Heavy-load vehicle state estimation method and device, electronic equipment and storage medium

Abstract

The invention discloses a heavy-load vehicle state estimation method and device, electronic equipment and a storage medium, and can be applied to the technical field of vehicle data processing. According to the method, the heavy-load vehicle parameters are obtained, the first historical data are preprocessed to obtain the second historical data, and then according to the heavy-load vehicle parameters and the second historical data, the first state transition equation of the vehicle dynamics model is established by adopting the nonlinear system dynamics sparse identification algorithm; therefore, a small number of functions which can most explain the dynamic state of the vehicle system can be selected from a large number of candidate functions, features implied in data are effectively extracted, the complexity and calculation burden in the process of establishing a heavy-load vehicle dynamic model are reduced, and the dynamic model of the heavy-load vehicle is established on the basis of the first state transition equation and the self-adaptive extended Kalman filtering algorithm. Vehicle state estimation is carried out according to the first real-time data, so that a vehicle system can cope with a complex and changeable driving environment, and the accuracy of a heavy-load vehicle state estimation value is effectively improved.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle data processing, and in particular to a method and device for estimating the state of a heavy-loaded vehicle, an electronic device, and a storage medium. Background Art

[0002] In the related art, with the development of autonomous driving technology, heavy-duty vehicles are increasingly used in logistics, transportation, construction and other fields. However, due to their heavy weight, uneven load and high center of gravity, these vehicles have complex dynamic characteristics, large inertia and low stability under conditions such as turning and braking. Generally speaking, vehicle state data can be directly obtained through on-board sensors. However, since the sensor data of heavy-duty vehicles under different load conditions are easily affected by factors such as vibration and temperature changes, the data noise is large and the accuracy is difficult to guarantee. Especially in the case of complex road conditions and dynamic load changes, traditional state estimation methods such as extended Kalman filter (EKF) and unscented Kalman filter (UKF) often show instability and inaccuracy when dealing with the highly complex dynamic model of heavy-duty vehicles. In addition, since the dynamic characteristics of heavy-duty vehicles vary significantly under different working conditions and loads, and the fixed noise covariance matrix is ​​difficult to effectively deal with system uncertainty and external disturbances under complex and dynamically changing heavy-duty vehicle working conditions, it is difficult to establish an accurate vehicle dynamics model, and thus it is difficult to obtain accurate vehicle state estimates.

[0003] In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to propose a heavy-load vehicle state estimation method and device, electronic equipment and storage medium, which can effectively improve the accuracy of the heavy-load vehicle state estimation value.

[0005] To achieve the above object, an embodiment of the present application provides a method for estimating a state of a heavy-loaded vehicle, the method comprising the following steps:

[0006] Acquire a heavy-load vehicle parameter, first historical data and first real-time data, wherein the first historical data includes first vehicle historical operating state information and first historical control information, and the first real-time data includes vehicle real-time operating state information;

[0007] Preprocessing the first historical data to obtain second historical data;

[0008] According to the heavy-load vehicle parameters and the second historical data, a nonlinear system dynamics sparse identification algorithm is used to establish a first state transfer equation of a vehicle dynamics model;

[0009] Based on the first state transfer equation and the adaptive extended Kalman filter algorithm, the vehicle state is estimated according to the first real-time data.

[0010] In some embodiments, the preprocessing of the first historical data includes:

[0011] De-noising the first historical data using a weighted average algorithm;

[0012] Performing standardization processing on the first historical data after denoising to obtain second historical operating state information and second historical control information;

[0013] The second historical running state information is derived to obtain third historical running state information.

[0014] In some embodiments, the first state transfer equation of the vehicle dynamics model is established using a nonlinear system dynamics sparse identification algorithm based on the heavy-load vehicle parameters and the second historical data, including:

[0015] Constructing a first space-time matrix according to the second historical operation state information;

[0016] Constructing a second space-time matrix according to the third historical operating state information;

[0017] constructing a third space-time matrix according to the second historical control information;

[0018] Construct a candidate basis function library matrix;

[0019] Constructing a sparse model according to the heavy-load vehicle parameters, the first space-time matrix, the second space-time matrix, the third space-time matrix and the candidate basis function library matrix;

[0020] Determining a sparse solution to the sparse model according to sequential least squares regression;

[0021] According to the sparse solution and the candidate basis function library matrix, a nonlinear system dynamics sparse identification algorithm is adopted to establish a first state transfer equation of a vehicle dynamics model.

[0022] In some embodiments, the first state transfer equation is as follows:

[0023] x k+1 =x k +Δt·Θ(x k ,u k ; μ)Ξ;

[0024] In the formula, x k+1 represents the vehicle state after the transfer, x krepresents the vehicle state before the transfer, Δt represents the time step, Ξ represents the sparse solution, Θ(x k ,u k ; μ) represents the candidate basis function library matrix.

[0025] In some embodiments, the estimating the vehicle state according to the first real-time data based on the first state transfer equation and the adaptive extended Kalman filter algorithm includes:

[0026] Constructing a second state transfer equation for the heavy-duty vehicle according to the first state transfer equation;

[0027] Constructing a measurement equation according to the second state transfer equation;

[0028] Calculating a priori vehicle state estimation according to the second state transfer equation;

[0029] Calculate the Jacobian matrix based on the posterior vehicle state estimate;

[0030] Calculate the state estimation error covariance matrix according to the Jacobi matrix;

[0031] An a posteriori state estimation error covariance matrix and a posteriori vehicle state estimate are calculated based on the first real-time data and the a priori vehicle state estimate.

[0032] In some embodiments, the calculating the a posteriori state estimation error covariance matrix and the a posteriori vehicle state estimation according to the first real-time data and the a priori vehicle state estimation includes:

[0033] Calculating the difference between the first real-time data at a preset time and the prior vehicle state estimate as new information;

[0034] Update the Kalman gain matrix;

[0035] matching an adaptive noise covariance according to the innovation;

[0036] The a posteriori vehicle state estimate is calculated based on the updated Kalman gain matrix and the prior vehicle state estimate, and the a posteriori state estimate error covariance matrix is ​​calculated based on the updated Kalman gain matrix.

[0037] In some embodiments, the calculation formula for the posterior vehicle state estimation is as follows:

[0038]

[0039] In the formula, represents the posterior state estimate at time k, represents the prior state estimate at time k, K k represents the updated Kalman gain matrix, Hm represents the observation matrix, z k represents the measurement equation at time k;

[0040] The calculation formula of the posterior state estimation error covariance matrix is ​​as follows:

[0041]

[0042] In the formula, represents the posterior state estimation error covariance matrix at time k, represents the prior state estimation error covariance matrix at time k, and I represents the unit matrix.

[0043] To achieve the above object, another aspect of the embodiment of the present application provides a heavy-load vehicle state estimation device, the device comprising:

[0044] A first module is used to obtain heavy-load vehicle parameters, first historical data and first real-time data, wherein the first historical data includes first vehicle historical operating state information and first historical control information, and the first real-time data includes vehicle real-time operating state information;

[0045] A second module is used to preprocess the first historical data to obtain second historical data;

[0046] A third module is used to establish a first state transfer equation of a vehicle dynamics model using a nonlinear system dynamics sparse identification algorithm according to the heavy-load vehicle parameters and the second historical data;

[0047] The fourth module is used to estimate the vehicle state according to the first real-time data based on the first state transfer equation and the adaptive extended Kalman filter algorithm.

[0048] To achieve the above object, another aspect of an embodiment of the present application provides an electronic device, including:

[0049] at least one processor;

[0050] at least one memory for storing at least one program;

[0051] When the at least one program is executed by the at least one processor, the at least one processor implements the above method.

[0052] To achieve the above objective, another aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0053] The embodiments of the present application include at least the following beneficial effects: The present application provides a method and device for estimating the state of a heavy-loaded vehicle, an electronic device and a storage medium. The scheme obtains the heavy-loaded vehicle parameters, the first historical data and the first real-time data, and then pre-processes the first historical data to obtain the second historical data. Then, based on the heavy-loaded vehicle parameters and the second historical data, a nonlinear system dynamics sparse identification algorithm is used to establish the first state transfer equation of the vehicle dynamics model, so that a small number of functions that can best explain the dynamics of the vehicle system can be selected from a large number of candidate functions, thereby effectively extracting the features implicit in the data, reducing the complexity and computational burden in the process of establishing the heavy-loaded vehicle dynamics model, and improving the accuracy of the heavy-loaded vehicle dynamics model. Based on the first state transfer equation and the adaptive extended Kalman filter algorithm, the vehicle state is estimated according to the first real-time data, so that the vehicle system can cope with complex and changeable driving environments, thereby effectively improving the accuracy of the heavy-loaded vehicle state estimate. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 is a flow chart of a method for estimating a state of a heavy-loaded vehicle provided in an embodiment of the present application;

[0055] Figure 2 is a schematic diagram of constructing a vehicle dynamics model provided in an embodiment of the present application;

[0056] Figure 3 is a data processing schematic diagram of vehicle state estimation provided by an embodiment of the present application;

[0057] Figure 4 is a structural schematic diagram of a heavy-load vehicle state estimation device provided in an embodiment of the present application;

[0058] Figure 5 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application, they are only examples of devices and methods consistent with some aspects of the embodiments of the present application.

[0060] It is understood that the terms "first", "second", etc. used in this application can be used to describe various concepts in this article, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another concept. For example, without departing from the scope of the embodiment of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determination".

[0061] The terms "at least one", "multiple", "each", "any", etc. used in this application, at least one includes one, two or more, multiple includes two or more, each refers to each of the corresponding multiple, and any refers to any one of the multiple.

[0062] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0063] In the related art, the state estimation methods in the prior art, such as the extended Kalman filter (EKF) and the unscented Kalman filter (UKF), often show instability and inaccuracy when dealing with the highly complex dynamic models of heavy-loaded vehicles under complex road conditions and dynamic load changes. This method relies on the establishment of an accurate vehicle dynamics model, but the dynamic characteristics of heavy-loaded vehicles vary significantly under different working conditions and loads. Moreover, the fixed noise covariance matrix is ​​difficult to effectively deal with system uncertainties and external disturbances under complex and dynamically changing heavy-load vehicle working conditions.

[0064] In view of this, a method and device for estimating the state of a heavy-loaded vehicle, an electronic device and a storage medium are provided in an embodiment of the present application. After obtaining the heavy-loaded vehicle parameters, the first historical data and the first real-time data, the first historical data are pre-processed to obtain the second historical data. Then, based on the heavy-loaded vehicle parameters and the second historical data, a nonlinear system dynamics sparse identification algorithm is used to establish the first state transfer equation of the vehicle dynamics model, so that a small number of functions that can best explain the dynamics of the vehicle system can be selected from a large number of candidate functions, thereby effectively extracting the features implicit in the data, reducing the complexity and computational burden in the process of establishing the heavy-loaded vehicle dynamics model, and improving the accuracy of the heavy-loaded vehicle dynamics model. Based on the first state transfer equation and the adaptive extended Kalman filter algorithm, the vehicle state is estimated according to the first real-time data, so that the vehicle system can cope with complex and changeable driving environments, thereby effectively improving the accuracy of the heavy-loaded vehicle state estimation value.

[0065] The heavy-loaded vehicle state estimation method provided in the embodiment of the present application relates to the field of vehicle data processing technology. The heavy-loaded vehicle state estimation method provided in the embodiment of the present application can be applied to a terminal, can also be applied to a server, and can also be software running in a terminal or a server. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, and a vehicle-mounted terminal, etc., but is not limited to this; the server side can be configured as an independent physical server, or it can be configured as a server cluster or a distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network; the software can be an application that implements the heavy-loaded vehicle state estimation method, etc., but is not limited to the above forms.

[0066] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0067] Figure 1 is an optional flowchart of the heavy-load vehicle state estimation method provided in an embodiment of the present application. Figure 1 The method may include but is not limited to steps S101 to S106.

[0068] Step S110, acquiring the heavy-load vehicle parameters, first historical data and first real-time data, wherein the first historical data includes first vehicle historical operating state information and first historical control information, and the first real-time data includes vehicle real-time operating state information;

[0069] Step S120: preprocess the first historical data to obtain second historical data;

[0070] Step S130, establishing a first state transfer equation of a vehicle dynamics model using a nonlinear system dynamics sparse identification algorithm according to the heavy-load vehicle parameters and the second historical data;

[0071] Step S140: Based on the first state transfer equation and the adaptive extended Kalman filter algorithm, estimate the vehicle state according to the first real-time data.

[0072] It can be understood that the heavy-load vehicle parameters can be expressed by Formula 1:

[0073] μ=[m,l1,l2,k1,k2,I z ] T Formula 1;

[0074] In the formula, m is the vehicle mass, l1 and l2 are the distances from the center of mass of the vehicle to the front axle and the distances to the rear axle, k1 and k2 are the cornering stiffness of the front and rear wheels, and I z is the moment of inertia of the vehicle around the z-axis, and T represents the transpose of the matrix.

[0075] The first vehicle historical operating state information can be expressed by Formula 2, and the first historical control information can be expressed by Formula 3:

[0076] X=[x,y,v,θ,ω] T Formula 2;

[0077] U=[a,δ] T Formula 3;

[0078] In the formula, x and y are the horizontal and vertical coordinates of the vehicle, v is the speed, θ is the yaw angle, ω is the yaw angular velocity, a is the vehicle acceleration, and δ is the front wheel turning angle.

[0079] In the embodiment of the present application, a weighted average algorithm may be used to denoise the first historical data, as specifically shown in Formula 4:

[0080]

[0081] In the formula, k is an integer, which indicates the window size of the moving average; y t+i represents the first historical data at time t+i (historical data before denoising); represents the historical data at time t (historical data after denoising); represents the weight, w i ∈(0,1).

[0082] The denoised historical operating status information is standardized by Formula 5, and the denoised historical control information is standardized by Formula 6:

[0083]

[0084] In the formula, x i ′ represents the standardized historical operation status information (second historical operation status information), u i ′ represents the standardized historical control information (second historical control information), x i Indicates the historical operation status information before standardization, u i Historical control information before standardization, μ x and μ u Respectively represent the mean of historical operation status information and historical control information, σ x and σ u They represent the standard deviation of historical operation status information and historical control information respectively, and n represents the total number of time steps.

[0085] The second historical operation status information is derived by formula 7:

[0086]

[0087] In the formula, Indicates the third historical running status information.

[0088] In the embodiments of the present application, Figure 2 As shown, after the historical data is preprocessed, the first state transfer equation of the vehicle dynamics model is constructed according to the preprocessed historical data. It can be understood that this embodiment establishes the first state transfer equation of the nonlinear system dynamics sparse identification model (SINDy) according to the preprocessed historical data. Specifically, this embodiment includes but is not limited to the following steps:

[0089] Constructing a first space-time matrix according to the second historical operation state information;

[0090] constructing a second space-time matrix according to the third historical operation state information;

[0091] constructing a third space-time matrix according to the second historical control information;

[0092] Construct a candidate basis function library matrix;

[0093] A sparse model is constructed according to the heavy-load vehicle parameters, the first space-time matrix, the second space-time matrix, the third space-time matrix, and the candidate basis function library matrix;

[0094] Determine sparse solutions to sparse models based on sequential least squares regression;

[0095] According to the sparse solution and the candidate basis function library matrix, a nonlinear system dynamics sparse identification algorithm is adopted to establish the first state transfer equation of the vehicle dynamics model.

[0096] It can be understood that the first space-time matrix X is as shown in Formula 8, and the second space-time matrix As shown in Formula 9, the third space-time matrix U is shown in Formula 10:

[0097]

[0098] In the formula, m1 represents the number of vehicle state variables, m2 represents the number of vehicle control inputs, and n represents the total number of time steps.

[0099] In the embodiment of the present application, after obtaining the first space-time matrix X and the second space-time matrix After the third spatiotemporal matrix U is obtained, the candidate basis function library matrix can be constructed based on these matrices. Specifically, when the candidate basis function library matrix is ​​constructed with the first spatiotemporal matrix X, the columns of the matrix are composed of the selected basis function set applied to the data, as shown in Formula 11:

[0100]

[0101] in, It can be expressed as shown in formula 12:

[0102]

[0103] After obtaining the candidate basis function library matrix Θ(X,U;μ) constructed by the first space-time matrix X, the third space-time matrix U and the heavy-duty vehicle parameter μ, combined with the second space-time matrix The sparse regression process is performed with the sparse solution Ξ to obtain the sparse model shown in formula 13:

[0104]

[0105] Specifically, the sparse solution Ξ can be determined by sequential least squares regression. After the sparse solution is obtained, the candidate basis function library matrix Θ(X, U; μ) is combined and the nonlinear system dynamics sparse identification algorithm (SI NDy) is used to establish the first state transfer equation of the vehicle dynamics model shown in Formula 14:

[0106] x k+1 =x k +Δt·Θ(x k ,u k ; μ)Ξ Formula 14;

[0107] In the formula, Δt represents the time step, x k+1 represents the vehicle state after the transfer, x k Indicates the vehicle status before transfer.

[0108] After obtaining the first state transfer equation, the vehicle state is estimated based on the first real-time data combined with the adaptive extended Kalman filter algorithm (AEKF). It can be understood that if Figure 3As shown, this embodiment constructs the second state transfer equation of the heavy-duty vehicle as shown in Formula 15 based on the first state transfer equation:

[0109] x k =f(x k-1 ,u k-1 ,w k-1 )=x k-1 +Δt·Θ(x k-1 ,u k-1 ; μ)Ξ+w k-1 Formula 15;

[0110] The measurement equation shown in Formula 16 is constructed based on the second state transfer equation:

[0111] z k =H m x k +v k Formula 16;

[0112] In the formula, H m Represents the observation matrix, as shown in Formula 17:

[0113]

[0114] In the formula, w~N(0,Q) and v~N(0,R) are process noise and measurement noise respectively. They conform to the normal distribution, with an expected value of 0, and their covariance matrices are Q and R respectively.

[0115] Then set the initial value of the vehicle system. Specifically, set the initial values ​​x0, P0, Q0, and R0. Among them, x0 is the initial state of the vehicle system, P0 is the initial prior state estimation error covariance matrix of the vehicle system, Q0 and R0 are the covariance matrix of process noise and the covariance matrix of observation noise respectively.

[0116] After completing the initial value setting, the prior vehicle state estimate is calculated according to the second state transfer equation Specifically, it can be calculated by formula 18:

[0117]

[0118] In the formula, f is the vehicle dynamics state transfer equation (second state transfer equation) fitted by the nonlinear system dynamics sparse identification algorithm SINDy model.

[0119] The Jacobian matrix is ​​calculated based on the a posteriori vehicle state estimate. Specifically, this embodiment linearizes the nonlinear state space equation (the first state transfer equation) using a first-order Taylor series expansion, as shown in Formula 19, and calculates the Jacobian matrix A according to Formula 20: k :

[0120] x k =f(x k-1 ,u k-1 ,w k-1 )=x k-1 +Δt·Θ(x k-1 ,u k-1 ; μ)Ξ+w k-1 Formula 19;

[0121]

[0122] In the formula, is the posterior state estimate at time k-1, A k It is the Jacobian matrix obtained by taking the partial derivative of f with respect to x at time k.

[0123] The state estimation error covariance matrix is ​​calculated based on the Jacobi matrix, as shown in Formula 21:

[0124]

[0125] In the formula, P k is the covariance matrix of the posterior state estimate at time k.

[0126] Then, the a posteriori state estimation error covariance matrix and the a posteriori vehicle state estimation are calculated based on the first real-time data and the a priori vehicle state estimation. Specifically, this embodiment calculates the difference between the first real-time data and the a priori vehicle state estimation at a preset time as the new information, and after updating the Kalman gain matrix, matches the adaptive noise covariance according to the new information, calculates the a posteriori vehicle state estimation according to the updated Kalman gain matrix and the a priori vehicle state estimation, and calculates the a posteriori state estimation error covariance matrix according to the updated Kalman gain matrix. It can be understood that the calculation process of the new information is as shown in Formula 22:

[0127]

[0128] The update process of the Kalman gain matrix is ​​shown in Formula 23:

[0129] K k =P k - H m T (H m P k - H m T +R k ) Formula 23;

[0130] In the formula, P k -is the covariance matrix of the prior state estimation error.

[0131] The process of adaptive noise covariance matching in real time according to the new information is shown in formula 24:

[0132]

[0133] In the formula, L k is the covariance matrix estimate of the new information at time k, e j is the new information at time step j, that is, the difference between the measured value and the predicted value, and N is the sliding window value.

[0134] The posterior vehicle state estimate is then calculated using Formula 25, and the posterior state estimate error covariance matrix is ​​calculated using Formula 26:

[0135]

[0136] In the formula, represents the posterior state estimate at time k, represents the prior state estimate at time k, K k represents the updated Kalman gain matrix, H m represents the observation matrix, z k represents the measurement equation at time k;

[0137]

[0138] In the formula, represents the posterior state estimation error covariance matrix at time k, represents the prior state estimation error covariance matrix at time k, and I represents the unit matrix.

[0139] From the above content, it can be seen that the embodiment of the present application uses the sparse identification method of nonlinear system dynamics (SINDy) as a data-driven technology, so that a small number of functions that can best explain the system dynamics can be selected from a large number of candidate functions, effectively extracting the features implicit in the data, thereby reducing the complexity and computational burden in the process of establishing a heavy-load vehicle dynamics model. Compared with traditional modeling methods, the embodiment of the present application has higher accuracy under the same complexity. In addition, the vehicle state estimation algorithm based on AEKF in the embodiment of the present application can dynamically control the noise covariance matrix through the residual of the measured value and the estimated value at each time step, so as to cope with more complex and changeable driving environments and improve the accuracy of vehicle state estimation.

[0140] Reference Figure 4 , an embodiment of the present application provides a heavy-load vehicle state estimation device, the device comprising:

[0141] The first module 410 is used to obtain the heavy-load vehicle parameters, first historical data and first real-time data, the first historical data includes first vehicle historical running state information and first historical control information, and the first real-time data includes vehicle real-time running state information;

[0142] The second module 420 is used to pre-process the first historical data to obtain second historical data;

[0143] The third module 430 is used to establish a first state transfer equation of the vehicle dynamics model using a nonlinear system dynamics sparse identification algorithm according to the heavy-load vehicle parameters and the second historical data;

[0144] The fourth module 440 is used to estimate the vehicle state according to the first real-time data based on the first state transfer equation and the adaptive extended Kalman filter algorithm.

[0145] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0146] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned heavy-load vehicle state estimation method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a vehicle-mounted computer, etc.

[0147] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0148] See also Figure 5 , Figure 5 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0149] The processor 510 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0150] The memory 520 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 520 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 520, and the processor 510 calls and executes the heavy-load vehicle state estimation method of the embodiment of this application;

[0151] Input / output interface 530, used to implement information input and output;

[0152] Communication interface 540, used to realize communication interaction between the device and other devices, which can be realized through wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);

[0153] bus 550 , which transmits information between the various components of the device (e.g., processor 510 , memory 520 , input / output interface 530 , and communication interface 540 );

[0154] The processor 510 , the memory 520 , the input / output interface 530 and the communication interface 540 are connected to each other in communication within the device via the bus 550 .

[0155] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned heavy-load vehicle state estimation method is implemented.

[0156] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiments, the functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0157] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0158] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0159] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0160] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0161] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0162] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0163] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0164] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0165] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0166] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0167] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0168] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A method for estimating a heavy-load vehicle state, characterized in that: The method comprises the following steps: Acquire a heavy-load vehicle parameter, first historical data and first real-time data, wherein the first historical data includes first vehicle historical operating state information and first historical control information, and the first real-time data includes vehicle real-time operating state information; Preprocessing the first historical data to obtain second historical data; According to the heavy-load vehicle parameters and the second historical data, a nonlinear system dynamics sparse identification algorithm is used to establish a first state transfer equation of a vehicle dynamics model; Based on the first state transfer equation and the adaptive extended Kalman filter algorithm, the vehicle state is estimated according to the first real-time data.

2. The method according to claim 1, characterized in that The preprocessing of the first historical data includes: De-noising the first historical data using a weighted average algorithm; Performing standardization processing on the first historical data after denoising to obtain second historical operating state information and second historical control information; The second historical running state information is derived to obtain third historical running state information.

3. The method according to claim 2, characterized in that The method of establishing a first state transfer equation of a vehicle dynamics model using a nonlinear system dynamics sparse identification algorithm based on the heavy-load vehicle parameters and the second historical data includes: Constructing a first space-time matrix according to the second historical operation state information; Constructing a second space-time matrix according to the third historical operating state information; constructing a third space-time matrix according to the second historical control information; Construct a candidate basis function library matrix; Constructing a sparse model according to the heavy-load vehicle parameters, the first space-time matrix, the second space-time matrix, the third space-time matrix and the candidate basis function library matrix; Determining a sparse solution to the sparse model according to sequential least squares regression; According to the sparse solution and the candidate basis function library matrix, a nonlinear system dynamics sparse identification algorithm is adopted to establish a first state transfer equation of a vehicle dynamics model.

4. The method according to claim 1, characterized in that: The first state transfer equation is as follows: x k+1 =x k +Δt·Θ(x k ,u k ;m)Ξ; In the formula, x k+1 represents the vehicle state after the transfer, x k represents the vehicle state before the transfer, Δt represents the time step, Ξ represents the sparse solution, Θ(x k ,u k ; μ) represents the candidate basis function library matrix.

5. The method according to claim 1, characterized in that The method of estimating the vehicle state based on the first state transfer equation and the adaptive extended Kalman filter algorithm according to the first real-time data includes: Constructing a second state transfer equation for the heavy-duty vehicle according to the first state transfer equation; Constructing a measurement equation according to the second state transfer equation; Calculating a priori vehicle state estimation according to the second state transfer equation; Calculate the Jacobian matrix based on the posterior vehicle state estimate; Calculate the state estimation error covariance matrix according to the Jacobi matrix; An a posteriori state estimation error covariance matrix and a posteriori vehicle state estimate are calculated based on the first real-time data and the a priori vehicle state estimate.

6. The method according to claim 5, characterized in that The calculating the a posteriori state estimation error covariance matrix and the a posteriori vehicle state estimation according to the first real-time data and the a priori vehicle state estimation comprises: Calculating the difference between the first real-time data at a preset time and the prior vehicle state estimate as new information; Update the Kalman gain matrix; matching an adaptive noise covariance according to the innovation; The a posteriori vehicle state estimate is calculated based on the updated Kalman gain matrix and the prior vehicle state estimate, and the a posteriori state estimate error covariance matrix is ​​calculated based on the updated Kalman gain matrix.

7. The method according to claim 6, characterized in that The calculation formula for the posterior vehicle state estimation is as follows: In the formula, represents the posterior state estimate at time k, represents the prior state estimate at time k, K k represents the updated Kalman gain matrix, H m represents the observation matrix, z k represents the measurement equation at time k; The calculation formula of the posterior state estimation error covariance matrix is ​​as follows: In the formula, represents the posterior state estimation error covariance matrix at time k, represents the prior state estimation error covariance matrix at time k, and I represents the unit matrix.

8. A heavy-load vehicle state estimation device, characterized in that: The device comprises: A first module is used to obtain heavy-load vehicle parameters, first historical data and first real-time data, wherein the first historical data includes first vehicle historical operating state information and first historical control information, and the first real-time data includes vehicle real-time operating state information; A second module is used to preprocess the first historical data to obtain second historical data; A third module is used to establish a first state transfer equation of a vehicle dynamics model using a nonlinear system dynamics sparse identification algorithm according to the heavy-load vehicle parameters and the second historical data; The fourth module is used to estimate the vehicle state according to the first real-time data based on the first state transfer equation and the adaptive extended Kalman filter algorithm.

9. An electronic device, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images