Vehicle mass center side slip angle calculation method and device, electronic equipment and storage medium

Abstract

The application discloses a vehicle centroid side slip angle calculation method and device, electronic equipment and a storage medium. According to the importance evaluation score of the first running parameter of the vehicle, a first feature set is selected. After a centroid side slip angle calculation model is trained according to the first feature set, the lateral acceleration of the vehicle to be measured, the steering wheel rotation angle and the left front wheel rotation angular velocity are input into the centroid side slip angle calculation model, and the centroid side slip angle of the vehicle to be measured is directly calculated. The problem that the error is large caused by directly integrating the vehicle-mounted sensor signal to obtain the centroid side slip angle in the prior art can be avoided. The problem that the calculation precision of the centroid side slip angle is not high caused by the fact that the dynamic model does not conform to the actual situation in the prior art can also be avoided, so that the calculation precision of the centroid side slip angle is better guaranteed.

Description

Technical Field

[0001] This application relates to the field of intelligent vehicle condition detection technology, and in particular to a method and device for calculating the sideslip angle of a vehicle's center of gravity, an electronic device, and a storage medium. Background Technology

[0002] The sideslip angle is a crucial parameter for measuring a vehicle's lateral stability, and accurately acquiring this key vehicle state parameter in real time is essential for vehicle active safety control systems and advanced driver assistance systems. However, directly measuring the sideslip angle using Global Positioning System (GPS) and Inertial Navigation System (INS) or non-contact optical sensors faces challenges such as high cost and susceptibility to environmental influences.

[0003] Current methods for calculating vehicle center of gravity sideslip angle can be mainly divided into two categories: one is based on kinematic models, which directly integrates the onboard sensor signals by analyzing the vehicle's kinematic model to obtain the center of gravity sideslip angle. This type of method largely depends on the accuracy of the sensors, and long-term integration will lead to the continuous accumulation of errors. The other type is based on dynamic models. This type of method usually designs observers, such as Luneburg observers, gliding observers, and robust observers, and uses methods such as Kalman filtering, extended Kalman filtering, and unscented Kalman filtering to obtain the center of gravity sideslip angle. This type of method requires a relatively accurate vehicle dynamic model as its basis, and when using Kalman filtering and its variants, it is necessary to assume that the sensor noise is Gaussian noise, which does not match the actual situation.

[0004] In summary, existing methods for calculating the sideslip angle of a vehicle's center of gravity suffer from low accuracy. Summary of the Invention

[0005] The main objective of this application is to propose a method and apparatus for calculating the sideslip angle of a vehicle's center of gravity, an electronic device, and a storage medium, with the aim of improving the accuracy of the calculation.

[0006] To achieve the above objectives, one aspect of this application proposes a method for calculating the sideslip angle of a vehicle's center of gravity, the method comprising:

[0007] Obtain the vehicle's initial operating parameters;

[0008] The importance assessment score is calculated based on the vehicle's primary operating parameters;

[0009] Based on the importance assessment score and the vehicle's first operating parameters, a first feature set is determined; the first feature set includes: vehicle lateral acceleration feature set, steering wheel angle feature set, and left front wheel rotational angular velocity feature set;

[0010] The preset model is trained based on the first feature set to generate a centroid side deflection angle calculation model;

[0011] The first lateral acceleration, first steering wheel angle, and first left front wheel rotational angular velocity of the vehicle to be measured are obtained.

[0012] The sideslip angle of the vehicle under test is calculated using the lateral acceleration of the first vehicle, the first steering wheel angle, and the rotational angular velocity of the first left front wheel through the sideslip angle calculation model.

[0013] In some embodiments, the importance assessment score is calculated based on the vehicle's first operating parameters, including:

[0014] A dedicated feature set is generated based on the first mapping relationship and the vehicle's first operating parameters; wherein, the first mapping relationship is the mapping relationship between the centroid sideslip angle and the vehicle's first operating parameters;

[0015] Calculate the Pearson correlation coefficient between each feature in the dedicated feature set;

[0016] Based on the Pearson correlation coefficient and a dedicated feature set, a feature set to be evaluated is generated.

[0017] The importance score of each feature in the feature set to be evaluated is calculated using the random forest algorithm.

[0018] In some embodiments, a first feature set is determined based on an importance assessment score and first vehicle operating parameters, including:

[0019] The importance assessment scores are normalized to obtain normalized importance scores;

[0020] The normalized importance scores are sorted to obtain the ranking results;

[0021] The first feature set is obtained by filtering from the dedicated feature set based on the sorting results and score thresholds.

[0022] In some embodiments, a dedicated feature set is generated based on a first mapping relationship and a first vehicle operating parameter, including:

[0023] Based on the vehicle's first operating parameters, combined with the definition formula for the center of gravity sideslip angle and the vehicle dynamics equations, the first mapping relationship is obtained;

[0024] Based on the first mapping relationship and the first vehicle operating parameters, the first set of variables is obtained; the first set of variables includes: vehicle longitudinal velocity, vehicle longitudinal acceleration, vehicle lateral acceleration, vehicle yaw rate, wheel drive torque, wheel rotational angular velocity and steering wheel angle.

[0025] Data is collected based on the first set of variables to generate a dedicated feature set.

[0026] In some embodiments, a preset model is trained based on a first feature set to generate a centroid sideslip angle calculation model, including:

[0027] The first feature set is divided into a training set, a validation set, and a test set;

[0028] The preset model is trained based on the training set; wherein the preset model is a model built by a machine learning algorithm or a model built by a deep learning algorithm.

[0029] Adjust the model parameters of the preset model during training based on the validation set;

[0030] When the number of iterations of the model parameters meets the preset requirements, a centroid sideslip angle calculation model is generated.

[0031] The performance of the centroid sideslip angle calculation model was verified using the test set.

[0032] In some embodiments, verifying the performance of the centroid sideslip angle calculation model against a test set includes:

[0033] The test set is input into the centroid sideslip angle calculation model to generate the first calculation result;

[0034] The test set is input into the simulation platform so that the simulation platform can calculate the second calculation result;

[0035] Calculate the root mean square deviation and error between the first and second calculation results;

[0036] The performance of the centroid side deflection angle calculation model was verified based on the mean square error and the error.

[0037] In some embodiments, data is collected based on a first set of variables to generate a dedicated feature set, including:

[0038] Acquire preset data collection conditions, specific road surface adhesion coefficients, and specific vehicle speed ranges;

[0039] Under preset data acquisition conditions, specific road surface adhesion coefficients, and specific vehicle speed ranges, the first set of variables is collected through a simulation platform to generate a dedicated feature set; wherein, the sampling frequency of the simulation sensor in the simulation platform is 100Hz.

[0040] To achieve the above objectives, another aspect of this application provides a vehicle center of gravity sideslip angle calculation device, the device comprising:

[0041] The first acquisition module is used to acquire the first operating parameters of the vehicle;

[0042] The first calculation module is used to calculate the importance assessment score based on the vehicle's first operating parameters;

[0043] The second acquisition module is used to determine the first feature set based on the importance assessment score and the first operating parameters of the vehicle; wherein, the first feature set includes: the vehicle lateral acceleration feature set, the steering wheel angle feature set, and the left front wheel rotational angular velocity feature set;

[0044] The training module is used to train the preset model based on the first feature set and generate a centroid side slip angle calculation model.

[0045] The third acquisition module is used to acquire the first vehicle lateral acceleration, the first steering wheel angle, and the first left front wheel rotational angular velocity of the vehicle to be measured.

[0046] The second calculation module is used to calculate the center of gravity sideslip angle of the vehicle to be measured by using the center of gravity sideslip angle calculation model based on the lateral acceleration of the first vehicle, the first steering wheel angle, and the first left front wheel rotational angular velocity.

[0047] To achieve the above objectives, another aspect of the embodiments of this application proposes an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the aforementioned method for calculating the vehicle center of gravity sideslip angle.

[0048] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned method for calculating the vehicle center of gravity sideslip angle.

[0049] The embodiments of this application include at least the following beneficial effects: This application provides a method and apparatus for calculating the sideslip angle of a vehicle's center of gravity, an electronic device, and a storage medium. This scheme selects a first feature set based on the importance evaluation score of a first operating parameter of the vehicle. After training a sideslip angle calculation model based on the first feature set, the accuracy of the trained sideslip angle calculation model can be improved because the vehicle lateral acceleration feature set, steering wheel angle feature set, and left front wheel rotational angular velocity feature set in the first feature set have high importance evaluation scores for the sideslip angle. Furthermore, by combining the vehicle lateral acceleration, steering wheel angle, and left front wheel rotational angular velocity of the vehicle to be measured with the trained sideslip angle calculation model, the sideslip angle of the vehicle to be measured can be directly calculated. This avoids the problem of large errors caused by directly integrating the signals from onboard sensors to obtain the sideslip angle in the prior art; it also avoids the problem of low sideslip angle calculation accuracy caused by the discrepancy between the dynamic model and the actual situation in the prior art, thereby better ensuring the calculation accuracy of the sideslip angle. Attached Figure Description

[0050] Figure 1 This is a flowchart of the vehicle center of gravity sideslip angle calculation method provided in the embodiments of this application;

[0051] Figure 2 This is a diagram illustrating the correlation R values ​​between each feature in the dedicated feature set;

[0052] Figure 3 This is a schematic diagram illustrating the saliency P between each feature in the dedicated feature set;

[0053] Figure 4 This is a diagram illustrating the normalized importance assessment score;

[0054] Figure 5 This is a schematic diagram of the calculation results of the centroid sideslip angle in the first scenario;

[0055] Figure 6 This is a schematic diagram of the calculation results of the centroid sideslip angle in the second scene;

[0056] Figure 7 This is a schematic diagram of the vehicle center of gravity sideslip angle calculation device provided in the embodiments of this application;

[0057] Figure 8 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0058] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying 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 those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application.

[0059] It is understood that the terms “first,” “second,” etc., used in this application may be used herein to describe various concepts, but unless otherwise stated, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the words “if,” “when,” or “in response to a determination” as used herein may be interpreted as “when…” or “when…” or “in response to a determination.”

[0060] As used in this application, the terms "at least one", "multiple", "each", "any", etc., "at least one" includes one, two or more, "multiple" includes two or more, "each" refers to each of the corresponding multiples, and "any" refers to any one of the multiples.

[0061] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0062] In related technologies, current methods for calculating the vehicle's center of gravity sideslip angle can be mainly divided into two categories: one is based on kinematic models, which directly integrates the onboard sensor signals to obtain the center of gravity sideslip angle by analyzing the vehicle's kinematic model. This type of method largely depends on the accuracy of the sensors, and long-term integration will lead to the continuous accumulation of errors. The other type is based on dynamic models. This type of method usually designs observers, such as Luneburg observers, gliding observers, and robust observers, and performs methods such as Kalman filtering, extended Kalman filtering, and unscented Kalman filtering to obtain the center of gravity sideslip angle. This type of method requires a relatively accurate vehicle dynamic model as its basis, and when using Kalman filtering and its variants, it is necessary to assume that the sensor noise is Gaussian noise, which does not match the actual situation.

[0063] In view of this, this application provides a method and apparatus, electronic device and storage medium for calculating the center of gravity sideslip angle of a vehicle. This scheme selects a first feature set based on the importance evaluation score of a first operating parameter of the vehicle. After training a center of gravity sideslip angle calculation model based on the first feature set, the accuracy of the trained model is improved because the vehicle lateral acceleration feature set, steering wheel angle feature set, and left front wheel rotational angular velocity feature set in the first feature set have high importance evaluation scores for the center of gravity sideslip angle. Furthermore, by combining the vehicle lateral acceleration, steering wheel angle, and left front wheel rotational angular velocity of the vehicle under test with the trained center of gravity sideslip angle calculation model, the center of gravity sideslip angle of the vehicle under test is directly calculated. This avoids the problem of large errors caused by directly integrating the vehicle sensor signals to obtain the center of gravity sideslip angle in the prior art; it also avoids the problem of low accuracy in calculating the center of gravity sideslip angle due to the discrepancy between the dynamic model and the actual situation in the prior art, thus better ensuring the accuracy of the center of gravity sideslip angle calculation.

[0064] The vehicle center of gravity sideslip angle calculation method provided in this application relates to the field of intelligent vehicle state measurement technology. The vehicle center of gravity sideslip angle calculation method provided in this application can be applied to a terminal, a server, or software running on a terminal or server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, or in-vehicle terminal, but is not limited to these. The server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, 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 implementing the vehicle center of gravity sideslip angle calculation method, but is not limited to the above forms.

[0065] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: 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, and distributed computing environments including any of the above systems or devices. This application can be described in a first context of computer-executable instructions, such as program modules, executed by a computer. Firstly, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0066] Figure 1 This is an optional flowchart of the vehicle center of gravity sideslip angle calculation method provided in the embodiments of this application. Figure 1 The method may include, but is not limited to, steps S101 to S106.

[0067] S101: Obtain the first operating parameters of the vehicle.

[0068] S102: The importance assessment score is calculated based on the vehicle's first operating parameters.

[0069] Furthermore, an importance assessment score is calculated based on the vehicle's primary operating parameters, including:

[0070] A dedicated feature set is generated based on the first mapping relationship and the vehicle's first operating parameters; wherein, the first mapping relationship is the mapping relationship between the centroid sideslip angle and the vehicle's first operating parameters;

[0071] Calculate the Pearson correlation coefficient between each feature in the dedicated feature set;

[0072] Based on the Pearson correlation coefficient and a dedicated feature set, a feature set to be evaluated is generated.

[0073] The importance score of each feature in the feature set to be evaluated is calculated using the random forest algorithm.

[0074] Furthermore, based on the first mapping relationship and the vehicle's first operating parameters, a dedicated feature set is generated, including:

[0075] Based on the vehicle's first operating parameters, combined with the definition formula for the center of gravity sideslip angle and the vehicle dynamics equations, the first mapping relationship is obtained;

[0076] Based on the first mapping relationship and the first vehicle operating parameters, the first set of variables is obtained; the first set of variables includes: vehicle longitudinal velocity, vehicle longitudinal acceleration, vehicle lateral acceleration, vehicle yaw rate, wheel drive torque, wheel rotational angular velocity and steering wheel angle.

[0077] Data is collected based on the first set of variables to generate a dedicated feature set.

[0078] In one specific embodiment, the formula for defining the centroid sideslip angle is as follows:

[0079]

[0080] Where: β is the centroid sideslip angle; v x v is the longitudinal velocity of the vehicle. y This represents the vehicle's lateral speed.

[0081] Therefore, the sideslip angle β is mainly determined by the vehicle's longitudinal velocity v. x and vehicle lateral speed v y Considering the nonlinear characteristics of vehicles in high-speed, low-adhesion scenarios, the longitudinal velocity v of the vehicle should be calculated using the vehicle dynamics equations. x and vehicle lateral speed v y A vehicle dynamics model considering the longitudinal, lateral, and yaw directions of the vehicle body can fully describe the vehicle's motion in a plane, so the vehicle dynamics equations are as follows:

[0082]

[0083] Where a is the distance from the center of gravity to the front axle, b is the distance to the rear axle; m is the vehicle mass; a xLet a be the longitudinal acceleration of the vehicle. y γ is the lateral acceleration of the vehicle; γ is the yaw rate; δ is the front wheel steering angle; d f d is the front wheel track. r F is the rear wheel track. x For the longitudinal force of the tire; F y The lateral force of the tire is ij; fl, fr, rl, rr represent fl of the left front wheel, fr of the right front wheel, rl of the left rear wheel, and rr of the right rear wheel, respectively.

[0084] The front wheel steering angle δ can be calculated using the following formula:

[0085]

[0086] Where, δ sw θ represents the steering wheel angle; i represents the steering gear ratio.

[0087] From the above, it can be seen that in order to further solve for the vehicle's longitudinal velocity v x lateral speed of the vehicle v y The longitudinal acceleration a of the vehicle needs to be known. x lateral acceleration of the vehicle a y The vehicle's yaw rate γ. Additionally, the vehicle's longitudinal acceleration a. x and vehicle lateral acceleration a y It is necessary to use the longitudinal force F of each tire xij Tire lateral force F yij The calculated longitudinal force F of the tire is... xij Tire lateral force F yij Mapping can be performed using the following functions:

[0088]

[0089] Where: μ is the road surface adhesion coefficient; F z λ represents the vertical load on the tire; λ represents the wheel slip / rotation rate; α represents the tire slip angle.

[0090] During vehicle operation, load transfer occurs due to steering, braking, and other actions, affecting the four wheels. z Generally not equal, the vertical load F of each tire z The calculation is as follows:

[0091]

[0092] Where: L is the wheelbase; h g ρ is the height of the center of mass; g is the acceleration due to gravity.

[0093] Wheel slip / rotation rate λ can be obtained by the following formula:

[0094]

[0095] Where: ω is the angular velocity of the wheel rotation; v xij R is the tire center speed; e This is the effective rolling radius of the tire.

[0096] The formula for calculating the tire slip angle α is as follows:

[0097]

[0098] The tire center speed is:

[0099]

[0100] The wheel rotational angular velocity ω is also related to the driving torque and F x related:

[0101]

[0102] Where: J is the moment of inertia of the wheel; T d This refers to the driving torque for each wheel.

[0103] From the above analysis process combining the definition formula of the center of gravity sideslip angle and the vehicle dynamics equations, it can be concluded that the first vehicle operating parameters that have a mapping relationship with the center of gravity sideslip angle include: vehicle longitudinal acceleration a. x lateral acceleration of the vehicle a y Vehicle longitudinal speed v x lateral speed of the vehicle v y Vehicle yaw rate γ, steering wheel angle δ sw angular velocity ω of the wheel ij Wheel drive torque T dij and road surface adhesion coefficient μ.

[0104] Furthermore, based on the first mapping relationship and the vehicle's first operating parameters, the first set of variables is analyzed and includes: vehicle longitudinal acceleration a. x lateral acceleration of the vehicle a y Vehicle longitudinal speed v x Vehicle yaw rate γ, steering wheel angle δ sw angular velocity ω of the wheel ij and wheel drive torque T dij .

[0105] In one specific embodiment, data is collected based on a first set of variables to generate a dedicated feature set, including:

[0106] Acquire preset data collection conditions, specific road surface adhesion coefficients, and specific vehicle speed ranges;

[0107] Under preset data acquisition conditions, specific road surface adhesion coefficients, and specific vehicle speed ranges, the first set of variables is collected through a simulation platform to generate a dedicated feature set; wherein, the sampling frequency of the simulation sensor in the simulation platform is 100Hz.

[0108] When collecting data, considering the highly nonlinear system of the vehicle during driving, the established dataset should fully account for the vehicle's dynamic response characteristics under low speed, high speed, low adhesion, and high adhesion scenarios. This means data collection needs to be conducted under both normal and extreme operating conditions. Therefore, the preset collection conditions include: double lane change and serpentine driving. Since the extreme operating conditions are extremely dangerous, a Matlab / Simulink and Carsim co-simulation platform is used for data collection. The specific vehicle speed range for data collection is set to 20-100 km / h, with a 10 km / h interval between each speed group; specific road adhesion coefficients are set to 0.3, 0.5, and 0.85, representing low, medium, and high adhesion roads, respectively; the sampling frequency of each sensor in the simulation platform is 100Hz; the vehicle can complete the scenario test under all vehicle speed and road adhesion coefficient conditions. Specific data collection scenarios are shown in Table 1.

[0109] Table 1 Specific Data Collection Scenarios

[0110]

[0111] The longitudinal acceleration a of the vehicle was collected. x lateral acceleration of the vehicle a y Vehicle longitudinal speed v x Vehicle yaw rate γ, steering wheel angle δ sw angular velocity ω of the wheel ij Wheel drive torque T dij The sideslip angle β is one set of data, totaling 39 sets, which is sufficient to characterize the nonlinear response of the vehicle during driving. Among them, the longitudinal acceleration a... x lateral acceleration of the vehicle a y Vehicle longitudinal speed v x Vehicle yaw rate γ, steering wheel angle δ sw angular velocity ω of the wheel ij and wheel drive torque T dij The resulting dataset is the dedicated feature set.

[0112] S103: Based on the importance assessment score and the vehicle's first operating parameters, the first feature set is determined.

[0113] The first feature set includes: vehicle lateral acceleration feature set, steering wheel angle feature set, and left front wheel rotational angular velocity feature set.

[0114] Furthermore, based on the importance assessment score and the vehicle's first operating parameters, a first feature set is determined, including:

[0115] The importance assessment scores are normalized to obtain normalized importance scores;

[0116] The normalized importance scores are sorted to obtain the ranking results;

[0117] The first feature set is obtained by filtering from the dedicated feature set based on the sorting results and score thresholds.

[0118] S104: Train the preset model based on the first feature set to generate a centroid side deflection angle calculation model.

[0119] Further, the preset model is trained based on the first feature set to generate a centroid sideslip angle calculation model, including:

[0120] The first feature set is divided into a training set, a validation set, and a test set;

[0121] The preset model is trained based on the training set; wherein the preset model is a model built by a machine learning algorithm or a model built by a deep learning algorithm.

[0122] Adjust the model parameters of the preset model during training based on the validation set;

[0123] When the number of iterations of the model parameters meets the preset requirements, a centroid sideslip angle calculation model is generated.

[0124] The performance of the centroid sideslip angle calculation model was verified using the test set.

[0125] In one specific embodiment, verifying the performance of the centroid sideslip angle calculation model based on a test set includes:

[0126] The test set is input into the centroid sideslip angle calculation model to generate the first calculation result;

[0127] The test set is input into the simulation platform so that the simulation platform can calculate the second calculation result;

[0128] Calculate the root mean square deviation and error between the first and second calculation results;

[0129] The performance of the centroid side deflection angle calculation model was verified based on the mean square error and the error.

[0130] S105: Obtain the first lateral acceleration, first steering wheel angle, and first left front wheel rotational angular velocity of the vehicle to be measured.

[0131] S106: Based on the lateral acceleration of the first vehicle, the first steering wheel angle, and the rotational angular velocity of the first left front wheel, the sideslip angle of the vehicle to be measured is calculated using the sideslip angle calculation model.

[0132] In one specific embodiment, the Pearson correlation coefficient is used to analyze the relationship between the features in the dedicated feature set, the random forest algorithm is applied to evaluate the importance of each feature in the dedicated feature set, and important features are selected as the first feature set.

[0133] After establishing a dedicated feature set, feature engineering analysis is performed to reduce data dimensionality while maintaining the accuracy of the centroid sideslip angle estimation, thereby improving effective data utilization and algorithm performance. Therefore, two aspects of analysis are conducted: the relationships between variables and the relationship between variables and the centroid sideslip angle. The Pearson correlation coefficient between each feature in the dedicated feature set is calculated, specifically based on the vehicle longitudinal acceleration 'a' obtained from the collected dedicated feature set. x lateral acceleration of the vehicle a y Vehicle longitudinal speed v x Vehicle yaw rate γ, steering wheel angle δ sw angular velocity ω of the wheel ij and wheel drive torque T dij Perform Pearson correlation coefficient (PCC) analysis between variables, and analyze the correlation R value and significance P value.

[0134] (1) Correlation determination: Calculate the correlation coefficient R value between each variable. The calculation formula is as follows:

[0135]

[0136] Where: N is the number of samples; X and Y are two variables; These are the means of the two variables, respectively.

[0137] When |R|≥0.8, it can be determined that there is a very strong correlation between X and Y, and X can be linearly represented by Y; further, when |R|=1, X and Y are perfectly correlated, and one variable can be replaced by the other variable. At this time, X and Y have fault tolerance.

[0138] (2) Significance determination: Calculate the t-statistics between each variable, and then determine the significance P-value by looking up the t-distribution table. The formula for calculating the t-statistic is as follows:

[0139]

[0140] When P ≤ 0.05, it can be determined that the significance level between the two variables is high; when P > 0.05, the significance level is insufficient, and it cannot be ruled out that the large correlation coefficient R value is caused by accidental factors.

[0141] Please refer to Figure 2 , Figure 2 This diagram illustrates the correlation R values ​​between each feature in a specific feature set. Figure 2 Therefore, the lateral acceleration a of the vehicle can be obtained. y The relationship between the vehicle's yaw rate γ and the steering wheel angle δ. sw Left front wheel drive torque T dfl With right front wheel drive torque T dfr Right rear wheel drive torque T drr Right front wheel drive torque T dfr With left rear wheel drive torque T drl Left rear wheel drive torque T drl With right rear wheel drive torque T drr There is a very strong correlation; vehicle longitudinal speed v x With the angular velocity ω of the wheel rotation ij angular velocity of wheel rotation ω ij Between, and the left front wheel drive torque T dfl With left rear wheel drive torque T drl Right front wheel drive torque T dfr With right rear wheel drive torque T drr They are completely related.

[0142] Please refer to Figure 3 , Figure 3 This is a schematic diagram illustrating the significance (P-value) between each feature in the specific feature set. Figure 3 Therefore, the above correlation analysis results are not caused by random factors.

[0143] Furthermore, analysis using the PCC Pearson correlation coefficient shows that the wheel rotational angular velocity ω ij Between, left front wheel drive torque T dfl With left rear wheel drive torque T drl Right front wheel drive torque T dfr With right rear wheel drive torque T drr Full correlation provides fault tolerance for sensor signals in data-driven centroid sideslip angle estimation. If one wheel speed sensor fails, other speed sensors can provide the signal; the same applies to the torque signals of the left front and left rear wheels, and the right front and right rear wheels. Therefore, a typical left front wheel rotational angular velocity ω is selected. fl Left front wheel drive torque T dfl and right front wheel drive torque T dfr The signal is used as a feature for subsequent importance assessment, and the sensor signal that is completely related to it is used as the fault-tolerant signal for estimating the system. Therefore, the feature set to be evaluated includes a dataset consisting of the following parameters: the left front wheel rotational angular velocity ω. fl Left front wheel drive torque T dflRight front wheel drive torque T dfr Vehicle longitudinal acceleration a x lateral acceleration of the vehicle a y Vehicle longitudinal speed v x Vehicle yaw rate γ and steering wheel angle δ sw .

[0144] Random Forest (RF) integrates multiple decision trees to improve regression accuracy and can assess feature importance, thus it is used to analyze the relationship between variables and centroid sideslip angle. For the RF algorithm, if the mean squared error (MSE) is chosen as the node impurity function, then for a given node, the impurity calculation formula is:

[0145]

[0146] The importance score of a feature can be calculated using the following formula:

[0147] n m =w m G m -w left G left -w right G right

[0148]

[0149] Where: N is the number of training samples; X is a feature in the samples; V is the segmentation value of feature X; X left and X right y represents the training sample sets of the left and right child nodes of node m, respectively; l and y r These are the values ​​of the left and right child nodes of node m, respectively. and G represents the average value of the target variable in the samples of the left and right child nodes of node m, respectively; m (X,V) represents the impurity of node m under feature X; w m w left w right G represents the ratio of the number of training samples in node m and its left and right child nodes to the total number of training samples, respectively. m G left G right Let n be the impurity of node m and its left and right child nodes, respectively; n be the impurity of node m and its left and right child nodes, respectively. m Let m be the importance of node m; M be the total number of nodes in a decision tree; n i The feature is X i The node; I is the feature X i The number of nodes; f(X) i ) represents feature X iImportance; K is the number of sample features; f(X) i ) nor For feature X i The normalized importance assessment score.

[0150] Using the final normalized importance assessment score of 1 / K (i.e., the score threshold) as the standard, features with scores exceeding this threshold are selected as inputs for subsequent training. Here, K is the number of features used for importance assessment.

[0151] In this embodiment, the Random Forest algorithm is applied to evaluate the vehicle longitudinal acceleration α in the feature set to be evaluated. x lateral acceleration of the vehicle a y Vehicle longitudinal speed v x Vehicle yaw rate γ, steering wheel angle δ sw ω, the rotational angular velocity of the left front wheel fl Left front wheel drive torque T dfl Right front wheel drive torque T dfr A total of 8 features were evaluated for importance. Please refer to [link / reference] for the final normalized importance scores and their ranking. Figure 4 .

[0152] Figure 4 This is a diagram illustrating the normalized importance assessment score, from... Figure 4 It can be seen that the feature with an importance score greater than 1 / 8 of the score threshold is the vehicle lateral acceleration a. y Steering wheel angle δ sw ω, the rotational angular velocity of the left front wheel fl Therefore, the lateral acceleration a of the vehicle is selected. y Steering wheel angle δ sw ω, the rotational angular velocity of the left front wheel fl The corresponding dataset is used as the first feature set (including: vehicle lateral acceleration feature set, steering wheel angle feature set, and left front wheel rotation angular velocity feature set), and the first feature set is input into the preset model for training.

[0153] Furthermore, the Backpropagation Neural Network (BPNN) is one of the most typical training algorithms in the field of deep learning. In this embodiment, a typical BPNN is applied to train the first feature set. The BPNN consists of three layers: one input layer, one hidden layer, and one output layer. The input layer has three neurons, and the input information is: the vehicle's lateral acceleration a. y Steering wheel angle δ sw and the rotational angular velocity ω of the left front wheel flThe corresponding dataset; the hidden layer contains 20 neurons; the output layer has 1 neuron, and the output information is the centroid side-slip angle β. The training set, test set, and validation set are divided according to a certain ratio, and the Levenberg-Marquardt algorithm is used for training, with the performance metric being MSE.

[0154] After training, deploy the model using the vehicle's lateral acceleration a. y Steering wheel angle δ sw ω, the rotational angular velocity of the left front wheel fl As model input, the model was validated using a joint simulation platform of Matlab / Simulink and Carsim.

[0155] In the first scenario setting with a vehicle speed of 65 km / h, a road adhesion coefficient μ of 0.6, and a double lane change condition, please refer to the calculation results of the centroid sideslip angle. Figure 5 , Figure 5 This is a schematic diagram showing the calculated centroid sideslip angle for the first scene. Figure 5 Therefore, the centroid sideslip angle calculation method proposed in this invention can accurately estimate the centroid sideslip angle of the vehicle. The root mean square error (RMSE) is used as the evaluation index, and its value is 0.0004.

[0156] In the second scenario setting, with a vehicle speed of 55 km / h, a road adhesion coefficient μ of 0.7, and a serpentine driving condition, please refer to the following for the centroid sideslip angle estimation results. Figure 6 , Figure 6 This is a schematic diagram showing the calculation results of the centroid sideslip angle for the second scene. Figure 6 As can be seen, RMSE is 0.0007, which can accurately calculate the centroid sideslip angle.

[0157] After the training is completed, the center of gravity sideslip angle calculation model is deployed, and the selected features (i.e. the first vehicle lateral acceleration, the first steering wheel angle, and the first left front wheel rotational angular velocity of the vehicle to be measured) are used as inputs to the center of gravity sideslip angle calculation model, and finally the center of gravity sideslip angle of the vehicle to be measured is obtained.

[0158] Furthermore, it also includes a sensor failure detection and fault-tolerant switching process, specifically: determining whether the variable signal with |R|=1 in the PCC correlation analysis of the data-driven vehicle center of gravity sideslip angle estimation method is faulty or erroneous, for example: determining whether the ω in the on-board sensor is faulty or erroneous. fl If the signal fails or erroneous, immediately switch ω. fr ω rl ω rr If any of the three signals fails again, the rotational angular velocity signals of the other wheels will be switched accordingly.

[0159] Please see Figure 7 , Figure 7This diagram illustrates a vehicle center-of-gravity sideslip angle calculation device, characterized in that the device comprises:

[0160] The first acquisition module 701 is used to acquire the first operating parameters of the vehicle;

[0161] The first calculation module 702 is used to calculate the importance assessment score based on the first operating parameters of the vehicle;

[0162] The second acquisition module 703 is used to determine the first feature set based on the importance assessment score and the first operating parameters of the vehicle; wherein, the first feature set includes: vehicle lateral acceleration feature set, steering wheel angle feature set and left front wheel rotation angular velocity feature set;

[0163] Training module 704 is used to train the preset model based on the first feature set to generate a centroid side slip angle calculation model;

[0164] The third acquisition module 705 is used to acquire the first vehicle lateral acceleration, the first steering wheel angle, and the first left front wheel rotational angular velocity of the vehicle to be measured.

[0165] The second calculation module 706 is used to calculate the center of gravity sideslip angle of the vehicle to be measured by using the center of gravity sideslip angle calculation model based on the lateral acceleration of the first vehicle, the first steering wheel angle, and the first left front wheel rotation angular velocity.

[0166] It is understood that the content of the above method embodiments is applicable to the present device embodiments. The specific functions 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.

[0167] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method for calculating the vehicle's center of gravity sideslip angle. This electronic device can be any smart terminal, including a tablet computer or an in-vehicle computer.

[0168] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment 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.

[0169] Please see Figure 8 , Figure 8 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes:

[0170] The processor 801 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, 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 this application.

[0171] The memory 802 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 802 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 802 and called by the processor 801 to execute the vehicle center of gravity sideslip angle calculation method of the embodiments of this application.

[0172] The 803 input / output interface is used to implement information input and output.

[0173] The communication interface 804 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0174] Bus 805 transmits information between various components of the device (e.g., processor 801, memory 802, input / output interface 803, and communication interface 804);

[0175] The processor 801, memory 802, input / output interface 803, and communication interface 804 are connected to each other within the device via bus 805.

[0176] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for calculating the vehicle center of gravity sideslip angle.

[0177] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0178] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0179] The vehicle center-of-gravity sideslip angle calculation method, device, electronic device, and storage medium provided in this application embodiment select a first feature set based on the importance evaluation score of the vehicle's first operating parameters. After training a center-of-gravity sideslip angle calculation model based on the first feature set, the vehicle lateral acceleration feature set, steering wheel angle feature set, and left front wheel rotational angular velocity feature set in the first feature set have high importance evaluation scores for the center-of-gravity sideslip angle, thus improving the calculation accuracy of the trained center-of-gravity sideslip angle calculation model. Furthermore, by combining the vehicle lateral acceleration, steering wheel angle, and left front wheel rotational angular velocity of the vehicle to be measured with the trained center-of-gravity sideslip angle calculation model, the center-of-gravity sideslip angle of the vehicle to be measured can be directly calculated. This avoids the problem of large errors caused by directly integrating the center-of-gravity sideslip angle from onboard sensor signals in the prior art; it also avoids the problem of low calculation accuracy of the center-of-gravity sideslip angle caused by the discrepancy between the dynamic model and the actual situation in the prior art, thereby better ensuring the calculation accuracy of the center-of-gravity sideslip angle.

[0180] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0181] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0182] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0183] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0184] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0185] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " first indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0186] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0187] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0188] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0189] If the integrated unit is implemented as 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 this application, in essence, 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. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0190] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for calculating the sideslip angle of a vehicle's center of gravity, characterized in that, The method includes: Obtain the vehicle's initial operating parameters; The importance assessment score is calculated based on the vehicle's first operating parameters; Based on the importance assessment score and the vehicle's first operating parameters, a first feature set is determined; wherein, the first feature set includes: a vehicle lateral acceleration feature set, a steering wheel angle feature set, and a left front wheel rotational angular velocity feature set; The preset model is trained based on the first feature set to generate a centroid side deflection angle calculation model; The first lateral acceleration, first steering wheel angle, and first left front wheel rotational angular velocity of the vehicle to be measured are obtained. The center-of-gravity sideslip angle of the vehicle under test is calculated using the center-of-gravity sideslip angle calculation model based on the lateral acceleration of the first vehicle, the first steering wheel angle, and the first left front wheel rotational angular velocity.

2. The method for calculating the sideslip angle of a vehicle's center of gravity according to claim 1, characterized in that, The importance assessment score calculated based on the vehicle's first operating parameters includes: A dedicated feature set is generated based on the first mapping relationship and the first operating parameters of the vehicle; wherein, the first mapping relationship is the mapping relationship between the centroid sideslip angle and the first operating parameters of the vehicle; Calculate the Pearson correlation coefficient between each feature in the dedicated feature set; Based on the Pearson correlation coefficient and the specific feature set, a feature set to be evaluated is generated; The importance score of each feature in the feature set to be evaluated is calculated using the random forest algorithm.

3. The method for calculating the sideslip angle of a vehicle's center of gravity according to claim 2, characterized in that, The process of determining the first feature set based on the importance assessment score and the vehicle's first operating parameters includes: The importance assessment scores are normalized to obtain normalized importance scores; The normalized importance scores are sorted to obtain the sorting results; The first feature set is obtained by filtering from the dedicated feature set based on the sorting results and score thresholds.

4. The method for calculating the sideslip angle of a vehicle's center of gravity according to claim 3, characterized in that, The step of generating a dedicated feature set based on the first mapping relationship and the first operating parameters of the vehicle includes: Based on the vehicle's first operating parameters, combined with the definition formula for the center of gravity sideslip angle and the vehicle dynamics equations, the first mapping relationship is obtained; Based on the first mapping relationship and the first vehicle operating parameters, a first set of variables is obtained; wherein, the first set of variables includes: vehicle longitudinal velocity, vehicle longitudinal acceleration, vehicle lateral acceleration, vehicle yaw rate, wheel drive torque, wheel rotational angular velocity and steering wheel angle; Data is collected based on the first set of variables to generate the dedicated feature set.

5. The method for calculating the sideslip angle of a vehicle's center of gravity according to claim 4, characterized in that, The step of training the preset model based on the first feature set to generate a centroid sideslip angle calculation model includes: The first feature set is divided into a training set, a validation set, and a test set; The preset model is trained based on the training set; wherein the preset model is a model built by a machine learning algorithm or a model built by a deep learning algorithm. The model parameters of the preset model are adjusted during training based on the validation set. When the number of iterations of the model parameters meets the preset requirements, the centroid sideslip angle calculation model is generated; The performance of the centroid sideslip angle calculation model was verified using the test set.

6. The method for calculating the sideslip angle of a vehicle's center of gravity according to claim 5, characterized in that, The step of verifying the performance of the centroid sideslip angle calculation model based on the test set includes: The test set is input into the centroid sideslip angle calculation model to generate the first calculation result; The test set is input into the simulation platform so that the simulation platform can calculate the second calculation result. Calculate the mean square error and the error between the first calculation result and the second calculation result; The performance of the centroid side deflection angle calculation model is verified based on the mean square error and the error.

7. The method for calculating the sideslip angle of a vehicle's center of gravity according to claim 6, characterized in that, The step of collecting data based on the first variable group and generating the dedicated feature set includes: Acquire preset data collection conditions, specific road surface adhesion coefficients, and specific vehicle speed ranges; Under the preset data acquisition conditions, the specific road surface adhesion coefficient, and the specific vehicle speed range, the first variable group is collected through the simulation platform to generate the dedicated feature set; wherein, the sampling frequency of the simulation sensor in the simulation platform is 100Hz.

8. A vehicle center of gravity sideslip angle calculation device, characterized in that, The device includes: The first acquisition module is used to acquire the first operating parameters of the vehicle; The first calculation module is used to calculate the importance assessment score based on the first operating parameters of the vehicle; The second acquisition module is used to determine a first feature set based on the importance assessment score and the first vehicle operating parameters; wherein, the first feature set includes: a vehicle lateral acceleration feature set, a steering wheel angle feature set, and a left front wheel rotational angular velocity feature set; The training module is used to train the preset model based on the first feature set to generate a centroid side deflection angle calculation model. The third acquisition module is used to acquire the first vehicle lateral acceleration, the first steering wheel angle, and the first left front wheel rotational angular velocity of the vehicle to be measured. The second calculation module is used to calculate the center-of-gravity sideslip angle of the vehicle to be measured by using the center-of-gravity sideslip angle calculation model based on the lateral acceleration of the first vehicle, the first steering wheel angle, and the rotational angular velocity of the first left front wheel.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the vehicle center of gravity sideslip angle calculation 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 the processor, it implements the vehicle center of gravity sideslip angle calculation method as described in any one of claims 1 to 7.

Images