the present application.

[0196] As shown in Figure 7 , the computer device 700 includes a central processing unit (CPU) 701 and a graphics processor (GPU) 702, which can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 703 or programs loaded into a random access memory (RAM) 704 from a storage portion 709. In the RAM 704, various programs and data required for the operation of the device 700 are also stored. The CPU 701, the GPU 702, the ROM 703, and the RAM 704 are connected to each other through a bus 705. An input / output (I / O) interface 706 is also connected to the bus 705.

[0197] The following components are connected to the I / O interface 706: an input portion 707 including a keyboard, a mouse, and the like; an output portion 708 including a display such as a cathode ray tube (CRT) display, a liquid crystal display (LCD), and the like, and a speaker, and the like; a storage portion 709 including a hard disk, and the like; and a communication portion 710 including a network interface card such as a LAN card, a modem, and the like. The communication portion 710 performs communication processing via a network such as the Internet. A drive 711 can also be connected to the I / O interface 706 as needed. A removable recording medium 712 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, and the like is attached to the drive 711 as needed, so that a computer program read therefrom is installed in the storage portion 709 as needed.

[0198] In particular, the processes described above with reference to the flowcharts can be implemented as a computer software program in accordance with embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer readable medium, the computer program comprising program code for executing the methods illustrated by the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via the communication section 710, and / or installed from the removable medium 712. When the computer program is executed by the central processing unit (CPU) 701 and the graphics processor (GPU) 702, the above-described functions defined in the methods of the present application are executed.

[0199] It should be noted that the computer readable medium described in the present application can be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor device, device or means, or any combination of the above. More specific examples of computer readable medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, the computer readable medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution device, device or means. In the present application, the computer readable signal medium can include a data signal carried in a baseband or as a part of a carrier wave, which carries computer readable program code. Such a propagated data signal can take many forms, including but not limited to an electromagnetic signal, an optical signal or any suitable combination of the above. The computer readable signal medium can also be any computer readable medium other than the computer readable medium that can send, propagate or transmit the program for use by or in conjunction with an instruction execution device, device or means. The program code contained on the computer readable medium can be transmitted by any suitable medium, including but not limited to wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0200] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0201] The computer program instructions can also be loaded onto a computer or other programmable information processing apparatus to cause a series of operations to be performed on the computer or other programmable information processing apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable information processing apparatus implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0202] The modules described in the embodiments of the present application can be implemented by software, or by hardware. The modules described can also be arranged in a processor.

[0203] As another aspect, the application also provides a computer readable medium, which can be included in the electronic device described in the above embodiments, or can exist independently without being assembled into the electronic device. The computer readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: acquire a first longitudinal speed, a lateral acceleration, a wheel longitudinal force, a wheel steering angle and a wheel lateral force of a vehicle at a current time, input the wheel longitudinal force, the wheel steering angle and the wheel lateral force at the current time into a nonlinear vehicle model to obtain a yaw rate, input the wheel steering angle, the lateral acceleration, the yaw rate and the first longitudinal speed into a state parameter observation model to obtain a first mass center side slip angle, the state parameter observation model adopting an adaptive fuzzy neural network model, construct a first sliding mode observer with the yaw rate and the first mass center side slip angle as observation vectors, input the wheel steering angle, the wheel longitudinal force and the wheel lateral force into the first sliding mode observer to obtain a second longitudinal speed and a second lateral speed, and obtain a second mass center side slip angle according to the second longitudinal speed and the second lateral speed.

[0204] The above description is merely preferred embodiments of the application and a description of the principles of the technology used. It should be understood by those skilled in the art that the scope of the application involved in the present application is not limited to the technical solutions formed by the specific combinations of the above technical features, and should also cover other technical solutions formed by any combinations of the above technical features or their equivalent features without departing from the above inventive concept. For example, the above features can be replaced with the technical features disclosed in the present application (but not limited to) having similar functions to form technical solutions.

Claims

1. A method for observing state parameters of a distributed electric drive vehicle, characterized in that, Includes the following steps: S1, obtain the vehicle's current longitudinal velocity, lateral acceleration, wheel longitudinal force, wheel rotation angle, and wheel lateral force, and input the current wheel longitudinal force, wheel rotation angle, and wheel lateral force into the nonlinear vehicle model to obtain the yaw rate; S2, the wheel rotation angle, lateral acceleration, yaw rate, and first longitudinal velocity are input into the state parameter observation model to obtain the first centroid sideslip angle. The state parameter observation model adopts an adaptive fuzzy neural network model, which includes an input node layer, a rule node layer, an average node layer, a conclusion node layer, and an output node layer. The input node layer is used to fuzzify the input variables, and each node is an adaptive node with a specific node function. The node function is: ； Where x is the node input, and {a, b, c} is a set of variable parameters, called the premise parameters of the rule, which can reflect the different membership functions in the fuzzy set; The node output function of the input node layer is expressed as follows: ； Where x1, x2, ..., x n The node output is the fuzzy variable A. i B j and C k The membership function values ​​represent the node inputs x1, x2, ..., x3. n For A i B j and C k The degree of membership; The nodes of the rule node layer are fixed nodes denoted by the cumulative multiplication symbol ∏. The output function of the nodes in the input node layer serves as the input signal of the rule node layer. The input of the rule node layer is the product of all input signals in the rule node layer. ； The nodes in the average node layer are fixed nodes labeled n. The output of each node is the ratio of the excitation intensity to the sum of the excitation intensities in the rule base. This ratio represents the normalization of the rule intensity. ； The nodes in the conclusion node layer are adaptive nodes with node functions, and the output of the nodes in the conclusion node layer is represented as follows: ； Where, p i q i and r i For the consequent parameter, f i It is a symbol representing the product of the consequent parameter and the system input; The nodes in the output node layer are adaptive nodes with node functions, and the output of the nodes in the output node layer is represented as follows: ； The input to the adaptive fuzzy neural network model is the wheel rotation angle, lateral acceleration, yaw rate, and first longitudinal velocity input state parameter observation model, and the output of the adaptive fuzzy neural network model is the first centroid sideslip angle β. ANFIS ; S3, construct a first sliding mode observer using the yaw rate and the first centroid sideslip angle as observation vectors; S4, input the wheel rotation angle, wheel longitudinal force, and wheel lateral force into the first sliding mode observer to obtain the second longitudinal velocity and the second lateral velocity, and obtain the second centroid side slip angle based on the second longitudinal velocity and the second lateral velocity.

2. The method for observing state parameters of a distributed electric drive vehicle according to claim 1, characterized in that, The training process of the adaptive fuzzy neural network model specifically includes: Construct a second sliding mode observer using the yaw rate as the observation vector: The second sliding mode observer is described by the following formula: ； Where x is the state vector, u is the input variable, z is the observation vector, and K is the robust control term matrix; The nonlinear expression of the second sliding mode observer is: ； The input variables are: ； Where δ is the wheel rotation angle, F x F is the longitudinal force acting on the wheel. y This refers to the lateral force acting on the wheel. The state vector and observation vector are respectively: ； ； Where, ν x For the third longitudinal velocity, ν y The third lateral velocity is r, and the yaw rate is r. The second sliding mode observer is constructed based on the sliding mode variable structure theory as follows: ； ； ； H is the damping coefficient matrix, I s This is the switching function; The damping coefficient matrix H of the second sliding mode observer is: ； Where h1, h2, and h3 are the damping coefficients obtained during the simulation process; The robust control term matrix K of the second sliding mode observer is: ； Wherein, k1, k2, and k3 are the robust control terms obtained during the simulation process; Choosing the saturation function as the switching function for the second sliding mode observer is equivalent to setting a boundary layer near the sliding surface, then: ； Where λ is the thickness of the boundary layer; The third longitudinal velocity v is estimated using the second sliding mode observer. x and the third lateral velocity v y Then, the first centroid sideslip angle is estimated using the following formula: ； The wheel rotation angle, lateral acceleration, yaw rate, and first longitudinal velocity are collected during the vehicle's operation. The wheel rotation angle, lateral acceleration, yaw rate, and first longitudinal velocity, along with the first centroid sideslip angle, are used to form training data. The adaptive fuzzy neural network model is trained using the training data to obtain a state parameter observation model.

3. The method for observing state parameters of a distributed electric drive vehicle according to claim 1, characterized in that, Step S1 specifically includes: A three-degree-of-freedom dynamics model is chosen as the nonlinear vehicle model for the distributed electric drive vehicle: ； Where m is the vehicle mass, ν 0 x Let ν be the first longitudinal velocity. 0 y Let be the first lateral velocity, r be the yaw rate, δ be the wheel angle, d be the track width between the front and rear axles, a be the distance from the vehicle's center of gravity to the front axle, b be the distance from the vehicle's center of gravity to the rear axle, and I be the distance from the vehicle's center of gravity to the rear axle. z F is the moment of inertia of yaw rotation. x F is the longitudinal force acting on the wheel. y F is the lateral force acting on the wheel. xij and F yij In the equation, ij = fl, fr, rl, rr represent the front left wheel, front right wheel, rear left wheel, and rear right wheel, respectively.

4. The distributed electric drive vehicle state parameter observation method according to claim 3, characterized in that, The longitudinal force F of the wheel x The calculation formula is as follows: ； Among them, J w It is the moment of inertia of the wheel, r w It is the effective radius of the wheel, w ij and T ij These represent the angular velocity and wheel torque of each wheel, respectively.

5. The method for observing state parameters of a distributed electric drive vehicle according to claim 2, characterized in that, Step S3 specifically includes: The nonlinear expression of the first sliding mode observer is: ； The state vector is: ； The observation vector is: ； Where, β ANFIS The first centroid sideslip angle predicted by the adaptive fuzzy neural network; The input vector is: ； Therefore, the first sliding mode observer is constructed as follows: ； ； 。 6. The method for observing state parameters of a distributed electric drive vehicle according to claim 1, characterized in that, Step S4 specifically includes: The second longitudinal velocity v' of the car is estimated using the first sliding mode observer. x Second lateral velocity v' y Then, the second centroid sideslip angle is estimated using the following formula: 。 7. A distributed electric vehicle state parameter observation device, employing the distributed electric vehicle state parameter observation method according to any one of claims 1-6, characterized in that, include: The yaw rate calculation module is configured to acquire the vehicle's current longitudinal velocity, lateral acceleration, wheel longitudinal force, wheel rotation angle, and wheel lateral force, and input the current wheel longitudinal force, wheel rotation angle, and wheel lateral force into the nonlinear vehicle model to obtain the yaw rate. The first center of gravity sideslip angle calculation module is configured to input the wheel rotation angle, lateral acceleration, yaw rate and first longitudinal velocity into the state parameter observation model to obtain the first center of gravity sideslip angle. The state parameter observation model adopts an adaptive fuzzy neural network model. The first sliding mode observer construction module is configured to construct a first sliding mode observer using the yaw rate and the first centroid sideslip angle as observation vectors. The second centroid sideslip angle calculation module is configured to input the wheel rotation angle, wheel longitudinal force, and wheel lateral force into the first sliding mode observer to obtain the second longitudinal velocity and the second lateral velocity, and to obtain the second centroid sideslip angle based on the second longitudinal velocity and the second lateral velocity.

8. An electronic device, comprising: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-6.

Images