Real-time prediction method, device and server for wheel center force

Abstract

The present invention provides a method, device and server for predicting real-time wheel center force, relating to the technical field of vehicle dynamics modeling and intelligent control, including: acquiring high-dimensional original feature data in real time, wherein the original feature data includes wheel center acceleration data and dynamic auxiliary data, and the dynamic auxiliary data includes vehicle speed, steering angle, tire pressure, tire force, vehicle body force and vehicle dynamics relationship; combining principal component analysis with physical constraints to perform dynamic order reduction processing on the original feature data to determine the target feature data after order reduction; calculating and processing the weight values corresponding to different input features in the target feature data through a preset deep neural network to dynamically adjust the importance of each input feature, and generating a target wheel center force prediction result at the output layer of the preset deep neural network by performing weighted calculation on the weight values and the target feature data. The present invention can significantly improve the accuracy of wheel center force prediction.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle dynamics modeling and intelligent control, and particularly to a method, device and server for predicting real-time wheel center forces. Background Art

[0002] The wheel center force is an important indicator for describing the dynamic operation of a vehicle. However, directly measuring the wheel center force through physical sensors has a high measurement cost and complex sensor installation problems. Currently, related technologies propose that the wheel center force can be deduced by combining physical models with vehicle structure parameters, but this solution has complex calculations and is difficult to adapt to different vehicles and working conditions. In addition, algorithms such as neural networks can be used to learn prediction models from data, but this solution is prone to overfitting or a decline in generalization performance when dealing with data with too high dimensions or non-stationary characteristics, thus affecting the accuracy of wheel center force prediction. Summary of the Invention

[0003] In view of this, the purpose of the present invention is to provide a method, device and server for predicting real-time wheel center forces, which can significantly improve the accuracy of wheel center force prediction.

[0004] In a first aspect, an embodiment of the present invention provides a method for predicting real-time wheel center forces, the method including: obtaining high-dimensional original feature data in real time, where the original feature data includes: wheel center acceleration data and dynamic auxiliary data, and the dynamic auxiliary data includes: vehicle speed, steering angle, tire pressure, tire force, vehicle body force and vehicle dynamics relationship; combining principal component analysis with physical constraints to perform dynamic dimensionality reduction processing on the original feature data to determine the target feature data after dimensionality reduction; calculating and processing the weight values corresponding to different input features in the target feature data through a preset deep neural network to dynamically adjust the importance of each input feature, and generating a target wheel center force prediction result at the output layer of the preset deep neural network by performing weighted calculation on the weight values and the target feature data.

[0005] In an implementation manner, the step of combining principal component analysis with physical constraints to perform dynamic dimensionality reduction processing on the original feature data to determine the target feature data after dimensionality reduction includes: performing dynamic dimensionality reduction processing on the original feature data through a preset principal component analysis model, mapping the original feature data from a high-dimensional space to a low-dimensional feature space, and making the reduced-dimensional feature space conform to the vehicle dynamics model by adding a first physical constraint term during the dynamic dimensionality reduction process to determine the target feature data after dimensionality reduction, where the objective function of the preset principal component analysis model is:

[0006] Z = X

[0007] Among them, W is the reduced-order matrix, X is the original feature data, and Z is the low-dimensional target feature data after dimensionality reduction.

[0008] In one implementation, the steps of making the feature space after dimensionality reduction conform to the vehicle dynamics model by adding a first physical constraint term during the dynamic reduced-order process include: updating the objective function of the preset principal component analysis model through the first physical constraint term to determine the updated objective function; using the updated objective function to perform dynamic reduced-order processing on the original feature data to determine the target feature data after reduced order, where the updated objective function is:

[0009]

[0010] Among them, is the first physical constraint term, is the weight coefficient for balancing the reconstruction error and physical consistency.

[0011] In one implementation, the method includes: determining the first physical constraint term according to the constraint relationship between the tire force and the vehicle body force, where the first physical constraint term is expressed as:

[0012]

[0013] Among them, is the tire force, is the friction coefficient, is the normal force, is the vehicle body force, is the vehicle body mass, is the vehicle body acceleration.

[0014] In one implementation, after the step of determining the target feature data after reduced order, it includes: obtaining the real-time working condition of the vehicle and the data distribution of the target feature data, and using a preset dynamic optimization model to perform dynamic adjustment processing on the dimensions of various types of data in the target feature data according to the real-time working condition and the data distribution, so that in the optimized target feature data, the dimension of the data is proportional to the correlation degree with the data and the wheel force prediction.

[0015] In one implementation, before the step of generating the target wheel force prediction result at the output layer of the preset deep neural network, it includes: determining a second physical constraint term using the relationship between force and vehicle dynamics, and determining a loss function based on the second physical constraint term to optimize the model parameters of the neural network using the loss function, where the loss function is:

[0016]

[0017] Among them, is the real wheel force, is the predicted wheel force, is the second physical constraint term.

[0018] In one embodiment, the step of determining the second physical constraint term by using the force-vehicle dynamics relationship includes: based on the force-vehicle dynamics relationship, determining the maximum allowable force of the vehicle under different working conditions, and determining the second physical constraint term according to the maximum allowable force, where the second physical constraint term is:

[0019]

[0020] where is the predicted value of the force, is the maximum allowable force of the vehicle under different working conditions.

[0021] In a second aspect, an embodiment of the present invention further provides a real-time wheel center force prediction device, which includes: a data acquisition module that acquires high-dimensional raw feature data in real time, where the raw feature data includes: wheel center acceleration data and dynamic auxiliary data, and the dynamic auxiliary data includes: vehicle speed, steering angle, tire pressure, tire force, vehicle body force, and vehicle dynamics relationship; a dynamic order reduction module that combines principal component analysis with physical constraints to perform dynamic order reduction processing on the raw feature data to determine the reduced-order target feature data; a wheel center force prediction module that calculates and processes the weight values corresponding to different input features in the target feature data through a preset deep neural network to dynamically adjust the importance of each input feature, and generates a target wheel center force prediction result at the output layer of the preset deep neural network by performing weighted calculation on the weight values and the target feature data.

[0022] In a third aspect, an embodiment of the present invention further provides a server, which includes a processor and a memory, and the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the method according to any one of the first aspect.

[0023] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, which stores computer-executable instructions, and when the computer-executable instructions are called and executed by a processor, the computer-executable instructions cause the processor to implement the method according to any one of the first aspect.

[0024] The embodiments of the present invention bring the following beneficial effects:

[0025] A method, device and server for predicting real-time wheel force provided by an embodiment of the present invention. After acquiring high-dimensional original feature data in real time, this method combines principal component analysis with physical constraints to perform dynamic dimensionality reduction processing on the original feature data, determines the target feature data after dimensionality reduction, and then calculates and processes the weight values corresponding to different input features in the target feature data through a preset deep neural network to dynamically adjust the importance of each input feature, and generates a target wheel force prediction result at the output layer of the preset deep neural network by performing weighted calculation on the weight values and the target feature data. Embodiments of the present invention can combine neural networks, dimensionality reduction models and adaptive learning mechanisms, and based on high-dimensional input data collected by vehicle sensors, predict wheel force in real time and efficiently, and significantly improve the accuracy of wheel force prediction, providing support for intelligent driving decision-making, vehicle dynamic control and tire performance optimization.

[0026] Other features and advantages of the present invention will be described in the following specification, and, in part, will be obvious from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention are realized and obtained by the structures specifically pointed out in the specification, claims and drawings.

[0027] To make the above objectives, features and advantages of the present invention more obvious and understandable, the following specific preferred embodiments are given, and in conjunction with the accompanying drawings, the detailed description is as follows. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0029] Figure 1 A flowchart of a method for predicting real-time wheel force provided by an embodiment of the present invention;

[0030] Figure 2 A flowchart of another method for predicting real-time wheel force provided by an embodiment of the present invention;

[0031] Figure 3 A structural schematic diagram of a device for predicting real-time wheel force provided by an embodiment of the present invention;

[0032] Figure 4 A structural schematic diagram of a server provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0033] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0034] Currently, wheel center force is an important indicator for describing the dynamic operation of a vehicle, including longitudinal force (Fx), lateral force (Fy), and vertical force (Fz), which can characterize the traction, braking, and lateral stability performance of the vehicle. However, directly measuring the wheel center force by means of physical sensors has a high measurement cost and complex sensor installation problems. Related technologies propose that based on the physical model method, the wheel center force can be deduced through dynamic formulas and vehicle structure parameters. However, this solution has complex calculations and is difficult to adapt to different vehicles and working conditions. In addition, based on the data-driven method, algorithms such as neural networks can be used to learn prediction models from data. However, this solution is prone to overfitting or degradation of generalization performance when dealing with data with too high dimensions or non-stationary characteristics, thus affecting the accuracy of wheel center force prediction.

[0035] Based on this, the prediction method, device, and server for real-time wheel center force provided by the embodiments of the present invention can significantly improve the prediction accuracy and real-time performance under complex working conditions. Through dynamic order reduction modeling, high-dimensional data redundancy can be effectively reduced, key features can be retained, and the model complexity can be reduced. In addition, multi-modal data fusion and physical constraint optimization ensure the physical consistency of the prediction results, solve the instability problem of traditional methods, and combine the nonlinear modeling and adaptive parameter adjustment mechanism of neural networks. The model can adapt to different road surfaces and driving conditions in real time, realizing high-precision prediction of longitudinal force, lateral force, and vertical force. Compared with traditional methods, the prediction accuracy is increased by more than 15%, and the calculation efficiency is increased by 30%. It is widely applicable to the fields of intelligent vehicle control and autonomous driving.

[0036] See Figure 1 The flowchart of a prediction method for real-time wheel center force as shown, this method mainly includes the following steps S102 to step S106:

[0037] Step S102, obtain high-dimensional original feature data in real time. Among them, the original feature data includes: wheel center acceleration data and dynamic auxiliary data, and the dynamic auxiliary data includes: vehicle speed, steering angle, tire pressure, tire force, vehicle body force, and vehicle dynamic relationship.

[0038] Step S104: Combine principal component analysis with physical constraints to perform dynamic dimensionality reduction on the original feature data and determine the target feature data after dimensionality reduction. In one implementation, the dimensionality reduction dimension can be dynamically adjusted, and the number of principal components can be dynamically determined according to the real-time working conditions and data distribution to adapt to the non-stationary characteristics of the input data.

[0039] Step S106: Calculate and process the weight values corresponding to different input features in the target feature data through a preset deep neural network to dynamically adjust the importance of each input feature, and generate a target wheel force prediction result at the output layer of the preset deep neural network by performing weighted calculation on the weight values and the target feature data. Among them, the deep neural network (DNN) includes: an input layer, a hidden layer, an attention mechanism module, and an output layer. Specifically, the input layer is used to receive the low-dimensional feature vector Z (i.e., the target feature data) after dimensionality reduction; the hidden layer consists of multiple fully connected networks, and the activation function of each layer uses ReLU: f(x)=max(0,x); the attention mechanism module is used to dynamically adjust the importance of the input features by calculating the weights of the features, helping the network to pay more attention to key features, improving the expression ability and accuracy of the model. Through the weighted sum mechanism, the weight values of different features are multiplied by the input data so that the neural network can focus on the features that are more important for wheel force prediction; the output layer is used to predict the longitudinal force Fx, the lateral force Fy, and the vertical force Fz (i.e., the target wheel force prediction result).

[0040] The above real-time wheel force prediction method provided by the embodiments of the present invention can significantly improve the accuracy of wheel force prediction.

[0041] The embodiments of the present invention also provide an implementation manner for predicting wheel force in real time, which reduces high-dimensional data redundancy, retains key features, and reduces the model complexity through dynamic dimensionality reduction modeling. Specifically, refer to the following (1) to (3):

[0042] (1) Adopt a dynamic dimensionality reduction method that combines principal component analysis (PCA) with physical constraints. The role of PCA is to reduce the dimension by retaining the main components of the data while retaining as much original information as possible, and map the data from the high-dimensional space to the low-dimensional feature space. Specifically, through a preset principal component analysis model, perform dynamic dimensionality reduction processing on the original feature data, map the original feature data from the high-dimensional space to the low-dimensional feature space, and by adding a first physical constraint term during the dynamic dimensionality reduction process, make the reduced feature space conform to the vehicle dynamics model to determine the target feature data after dimensionality reduction. Among them, the objective function of the preset principal component analysis model is:

[0043] Z = X

[0044] Among them, W is the reduced-order matrix, X is the original feature data, and Z is the low-dimensional target feature data after dimensionality reduction.

[0045] (2) During the reduction process, a physical constraint term is added to ensure that the feature space after dimensionality reduction conforms to the vehicle dynamics model. Specifically, the objective function of the preset principal component analysis model is updated through the first physical constraint term to determine the updated objective function.

[0046] The original feature data is dynamically reduced using the updated objective function to determine the target feature data after reduction. Among them, the updated objective function is:

[0047]

[0048] Among them, is the first physical constraint term, is the weight coefficient for balancing the reconstruction error and physical consistency.

[0049] Further, according to the constraint relationship between the tire force and the vehicle body force, the first physical constraint term is determined. Among them, the first physical constraint term is expressed as:

[0050]

[0051] Among them, is the tire force, is the friction coefficient, is the normal force, is the vehicle body force, is the vehicle body mass, is the vehicle body acceleration.

[0052] (3) According to the real-time working conditions and data distribution, the dimensionality reduction dimension k is dynamically adjusted to ensure that the features after dimensionality reduction retain as much important information as possible. Specifically, the real-time working conditions of the vehicle and the data distribution of the target feature data are obtained, and using the preset dynamic optimization model, according to the real-time working conditions and data distribution, the dimensions of various types of data in the target feature data are dynamically adjusted so that in the optimized target feature data, the dimensions of the data are proportional to the degree of correlation with the data and the wheel force prediction. The dynamic adjustment of the dimensionality reduction dimension can be achieved through the following formula:

[0053]

[0054] Among them, is the eigenvalue of the covariance matrix; τ is the cumulative variance contribution rate threshold, with a value of 95%.

[0055] The embodiments of the present invention also provide an implementation method for predicting wheel forces in real time. By combining the non - linear modeling of a neural network and an adaptive parameter adjustment mechanism, the model can adapt to different road surfaces and driving conditions in real time, and achieve high - precision prediction of longitudinal force, lateral force, and vertical force. Specifically, refer to the following (1) to (2):

[0056] (1) To ensure the accuracy of the prediction results, physical constraints are introduced and a loss function is defined. Specifically, the second physical constraint term is determined using the relationship between force and vehicle dynamics, and the loss function is determined based on the second physical constraint term to optimize the model parameters of the neural network. Among them, the loss function is:

[0057]

[0058] Among them, is the true wheel force, is the predicted wheel force, is the second physical constraint term.

[0059] Based on the relationship between force and vehicle dynamics, the maximum allowable force of the vehicle under different working conditions is determined, and the second physical constraint term is determined according to the maximum allowable force. Among them, the second physical constraint term is:

[0060]

[0061] Among them, is the predicted value of the force, is the maximum allowable force of the vehicle under different working conditions.

[0062] (2) Under different working conditions, in order to improve the adaptability of the model, the Bayesian optimization method can be used to dynamically adjust the key parameters of the model, so as to avoid over - fitting or under - fitting problems while optimizing the model performance. To improve the adaptability of the model under different working conditions, the Bayesian optimization is used to dynamically adjust the key parameters of the model (such as learning rate, regularization coefficient, etc.). Among them, the objective function can be constructed by a Gaussian process to obtain a surrogate model, and the acquisition function is defined as the expected improvement (EI):

[0063]

[0064] Thus, by maximizing the best parameter update direction is found.

[0065] In one embodiment, the dynamic parameter update process includes: initialization, real-time working condition monitoring, Bayesian search, and parameter update. Specifically, in the initialization process, the model is trained using initial parameters and the loss value is recorded. In the real-time working condition monitoring process, parameter optimization is triggered. In the Bayesian search process, the optimal parameters are found. In the parameter update process, the model parameters are adjusted and training continues, thereby efficiently searching for the global optimal parameters and improving the prediction accuracy and model robustness under complex dynamic working conditions.

[0066] See Figure 2 The flow schematic diagram of another real-time wheel force prediction method shown in the figure. In modern vehicle engineering, real-time prediction of wheel forces (including longitudinal force, lateral force, and vertical force) is crucial for improving vehicle handling, safety, and comfort. Especially under different road conditions and driving conditions, accurate prediction of wheel forces can help the control system adjust the vehicle state in real time and improve the driving experience. This example demonstrates how to use a prediction method based on the fusion of dynamic order reduction and neural network, combined with sensor data and vehicle dynamics models, to predict wheel forces.

[0067] 1. Input Feature Selection and Data Acquisition

[0068] 1.1 Wheel Center Acceleration Data

[0069] The triaxial acceleration data, including longitudinal acceleration, lateral acceleration, and vertical acceleration, is collected in real time through the accelerometers on each wheel of the vehicle. Assume that each wheel is equipped with an acceleration sensor, and the data acquisition frequency is 100 Hz.

[0070] The wheel center acceleration data includes the following content, represented as a time series:

[0071] Time t1: Longitudinal acceleration ax = 1.2 m / s2, lateral acceleration ay = 0.5 m / s2, vertical acceleration az = -9.8 m / s2.

[0072] Time t2: Longitudinal acceleration ax = 1.3 m / s2, lateral acceleration ay = 0.6 m / s2, vertical acceleration az = -9.7 m / s2.

[0073] 1.2 Kinetic Auxiliary Data:

[0074] Vehicle speed: Collected through the vehicle speed sensor. Assume the vehicle speed data is as follows:

[0075] Time t1: Vehicle speed v = 80 km / h.

[0076] Time t2: Vehicle speed v = 85 km / h.

[0077] Steering angle: Obtained from the steering angle sensor. Assume the steering angle data is as follows:

[0078] Time t1: Steering angle δ = 2°

[0079] Time t2: Steering angle δ = 3°

[0080] Tire pressure: The pressure of each tire is provided in real time by a tire pressure sensor. Assume the tire pressure data is as follows:

[0081] Time t1: Tire pressure p = 2.3 bar.

[0082] Time t2: Tire pressure p = 2.2 bar.

[0083] Road surface conditions: The road surface friction coefficient is provided in real time by a ground friction sensor. Assume the friction coefficient is μ = 0.9 at times t1 and t2.

[0084] The above data is synchronously collected by the vehicle's control system (such as an on-vehicle computer) and transmitted to the wheel force prediction system in real time.

[0085] 2. Data preprocessing and dynamic order reduction

[0086] 2.1 Data preprocessing:

[0087] Denoising processing: The sensor data is denoised by Kalman filtering to remove high-frequency noise and ensure data quality.

[0088] Normalization processing: All input data is normalized so that its mean is 0 and variance is 1 to ensure consistency when the data is input into the neural network.

[0089] 2.2 Dynamic order reduction processing:

[0090] PCA order reduction: First, perform PCA dimensionality reduction on all the above input features to obtain a low-dimensional feature space.

[0091] Introduce physical constraints: During the dimensionality reduction process, add physical constraints of vehicle dynamics to ensure that the reduced features satisfy the vehicle mechanics model. For example, by calculating the constraint relationship between tire forces and vehicle body forces, ensure the physical consistency of the data in the reduced feature space.

[0092] The physical constraint terms are as follows:

[0093]

[0094] Among them, is the tire force, is the friction coefficient, is the normal force, is the vehicle body force, is the vehicle body mass.

[0095] is the vehicle body acceleration.

[0096] Dynamically adjust the dimension reduction dimension: According to the real-time working conditions and data distribution, dynamically adjust the dimension reduction dimension k to ensure that the most important information is retained in the features after dimension reduction.

[0097] 3. Adaptive neural network modeling

[0098] 3.1 Neural network architecture:

[0099] Input layer: The features Z after dimension reduction are used as the input, with a size of N×k, where N is the number of samples and k is the dimension of the features after dimension reduction.

[0100] Hidden layer: A multi-layer fully connected network is adopted, and each layer uses the ReLU activation function for non-linear mapping.

[0101] · Hidden layer 1: 512 nodes, activation function ReLU

[0102] · Hidden layer 2: 256 nodes, activation function ReLU

[0103] · Hidden layer 3: 128 nodes, activation function ReLU

[0104] Attention mechanism module: This module is used to dynamically adjust the weights of the input features, calculate the weights of each feature based on the weighted sum mechanism, and then perform weighted calculation. This module helps the network focus on the most important features and improve the accuracy of prediction.

[0105] Output layer: Output the three wheel force components of the vehicle:

[0106] · Longitudinal force Fx

[0107] · Lateral force Fy

[0108] · Vertical force Fz

[0109] The unit of the output is Newton (N).

[0110] 4. Physical constraints and loss function

[0111] 4.1 Loss function:

[0112] To ensure the accuracy of the prediction results and comply with physical laws, the loss function is designed as:

[0113]

[0114] Where:

[0115] is the real wheel force, To predict the wheel forces, is the physical constraint term to ensure that the predicted force values comply with vehicle dynamics constraints.

[0116] 4.2 Physical constraint term:

[0117] The physical constraint term is used to constrain the relationship between the prediction result and the actual vehicle dynamics. The specific form is:

[0118]

[0119] where is the predicted force value, is the maximum allowable force of the vehicle under specific working conditions.

[0120] 5. Bayesian optimization and adaptive learning

[0121] 5.1 Principle of Bayesian optimization:

[0122] Objective: Dynamically adjust the hyperparameters in the neural network, such as the learning rate, regularization coefficient, etc., through Bayesian optimization to optimize the training process and avoid overfitting or underfitting.

[0123] Optimization process: Use the Gaussian process model to construct a surrogate model of the objective function define the acquisition function and maximize EI to search for the optimal hyperparameters.

[0124] 5.2 Dynamic parameter update:

[0125] Real-time working condition monitoring: Monitor the changes in the vehicle working conditions at each data input, and trigger the Bayesian optimization algorithm for hyperparameter optimization.

[0126] Optimization update: Adjust the model hyperparameters, such as the learning rate, regularization coefficient, etc., according to the current working conditions and the loss function, so as to improve the prediction accuracy of the model under the new working conditions.

[0127] 6. Output results

[0128] Prediction results:

[0129] Time t1:

[0130] · Longitudinal force Fx = 1200

[0131] · Lateral force Fy = 400N

[0132] · Vertical force Fz = 8500N

[0133] Time t2:

[0134] · Longitudinal force Fx = 1250N

[0135] · Lateral force Fy = 430 N

[0136] · Vertical force Fz = 8600 N

[0137] These predicted values are consistent with the actual working conditions and physical constraints of the vehicle, and can be effectively used to dynamically adjust the vehicle control system to ensure stability and safety during driving.

[0138] In summary, the present invention can improve the physical interpretability of feature selection by combining physical characteristics and principal component analysis (PCA) in the dimension reduction process through an improved dynamic reduced-order model, and incorporate vehicle dynamics constraints. In addition, by designing a hybrid neural network architecture with adaptive learning ability, using an online update mechanism to improve the adaptability of the model to working condition changes, and using multi-modal fusion technology to combine sensor data with vehicle historical operating state data, an accurate modeling of complex non-linear relationships can be achieved.

[0139] For the real-time wheel force prediction method provided in the foregoing embodiments, the present invention provides a real-time wheel force prediction device. Refer to Figure 3 the structural schematic diagram of a real-time wheel force prediction device shown, and the device includes the following parts:

[0140] A data acquisition module 302 that acquires high-dimensional original feature data in real time, where the original feature data includes: wheel center acceleration data and dynamic auxiliary data, and the dynamic auxiliary data includes: vehicle speed, steering angle, tire pressure, tire force, vehicle body force, and vehicle dynamics relationship;

[0141] A dynamic reduced-order module 304 that combines principal component analysis and physical constraints to perform dynamic reduced-order processing on the original feature data to determine the target feature data after reduction;

[0142] A wheel force prediction module 306 that calculates and processes the weight values corresponding to different input features in the target feature data through a preset deep neural network to dynamically adjust the importance of each input feature, and generates a target wheel force prediction result at the output layer of the preset deep neural network by performing weighted calculation on the weight values and the target feature data.

[0143] The above real-time wheel force prediction device provided by the embodiments of the present application can significantly improve the accuracy of wheel force prediction.

[0144] In one implementation, when performing the step of combining principal component analysis with physical constraints to dynamically reduce the dimension of the original feature data and determine the reduced target feature data, the above-mentioned dynamic dimension reduction module 304 is further configured to: perform dynamic dimension reduction processing on the original feature data through a preset principal component analysis model, map the original feature data from a high-dimensional space to a low-dimensional feature space, and make the reduced feature space conform to the vehicle dynamics model by adding a first physical constraint term during the dynamic dimension reduction process, so as to determine the reduced target feature data, where the objective function of the preset principal component analysis model is:

[0145] Z = X

[0146] where W is the dimension reduction matrix, X is the original feature data, and Z is the reduced low-dimensional target feature data.

[0147] In one implementation, when performing the step of making the reduced feature space conform to the vehicle dynamics model by adding a first physical constraint term during the dynamic dimension reduction process, the above-mentioned dynamic dimension reduction module 304 is further configured to: update the objective function of the preset principal component analysis model through the first physical constraint term to determine the updated objective function; use the updated objective function to perform dynamic dimension reduction processing on the original feature data to determine the reduced target feature data, where the updated objective function is:

[0148]

[0149] where is the first physical constraint term, is the weight coefficient for balancing the reconstruction error and physical consistency.

[0150] In one implementation, the above-mentioned dynamic dimension reduction module 304 is further configured to: determine the first physical constraint term according to the constraint relationship between the tire force and the vehicle body force, where the first physical constraint term is expressed as:

[0151]

[0152] where is the tire force, is the friction coefficient, is the normal force, is the vehicle body force, is the vehicle body mass, is the vehicle body acceleration.

[0153] In one implementation, after the step of determining the target feature data after order reduction, the above dynamic order reduction module 304 is further configured to: obtain the real-time working condition of the vehicle and the data distribution of the target feature data, and use a preset dynamic optimization model to dynamically adjust the dimensions of various types of data in the target feature data according to the real-time working condition and the data distribution, so that in the optimized target feature data, the dimension of the data is proportional to the degree of correlation with the wheel force prediction.

[0154] In one implementation, before the step of generating the target wheel force prediction result by the output layer of the preset deep neural network, it includes: determining a second physical constraint term by using the relationship between force and vehicle dynamics, and determining a loss function based on the second physical constraint term to optimize the model parameters of the neural network by using the loss function, where the loss function is:

[0155]

[0156] Where is the real wheel force, is the predicted wheel force, is the second physical constraint term.

[0157] In one implementation, in the step of determining the second physical constraint term by using the relationship between force and vehicle dynamics, it includes: determining the maximum allowable force of the vehicle under different working conditions based on the relationship between force and vehicle dynamics, and determining the second physical constraint term according to the maximum allowable force, where the second physical constraint term is:

[0158]

[0159] Where is the predicted value of the force, is the maximum allowable force of the vehicle under different working conditions.

[0160] The device provided by the embodiments of the present invention has the same implementation principle and the same technical effects as those of the foregoing method embodiments. For the sake of brief description, for the parts not mentioned in the device embodiments, reference may be made to the corresponding content in the foregoing method embodiments.

[0161] The embodiments of the present invention provide a server. Specifically, the server includes a processor and a storage device; a computer program is stored on the storage device, and when the computer program is run by the processor, it executes the method according to any one of the above-mentioned implementations.

[0162] Figure 4A schematic structural diagram of a server provided by an embodiment of the present invention. The server 100 includes: a processor 40, a memory 41, a bus 42, and a communication interface 43. The processor 40, the communication interface 43, and the memory 41 are connected through the bus 42. The processor 40 is configured to execute an executable module stored in the memory 41, such as a computer program.

[0163] Among them, the memory 41 may include a high-speed random access memory (RAM, Random Access Memory), and may also include a non-volatile memory, such as at least one disk memory. Through at least one communication interface 43 (which can be wired or wireless), a communication connection is realized between this system network element and at least one other network element. The Internet, wide area network, local area network, metropolitan area network, etc. can be used.

[0164] The bus 42 can be an ISA bus, a PCI bus, an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, Figure 4 only a bidirectional arrow is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0165] Among them, the memory 41 is used to store a program. After receiving an execution instruction, the processor 40 executes the program. The method executed by the device defined by the flow process disclosed in any one of the foregoing embodiments of the present invention can be applied to the processor 40 or implemented by the processor 40.

[0166] The processor 40 may be an integrated circuit chip with signal processing capabilities. In the implementation process, the steps of the above method can be completed by the integrated logic circuit of the hardware in the processor 40 or the instructions in the form of software. The above-mentioned processor 40 may be a general-purpose processor, including a central processing unit (CPU for short), a network processor (NP for short), etc.; it may also be a digital signal processor (DSP for short), an application specific integrated circuit (ASIC for short), a field-programmable gate array (FPGA for short), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present invention can be directly embodied as being executed and completed by a hardware decoding processor, or executed and completed by a combination of hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory 41, and the processor 40 reads the information in the memory 41 and combines its hardware to complete the steps of the above method.

[0167] The computer program product of the readable storage medium provided by the embodiments of the present invention includes a computer-readable storage medium storing program code, and the instructions included in the program code can be used to execute the method described in the foregoing method embodiments. For the specific implementation, reference can be made to the foregoing method embodiments and will not be elaborated here.

[0168] When the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0169] Finally, it should be noted that the above-mentioned embodiments are only specific implementation manners of the present invention, used to illustrate the technical solutions of the present invention, rather than limiting it. The protection scope of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: any person skilled in the art within the technical scope disclosed by the present invention can still modify the technical solutions recorded in the foregoing embodiments or easily conceive of changes, or perform equivalent replacements on some of the technical features; and these modifications, changes, or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A method for predicting real-time wheel center force, characterized in that, The method includes: Obtaining raw feature data in real time in a high-dimensional space, where the raw feature data includes: wheel center acceleration data and dynamic auxiliary data, and the dynamic auxiliary data includes: vehicle speed, steering angle, tire pressure, tire force, vehicle body force, and vehicle dynamics relationship; Combining principal component analysis with physical constraints, performing dynamic dimensionality reduction processing on the raw feature data, and determining the target feature data after dimensionality reduction; Calculating and processing the weight values corresponding to different input features in the target feature data through a preset deep neural network to dynamically adjust the importance of each input feature, and generating a target wheel force prediction result at the output layer of the preset deep neural network by performing weighted calculation on the weight values and the target feature data; Among them, the step of combining principal component analysis with physical constraints, performing dynamic dimensionality reduction processing on the raw feature data, and determining the target feature data after dimensionality reduction includes: performing dynamic dimensionality reduction processing on the raw feature data through a preset principal component analysis model, mapping the raw feature data from a high-dimensional space to a low-dimensional feature space, and making the feature space after dimensionality reduction conform to the vehicle dynamics model by adding a first physical constraint term during the dynamic dimensionality reduction process to determine the target feature data after dimensionality reduction, where the objective function of the preset principal component analysis model is: Z= X Among them, W is the dimensionality reduction matrix, X is the raw feature data, and Z is the low-dimensional target feature data after dimensionality reduction; Among them, the step of making the feature space after dimensionality reduction conform to the vehicle dynamics model by adding a first physical constraint term during the dynamic dimensionality reduction process includes: updating the objective function of the preset principal component analysis model through the first physical constraint term to determine the updated objective function; using the updated objective function to perform dynamic dimensionality reduction processing on the raw feature data to determine the target feature data after dimensionality reduction, where the updated objective function is: Among them, is the first physical constraint term, is the weight coefficient for balancing reconstruction error and physical consistency; Among them, the first physical constraint term is determined according to the constraint relationship between the tire force and the vehicle body force, and the first physical constraint term is expressed as: Among them, is the tire force, is the friction coefficient, is the normal force, is the vehicle body force, is the vehicle body mass, is the vehicle body acceleration.

2. The real-time wheel force prediction method according to claim 1, characterized in that After the step of determining the target feature data after dimensionality reduction, it includes: Obtaining the real-time working condition of the vehicle and the data distribution of the target feature data, and using a preset dynamic optimization model to perform dynamic adjustment processing on the dimensions of various types of data in the target feature data according to the real-time working condition and the data distribution, so that in the optimized target feature data, the dimension of the data is proportional to the degree of correlation between the data and the wheel force prediction.

3. The real-time wheel force prediction method according to claim 1, characterized in that Before the step of generating a target wheel force prediction result at the output layer of the preset deep neural network, it includes: Determining a second physical constraint term using the relationship between force and vehicle dynamics, and determining a loss function based on the second physical constraint term to optimize the model parameters of the neural network, where the loss function is: Among them, is the real wheel force, is the predicted wheel force, is the second physical constraint term.

4. The real-time wheel force prediction method according to claim 3, wherein The step of determining the second physical constraint term using the relationship between force and vehicle dynamics includes: Based on the relationship between force and vehicle dynamics, determine the maximum allowable force of the vehicle under different working conditions, and determine the second physical constraint term according to the maximum allowable force, where the second physical constraint term is: Among them, is the predicted value of the force, is the maximum allowable force of the vehicle under different working conditions.

5. A prediction device for real-time wheel center force, characterized in that, The device includes: A data acquisition module that acquires high-dimensional original feature data in real time, where the original feature data includes: wheel center acceleration data and dynamic auxiliary data, and the dynamic auxiliary data includes: vehicle speed, steering angle, tire pressure, tire force, vehicle body force, and vehicle dynamics relationship; A dynamic reduction module that combines principal component analysis and physical constraints to perform dynamic reduction processing on the original feature data to determine the reduced target feature data; A wheel center force prediction module that calculates and processes the weight values corresponding to different input features in the target feature data through a preset deep neural network to dynamically adjust the importance of each input feature, and generates a target wheel center force prediction result at the output layer of the preset deep neural network by performing weighted calculation on the weight values and the target feature data; Among them, the step of combining principal component analysis and physical constraints to perform dynamic reduction processing on the original feature data to determine the reduced target feature data includes: performing dynamic reduction processing on the original feature data through a preset principal component analysis model, mapping the original feature data from a high-dimensional space to a low-dimensional feature space, and making the reduced feature space conform to the vehicle dynamics model by adding a first physical constraint term during the dynamic reduction process to determine the reduced target feature data, where the objective function of the preset principal component analysis model is: Z= X Among them, W is the reduction matrix, X is the original feature data, and Z is the reduced low-dimensional target feature data; Among them, the step of making the reduced feature space conform to the vehicle dynamics model by adding a first physical constraint term during the dynamic reduction process includes: updating the objective function of the preset principal component analysis model through the first physical constraint term to determine the updated objective function; using the updated objective function to perform dynamic reduction processing on the original feature data to determine the reduced target feature data, where the updated objective function is: Among them, is the first physical constraint term, is the weight coefficient for balancing reconstruction error and physical consistency; Among them, according to the constraint relationship between the tire force and the vehicle body force, determine the first physical constraint term, where the first physical constraint term is expressed as: Among them, is the tire force, is the friction coefficient, is the normal force, is the vehicle body force, is the vehicle body mass, is the vehicle body acceleration.

6. A server, characterized in that, It includes a processor and a memory, and the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are called and executed by the processor, the computer-executable instructions cause the processor to implement the method according to any one of claims 1 to 4.

Images