CN115571141A - Distributed electric drive automobile state parameter observation method and device and readable medium - Google Patents

Abstract

The invention discloses a distributed electric drive automobile state parameter observation method, a device and a readable medium, wherein a yaw velocity is obtained by acquiring a first longitudinal velocity, a transverse acceleration, a wheel longitudinal force, a wheel corner and a wheel lateral force of an automobile at the current moment and inputting the wheel longitudinal force, the wheel corner and the wheel lateral force at the current moment into a nonlinear vehicle model; inputting the wheel rotation angle, the transverse acceleration, the yaw angular velocity and the first longitudinal velocity into a state parameter observation model to obtain a first mass center slip angle, wherein the state parameter observation model adopts a self-adaptive fuzzy neural network model; constructing a first sliding-mode observer by taking the yaw angular velocity and the first centroid sideslip angle as observation vectors; and the wheel corner, the wheel longitudinal force and the wheel lateral force are input into the first sliding-mode observer to obtain a second longitudinal speed and a second lateral speed, and a second centroid slip angle is obtained according to the second longitudinal speed and the second lateral speed, so that the estimation precision of the automobile state parameters is effectively improved.

Description

Method, device and readable medium for observing state parameters of distributed electric drive vehicles

technical field

The invention relates to the technical field of distributed electric drive vehicles, in particular to a method, device and readable medium for observing state parameters of distributed electric drive vehicles.

Background technique

With the advancement of information technology, the development of smart cars has also made great progress. In the field of passenger cars, the trend of electrification and intelligence is becoming more and more obvious. Compared with the traditional centralized drive bus, the biggest advantage of the distributed electric drive bus is that it can flexibly distribute the torque of the four wheels, expand the application range of vehicle dynamics control, and improve control accuracy and response speed. Safety is one of the core issues in the process of driving a passenger car. The working conditions of passenger cars are complex and changeable. Therefore, vehicle dynamics control is required for passenger cars. Vehicle dynamics control is the key technology of vehicle active safety control, and the primary problem is to accurately obtain important parameters such as the current state of the bus.

Some state parameters of traditional vehicles can be directly measured by sensors, but some sensors are very expensive and have relatively high environmental requirements, which seriously affect the accurate acquisition of vehicle state parameters, which will inevitably affect the control effect of the control system . Moreover, there are still some key parameters that cannot be directly measured, and can only be obtained through some predictive methods. For example, the side slip angle of the vehicle center of mass. The vehicle state parameter estimation method aims at minimizing the residual error between the measured value and the estimated value of the easy-to-measure state, and realizes the optimal estimation of the state to be estimated. Some commonly used estimation algorithms, including Kalman filter algorithm and sliding mode observer, have their own defects. For example, the noise of Kalman filter is greatly affected by external factors. The error of the sliding mode observer is prone to chattering, and these shortcomings have a great impact on the accuracy of the observer.

Through the analysis of the existing research results, it can be seen that how to ensure the stability of the estimation method and how to further improve the estimation accuracy are the key issues that need to be solved urgently. Therefore, it is necessary to develop an estimation method that can accurately estimate the state parameters of the passenger car during the driving process.

Contents of the invention

In view of the low observation accuracy of the previous vehicle state observer, it is easy to be interfered 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 section above.

In a first aspect, the present invention provides a method for observing state parameters of a distributed electric drive vehicle, comprising the following steps:

S1. Obtain the first longitudinal velocity, lateral acceleration, wheel longitudinal force, wheel angle and wheel lateral force of the vehicle at the current moment, input the current wheel longitudinal force, wheel angle and wheel lateral force into the nonlinear vehicle model, and obtain the transverse pendulum speed;

S2. Input the wheel angle, lateral acceleration, yaw rate, and first longitudinal velocity into the state parameter observation model to obtain the first center-of-mass sideslip angle. The state parameter observation model adopts an adaptive fuzzy neural network model;

S3, using the yaw rate and the first center-of-mass sideslip angle as observation vectors to construct a first sliding mode observer;

S4, input the wheel angle, wheel longitudinal force, and wheel lateral force into the first sliding model observer to obtain the second longitudinal velocity and the second lateral velocity, and obtain the second centroid side according to the second longitudinal velocity and the second lateral velocity declination.

As preferably, the adaptive fuzzy neural network model includes an input node layer, a regular node layer, an average node layer, a conclusion node layer and an output node layer, and the input node layer is used to fuzzify input variables, and each node is a node with a specific node function Adaptive node, the node function is:

Among them, x is the node input, and {a, b, c} is a variable parameter set, which is called the premise part parameter of the rule, which can reflect different membership functions in the fuzzy set;

The node output function of the input node layer is expressed as:

Among them, x ₁ , x ₂ ,…, x _n are node outputs, which are the membership function values of fuzzy variables A _i , B _j and C _k , which represent the node input x ₁ , x ₂ ,…, x _n for A _i , the degree of membership of B _j and C _k ;

The node of the regular node layer is a fixed node represented by the multiplication symbol (∏), which is the node output function of the input node layer as the input signal of the regular node layer, and the input of the regular node layer is the sum of all input signals in the regular node layer product:

The node of the average node layer is a fixed node marked with N, and the output of the node is the ratio of the sum of the excitation strength and the excitation strength in the rule base, which means that the rule strength is normalized:

The nodes of the conclusion node layer are adaptive nodes with node functions, and the node output of the conclusion node layer is expressed as:

Among them, p _i , q _i and r _i are the consequent parameters, and f _i is the symbol representing the product of the consequent parameter and the system input;

The nodes of the output node layer are adaptive nodes with node functions, and the node output of the output node layer is expressed as:

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

As preferably, the training process of adaptive fuzzy neural network model specifically includes:

Construct the second sliding mode observer with the yaw rate as the observation vector:

The second sliding mode observer is described by the following equation:

Among them, 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 form expression of the second sliding mode observer is:

Among them, the input variables are:

u = [δ F _x F _y ];

Among them, δ is the wheel rotation angle, F _x is the wheel longitudinal force acting on the wheel, F _y is the wheel lateral force acting on the wheel; the state vector and observation vector are respectively:

x=[v _x v _y r];

y = [r];

Wherein, ν _x is the third longitudinal velocity, ν _y is the third lateral velocity, and r is the yaw rate;

Based on the sliding mode variable structure theory, the second sliding mode observer is constructed as follows:

I _s =sgn(s);

H is the damping coefficient matrix, I _s is the switching function;

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

H=[h ₁ h ₂ h ₃ ];

Among them, h ₁ , h ₂ , h ₃ are the damping coefficients obtained in the simulation process;

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

K=[k ₁ k ₂ k ₃ ];

Among them, k ₁ , k ₂ , and k ₃ are the robust control items obtained in the simulation process;

Selecting the saturation function as the switching function of the second sliding mode observer is equivalent to setting a boundary layer near the sliding mode surface, then:

I _s =sat(s/λ);

where λ is the thickness of the boundary layer;

The third longitudinal velocity v _x and the third lateral velocity v _y are estimated by the second sliding mode observer, and then the first center-of-mass sideslip angle is estimated according to the following formula:

Collect the wheel angle, lateral acceleration, yaw rate and first longitudinal velocity during the operation of the car, and use the wheel angle, lateral acceleration, yaw rate, first longitudinal velocity and the first center of mass sideslip angle to form the training data, and use the training data The adaptive fuzzy neural network model is trained to obtain the state parameter observation model.

Preferably, step S1 specifically includes:

The three-degree-of-freedom dynamics model is chosen as the nonlinear vehicle model for the distributed electric drive vehicle:

Among them, m is the mass of the vehicle, ν ⁰ _x is the first longitudinal velocity, ν 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, and a is the center of mass of the vehicle is the distance from the front axle to the front axle, b is the distance from the center of mass of the vehicle 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 ij=fl, fr, rl, rr in F _yij represent the front left wheel, the front right wheel, the rear left wheel, and the rear right wheel respectively.

Preferably, the calculation formula of the wheel longitudinal force Fx _is as follows:

Among them, J _w is the moment of inertia of the wheel, r _w is the effective radius of the wheel, w _ij and T _ij represent the angular velocity and wheel torque of each wheel, respectively.

As preferably, step S3 specifically includes:

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

Among them, the state vector is:

x=[v' _x v' _y r];

The observation vector is

y=[r β _ANFIS ];

Among them, β _ANFIS is the side slip angle of the first center of mass estimated by the adaptive fuzzy neural network;

The input vector is

u = [δ F _x F _y ];

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

I _s =sat(s/λ);

As preferably, step S4 specifically includes:

The second longitudinal velocity v' _x and the second lateral velocity v' _y of the vehicle are estimated by the first sliding mode observer, and then the second center-of-mass sideslip angle is estimated according to the following formula:

In a second aspect, the present invention provides a distributed electric drive vehicle state parameter observation device, including:

The yaw rate calculation module is configured to obtain the first longitudinal velocity, lateral acceleration, wheel longitudinal force, wheel angle and wheel lateral force of the vehicle at the current moment, and input the wheel longitudinal force, wheel angle and wheel lateral force at the current moment Non-linear vehicle model to obtain the yaw rate;

The first center-of-mass sideslip angle calculation module is configured to input the wheel angle, lateral acceleration, yaw rate, and first longitudinal velocity into the state parameter observation model to obtain the first center-of-mass sideslip angle. The state parameter observation model adopts an adaptive fuzzy neural network network model;

The first sliding mode observer construction module is configured to use the yaw rate and the first center of mass sideslip angle as observation vectors to construct the first sliding mode observer;

The second center-of-mass sideslip angle calculation module is configured to input the wheel angle, wheel longitudinal force, and wheel lateral force into the first sliding model observer to obtain the second longitudinal velocity and the second lateral velocity, according to the second longitudinal velocity and The second lateral velocity results in a second center-of-mass slip angle.

In a third aspect, the present invention provides an electronic device, including one or more processors; a storage device for storing one or more programs, when one or more programs are executed by one or more processors, so that a or multiple processors implement the method described in any implementation manner of the first aspect.

In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method described in any implementation manner in the first aspect is implemented.

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

(1) The state parameter observation method of the distributed electric drive vehicle proposed by the present invention pre-estimates the vehicle state parameters by designing the second sliding mode observer, and on this basis, introduces the self-adaptive fuzzy neural network model, through the second The first center-of-mass side slip angle estimated by the sliding mode observer is combined with the wheel angle, lateral acceleration, yaw rate and first longitudinal velocity to form training data, and the training data is used to train the adaptive fuzzy neural network model to obtain state parameter observations The model can effectively solve the problem of poor estimation accuracy of the sliding mode observer due to the chattering caused by the sliding mode surface.

(2) The state parameter observation method of the distributed electric drive vehicle proposed by the present invention finally obtains the second centroid lateral angle which is relatively close to the real value, with high estimation accuracy and small error.

(3) The method for observing state parameters of distributed electric-driven automobiles proposed by the present invention overcomes the shortcomings of existing observers on automobiles, improves the estimation accuracy of automobile state parameters, and is suitable for state parameter estimation of passenger cars.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings that need to be used in the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For Those of ordinary skill in the art can also obtain other drawings based on these drawings without making creative efforts.

Fig. 1 is an exemplary device architecture diagram to which an embodiment of the present application can be applied;

FIG. 2 is a schematic flow diagram of a method for observing state parameters of a distributed electric drive vehicle according to an embodiment of the present application;

Fig. 3 is the block flow diagram of the state parameter observation method of the distributed electric drive vehicle of the embodiment of the present application;

4 is a schematic diagram of data processing between the adaptive fuzzy neural network model and the first sliding mode observer of the distributed electric drive vehicle state parameter observation method of the embodiment of the present application;

Fig. 5 is the comparison chart of the result of the state parameter observation method of the distributed electric drive vehicle of the embodiment of the present application and the original method and the true value;

6 is a schematic diagram of a distributed electric drive vehicle state parameter observation device according to an embodiment of the present application;

Fig. 7 is a schematic structural diagram of a computer device suitable for realizing the electronic equipment of the embodiment of the present application.

detailed description

In order to make the purpose, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only some of the embodiments of the present invention, rather than all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

Fig. 1 shows an exemplary device architecture 100 to which the method for observing state parameters of a distributed electric drive vehicle or the device for observing state parameters of a distributed electric drive vehicle according to an embodiment of the present application can be applied.

As shown in FIG. 1 , the device architecture 100 may include terminal devices 101 , 102 , 103 , a network 104 and a server 105 . The network 104 is used as a medium for providing communication links between the terminal devices 101 , 102 , 103 and the server 105 . Network 104 may include various connection types, such as wires, wireless communication links, or fiber optic cables, among others.

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

The terminal devices 101, 102, and 103 may be hardware or software. When the terminal devices 101, 102, 103 are hardware, they may be various electronic devices, including but not limited to smart phones, tablet computers, laptop computers, desktop computers and the like. When the terminal devices 101, 102, 103 are software, they can be installed in the electronic devices listed above. It can be implemented as multiple software or software modules (such as software or software modules for providing distributed services), or as a single software or software module. No specific limitation is made here.

The server 105 may be a server that provides various services, such as a background data processing server that processes files or data uploaded by the terminal devices 101 , 102 , and 103 . The background data processing server can process the obtained files or data and generate processing results.

It should be noted that the distributed electric drive vehicle state parameter observation method provided in the embodiment of the present application can be executed by the server 105, and can also be executed by the terminal devices 101, 102, 103. Correspondingly, the distributed electric drive vehicle state parameter observation method The device may be set in the server 105 or in the terminal devices 101 , 102 , 103 .

It should be understood that the numbers of terminal devices, networks and servers in Fig. 1 are only illustrative. According to the implementation needs, there can be any number of terminal devices, networks and servers. In the case that the data to be processed does not need to be acquired from a remote location, the above device architecture may not include a network, but only need a server or a terminal device.

Fig. 2 shows a method for observing state parameters of a distributed electric drive vehicle provided by an embodiment of the present application, including the following steps:

S1. Obtain the first longitudinal velocity, lateral acceleration, wheel longitudinal force, wheel angle and wheel lateral force of the vehicle at the current moment, input the current wheel longitudinal force, wheel angle and wheel lateral force into the nonlinear vehicle model, and obtain the transverse pendulum speed.

In a specific embodiment, step S1 specifically includes:

The three-degree-of-freedom dynamics model is chosen as the nonlinear vehicle model for the distributed electric drive vehicle:

Among them, m is the mass of the vehicle, ν ⁰ _x is the first longitudinal velocity, ν 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, and a is the center of mass of the vehicle is the distance from the front axle to the front axle, b is the distance from the center of mass of the vehicle 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 ij=fl, fr, rl, rr in F _yij represent the front left wheel, the front right wheel, the rear left wheel, and the rear right wheel respectively.

In a specific embodiment, the calculation formula of the wheel longitudinal force Fx _is as follows:

Among them, J _w is the moment of inertia of the wheel, r _w is the effective radius of the wheel, w _ij and T _ij represent the angular velocity and wheel torque of each wheel, respectively.

Specifically, with reference to Fig. 3, the wheel longitudinal force, the wheel lateral force and the wheel angle of the automobile are acquired directly through sensors such as GPS system, gyroscope, tire force sensor, front wheel angle or vehicle-mounted CAN installed on the passenger car, as a preferred , the wheel angle is the front wheel angle. The longitudinal force of the wheel is calculated by the above formula, and the lateral force of the wheel can be directly measured. Input the longitudinal force of the wheel, the wheel angle and the lateral force of the wheel at the current moment into the nonlinear vehicle model of the distributed electric drive vehicle to obtain the yaw rate r .

S2. Input the wheel angle, lateral acceleration, yaw rate, and first longitudinal velocity into the state parameter observation model to obtain the first center of mass sideslip angle. The state parameter observation model adopts an adaptive fuzzy neural network model.

Specifically, referring to FIG. 4 , the adaptive fuzzy neural network model is a type of intelligent system combined with a fuzzy reasoning system and a neural network. The system covers a multi-input, single-output and multi-rule five-layer network.

In a specific embodiment, 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, and the input node layer is used to fuzzify input variables, and each node has An adaptive node for a specific node function, the node function is:

Among them, x is the node input, and {a, b, c} is a variable parameter set, which is called the premise part parameter of the rule, which can reflect different membership functions in the fuzzy set;

The node output function of the input node layer is expressed as:

Among them, x ₁ , x ₂ ,…, x _n are node outputs, which are the membership function values of fuzzy variables A _i , B _j and C _k , which represent the node input x ₁ , x ₂ ,…, x _n for A _i , the degree of membership of B _j and C _k ;

The node of the regular node layer is a fixed node represented by the multiplication symbol (∏), which is the node output function of the input node layer as the input signal of the regular node layer, and the input of the regular node layer is the sum of all input signals in the regular node layer product:

The node of the average node layer is a fixed node marked with N, and the output of the node is the ratio of the sum of the excitation strength and the excitation strength in the rule base, which means that the rule strength is normalized:

The nodes of the conclusion node layer are adaptive nodes with node functions, and the node output of the conclusion node layer is expressed as:

Among them, p _i , q _i and r _i are the consequent parameters, and f _i is the symbol representing the product of the consequent parameter and the system input;

The nodes of the output node layer are adaptive nodes with node functions, and the node output of the output node layer is expressed as:

The input of the adaptive fuzzy neural network model is the wheel angle, lateral acceleration, yaw rate, and the first longitudinal velocity v° _x input state parameter observation model, and the output of the adaptive fuzzy neural network model is the first centroid side slip angle β _ANFIS .

Specifically, the criteria considered for selecting input parameters of the adaptive fuzzy neural network model are: select the minimum number of inputs, and select signals that can be measured by the vehicle sensor. After comprehensive consideration, the following parameters are selected as input: wheel rotation angle, lateral acceleration, yaw rate and first longitudinal velocity, and the output is the first center-of-mass sideslip angle β _ANFIS . Among them, the first center-of-mass sideslip angle is calculated from the constructed second sliding mode observer.

Finally, the data of the above-mentioned input and output parameters are extracted from a large amount of data generated during vehicle operation, and then sorted out to form a state input and state output data set to form training data. The adaptive fuzzy neural network model is trained by using the training data to obtain the state parameter observation model.

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

Construct the second sliding mode observer with the yaw rate as the observation vector:

The second sliding mode observer is described by the following equation:

Among them, 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 form expression of the second sliding mode observer is:

Among them, the input variables are:

u = [δ F _x F _y ];

Among them, δ is the wheel rotation angle, F _x is the wheel longitudinal force acting on the wheel, F _y is the wheel lateral force acting on the wheel; the state vector and observation vector are respectively:

x=[v _x v _y r];

y = [r];

Wherein, ν _x is the third longitudinal velocity, ν _y is the third lateral velocity, and r is the yaw rate;

Based on the sliding mode variable structure theory, the second sliding mode observer is constructed as follows:

I _s =sgn(s);

H is the damping coefficient matrix, I _s is the switching function;

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

H=[h ₁ h ₂ h ₃ ];

Among them, h ₁ , h ₂ , h ₃ are the damping coefficients obtained in the simulation process;

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

K=[k ₁ k ₂ k ₃ ];

Among them, k ₁ , k ₂ , and k ₃ are the robust control items obtained in the simulation process;

Selecting the saturation function as the switching function of the second sliding mode observer is equivalent to setting a boundary layer near the sliding mode surface, then:

I _s =sat(s/λ);

where λ is the thickness of the boundary layer;

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 center-of-mass sideslip angle is estimated according to the following formula:

Collect the wheel angle, lateral acceleration, yaw rate and first longitudinal velocity during the operation of the car, and use the wheel angle, lateral acceleration, yaw rate, first longitudinal velocity and the first side slip angle of the center of mass to form the training data. The data is used to train the adaptive fuzzy neural network model to obtain the state parameter observation model. The first longitudinal velocity is data obtained through actual measurement, and the third longitudinal velocity is data estimated through the second sliding mode observer.

Specifically, adjusting the gain matrix K can eliminate the uncertain terms of the system, and achieve the sliding condition by switching the switching function I _s at high speed near the sliding mode surface. In order to eliminate chattering when designing the second sliding mode observer, the saturation function should be selected as the switching function of the second sliding mode observer, which is equivalent to setting a boundary layer near the sliding mode surface, and the thickness of the boundary layer λ can be reasonably selected , to obtain satisfactory performance of the second sliding mode observer. The second sliding mode observer is constructed with the yaw rate as the observation vector, and the wheel angle, wheel longitudinal force, and wheel lateral force are input into the second sliding mode observer to estimate the side slip angle of the first center of mass, and the first center of mass sideslip Combined with the wheel angle, lateral acceleration, yaw angular velocity and first longitudinal velocity during the operation of the vehicle, the training data of the adaptive fuzzy neural network model is formed, and the adaptive fuzzy neural network model is trained to obtain the state parameter observation model.

S3, using the yaw rate and the first center-of-mass sideslip angle as observation vectors to construct a first sliding mode observer.

In a specific embodiment, step S3 specifically includes:

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

Among them, the state vector is:

x=[v' _x v' _y r];

The observation vector is

y=[r β _ANFIS ];

Among them, β _ANFIS is the side slip angle of the first center of mass estimated by the adaptive fuzzy neural network;

The input vector is

u = [δ F _x F _y ];

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

I _s =sat(s/λ);

S4, input the wheel angle, wheel longitudinal force, and wheel lateral force into the first sliding model observer to obtain the second longitudinal velocity and the second lateral velocity, and obtain the second centroid side according to the second longitudinal velocity and the second lateral velocity declination.

In a specific embodiment, step S4 specifically includes:

The second longitudinal velocity v' _x and the second lateral velocity v' _y of the vehicle are estimated by the first sliding mode observer, and then the second center-of-mass sideslip angle is estimated according to the following formula:

Fig. 5 is a result comparison chart of the state parameter observation method of the distributed electric drive vehicle proposed by the embodiment of the present application and the original method, as can be seen from Fig. 5, the state parameter observation method of the distributed electric drive vehicle proposed by the embodiment of the present application The obtained estimation result of the side slip angle of the center of mass reflecting the state of the vehicle is better than the original method, and is very close to the real value.

Further referring to FIG. 6, as an implementation of the methods shown in the above-mentioned figures, the present application provides an embodiment of a distributed electric drive vehicle state parameter observation device, which is similar to the method embodiment shown in FIG. 2 Correspondingly, the device can be specifically applied to various electronic devices.

An embodiment of the present application provides a distributed electric drive vehicle state parameter observation device, including:

The yaw rate calculation module 1 is configured to obtain the first longitudinal velocity, lateral acceleration, wheel longitudinal force, wheel angle and wheel lateral force of the vehicle at the current moment, and calculate the current wheel longitudinal force, wheel angle and wheel lateral force Input the nonlinear vehicle model to get the yaw rate;

The first center-of-mass sideslip angle calculation module 2 is configured to input the wheel angle, lateral acceleration, yaw rate, and first longitudinal velocity into the state parameter observation model to obtain the first center-of-mass sideslip angle. The state parameter observation model adopts adaptive fuzzy neural network model;

The first sliding mode observer construction module 3 is configured to construct a first sliding mode observer using the yaw rate and the first center-of-mass sideslip angle as observation vectors;

The second center-of-mass sideslip angle calculation module 4 is configured to input the wheel angle, wheel longitudinal force, and wheel lateral force into the first sliding model observer to obtain the second longitudinal velocity and the second lateral velocity, according to the second longitudinal velocity and a second lateral velocity to obtain a second center-of-mass slip angle.

Referring now to FIG. 7 , it shows a schematic structural diagram of a computer device 700 suitable for implementing an electronic device (such as the server or terminal device shown in FIG. 1 ) in the embodiment of the present application. The electronic device shown in FIG. 7 is only an example, and should not limit the functions and scope of use of this embodiment of the present application.

As shown in FIG. 7, a computer device 700 includes a central processing unit (CPU) 701 and a graphics processing unit (GPU) 702, which can be randomly accessed according to a program stored in a read-only memory (ROM) 703 or loaded from a storage section 709. Various appropriate actions and processes are executed by programs in the memory (RAM) 704 . In the RAM 704, various programs and data necessary for the operation of the device 700 are also stored. The CPU 701 , GPU 702 , ROM 703 , and RAM 704 are connected to each other via a bus 705 . An input/output (I/O) interface 706 is also connected to the bus 705 .

The following components are connected to the I/O interface 706: an input section 707 including a keyboard, a mouse, etc.; an output section 708 including, for example, a liquid crystal display (LCD), etc., and a speaker; a storage section 709 including a hard disk, etc.; The communication part 710 of a network interface card such as a modem or the like. The communication section 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 medium 712 such as a magnetic disk, optical disk, magneto-optical disk, semiconductor memory, etc. is mounted on the drive 711 as necessary so that a computer program read therefrom is installed into the storage section 709 as necessary.

In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, where the computer program includes program codes for executing the methods shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via communication portion 710 and/or installed from removable media 712 . When the computer program is executed by a central processing unit (CPU) 701 and a graphics processing unit (GPU) 702, the above-mentioned functions defined in the method of the present application are performed.

It should be noted that the computer-readable medium described in this application may be a computer-readable signal medium or a computer-readable medium or any combination of the above two. A computer readable medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor device, device, or device, or a combination of any of the above. More specific examples of computer readable media may include, but are not limited to, electrical connections with one or more conductors, portable computer diskettes, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable Read Only Memory (EPROM or Flash), fiber optics, portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this application, a computer-readable medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution device, apparatus, or device. In this application, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, in which computer-readable program codes are carried. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution apparatus, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Computer program code for carrying out the operations of this application may be written in one or more programming languages, or combinations thereof, including object-oriented programming languages—such as Java, Smalltalk, C++, and conventional A procedural programming language—such as "C" or a similar programming language. The program code may 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 cases involving a remote computer, the remote computer can be connected to the user computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connected via the Internet).

The flowchart and block diagrams in the figures illustrate the architecture, functions and operations of possible implementations of apparatuses, methods and computer program products according to various embodiments of the present application. In this regard, each block in a flowchart or block diagram may represent a module, program segment, or part of code that contains one or more programmable logic functions for implementing specified logical functions. Execute instructions. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved. It should also be noted that each block in the block diagrams and/or flowcharts, and combinations of blocks in the block diagrams and/or flowcharts, can be implemented by dedicated hardware-based devices that perform the specified functions or operations, Or it can be implemented using a combination of special purpose hardware and computer instructions.

The modules involved in the embodiments described in the present application may be implemented by means of software or hardware. The described modules may also be provided in a processor.

As another aspect, the present application also provides a computer-readable medium. The computer-readable medium may be included in the electronic device described in the above-mentioned embodiments; or it may exist independently without being assembled into the electronic device. middle. The above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the electronic device, the electronic device: acquires the first longitudinal velocity, lateral acceleration, wheel longitudinal force, wheel Rotation angle and wheel lateral force, input the current wheel longitudinal force, wheel rotation angle and wheel lateral force into the nonlinear vehicle model to obtain the yaw rate; input the wheel angle, lateral acceleration, yaw rate, and the first longitudinal velocity into the state Parameter observation model, the first center of mass side slip angle is obtained, and the state parameter observation model adopts an adaptive fuzzy neural network model; the first sliding mode observer is constructed with the yaw rate and the first center of mass side slip angle as the observation vector; the wheel angle, The wheel longitudinal force and wheel lateral force are input into the first sliding mode observer to obtain the second longitudinal velocity and the second lateral velocity, and the second center-of-mass sideslip angle is obtained according to the second longitudinal velocity and the second lateral velocity.

The above description is only a preferred embodiment of the present application and an illustration of the applied technical principles. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to the technical solution formed by the specific combination of the above-mentioned technical features, and should also cover the technical solutions formed by the above-mentioned technical features or without departing from the above-mentioned inventive concept. Other technical solutions formed by any combination of equivalent features. For example, a technical solution formed by replacing the above-mentioned features with technical features with similar functions disclosed in (but not limited to) this application.

Claims (10)

1. A distributed electric drive vehicle state parameter observation method, is characterized in that, comprises the following steps: S1. Obtain the first longitudinal velocity, lateral acceleration, wheel longitudinal force, wheel angle and wheel lateral force of the vehicle at the current moment, and input the current moment wheel longitudinal force, wheel angle and wheel lateral force into the nonlinear vehicle model, Get the yaw rate; S2. Input the wheel angle, lateral acceleration, yaw rate, and first longitudinal velocity into a state parameter observation model to obtain a first center-of-mass sideslip angle, and the state parameter observation model adopts an adaptive fuzzy neural network model; S3, using the yaw rate and the first center-of-mass sideslip angle as observation vectors to construct a first sliding mode observer; S4. Input the wheel angle, wheel longitudinal force, and wheel lateral force into the first sliding model observer to obtain the second longitudinal velocity and the second lateral velocity, and obtain the second longitudinal velocity and the second lateral velocity according to the second longitudinal velocity and the second lateral velocity Second centroid slip angle. 2. The state parameter observation method of distributed electric drive vehicles according to claim 1, wherein said 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 to fuzzify input variables, each node is an adaptive node with a specific node function, and the node function is:

Among them, x is the node input, and {a, b, c} is a variable parameter set, which is called the premise part parameter of the rule, which can reflect different membership functions in the fuzzy set; The node output function of the input node layer is expressed as:

Among them, x ₁ , x ₂ ,…, x _n are node outputs, which are the membership function values of fuzzy variables A _i , B _j and C _k , which represent the node input x ₁ , x ₂ ,…, x _n for A _i , the degree of membership of B _j and C _k ; The node of described rule node layer is by being marked with the fixed node represented by multiplication symbol (∏), is the node output function of described input node layer as the input signal of described rule node layer, the input of described rule node layer is The product of all input signals in the regular node layer:

The node of the average node layer is a fixed node marked with N, and the output of the node is the ratio of the sum of the excitation strength and the excitation strength in the rule base, and this ratio represents that the rule strength is normalized:

The node of the conclusion node layer is an adaptive node with a node function, and the node output of the conclusion node layer is expressed as:

Among them, p _i , q _i and r _i are the consequent parameters, and f _i is the symbol representing the product of the consequent parameter and the system input; The node of the output node layer is an adaptive node with a node function, and the node output of the output node layer is expressed as:

The input of the adaptive fuzzy neural network model is the wheel angle, lateral acceleration, yaw rate, and the first longitudinal velocity input state parameter observation model, and the output of the adaptive fuzzy neural network model is the first center-of-mass sideslip angle β _ANFIS . 3. The state parameter observation method of distributed electric drive vehicle according to claim 2, characterized in that, the training process of the adaptive fuzzy neural network model specifically comprises: Construct the second sliding mode observer with the yaw rate as the observation vector: The second sliding mode observer is described by the following formula:

Among them, 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 form expression of the second sliding mode observer is:

Among them, the input variables are: u=[δF _x F _y ]; Among them, δ is the wheel rotation angle, F _x is the wheel longitudinal force acting on the wheel, F _y is the wheel lateral force acting on the wheel; The state vector and observation vector are respectively: x=[v _x v _y r]; y = [r]; Wherein, ν _x is the third longitudinal velocity, ν _y is the third lateral velocity, and r is the yaw rate; The second sliding mode observer is constructed based on the sliding mode variable structure theory as follows:

I _s =sgn(s);

H is the damping coefficient matrix, I _s is the switching function; The damping coefficient matrix H of the second sliding mode observer is: H=[h ₁ h ₂ h ₃ ]; Among them, h ₁ , h ₂ , h ₃ are the damping coefficients obtained in the simulation process; The robust control term matrix K of the second sliding mode observer is: K=[k ₁ k ₂ k ₃ ]; Among them, k ₁ , k ₂ , and k ₃ are the robust control items obtained in the simulation process; Selecting the saturation function as the switching function of the second sliding mode observer is equivalent to setting the boundary layer near the sliding mode surface, then there are: I _s =sat(s/λ); where λ is the thickness of the boundary layer; The third longitudinal velocity v _x and the third lateral velocity v _y are estimated by the second sliding mode observer, and then the first center-of-mass sideslip angle is estimated according to the following formula:

Collect the wheel angle, lateral acceleration, yaw rate and the first longitudinal velocity during the operation of the vehicle, and compare the wheel angle, lateral acceleration, yaw rate and the first longitudinal velocity with the first center of mass The side slip angle constitutes training data, and the adaptive fuzzy neural network model is trained by using the training data to obtain a state parameter observation model. 4. The method for observing state parameters of a distributed electric drive vehicle according to claim 1, wherein the step S1 specifically includes: The three-degree-of-freedom dynamics model is selected as the nonlinear vehicle model of the distributed electric drive vehicle:

Among them, m is the mass of the vehicle, ν ⁰ _x is the first longitudinal velocity, ν 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, and a is the center of mass of the vehicle is the distance from the front axle to the front axle, b is the distance from the center of mass of the vehicle 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 ij=fl, fr, rl, rr in F _yij represent the front left wheel, the front right wheel, the rear left wheel, and the rear right wheel respectively. 5. The state parameter observation method of a distributed electric drive vehicle according to claim 4, wherein the calculation formula of the wheel longitudinal force F _x is as follows:

Among them, J _w is the moment of inertia of the wheel, r _w is the effective radius of the wheel, w _ij and T _ij represent the angular velocity and wheel torque of each wheel, respectively. 6. The method for observing state parameters of a distributed electric drive vehicle according to claim 3, wherein said step S3 specifically comprises: The nonlinear form expression of the first sliding mode observer is:

Among them, the state vector is: x=[v' _x v' _y r]; The observation vector is y=[r β _ANFIS ]; Among them, β _ANFIS is the side slip angle of the first center of mass estimated by the adaptive fuzzy neural network; The input vector is u = [δ F _x F _y ]; Therefore, the first sliding mode observer is constructed as follows:

I _s =sat(s/λ);

7. The method for observing state parameters of a distributed electric drive vehicle according to claim 1, wherein said step S4 specifically comprises: The second longitudinal velocity v' _x and the second lateral velocity v' _y of the vehicle are estimated by the first sliding mode observer, and then the second center-of-mass sideslip angle is estimated according to the following formula:

8. A distributed electric drive vehicle state parameter observation device, characterized in that it comprises: The yaw rate calculation module is configured to obtain the first longitudinal speed, lateral acceleration, wheel longitudinal force, wheel angle and wheel lateral force of the vehicle at the current moment, and calculate the current wheel longitudinal force, wheel angle and wheel lateral force Input the force into the nonlinear vehicle model to obtain the yaw rate; The first center-of-mass sideslip angle calculation module is configured to input the wheel angle, lateral acceleration, yaw rate, and first longitudinal velocity into a state parameter observation model to obtain a first center-of-mass sideslip angle, and the state parameter observation model adopts Adaptive fuzzy neural network model; A first sliding mode observer construction module configured to use the yaw rate and the first center-of-mass sideslip angle as observation vectors to construct a first sliding mode observer; The second center-of-mass sideslip angle calculation module is configured to input the wheel angle, wheel longitudinal force, and wheel lateral force into the first sliding model observer to obtain a second longitudinal velocity and a second lateral velocity, according to the first The second longitudinal velocity and the second lateral velocity result in a second center-of-mass slip angle. 9. An electronic device comprising: one or more processors; storage means 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 are made to implement the method according to any one of claims 1-7. 10. A computer-readable storage medium, on which a computer program is stored, wherein, when the program is executed by a processor, the method according to any one of claims 1-7 is implemented.

Images