Steer-by-wire variable-steering-ratio design method based on gaussian regression, and system and device

Abstract

A steer-by-wire variable-steering-ratio design method based on Gaussian regression, and a system and a device. The method comprises: establishing a kinetic equation of a steer-by-wire system (101); on the basis of the kinetic equation, solving steering ratio curves at different vehicle speeds (102); optimizing each steering ratio curve, so as to locally minimize the total open-loop variance of the steering ratio curve, and obtaining steering ratio fitness parameters corresponding to a local optimal solution for each vehicle speed (103); using a Gaussian process to perform regression analysis on the steering ratio fitness parameters corresponding to each vehicle speed, so as to obtain a random variable index (104); performing Gaussian process kernel regression simulation on the random variable index, so as to obtain a nonlinear parameter model (105); and on the basis of the nonlinear parameter model, learning a global optimal solution of a steering ratio (106). The steer-by-wire variable-steering-ratio design method based on Gaussian regression improves the robustness and provides a stable and reliable steering ratio under various vehicle conditions, thereby improving the experience of drivers under various vehicle conditions.

Description

Design method, system and equipment for variable transmission ratio of steer-by-wire based on Gaussian regression

[0001] This application claims the benefit of Chinese Patent Application No. 2024101472696, filed on February 2, 2024. The entire text of the aforementioned Chinese Patent Application is incorporated herein by reference. Technical Field

[0002] The present disclosure relates to the technical field of automobile steer-by-wire technology, and in particular to a steer-by-wire variable transmission ratio design method, system, and device based on Gaussian regression. Background Art

[0003] The angular transmission ratio of traditional mechanical steering is fixed and cannot solve the contradiction between "light" and "flexible" steering. The steer-by-wire system eliminates the mechanical connection between the steering wheel and the steering wheel, and can flexibly change the angular transmission ratio according to vehicle conditions to reduce the driver's steering load, thereby improving the vehicle's handling stability.

[0004] Currently, common steer-by-wire variable transmission ratio design methods are primarily based on the "fixed gain method" or the "genetic algorithm." However, these common steer-by-wire variable transmission ratio design methods have the following problems: The "fixed gain method"-based steer-by-wire variable transmission ratio design method has difficulty establishing mathematical models for complex or nonlinear systems, while the "genetic algorithm"-based steer-by-wire variable transmission ratio design method overly relies on the designer's experience and the quality of the data sample. Both the "fixed gain method" and the "genetic algorithm"-based steer-by-wire variable transmission ratio design method have difficulty providing a stable and reliable transmission ratio under special operating conditions.

[0005] Summary of the Invention

[0006] The technical problem to be solved by the present disclosure is to overcome the above-mentioned defects in the prior art and provide a method, system and device for designing a variable transmission ratio of wire-controlled steering based on Gaussian regression.

[0007] The present disclosure solves the above technical problems through the following technical solutions:

[0008] In a first aspect, a method for designing a steer-by-wire variable transmission ratio based on Gaussian regression is provided, comprising:

[0009] Establish the dynamic equations of the steer-by-wire system;

[0010] solving a transmission ratio curve according to the dynamic equation;

[0011] Optimizing each transmission ratio curve to minimize the total open-loop variance of the transmission ratio curve locally, and obtaining a transmission ratio fitness parameter corresponding to a local optimal solution for each vehicle speed;

[0012] Performing regression analysis on the transmission ratio fitness parameters corresponding to each vehicle speed using a Gaussian process to obtain a random variable index;

[0013] Performing a Gaussian process kernel regression simulation on the random variable exponent to obtain a nonlinear parameter model;

[0014] A global optimal solution for the transmission ratio is learned based on the nonlinear parameter model.

[0015] Optionally, a dynamic equation of the steer-by-wire system is established, including:

[0016] Establish the dynamic equations of the steer-by-wire system based on the two-degree-of-freedom model;

[0017] The kinetic equation is expressed as follows:

[0018] Among them, k f is the cornering stiffness of the front axle, k r is the cornering stiffness of the rear axle, β is the center of mass side slip angle, u is the x-axis component velocity, a is the front wheelbase, b is the rear wheelbase, ω r is the yaw rate, θ is the front wheel angle, m is the vehicle mass, v′ is the differential value of the vehicle speed, I z is the moment of inertia.

[0019] Optionally, solving the transmission ratio curve according to the dynamic equation includes:

[0020] A transmission ratio curve corresponding to the dynamic equation is solved based on a fixed gain method.

[0021] Optionally, solving the transmission ratio curve corresponding to the dynamic equation based on a fixed gain method includes:

[0022] Obtaining a yaw rate formula and a lateral acceleration formula of the steer-by-wire system according to the dynamic equation;

[0023] Determining the ratio of the yaw rate formula to the steering wheel angle as a steady-state yaw rate gain formula, and solving for a first ideal transmission ratio based on the yaw rate while keeping the steady-state yaw rate gain formula unchanged;

[0024] Determining the ratio of the lateral acceleration formula to the steering wheel angle as a steady-state lateral acceleration gain formula, and solving for a second ideal transmission ratio based on the ideal transmission ratio of the lateral acceleration while keeping the steady-state lateral acceleration gain formula unchanged;

[0025] The transmission ratio curve is determined according to a weighted result of the first ideal transmission ratio and the second ideal transmission ratio.

[0026] Optionally, the yaw angular velocity formula is expressed as follows:

[0027] Substitute the yaw rate formula into formula a y =v′+uω r , we get the lateral acceleration formula:

[0028] The first ideal transmission ratio is expressed as follows:

[0029] The second ideal transmission ratio is expressed as follows:

[0030] Among them, K w represents a positive scalable quantity describing the vehicle's driving sensitivity, K ay represents a positive scalable quantity that describes the stability performance of the vehicle.

[0031] Optionally, optimizing the transmission ratio curve to minimize the total open-loop variance of the transmission ratio curve locally and obtaining a transmission ratio fitness parameter of a local optimal solution includes:

[0032] The open-loop total variance formula of the transmission ratio curve is calculated according to the dynamic open-loop total variance evaluation method;

[0033] According to the genetic algorithm, the open-loop total variance formula is used as the fitness function, and the transmission ratio curve at each vehicle speed is optimized to make the open-loop total variance locally minimized, thereby obtaining the transmission ratio fitness parameter.

[0034] Optionally, the open-loop total variance formula is expressed as follows:

[0035] Among them, J e1 is the trajectory tracking quality indicator, J e2 is the direction error index, J b1 There are three indicators for the driver's burden, ω1 is J e1 The weighted proportional coefficient of J e2 The weighted proportional coefficient of J b1 The weighted proportional coefficient of J e2 The vehicle's radial velocity and the X-axis component of the vehicle's radial velocity are used to obtain J b1 Measured by the heaviness of the steering wheel.

[0036] Optionally, a Gaussian process is used to perform regression analysis on the transmission ratio fitness parameters corresponding to each vehicle speed to obtain a random variable index, including:

[0037] Gaussian process prior regression analysis is performed on the transmission ratio fitness parameters corresponding to each vehicle speed, and the random vector X=[x1,x2…,x n ] obeys the multivariate Gaussian distribution X~N(μ,∑), where X1=[x1,…,x m ] is the observed vector, X2=[x m+1 ,…,x n ] is the random variable index, then Then we get: n is the feature dimension in the time series, x1, x2…, x n is the feature sample on the corresponding dimension, X conforms to the normal distribution, μ is the mean vector, and ∑ is the covariance matrix;

[0038] Posterior distribution of X1 and X2: μ 2|1 =μ2+∑21∑11(X1-μ1), ∑2|1=∑22-∑21∑11∑12, and the probability of X2 and the predicted probability matrix are obtained.

[0039] Optionally, performing a Gaussian process kernel regression simulation on the random variable exponent to obtain a nonlinear parameter model includes:

[0040] Resample X2 and perform Gaussian process kernel regression simulation on the random variable of the resampled X2 to obtain a nonlinear parameter model. The formula for selecting the radial basis function and X by the Gaussian process kernel is as follows:

[0041] ti、t j is the dimensional index of the time series, U and S are obtained by singular value decomposition of the covariance matrix ∑, and y is a vector of n random variables generated by ∑.

[0042] In a second aspect, a steer-by-wire variable transmission ratio design system based on Gaussian regression is provided, comprising:

[0043] Establish a module for establishing the dynamic equations of the steer-by-wire system;

[0044] A curve solving module, used for solving a transmission ratio curve according to the dynamic equation;

[0045] a fitness parameter calculation module, configured to optimize each transmission ratio curve so as to locally minimize the total open-loop variance of the transmission ratio curve and obtain a transmission ratio fitness parameter corresponding to a local optimal solution for each vehicle speed;

[0046] An index calculation module, configured to perform regression analysis on the transmission ratio fitness parameters corresponding to each vehicle speed using a Gaussian process to obtain a random variable index;

[0047] A model calculation module is used to perform a Gaussian process kernel regression simulation on the random variable index to obtain a nonlinear parameter model;

[0048] The optimal solution solving module is used to learn the global optimal solution of the transmission ratio based on the nonlinear parameter model.

[0049] In a third aspect, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and for running on the processor, wherein when the processor executes the computer program, the Gaussian regression-based variable transmission ratio design method for wire-controlled steering described in any one of the first aspects is implemented.

[0050] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the Gaussian regression-based variable transmission ratio design method for wire-controlled steering described in any one of the first aspects is implemented.

[0051] In a fifth aspect, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the Gaussian regression-based steer-by-wire variable transmission ratio design method as described in any one of the first aspects.

[0052] On the basis of conforming to the common sense in this field, the above-mentioned preferred conditions can be arbitrarily combined to obtain the preferred embodiments of the present disclosure.

[0053] The positive progressive effect of the present disclosure is that the present disclosure improves the robustness through the wire-controlled steering variable transmission ratio design method based on Gaussian regression, provides a stable and reliable transmission ratio under various vehicle conditions, and thus improves the driver's experience under various vehicle conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] FIG1 is a flow chart of a Gaussian regression-based design method for a steer-by-wire variable transmission ratio according to an exemplary embodiment of the present disclosure;

[0055] FIG2 is a flowchart of step 102 in FIG1 ;

[0056] FIG3 is a flowchart of step 103 in FIG1 ;

[0057] FIG4 is a control principle diagram provided by an exemplary embodiment of the present disclosure;

[0058] FIG5 is a comparison diagram of a variable transmission ratio curve provided by an exemplary embodiment of the present disclosure;

[0059] FIG6 is a comparison diagram of yaw rate curves of a real vehicle provided by an exemplary embodiment of the present disclosure;

[0060] FIG7 is a module diagram of a steer-by-wire variable transmission ratio design system based on Gaussian regression provided by an exemplary embodiment of the present disclosure;

[0061] FIG8 is a schematic structural diagram of an electronic device provided by an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0062] The present disclosure is further illustrated below by way of examples, but the present disclosure is not limited to the scope of the examples.

[0063] In the embodiments of the present disclosure, prefixes such as "first" and "second" are used only to distinguish different description objects, and have no limiting effect on the position, order, priority, quantity or content of the described objects. In the embodiments of the present disclosure, the use of prefixes such as ordinal numbers to distinguish description objects does not constitute a limitation on the described objects. For the statement of the described objects, please refer to the description in the context of the claims or embodiments, and no unnecessary limitations should be constituted due to the use of such prefixes. In addition, in the description of this embodiment, unless otherwise specified, the meaning of "plurality" is two or more.

[0064] FIG1 is a flow chart of a Gaussian regression-based design method for a steer-by-wire variable transmission ratio according to an exemplary embodiment of the present disclosure. The method comprises the following steps:

[0065] Step 101: Establish a dynamic equation of a steer-by-wire system.

[0066] The vehicle's steer-by-wire system mainly consists of a steering wheel module, a front-wheel steering module, a main controller, etc.

[0067] Step 102: Solve the transmission ratio curve according to the dynamic equation.

[0068] The transmission ratio curve can be a transmission ratio curve at different vehicle speeds. The number of vehicle speeds matches the number of transmission ratio curves and can be set according to actual needs.

[0069] It should be noted that the transmission ratio curve represents the correspondence between the transmission ratio and parameters such as the lateral stiffness of the front axle, the lateral stiffness of the rear axle, the x-axial component speed, the front wheelbase, the rear wheelbase, and the vehicle mass. The transmission ratio curve is not limited to being represented in the form of a curve, but can also be represented in the form of a formula.

[0070] Step 103 : Optimize each transmission ratio curve to minimize the total open-loop variance of the transmission ratio curve locally, and obtain the transmission ratio fitness parameter corresponding to the local optimal solution for each vehicle speed.

[0071] By minimizing the total open-loop variance of the transmission ratio curve locally, a robust transmission ratio fitness parameter can be obtained, thereby improving handling stability. The value range of the transmission ratio fitness parameter is [0, 1].

[0072] Step 104 : Use a Gaussian process to perform regression analysis on the transmission ratio fitness parameters corresponding to each vehicle speed to obtain a random variable index.

[0073] Step 105: Perform a Gaussian process kernel regression simulation on the random variable exponent to obtain a nonlinear parameter model.

[0074] Step 106: Learn the global optimal solution of the transmission ratio based on the nonlinear parameter model.

[0075] In one embodiment, all inputs required for variable transmission ratio design can be obtained based on the two-degree-of-freedom model. In step 101, the dynamic equations of the steer-by-wire system are established based on the two-degree-of-freedom model. In other implementations, other models can also be used to establish the dynamic equations of the steer-by-wire system.

[0076] The dynamic equations of the two-degree-of-freedom model are expressed as follows:

[0077] Among them, k f is the cornering stiffness of the vehicle’s front axle, k r is the cornering stiffness of the rear axle of the vehicle, β is the center of mass side slip angle, u is the x-axis component velocity, a is the front wheelbase, b is the rear wheelbase, ω r is the yaw rate, θ is the front wheel angle, m is the vehicle mass, v′ is the differential value of the vehicle speed v, I z is the moment of inertia.

[0078] In one embodiment, in step 102 , a transmission ratio curve corresponding to the dynamic equation is solved based on a fixed gain method.

[0079] The following describes an implementation method for solving the transmission ratio curve. Referring to FIG2 , the steps for solving the transmission ratio curve corresponding to the dynamic equation based on the fixed gain method include:

[0080] Step 102-1: Obtain the yaw rate formula and lateral acceleration formula of the steer-by-wire system according to the dynamic equation.

[0081] According to the simplified dynamic equation, the yaw rate formula of the steer-by-wire system is expressed as follows:

[0082] In this embodiment, the steady-state lateral acceleration gain formula is derived from the lateral acceleration, and the transmission ratio curve is derived from the yaw rate gain formula and the control target with the lateral acceleration gain formula unchanged. Therefore, the yaw rate formula is substituted into formula a. y =v′+uω r , we get the lateral acceleration formula:

[0083] Step 102-2: Determine the ratio of the yaw rate formula to the steering wheel angle as the steady-state yaw rate gain formula, and solve for the first ideal transmission ratio based on the yaw rate while keeping the steady-state yaw rate gain formula unchanged.

[0084] The steady-state yaw rate gain formula can be expressed as follows:

[0085] G h =ω r / θ h ;

[0086] Among them, G h is the steady-state yaw rate gain formula; θ h is the steering wheel angle.

[0087] According to the two-degree-of-freedom model, the gain from the front wheel angle θ to the yaw rate can be obtained:

[0088] G f =ω r / θ;

[0089] Since the first ideal transmission ratio I based on the yaw angular velocity w =G f / G h ;

[0090] The steady-state yaw rate gain formula can be transformed into:

[0091] Let the steady-state yaw rate gain formula G h =K w The first ideal transmission ratio based on yaw rate is expressed as follows:

[0092] Among them, K w It is a positive scalable quantity that describes the vehicle's driving sensitivity, and its value range is [0.16, 0.65].

[0093] Step 102-3: Determine the ratio of the lateral acceleration formula to the steering wheel angle as the steady-state lateral acceleration gain formula, and while keeping the steady-state lateral acceleration gain formula unchanged, solve for the second ideal transmission ratio based on the ideal transmission ratio of the lateral acceleration.

[0094] The steady-state lateral acceleration gain formula can be expressed as follows:

[0095] G ay =a y / θ h ;

[0096] In steady state, let a y =v′+uω r v′=0, the steady-state lateral acceleration gain formula can be expressed as:

[0097] The first ideal transmission ratio I based on lateral acceleration a =G f / G ay , where I a and I w They represent the transmission ratios at steady-state yaw rate and steady-state lateral acceleration, respectively, which can be regarded as the transmission ratio I. Here, I a Just to distinguish the transmission ratio in the two states, I is used a Replace I W To do the calculation.

[0098] Let the steady-state lateral acceleration gain formula G ay =K ay Keeping it unchanged, the second ideal transmission ratio based on lateral acceleration can be expressed as follows:

[0099] Among them, K ay is a positive scalable quantity that describes the stability performance of vehicle driving, and its value range is [4,8].

[0100] Step 102-4: Determine a transmission ratio curve according to a weighted result of the first ideal transmission ratio and the second ideal transmission ratio.

[0101] The weighted results are expressed as follows:

[0102] I=K w I w +C a I a ;

[0103] C w +C a =1;

[0104] Among them, C w Represents the weighted proportional coefficient of the first ideal transmission ratio, C a Indicates the weighted proportional coefficient of the second ideal transmission ratio.

[0105] C w and Ca You can set it according to your actual needs, that is, whether you want the yaw rate to be more stable or the lateral acceleration to be more stable, which depends on the preferences of the debugger and the user. For example, C w The value range is [25%, 35%].

[0106] In one embodiment, referring to FIG3 , step 103 includes:

[0107] Step 103 - 1 : Calculate the open-loop total variance formula of the transmission ratio curve according to the dynamic open-loop total variance evaluation method.

[0108] The open-loop total variance formula is expressed as follows:

[0109] Among them, J e1 is the trajectory tracking quality indicator, J e2 is the direction error index, J b1 There are three indicators for the driver's burden, ω1 is J e1 The weighted proportional coefficient of J e2 The weighted proportional coefficient of J b1 The weighted proportional coefficient of J e2 The vehicle's radial velocity and the X-axis component of the vehicle's radial velocity are used to obtain J b1 Measured by the heaviness of the steering wheel. ω3 is greater than or equal to 50%. The range of the weighted proportional coefficient is [0,1)

[0110] The open-loop total variance formula is an open-loop calculation of the population variance, which can be solved to obtain the mean variance.

[0111] In this embodiment, a dynamic filtering model is calculated based on the three indicators of the open-loop total variance, and an optimized transmission ratio curve can be fitted.

[0112] Step 103-2: Using the genetic algorithm and the open-loop total variance formula as the fitness function, the transmission ratio curve at each vehicle speed is optimized to minimize the open-loop total variance locally, thereby obtaining the transmission ratio fitness parameter.

[0113] By locally minimizing the total open-loop variance of the transmission ratio curve, a transmission ratio fitness parameter with high robustness can be obtained, thereby improving handling stability.

[0114] In one embodiment, step 104 includes:

[0115] Step 104-1: Gaussian process prior regression analysis is performed on the transmission ratio fitness parameters corresponding to each vehicle speed. Let the random vector X = [x1, x2…, x n ] obeys the multivariate Gaussian distribution X~N(μ,∑), where X1=[x1,…,x m] is the observed vector (observed index), X2=[x m+1 ,…,x n ] is the random variable index (unknown variable), then Then we get: n is the feature dimension in the time series, x1, x2…, x n is the feature sample on the corresponding dimension, X conforms to the normal distribution, μ is the mean vector, and ∑ is the covariance matrix.

[0116] The random variable exponent is a variable coefficient. The distance is a random selection of 100 values ​​from the variable ratio curve, with a fixed step size. The mean vector represents the average value of each feature in the dataset, where each element corresponds to the mean of the feature.

[0117] Step 104-2: Calculate the posterior distribution of X1 and X2: μ 2|1 =μ2+∑21∑11(X1-μ1), ∑2|1=∑22-∑21∑11∑12, and the probability of X2 and the predicted probability matrix are obtained.

[0118] In one embodiment, step 105 includes: resampling X2, and performing Gaussian process kernel regression simulation on the random variable of X2 obtained by resampling to obtain a nonlinear parameter model and model output samples; Gaussian process kernel selection radial basis function and X o The formula is as follows:

[0119] Among them, t i , t j is the dimensional index on the time series, U and S are obtained by singular value decomposition of the covariance matrix ∑, y is a vector of n random variables generated by ∑, and σ is a constant parameter that can be calibrated.

[0120] FIG4 is a control principle diagram provided by an exemplary embodiment of the present disclosure, wherein the transmission ratio I′ calculated by the ideal two-degree-of-freedom model is obtained, and the transmission ratio I′ calculated by the genetic algorithm is inferred based on the transmission ratio fitness parameter obtained by the genetic algorithm. * , convert I' and I * Input the Gaussian regression model to obtain the optimal solution transmission ratio I, and further obtain the front wheel angle θ f and front wheel angle compensation value θ f Input the ideal two-degree-of-freedom model to obtain the ideal yaw angular velocity ω * r , ideal lateral acceleration a * y , and then according to ω * r 、a* y , true yaw rate ω r , true lateral acceleration a y Based on the comprehensive feedback strategy, Δω and Δθ are obtained, and the actual front wheel steering angle θ of the vehicle is combined spd The comprehensive compensation strategy is used to perform closed-loop control on relevant vehicle signals, such as PID control of the yaw rate and superimposing the obtained compensation angles.

[0121] Figure 5 shows a comparison of transmission ratio curves obtained by different methods. It can be seen from the figure that compared with the transmission ratio curves obtained based on constant yaw angular velocity, constant lateral acceleration, and genetic algorithm, the transmission ratio curve obtained by Gaussian regression of the embodiment of the present disclosure is closer to the ideal value when the vehicle speed is higher and is more stable, which proves the reliability of the algorithm of this embodiment.

[0122] Figure 6 shows a comparison of the yaw rate curves obtained using an embodiment of the present disclosure and the yaw rate actually measured by the sensor. The graph shows a close similarity between the two, demonstrating the high accuracy and reliability of the algorithm in this embodiment. Similar to the aforementioned Gaussian regression-based steer-by-wire variable transmission ratio design method embodiment, this disclosure also provides an embodiment of a Gaussian regression-based steer-by-wire variable transmission ratio design system.

[0123] FIG7 is a schematic diagram of a module of a steer-by-wire variable transmission ratio design system based on Gaussian regression according to an exemplary embodiment of the present disclosure. The system includes:

[0124] Establishing module 71 for establishing dynamic equations of the steer-by-wire system;

[0125] a curve solving module 72 for solving a transmission ratio curve according to the dynamic equation;

[0126] a fitness parameter calculation module 73 for optimizing each transmission ratio curve so as to locally minimize the total open-loop variance of the transmission ratio curve and obtain a transmission ratio fitness parameter corresponding to a local optimal solution for each vehicle speed;

[0127] An index calculation module 74 is configured to perform a regression analysis on the transmission ratio fitness parameters corresponding to each vehicle speed using a Gaussian process to obtain a random variable index;

[0128] A model calculation module 75 is used to perform a Gaussian process kernel regression simulation on the random variable index to obtain a nonlinear parameter model;

[0129] The optimal solution solving module 76 is used to learn the global optimal solution of the transmission ratio based on the nonlinear parameter model.

[0130] Optionally, the establishment module is specifically used to:

[0131] Establish the dynamic equations of the steer-by-wire system based on the two-degree-of-freedom model;

[0132] The kinetic equation is expressed as follows:

[0133] Among them, k f is the cornering stiffness of the front axle, k r is the cornering stiffness of the rear axle, β is the center of mass side slip angle, u is the x-axis component velocity, a is the front wheelbase, b is the rear wheelbase, ω r is the yaw rate, θ is the front wheel angle, m is the vehicle mass, v′ is the differential value of the vehicle speed, I z is the moment of inertia.

[0134] Optionally, the curve solving module is specifically used to:

[0135] A transmission ratio curve corresponding to the dynamic equation is solved based on a fixed gain method.

[0136] Optionally, the curve solving module is specifically used to:

[0137] Obtaining a yaw rate formula and a lateral acceleration formula of the steer-by-wire system according to the dynamic equation;

[0138] Determining the ratio of the yaw rate formula to the steering wheel angle as a steady-state yaw rate gain formula, and solving for a first ideal transmission ratio based on the yaw rate while keeping the steady-state yaw rate gain formula unchanged;

[0139] Determining the ratio of the lateral acceleration formula to the steering wheel angle as a steady-state lateral acceleration gain formula, and solving for a second ideal transmission ratio based on the ideal transmission ratio of the lateral acceleration while keeping the steady-state lateral acceleration gain formula unchanged;

[0140] The transmission ratio curve is determined according to a weighted result of the first ideal transmission ratio and the second ideal transmission ratio.

[0141] Optionally, the yaw angular velocity formula is expressed as follows:

[0142] Substitute the yaw rate formula into formula a y =v′+uω r , we get the lateral acceleration formula:

[0143] The first ideal transmission ratio is expressed as follows:

[0144] The second ideal transmission ratio is expressed as follows:

[0145] Among them, K w represents a positive scalable quantity describing the vehicle's driving sensitivity, K ay represents a positive scalable quantity that describes the stability performance of the vehicle.

[0146] Optionally, the fitness parameter calculation module is specifically used to:

[0147] The open-loop total variance formula of the transmission ratio curve is calculated according to the dynamic open-loop total variance evaluation method;

[0148] According to the genetic algorithm, the open-loop total variance formula is used as the fitness function, and the transmission ratio curve at each vehicle speed is optimized to make the open-loop total variance locally minimized, thereby obtaining the transmission ratio fitness parameter.

[0149] Optionally, the open-loop total variance formula is expressed as follows:

[0150] Among them, J e1 is the trajectory tracking quality indicator, J e2 is the direction error index, J b1 There are three indicators for the driver's burden, ω1 is J e1 The weighted proportional coefficient of J e2 The weighted proportional coefficient of J b1 The weighted proportional coefficient of J e2 The vehicle's radial velocity and the X-axis component of the vehicle's radial velocity are used to obtain J b1 Measured by the heaviness of the steering wheel.

[0151] Optionally, the index calculation module is used to:

[0152] Gaussian process prior regression analysis is performed on the transmission ratio fitness parameters corresponding to each vehicle speed, and the random vector X=[x1,x2…,x n ] obeys the multivariate Gaussian distribution X~N(μ,∑), where X1=[x1,…,x m ] is the observed vector, X2=[x m+1 ,…,x n ] is the random variable index, then Then we get: n is the feature dimension in the time series, x1, x2…, x n is the feature sample on the corresponding dimension, X conforms to the normal distribution, μ is the mean vector, and ∑ is the covariance matrix;

[0153] Posterior distribution of X1 and X2: μ 2|1=μ2+∑21∑11(X1-μ1), ∑2|1=∑22-∑21∑11∑12, and the probability of X2 and the predicted probability matrix are obtained.

[0154] Optionally, the model calculation module is specifically used to:

[0155] Resample X2 and perform Gaussian process kernel regression simulation on the random variable of the resampled X2 to obtain a nonlinear parameter model. The formula for selecting the radial basis function and X by the Gaussian process kernel is as follows:

[0156] t i , t j is the dimensional index of the time series, U and S are obtained by singular value decomposition of the covariance matrix ∑, and y is a vector of n random variables generated by ∑.

[0157] Since the system embodiments generally correspond to the method embodiments, reference will be made to the description of the method embodiments for relevant details. The system embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separate, and the components of the units may or may not be physical units, i.e., they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the disclosed solution.

[0158] Figure 8 is a schematic diagram of an electronic device according to an exemplary embodiment of the present disclosure. The electronic device includes a memory, a processor, and a computer program stored in the memory and executed on the processor. When the processor executes the computer program, it implements the Gaussian regression-based steer-by-wire variable transmission ratio design method described in any of the aforementioned embodiments. The electronic device 80 shown in Figure 8 is merely an example and should not limit the functionality or scope of application of the embodiments of the present disclosure.

[0159] As shown in FIG8 , electronic device 80 may be implemented as a general-purpose computing device, such as a server device. Components of electronic device 80 may include, but are not limited to, at least one processor 81, at least one memory 82, and a bus 83 connecting various system components (including memory 82 and processor 81).

[0160] The bus 83 includes a data bus, an address bus, and a control bus.

[0161] The memory 82 may include a volatile memory, such as a random access memory (RAM) 821 and / or a cache memory 822 , and may further include a read-only memory (ROM) 823 .

[0162] The memory 82 may also include a program tool 825 (or utility) having a set (at least one) of program modules 824, such program modules 824 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0163] The processor 81 executes various functional applications and data processing by running the computer program stored in the memory 82, such as the Gaussian regression-based steer-by-wire variable transmission ratio design method provided in any of the above embodiments.

[0164] The electronic device 80 can also communicate with one or more external devices 84 (e.g., a keyboard, pointing device, etc.). Such communication can occur via an input / output (I / O) interface 85. Furthermore, the electronic device 80 can communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 86. As shown, the network adapter 86 communicates with other modules of the electronic device 80 via a bus 83. It should be understood that, although not shown, other hardware and / or software modules can be used in conjunction with the electronic device 80, including but not limited to microcode, device drivers, redundant processors, external disk drive arrays, RAID (RAID) systems, tape drives, and data backup storage systems.

[0165] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided and embodied by multiple units / modules.

[0166] An embodiment of the present disclosure further provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the Gaussian regression-based variable transmission ratio design method for wire-controlled steering provided in any of the above embodiments is implemented.

[0167] The readable storage medium may include, but is not limited to, a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0168] An embodiment of the present disclosure further provides a computer program product, comprising a computer program, which, when executed by a processor, implements any of the above-mentioned methods for designing variable transmission ratios of steer-by-wire based on Gaussian regression.

[0169] The program code for executing the computer program product of the present disclosure may be written in any combination of one or more programming languages, and the program code may be executed entirely on the user device, partially on the user device, as a standalone software package, partially on the user device and partially on a remote device, or entirely on the remote device.

[0170] Although the specific embodiments of the present disclosure have been described above, those skilled in the art will appreciate that these are merely illustrative and that various changes or modifications may be made to these embodiments without departing from the principles and essence of the present disclosure. Therefore, the scope of protection of the present disclosure is defined by the appended claims.

Claims

1. A steer-by-wire variable transmission ratio design method based on Gaussian regression, characterized in that: include: Establish the dynamic equations of the steer-by-wire system; solving a transmission ratio curve according to the dynamic equation; Optimizing each transmission ratio curve to minimize the total open-loop variance of the transmission ratio curve locally, and obtaining a transmission ratio fitness parameter corresponding to a local optimal solution for each vehicle speed; Performing regression analysis on the transmission ratio fitness parameters corresponding to each vehicle speed using a Gaussian process to obtain a random variable index; Performing a Gaussian process kernel regression simulation on the random variable exponent to obtain a nonlinear parameter model; A global optimal solution for the transmission ratio is learned based on the nonlinear parameter model.

2. The Gaussian regression-based steer-by-wire variable transmission ratio design method according to claim 1, characterized in that: Establish the dynamic equations of the steer-by-wire system, including: Establish the dynamic equations of the steer-by-wire system based on the two-degree-of-freedom model; The kinetic equation is expressed as follows: Among them, k f is the cornering stiffness of the front axle, k r is the cornering stiffness of the rear axle, β is the center of mass side slip angle, u is the x-axis component velocity, a is the front wheelbase, b is the rear wheelbase, ω r is the yaw rate, θ is the front wheel angle, m is the vehicle mass, v′ is the differential value of the vehicle speed, I z is the moment of inertia.

3. The Gaussian regression-based steer-by-wire variable transmission ratio design method according to claim 1, characterized in that: Solving the transmission ratio curve according to the dynamic equation includes: A transmission ratio curve corresponding to the dynamic equation is solved based on a fixed gain method.

4. The Gaussian regression-based steer-by-wire variable transmission ratio design method according to claim 3, characterized in that: Solving the transmission ratio curve corresponding to the dynamic equation based on the fixed gain method includes: Obtaining a yaw rate formula and a lateral acceleration formula of the steer-by-wire system according to the dynamic equation; Determining the ratio of the yaw rate formula to the steering wheel angle as a steady-state yaw rate gain formula, and solving for a first ideal transmission ratio based on the yaw rate while keeping the steady-state yaw rate gain formula unchanged; Determining the ratio of the lateral acceleration formula to the steering wheel angle as a steady-state lateral acceleration gain formula, and solving for a second ideal transmission ratio based on the ideal transmission ratio of the lateral acceleration while keeping the steady-state lateral acceleration gain formula unchanged; The transmission ratio curve is determined according to a weighted result of the first ideal transmission ratio and the second ideal transmission ratio.

5. The Gaussian regression-based steer-by-wire variable transmission ratio design method according to claim 4, characterized in that: The yaw rate formula is as follows: Substitute the yaw rate formula into formula a y =v′+uω r , we get the lateral acceleration formula: The first ideal transmission ratio is expressed as follows: The second ideal transmission ratio is expressed as follows: Among them, K w represents a positive scalable quantity describing the vehicle's driving sensitivity, K ay represents a positive scalable quantity that describes the stability performance of the vehicle.

6. The Gaussian regression-based steer-by-wire variable transmission ratio design method according to claim 1, characterized in that: The transmission ratio curve is optimized to minimize the total open-loop variance of the transmission ratio curve locally, and the transmission ratio fitness parameter of the local optimal solution is obtained, including: The open-loop total variance formula of the transmission ratio curve is calculated according to the dynamic open-loop total variance evaluation method; According to the genetic algorithm, the open-loop total variance formula is used as the fitness function, and the transmission ratio curve at each vehicle speed is optimized to make the open-loop total variance locally minimized, thereby obtaining the transmission ratio fitness parameter.

7. The Gaussian regression-based steer-by-wire variable transmission ratio design method according to claim 6, characterized in that: The open-loop total variance formula is expressed as follows: Among them, J e1 is the trajectory tracking quality indicator, J e2 is the direction error index, J b1 There are three indicators for the driver's burden, ω1 is J e1 The weighted proportional coefficient of J e2 The weighted proportional coefficient of J b1 The weighted proportional coefficient of J e2 The vehicle's radial velocity and the X-axis component of the vehicle's radial velocity are used to obtain J b1 Measured by the heaviness of the steering wheel.

8. The Gaussian regression-based steer-by-wire variable transmission ratio design method according to claim 1, characterized in that: A Gaussian process is used to perform regression analysis on the transmission ratio fitness parameters corresponding to each vehicle speed to obtain random variable indices, including: Gaussian process prior regression analysis is performed on the transmission ratio fitness parameters corresponding to each vehicle speed, and the random vector X=[x1,x2…,x n ] obeys the multivariate Gaussian distribution X~N(μ,∑), where X1=[x1,…,x m ] is the observed vector, X2=[x m+1 ,…,x n ] is the random variable index, then Then we get: n is the feature dimension in the time series, x1, x2…, x n is the feature sample on the corresponding dimension, X conforms to the normal distribution, μ is the mean vector, and ∑ is the covariance matrix; Posterior distribution of X1 and X2: μ 2|1 =μ2+∑21∑11(X1-μ1), ∑2|1=∑22-∑21∑11∑12, and the probability of X2 and the predicted probability matrix are obtained.

9. The Gaussian regression-based steer-by-wire variable transmission ratio design method according to claim 8, characterized in that: Performing a Gaussian process kernel regression simulation on the random variable index to obtain a nonlinear parameter model, including: Resample X2 and perform Gaussian process kernel regression simulation on the random variable of the resampled X2 to obtain a nonlinear parameter model. The formula for selecting the radial basis function and X by the Gaussian process kernel is as follows: t i , t j is the dimensional index of the time series, U and S are obtained by singular value decomposition of the covariance matrix ∑, and y is a vector of n random variables generated by ∑.

10. A steer-by-wire variable transmission ratio design system based on Gaussian regression, characterized in that: include: Establish a module for establishing the dynamic equations of the steer-by-wire system; A curve solving module, used for solving a transmission ratio curve according to the dynamic equation; a fitness parameter calculation module, configured to optimize each transmission ratio curve so as to locally minimize the total open-loop variance of the transmission ratio curve and obtain a transmission ratio fitness parameter corresponding to a local optimal solution for each vehicle speed; An index calculation module, configured to perform regression analysis on the transmission ratio fitness parameters corresponding to each vehicle speed using a Gaussian process to obtain a random variable index; A model calculation module is used to perform a Gaussian process kernel regression simulation on the random variable index to obtain a nonlinear parameter model; The optimal solution solving module is used to learn the global optimal solution of the transmission ratio based on the nonlinear parameter model.

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and configured to run on the processor, wherein: When the processor executes the computer program, the Gaussian regression-based steer-by-wire variable transmission ratio design method according to any one of claims 1 to 9 is implemented.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the Gaussian regression-based steer-by-wire variable transmission ratio design method according to any one of claims 1 to 9 is implemented.

13. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the Gaussian regression-based steer-by-wire variable transmission ratio design method according to any one of claims 1 to 9 is implemented.

Images