Electric heavy-duty vehicle dynamics state prediction method, system and terminal device

Abstract

The application discloses an electric heavy-load vehicle dynamics state prediction method and system and a terminal device, and relates to the technical field of new energy vehicles.The application comprises the following steps: receiving heavy-load vehicle driving state information data and preprocessing the same, wherein the heavy-load vehicle driving state information data comprises longitudinal acceleration, lateral acceleration, yaw angular velocity, wheel rotational speed and wheel rotation angle; and constructing a lateral velocity model based on a Koopman operator according to the driving state information data, so as to predict the lateral velocity of the heavy-load vehicle.The application proposes a lateral velocity model based on a Koopman operator in view of the problem that the lateral velocity of an electric heavy-load vehicle is usually unmeasurable, can solve the problem that the lateral velocity cannot be obtained by using a traditional method, and proposes a linear heavy-load vehicle dynamics model to represent the nonlinear characteristics of the heavy-load vehicle, so that the heavy-load vehicle system is not required to be nonlinearly modeled, and subsequent controller design is facilitated.

Description

Technical Field

[0001] This invention relates to the field of new energy vehicle technology, specifically to a method, system, and terminal equipment for predicting the dynamic state of electric heavy-duty vehicles. Background Technology

[0002] With the rapid development of the automotive industry and the increasing demands for environmental protection and energy conservation, new energy vehicles, as environmentally friendly and energy-saving vehicles with great development potential, have received increasingly widespread attention and application. Most existing methods for modeling the dynamics of electric vehicles are based on the derivation of physical laws. These methods require the calibration of a large number of vehicle parameters, such as vehicle mass, inertia, and center of gravity position, which is not only difficult to calibrate but also lacks adaptability to various operating conditions. Some methods use machine learning to model vehicle dynamics, but these methods cannot obtain lateral velocity, and are inherently nonlinear models, posing challenges to subsequent controller design. Summary of the Invention

[0003] The purpose of this invention is to provide a method, system and terminal device for predicting the dynamic state of electric heavy-duty vehicles. It not only solves the problem of estimating lateral velocity, but more importantly, the final model obtained is a linear model, which facilitates subsequent controller design.

[0004] According to a first aspect of the present invention, in order to achieve the above-mentioned objective, the present invention provides the following technical solution: a method for predicting the dynamic state of an electric heavy-duty vehicle, comprising the following steps:

[0005] Receive driving status information data of heavy-duty vehicles, including longitudinal acceleration, lateral acceleration, yaw rate, wheel speed, and wheel angle;

[0006] A lateral velocity model based on the Koopman operator is constructed based on driving status information data to predict the lateral velocity of heavy-duty vehicles.

[0007] Based on the nonlinear dynamic model and the predicted lateral velocity, a linear dynamic model of heavy-duty vehicles based on the Koopman operator is constructed to predict the dynamic state of heavy-duty vehicles.

[0008] Furthermore, the longitudinal acceleration, lateral acceleration, yaw rate, wheel speed, and wheel angle in the heavy-duty vehicle driving status information data are obtained by the acceleration sensor, yaw rate sensor, speedometer, and angle sensor installed on the vehicle itself.

[0009] Furthermore, a lateral velocity model based on the Koopman operator is constructed based on the driving status information data to predict the lateral velocity of the heavy-duty vehicle, as follows:

[0010] (31) Let the state vector xvy =[a xk ,a yk ,γ k ,w k ], the input vector is u vyk =δ f Define the state dimensionality increase function of the Koopman operator oriented towards lateral velocity as σ. k (x vyk ,u vyk Its dynamic evolution is as follows:

[0011] σ k (x vyk+1 ,u vyk+1 )=σ k (g(x vyk ,u vyk ))=K vy σ k (x vyk ,u vyk );

[0012] (32) Suppose that the Koopman operator is composed of a set of matrices (A vy B vy C vy D vy To achieve this, let p k =σ k (x vyk ,u vyk Design the following linear dynamic model:

[0013] p k+1 =A vy p k +B vy u vyk

[0014] v yk =C vy p k +D vy u vyk

[0015] In the formula, p k p represents the state at the k-th step after dimensionality increase. k+1 This represents the state at step k+1 after dimensionality increase;

[0016] (33) Acquire signals from time 0 to time M, and define them in the following forms:

[0017] P M =[p0 p1…p M-1 ]

[0018] P M+1 =[p1 p2…pM ]

[0019] U vyM =[u vy0 u vy1 …u vyM-1 ]

[0020] V yM =[v y0 v y1 …v yM-1 ]

[0021] In the formula, P M Let P be a vector matrix with states ranging from 0 to M-1. M+1 U is a vector matrix representing states from 1 to M; vyM The input vector matrix V is from 0 to M-1. yM This is a vector matrix with lateral velocities ranging from 0 to M-1; M is the data length.

[0022] The Koopman linear model of lateral velocity can then be extended to the following form using data:

[0023] P M+1 =A vy P M +B vy U vyM

[0024] V yM =C vy P M +D vy U vyM

[0025] The system matrix (A) is obtained by solving using the least squares method. vy B vy C vy D vy ):

[0026]

[0027] In the formula ||·|| F Let Frobenius norm be the corresponding matrix; by solving the above equation, the lateral velocity can be predicted.

[0028] Furthermore, the construction of the nonlinear dynamic model is as follows:

[0029] (41) Based on the laws of vehicle motion and Newton's laws of motion, the traditional lateral and longitudinal coupled dynamic model of heavy-duty vehicles is described by the following equation:

[0030]

[0031] In the formula, m is the mass of the vehicle, in kg; v x It is the longitudinal speed of the vehicle, measured in m / s; v y γ is the vehicle's lateral velocity, measured in m / s; γ is the vehicle's yaw rate, measured in rad / s; δ f It is the front wheel steering angle, in rad; I z It is the yaw inertia, measured in kg·m. 2 L f It is the distance from the vehicle's center of gravity to the front axle, in meters (m); L r It is the distance from the vehicle's center of gravity to the rear axle, in meters (m). The longitudinal tire force of the front wheels, measured in N; The longitudinal tire force of the rear wheel, measured in N; The lateral force on the front tires, measured in N; The lateral force on the rear wheels, measured in N.

[0032] (42) Select the state vector as x k =[v x ,v y ,γ k ], the input vector is u k =δ f Then, the vehicle coupled dynamics model in (41) can be simplified to a general nonlinear dynamics model, as shown in the following expression:

[0033] x k+1 =f(x) k ,u k )

[0034] In the formula, x k Let u be the state vector. k The input vector.

[0035] Furthermore, based on the nonlinear dynamic model and the predicted lateral velocity, a linear heavy-duty vehicle dynamic model based on the Koopman operator is constructed to predict the dynamic state of the heavy-duty vehicle, as follows:

[0036] (51) Define the state-level-up function of the Koopman operator for heavy-duty vehicle dynamics as φ k (x k ,u k Its dynamic evolution is as follows:

[0037] φ k (x k+1 ,u k+1 )=φ k (f(x k ,u k ))=K vd φk (x k ,u k )

[0038] In the formula K vd It is the Koopman operator; the state matrix x k Includes lateral velocity, which is obtained through a lateral velocity model based on the Koopman operator;

[0039] (52) Let z k =φ k (x k ,u k ), and assume the Koopman operator K vd It consists of a set of matrices (A) vd B vd C vd D vd If this is achieved, the above equation can be transformed into the general form of a linear control system:

[0040] z k+1 =A vd z k +B vd u vdk

[0041] y k =C vd z k +D vd u vdk

[0042] In the formula z k ∈R q It is the upgraded state vector of the original linear control system, (A vd B vd C vd D vd The system matrix is ​​determined by the Koopman operator;

[0043] (53) By collecting the state data x of the linear control system k With input data u k Combining the definition of the dimension-upgrading function, we define the following data matrix:

[0044] Z k =[z0 z1…z N-1 ]

[0045] Z k+1 =[z1 z2…z N ]

[0046] U k =[u0 u1…u N-1 ]

[0047] Y k =[y0 y1…y N-1 ]

[0048] In the formula, N is the selected data length or data step size, and Z is... k Z k+1 U k With Y k These correspond to data segments from steps 0 to N-1 of the dimensionality-upgrading state, steps 1 to N of the dimensionality-upgrading state, steps 0 to N-1 of the turning input, and steps 0 to N-1 of the output vector, respectively, where Z k With Z k+1 Only one time step away;

[0049] (54) Using the above linear control system relationship, the relationship between the data is as follows:

[0050] Z k+1 =A vd Z k +B vd U k

[0051] Y k =C vd Z k +D vd U k

[0052] The system matrix (A) is obtained by solving using the least squares method. vd B vd C vd D vd )

[0053]

[0054] This leads to the linear dynamics model of heavy-duty vehicles after dimensionality enhancement.

[0055] According to a second aspect of the present invention, the present invention provides a dynamic state prediction system for electric heavy-duty vehicles, for implementing the above-described dynamic state prediction method for electric heavy-duty vehicles, comprising:

[0056] The receiving module is used to receive and preprocess the driving status information data of heavy-duty vehicles. The driving status information data of heavy-duty vehicles includes longitudinal acceleration, lateral acceleration, yaw rate, wheel speed, and wheel angle.

[0057] The first construction module is used to build a lateral velocity model based on the Koopman operator based on driving status information data, which is used to predict the lateral velocity of heavy-duty vehicles.

[0058] The second building module is used to construct a linear heavy-duty vehicle dynamics model based on the Koopman operator, based on the nonlinear dynamics model and the predicted lateral velocity, in order to predict the dynamic state of heavy-duty vehicles.

[0059] According to a third aspect of the present invention, the present invention provides a terminal device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the memory stores the computer program capable of running on the processor, and the processor loads and executes the computer program using the above-described method for predicting the dynamic state of electric heavy-duty vehicles.

[0060] According to a fourth aspect of the present invention, the present invention provides a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the above-described method for predicting the dynamic state of an electric heavy-duty vehicle.

[0061] The present invention has at least the following beneficial effects:

[0062] 1. This invention addresses the problem that the lateral velocity of electric heavy-duty vehicles is usually unmeasurable. It proposes a lateral velocity model based on the Koopman operator, which can solve the problem that traditional methods cannot obtain the lateral velocity, and does not require the acquisition of the vehicle's full-state parameters, such as mass, wheelbase, and inertia.

[0063] 2. Based on the traditional lateral and longitudinal coupled dynamic model of heavy-duty vehicles, this invention proposes a data-driven coupled linear dynamic model based on the Koopman operator to predict the dynamic state of heavy-duty vehicles. This model eliminates the need for various configuration parameters of heavy-duty vehicles, such as mass, wheelbase, and inertia. Furthermore, it uses a linear model to characterize the nonlinear characteristics of heavy-duty vehicles, avoiding nonlinear modeling of the heavy-duty vehicle system and facilitating subsequent controller design.

[0064] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0065] Figure 1 This is a flowchart illustrating the method described in this invention;

[0066] Figure 2 This is a schematic diagram illustrating the reconstruction effect of the lateral velocity model based on the Koopman operator in this invention.

[0067] Figure 3 This is a schematic diagram illustrating the predictive effect of the heavy-duty vehicle dynamics model on the vehicle's dynamic state in this invention. Detailed Implementation

[0068] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0069] Example 1:

[0070] Please see Figures 1-3 This invention provides a technical solution: a method for predicting the dynamic state of electric heavy-duty vehicles, comprising the following steps:

[0071] S1. Receive heavy-duty vehicle driving status information data, which includes longitudinal acceleration, lateral acceleration, yaw rate, wheel speed, and wheel angle;

[0072] It should be noted that the longitudinal acceleration, lateral acceleration, yaw rate, wheel speed, and wheel angle in the driving status information data of heavy-duty vehicles are collected by the acceleration sensor, yaw rate sensor, speedometer, and angle sensor installed on the vehicle itself, respectively.

[0073] S2. Construct a lateral velocity model based on the Koopman operator using the driving status information data to predict the lateral velocity of the heavy-duty vehicle, as follows:

[0074] (S21) Considering the nonlinear relationship between lateral velocity and parameters such as lateral acceleration, yaw rate, wheel rotation angle, and wheel motion state, that is:

[0075] v yk =g(a xk ,a yk ,γ k ,w k ,δ k )

[0076] This embodiment proposes using the Koopman operator to learn the lateral velocity of heavy-duty vehicles;

[0077] (S22) Let the state vector x be... vy =[a xk ,a yk ,γ k ,w k ], the input vector is u vyk =δ f Define the state dimensionality increase function of the Koopman operator oriented towards lateral velocity as σ. k (x vyk ,u vyk Its dynamic evolution is as follows:

[0078] σ k (x vyk+1 ,u vyk+1 )=σ k (g(x vyk ,u vyk ))=K vy σ k (x vyk ,u vyk )

[0079] Suppose the Koopman operator is composed of a set of matrices (A vy B vy C vy D vy To achieve this, let p k =σ k (x vyk ,u vyk Design the following linear dynamic model:

[0080] p k+1 =A vy p k +B vy u vyk

[0081] v yk =C vy p k +D vy u vyk

[0082] In the formula, p k p represents the state at the k-th step after dimensionality increase. k+1 This represents the state at step k+1 after dimensionality increase;

[0083] (S23) The above design can be understood as designing a high-dimensional state p using the Koopman operator linear model. k The dynamic evolution of it causes it to change under the input u vyk Under the influence of this method, the lateral velocity signal is reproduced by offline acquisition of a series of lateral velocity signals and the state vector x. vy The series of signals contained therein can realize the above matrix (A) vy B vy C vy D vy The identification of ) is used to predict lateral velocity;

[0084] First, the signals from time 0 to time M are acquired and defined as follows:

[0085] P M =[p0 p1…p M-1 ]

[0086] P M+1 =[p1 p2…p M ]

[0087] U vyM =[u vy0 u vy1 …u vyM-1 ]

[0088] V yM =[v y0 v y1 …v yM-1 ]

[0089] In the formula, P M Let P be a vector matrix with states ranging from 0 to M-1. M+1 U is a vector matrix representing states from 1 to M; vyM The input vector matrix V is from 0 to M-1. yM This is a vector matrix with lateral velocities ranging from 0 to M-1; M is the data length.

[0090] The Koopman linear model of lateral velocity can then be extended to the following form using data:

[0091] P M+1 =A vy P M +B vy U vyM

[0092] V yM =C vy P M +D vy U vyM

[0093] By constructing an optimization problem and using the least squares method, the system matrix set (A) can be obtained. vy B vy C vy D vy ):

[0094]

[0095] In the formula ||·|| F This represents the Frobenius norm of the corresponding matrix;

[0096] By solving the above optimization problem, the lateral velocity can be predicted.

[0097] S3. Based on the nonlinear dynamic model and the predicted lateral velocity, a linear heavy-duty vehicle dynamic model based on the Koopman operator is constructed to predict the dynamic state of heavy-duty vehicles, as detailed below:

[0098] (S31) Based on the laws of vehicle motion and Newton's laws of motion, the traditional lateral and longitudinal coupled dynamic model of heavy-duty vehicles can be described by the following equation:

[0099]

[0100] In the formula, m is the mass of the vehicle, in kg; v x It is the longitudinal speed of the vehicle, measured in m / s; v y γ is the vehicle's lateral velocity, measured in m / s; γ is the vehicle's yaw rate, measured in rad / s; δ f It is the front wheel steering angle, in rad; I z It is the yaw inertia, measured in kg·m. 2 L f It is the distance from the vehicle's center of gravity to the front axle, in meters (m); L r It is the distance from the vehicle's center of gravity to the rear axle, in meters (m). The longitudinal tire force of the front wheels, measured in N; The longitudinal tire force of the rear wheel, measured in N; The lateral force on the front tires, measured in N; The lateral force on the rear wheels, measured in N.

[0101] (S32) Select the state vector as x k =[v x ,v y ,γ k ], the input vector is u k =δ f Therefore, the above vehicle coupling dynamics can be simplified to a general nonlinear dynamics model, as shown in the following expression:

[0102] x k+1 =f(x) k ,u k )

[0103] For the aforementioned nonlinear heavy-duty vehicle system, the Koopman operator is used to achieve data-driven linear vehicle dynamics modeling. The state-level-increasing function of the Koopman operator for heavy-duty vehicle dynamics is defined as φ. k (x k ,u k Its dynamic evolution is as follows:

[0104] φ k (x k+1 ,u k+1)=φ k (f(x k ,u k ))=K vd φ k (x k ,u k )

[0105] In the formula K vd It is the Koopman operator. Note the original state matrix x mentioned above. k It includes lateral velocity, which is usually an unmeasurable signal. Here, this parameter is obtained based on the lateral velocity model of the Koopman operator.

[0106] (S33) Let z k =φ k (x k ,u k ), and assume the Koopman operator K vd It consists of a set of matrices (A) vd B vd C vd D vd If this is achieved, the above equation can be transformed into the general form of a linear control system:

[0107] z k+1 =A vd z k +B vd u vdk

[0108] y k =C vd z k +D vd u vdk

[0109] In the formula z k ∈R q It is the upgraded state vector of the original linear control system, (A vd B vd C vd D vd The system matrix is ​​determined by the Koopman operator;

[0110] (S34) Collect system status data x k With input data u k Combining the definition of the dimension-upgrading function, we define the following data matrix:

[0111] Z k =[z0 z1…z N-1 ]

[0112] Z k+1 =[z1 z2…zN ]

[0113] U k =[u0 u1…u N-1 ]

[0114] Y k =[y0 y1…y N-1 ]

[0115] In the formula, N is the selected data length or data step size, and Z is... k Z k+1 U k With Y k These correspond to data segments from steps 0 to N-1 of the dimensionality-upgrading state, steps 1 to N of the dimensionality-upgrading state, steps 0 to N-1 of the turning input, and steps 0 to N-1 of the output vector, respectively. Note that Z... k With Z k+1 Only one time step away;

[0116] (S35) Using the above linear system relationship, the relationship between the data is as follows:

[0117] Z k+1 =A vd Z k +B vd U k

[0118] Y k =C vd Z k +D vd U k

[0119] The system matrix (A) can be obtained by using the least squares method. vd B vd C vd D vd )

[0120]

[0121] Therefore, by using the data from the nonlinear electric heavy-duty vehicle system, the Koopman operator, and the aforementioned optimization algorithm, a linear heavy-duty vehicle dynamics model with increased dimensionality can be obtained.

[0122] The technical solution of this embodiment will be further verified next with reference to specific embodiments:

[0123] To verify the dual Koopman operator proposed in this embodiment, firstly, using signals such as the lateral and longitudinal acceleration, yaw rate, and wheel speed of the heavy-duty vehicle, a Koopman operator oriented towards lateral velocity is constructed and optimized. Corresponding to the content of step S2, the final reconstruction effect of the Koopman operator on lateral velocity is as follows: Figure 2 As shown, the operator fits the lateral velocity well on the training dataset.

[0124] Based on the lateral velocity obtained from the Koopman operator, we perform dynamic modeling of heavy-duty vehicles as mentioned in S3. The effects of the key dynamic states of the heavy-duty vehicle are as follows: Figure 3 As shown, it can also be seen that the three states in the dynamics of heavy-duty vehicles based on the dual Koopman operator are close to the true values, verifying the good modeling effect of the data-driven algorithm.

[0125] In summary, this invention proposes a dynamic coupling modeling method for electric heavy-duty vehicles based on dual Koopman operators. First, addressing the issue that the lateral velocity of electric heavy-duty vehicles is often unmeasurable, a linear prediction model based on easily measurable parameters such as longitudinal acceleration, lateral acceleration, yaw rate, and tire speed is proposed using the Koopman operator. Second, based on the traditional lateral-longitudinal coupled dynamic model of heavy-duty vehicles, a data-driven coupled linear dynamic model based on the Koopman operator is proposed to predict the dynamic state of heavy-duty vehicles. The aforementioned cascaded Koopman operator enables the prediction of the lateral-longitudinal coupled dynamic motion state of heavy-duty vehicles without lateral velocity sensors.

[0126] Example 2:

[0127] This embodiment provides a dynamic state prediction system for electric heavy-duty vehicles, used to implement the dynamic state prediction method for electric heavy-duty vehicles described in Embodiment 1, including:

[0128] The receiving module is used to receive and preprocess the driving status information data of heavy-duty vehicles. The driving status information data of heavy-duty vehicles includes longitudinal acceleration, lateral acceleration, yaw rate, wheel speed, and wheel angle.

[0129] The first construction module is used to build a lateral velocity model based on the Koopman operator based on driving status information data, which is used to predict the lateral velocity of heavy-duty vehicles.

[0130] The second building module is used to construct a linear heavy-duty vehicle dynamics model based on the Koopman operator, based on the nonlinear dynamics model and the predicted lateral velocity, in order to predict the dynamic state of heavy-duty vehicles.

[0131] Specifically, the aforementioned receiving module, first construction module, and second construction module can be embedded into a computer processing system. The computer, based on the aforementioned electric heavy-duty vehicle dynamic state prediction method, calls the aforementioned modules to complete the task of predicting the dynamic state of the heavy-duty vehicle. The aforementioned receiving module, first construction module, and second construction module can perform operations according to the specific steps given in the aforementioned electric heavy-duty vehicle dynamic state prediction method.

[0132] It should be noted that the division of the various modules in the above system is merely a division of logical functions. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. These modules can be implemented entirely in software through processing element calls; they can be fully implemented in hardware; or some modules can be implemented by processing element calls to software, while others are implemented in hardware. For example, the receiving module can be a separate processing element or integrated into a chip in the aforementioned device. Alternatively, it can be stored as program code in the memory of the aforementioned device, and called and executed by a processing element of the device. The implementation of other modules is similar. Furthermore, these modules can be fully or partially integrated together or implemented independently. The processing element mentioned here can be an integrated circuit with signal processing capabilities. During implementation, each step of the above method or each of the above modules can be completed through integrated logic circuits in the hardware of the processor element or through software instructions.

[0133] For example, these modules can be one or more integrated circuits configured to implement the above methods, such as one or more Application Specific Integrated Circuits (ASICs), one or more Digital Signal Processors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs). As another example, when a module is implemented using processing element scheduler code, the processing element can be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. Furthermore, these modules can be integrated together to form a system-on-a-chip (SOC).

[0134] Example 3:

[0135] The present invention provides a terminal device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor. The memory stores the computer program capable of running on the processor. When the processor loads and executes the computer program, it employs the above-mentioned method for predicting the dynamic state of electric heavy-duty vehicles.

[0136] It should be noted that the terminal device can be a computer device such as a desktop computer, a laptop computer, or a cloud server, and the terminal device includes, but is not limited to, a processor and a memory. For example, the terminal device may also include input / output devices, network access devices, and buses.

[0137] Furthermore, the processor can be a central processing unit (CPU). Of course, depending on the actual use, other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. can also be used. The general-purpose processor can be a microprocessor or any conventional processor, etc., and this application does not limit it in this regard.

[0138] Example 4:

[0139] The present invention provides a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the above-described method for predicting the dynamic state of electric heavy-duty vehicles.

[0140] The computer program can be stored in a computer-readable medium. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or certain middleware. The computer-readable medium includes any entity or device capable of carrying computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the computer-readable medium includes, but is not limited to, the above-mentioned components.

[0141] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0142] For those skilled in the art, the specific meaning of the above terms in this invention can be understood according to the specific circumstances. When an element is referred to as being "assembled on," "mounted on," "fixed to," or "set on" another element, it may be directly on the other element or there may be an intermediate element present. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be an intermediate element present. The terms "vertical," "horizontal," "upper," "lower," "left," "right," and similar expressions used herein are for illustrative purposes only and do not represent the only possible embodiments.

[0143] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

[0144] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

Claims

1. A method for predicting the dynamic state of electric heavy-duty vehicles, characterized in that, Includes the following steps: Receive driving status information data of heavy-duty vehicles, including longitudinal acceleration, lateral acceleration, yaw rate, wheel speed, and wheel angle; A lateral velocity model based on the Koopman operator is constructed based on driving status information data to predict the lateral velocity of heavy-duty vehicles. Based on the nonlinear dynamics model and the predicted lateral velocity, a linear dynamics model of heavy-duty vehicles based on the Koopman operator is constructed to predict the dynamic state of heavy-duty vehicles. The longitudinal acceleration, lateral acceleration, yaw rate, wheel speed, and wheel angle in the heavy-duty vehicle driving status information data are collected by the acceleration sensor, yaw rate sensor, speedometer, and angle sensor installed on the vehicle itself, respectively. A lateral velocity model based on the Koopman operator is constructed based on driving status information data to predict the lateral velocity of heavy-duty vehicles, as follows: Let the state vector be... The input vector is Define the state dimensionality increase function of the Koopman operator oriented towards lateral velocity as follows: Its dynamic evolution is as follows: ; Suppose the Koopman operator is composed of a set of matrices ( , , , To achieve, make The following linear dynamic model is designed: In the formula, This represents the state at the k-th step after dimensionality increase. This represents the state at step k+1 after dimensionality increase; The signals from time 0 to time M are collected and defined as follows: In the formula, Let M be a vector matrix representing the states from time 0 to M-1. Let M be the vector matrix representing the states from time 1 to M; The input vector matrix for steering is from time 0 to M-1; Let M be the vector matrix representing the lateral velocity from time 0 to M-1; For data length; The Koopman linear model of lateral velocity can then be extended to the following form using data: The system matrix is ​​obtained by solving using the least squares method. , , , ): In the formula Let Frobenius norm be the corresponding matrix; by solving the above equation, the lateral velocity can be predicted.

2. The method for predicting the dynamic state of electric heavy-duty vehicles according to claim 1, characterized in that, The nonlinear dynamic model is constructed as follows: (21) Based on the laws of vehicle motion and Newton's laws of motion, the traditional lateral and longitudinal coupled dynamic model of heavy-duty vehicles is described by the following equation: In the formula It refers to the mass of the vehicle, in units. kg ; It is the longitudinal speed of the vehicle, in units of m / s ; It is the lateral speed of the vehicle, in units of m / s ; It is the yaw rate of the vehicle, in units of rad / s ; It is the front wheel steering angle, in units of... rad ; It is the yaw inertia, in units of... ; It is the distance from the vehicle's center of gravity to the front axle, in units of... m ; It is the distance from the vehicle's center of gravity to the rear axle, in units of... m ; The longitudinal tire force of the front wheels, measured in units of... N ; The longitudinal tire force of the rear wheel, measured in units of... N ; The lateral tire force of the front wheels, measured in units of... N ; The lateral force of the rear tires, measured in units of... N ; (22) Choose the state vector as The input vector is Then, the vehicle coupled dynamics model in (41) can be simplified to a general nonlinear dynamics model, as shown in the following expression: In the formula, For state vectors, The input vector.

3. The method for predicting the dynamic state of electric heavy-duty vehicles according to claim 2, characterized in that, Based on the nonlinear dynamic model and the predicted lateral velocity, a linear dynamic model of heavy-duty vehicles based on the Koopman operator is constructed to predict the dynamic state of heavy-duty vehicles, as detailed below: (31) Define the state-level-up function of the Koopman operator for heavy-duty vehicle dynamics as follows: Its dynamic evolution is as follows: In the formula It is the Koopman operator; state matrix Includes lateral velocity, which is obtained through a lateral velocity model based on the Koopman operator; (32) Order And assume the Koopman operator It consists of a set of matrices ( , , , If this is achieved, the above equation can be transformed into the general form of a linear control system: In the formula It is the upgraded state vector of the original linear control system. , , , The system matrix is ​​determined by the Koopman operator; (33) By collecting state data of the linear control system With input data Combining the definition of the dimension-upgrading function, we define the following data matrix: In the formula N The selected data length, also known as the data step size. , , and These correspond to data segments from steps 0 to N-1 of the dimensionality-upgrading state, steps 1 to N of the dimensionality-upgrading state, steps 0 to N-1 of the turning input, and steps 0 to N-1 of the output vector, respectively. and Only one time step away; (34) Using the above linear control system relationship, the relationship between the data is as follows: The system matrix is ​​obtained by solving using the least squares method. , , , ) This leads to the linear dynamics model of heavy-duty vehicles after dimensionality enhancement.

4. A dynamic state prediction system for electric heavy-duty vehicles, used to implement the dynamic state prediction method for electric heavy-duty vehicles as described in any one of claims 1 to 3, characterized in that, include: The receiving module is used to receive and preprocess the driving status information data of heavy-duty vehicles. The driving status information data of heavy-duty vehicles includes longitudinal acceleration, lateral acceleration, yaw rate, wheel speed, and wheel angle. The first construction module is used to build a lateral velocity model based on the Koopman operator based on driving status information data, which is used to predict the lateral velocity of heavy-duty vehicles. The second building module is used to construct a linear heavy-duty vehicle dynamics model based on the Koopman operator, based on the nonlinear dynamics model and the predicted lateral velocity, in order to predict the dynamic state of heavy-duty vehicles.

5. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that, The memory stores a computer program that can run on a processor. When the processor loads and executes the computer program, it employs the electric heavy-duty vehicle dynamic state prediction method as described in any one of claims 1 to 3.

6. A storage medium containing computer-executable instructions, characterized in that, The computer-executable instructions, when executed by a computer processor, are used to perform the electric heavy-duty vehicle dynamics state prediction method as described in any one of claims 1 to 3.

Images