Commercial vehicle EBS road adhesion coefficient identification method, system and device and storage medium

Abstract

The invention provides a commercial vehicle EBS road adhesion coefficient identification method, system and device and a storage medium, and the method comprises the following steps: building a current sample point based on the obtained current slip rate data and current adhesion coefficient under an ABS triggering condition, historical sample points are constructed based on the obtained multiple historical slip rates and the historical attachment coefficients of the corresponding historical slip rates; preprocessing the historical sample points, and constructing the historical sample points and the current sample points to obtain a two-dimensional data set; performing noise reduction fitting on the two-dimensional data set through an RANSAC (Random Sample Consensus) algorithm, and calculating to obtain a primary fitting model parameter and an interior point data set; secondary fitting is carried out on the primary fitting model parameters and the interior point data set through a nonlinear least square method, and secondary fitting model parameters are obtained through calculation; and a peak road surface coefficient is calculated based on the quadratic fitting model parameters, a current road surface adhesion coefficient is identified based on the peak road surface coefficient, and the road surface adhesion condition is determined. The method can accurately identify the road adhesion coefficient.

Description

Technical Field

[0001] This invention belongs to the field of road surface adhesion coefficient processing technology, specifically to the method, system, equipment and storage medium for identifying the EBS road surface adhesion coefficient of commercial vehicles. Background Technology

[0002] The EBS (Electronic Braking System) road adhesion coefficient recognition in commercial vehicles is primarily for more precise adjustment of the force between the tires and the road surface when the ABS (Anti-lock Braking System) is activated. The dynamic perception and response capability of EBS to the road adhesion coefficient is a key technology for improving the safety, efficiency, and adaptability to complex operating conditions of commercial vehicles. Accurate tire-road adhesion recognition is the foundation of vehicle dynamics stability control. Based on the real-time wheel slip rate and road adhesion coefficient, ABS can control the wheels to track the optimal slip rate under the current road adhesion conditions or control the wheel angular acceleration to achieve the purpose of driving / braking anti-skid. Therefore, the road adhesion coefficient plays a crucial role in vehicle dynamics control and is vital to the vehicle's safety system. Accurately assessing the road adhesion coefficient can improve the effectiveness of the vehicle's active safety control system.

[0003] Currently, the road adhesion recognition technologies used in commercial vehicles are mainly divided into image-based methods and tire model methods. While the tire model method can roughly describe the friction characteristics between the tire and the road surface, it still struggles to accurately distinguish between dry asphalt, wet asphalt, dry pebbles, wet pebbles, snow, and ice. This inaccurate data for identifying high-adhesion and low-adhesion road surfaces leads to poor accuracy in the EBS system's control of the vehicle's location, impacting the user's driving experience. Image-based methods, on the other hand, primarily utilize open-source computer vision libraries (Open Source Computer Vision). The library (OpenCV) extracts image features from different road surfaces, trains the model using a convolutional neural network, and finally transmits the model to the vehicle chip. The model processes the real-time acquired road surface images to achieve real-time differentiation and prediction of different road surfaces. Although the image method can accurately distinguish different road surfaces and identify road conditions, it requires the installation of a vision sensor on the vehicle to acquire road surface images. These images then undergo complex processing to obtain the desired data, which is time-consuming. This results in a certain lag in the corresponding operations of the vehicle system. In addition, the training of the model in this box requires a large amount of dataset collection, annotation, and GPU training, which leads to long training times and high generation costs. Summary of the Invention

[0004] To address the problem that image-based identification of road surface adhesion in commercial vehicles is time-consuming and results in a delay in the corresponding actions taken by the onboard system, this invention provides a method, system, device, and storage medium for identifying the EBS road surface adhesion coefficient of commercial vehicles.

[0005] To achieve the above objectives, the present invention provides the following technical solution: This invention proposes a method for identifying the EBS road adhesion coefficient of commercial vehicles, comprising the following steps: Under ABS triggering conditions, the current sample point is constructed based on the current slip ratio data and the current adhesion coefficient, and the historical sample point is constructed based on the acquired multiple historical slip ratios and the corresponding historical adhesion coefficients of the historical slip ratios. After preprocessing the historical sample points, a two-dimensional dataset is constructed by combining them with the current sample points; The two-dimensional dataset is denoised and fitted using the RANSAC algorithm to calculate the parameters of the first-order fitted model and the inlier dataset. The parameters of the second-order fitting model are obtained by performing a second-order fitting on the parameters of the first-order fitting model and the inlier dataset using the nonlinear least squares method. The peak pavement coefficient is calculated based on the parameters of the quadratic fitting model, and the current pavement adhesion coefficient is identified based on the peak pavement coefficient to determine the pavement adhesion status.

[0006] Preferably, the step of obtaining the current slip ratio data and the current adhesion coefficient to construct the current sample point includes: The current slope of the vehicle's current location and the corresponding current braking deceleration are obtained, and the current adhesion coefficient is calculated using the slope and the corresponding current braking deceleration. The vehicle speed at the current moment is obtained and recorded as the current vehicle speed. The wheel speed of the vehicle at the current moment is obtained and recorded as the current wheel speed. The current slip ratio is calculated using the current vehicle speed and the current wheel speed. The current sample point is constructed by using the current slip rate as one coordinate data value within the current sample point and the current adhesion coefficient as another coordinate data value within the current sample point.

[0007] Preferably, the historical sample points are constructed by obtaining multiple historical slip rates and corresponding historical adhesion coefficients of the historical slip rates, including: A time period for acquiring data is preset to be located before the current time. Slope data of multiple time nodes within the time period are selected and recorded as historical slope data. The braking deceleration of the corresponding time node is acquired and recorded as historical braking deceleration. The historical adhesion coefficient is calculated by the historical slope and the historical braking deceleration corresponding to the historical slope. The vehicle speed at the time node is obtained and recorded as the historical vehicle speed, and the wheel speed of vehicle Wang Wenyu at the corresponding time node is obtained and recorded as the historical wheel speed. The historical slip ratio is calculated by the historical vehicle speed and the historical wheel speed. The historical sample point is constructed by using the historical slip rate as one coordinate data value within the historical sample point and the historical adhesion coefficient corresponding to the historical slip rate as another coordinate data value within the historical sample point.

[0008] Preferably, the step of performing noise reduction and fitting on the two-dimensional dataset using the RANSAC algorithm includes: Two data points are randomly selected from the two-dimensional dataset. A first straight line model is obtained by fitting one of the selected data points as the starting point and the other data point as the ending point. Calculate the vertical distance from the remaining data points in the two-dimensional dataset to the first straight line model; A preset distance threshold is used to compare all the vertical distances with the preset distance threshold; Points whose vertical distance is less than the distance threshold are recorded as interior points, and the number of interior points is counted; points whose vertical distance is greater than or equal to the distance threshold are recorded as non-interior points. Then select any two other data points in the two-dimensional dataset to reconstruct the first straight line model, until any two data points in the two-dimensional dataset have completed the construction of the first straight line model; The number of interior points is sorted according to their numerical values. The first straight line model corresponding to the maximum number of interior points is extracted and denoted as the optimal straight line model of the first fitting. The slope and intercept of the optimal straight line model of the first fitting are calculated to obtain the parameters of the first fitting model. In the two-dimensional dataset, the non-interior points marked by the first-fit optimal straight line model are removed to obtain the interior point dataset.

[0009] Preferably, the step of performing a second-order fitting of the first-order fitted model parameters and the interior point dataset using the nonlinear least squares method includes: A linear model is constructed by fitting the slope and intercept of the optimal linear model in one step. The in-point dataset is processed based on a linear model to obtain the in-point processed dataset; Extract all slip ratios and fitted adhesion coefficients from the in-point processing dataset, and calculate the sum of slip ratios, the sum of squared slip ratios, the sum of fitted adhesion coefficients, and the sum of the products of slip ratios and fitted adhesion coefficients; Based on the sum of slip ratios, the sum of squared slip ratios, the sum of fitted adhesion coefficients, and the sum of the products of slip ratios and fitted adhesion coefficients, the quadratic fitting slope and the quadratic fitting intercept are calculated, thus obtaining the parameters of the quadratic fitting model.

[0010] Preferably, the step of processing the interior point dataset based on a linear model to obtain an interior point processed dataset includes: The slip ratios in the inlier dataset are input into the linear model to calculate the fitting adhesion coefficients. The inlier processing dataset is then constructed based on the fitting adhesion coefficients and the corresponding slip ratios.

[0011] Preferably, the peak pavement coefficient is calculated based on the parameters of the quadratic fitting model, and the current pavement adhesion coefficient is identified based on the peak pavement coefficient, including: The compensation coefficient and peak pavement coefficient are determined based on the parameters of the quadratic fitting model. The peak pavement coefficient is compensated based on the compensation coefficient, and the current pavement adhesion coefficient is identified.

[0012] This invention proposes a commercial vehicle EBS road surface adhesion coefficient identification system to implement the aforementioned commercial vehicle EBS road surface adhesion coefficient identification method, characterized by comprising: The data acquisition module is configured to acquire current slip ratio data, current adhesion coefficient, multiple historical slip ratios, and the historical adhesion coefficients of the corresponding historical slip ratios. The sample point construction module is configured to construct a current sample point based on the current slip ratio data and the current adhesion coefficient under ABS triggering conditions, and to construct historical sample points based on the acquired multiple historical slip ratios and the corresponding historical adhesion coefficients of the historical slip ratios. The dataset construction module is configured to preprocess the historical sample points and then construct a two-dimensional dataset with the current sample points. The first-order fitting module is configured to perform noise reduction fitting on the two-dimensional dataset using the RANSAC algorithm, and calculate the first-order fitting model parameters and the inlier dataset. The quadratic fitting module is configured to perform a quadratic fitting of the first-fit model parameters and the interior point dataset using a nonlinear least squares method to calculate the quadratic fitting model parameters. The road surface adhesion identification module is configured to calculate the peak road surface coefficient based on the parameters of the quadratic fitting model, identify the current road surface adhesion coefficient based on the peak road surface coefficient, and determine the road surface adhesion status. The output module is configured to output the road surface adhesion condition and the peak pavement coefficient.

[0013] The present invention proposes a computer device, characterized in that it includes a memory, a processor, and a computer program stored in the memory and executable in the processor, wherein the processor executes the computer program to implement the steps of the above-described commercial vehicle EBS road adhesion coefficient identification method.

[0014] The present invention proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described commercial vehicle EBS road surface adhesion coefficient identification method.

[0015] Compared with the prior art, the present invention has the following beneficial technical effects: This invention proposes a method for identifying the road surface adhesion coefficient of commercial vehicles using EBS (Electrical Bumper System). This method constructs a two-dimensional dataset by combining real-time slip ratio-adhesion coefficient data with historical samples, enabling dynamic tracking of road surface conditions. The RANSAC algorithm is used for noise reduction and fitting, effectively eliminating sensor noise and interference from sudden road surface changes, thus improving model robustness. Nonlinear least-squares quadratic fitting is performed using the first-order fitting parameters as initial values, significantly improving fitting accuracy. The peak adhesion coefficient calculated based on the quadratic fitting model parameters accurately reflects the road surface's ultimate adhesion capability, providing the EBS system with precise decision-making basis for predicting road conditions in advance, shortening vehicle braking distance, and improving the active safety performance of commercial vehicles in complex road conditions.

[0016] Furthermore, this method calculates the current adhesion coefficient by acquiring the slope and corresponding braking deceleration of the vehicle's location in real time, and accurately calculates the slip ratio by combining the current vehicle speed and wheel speed, thus constructing a physically meaningful current sample point. This eliminates the interference of terrain on the adhesion coefficient calculation, making the data more consistent with the physical characteristics of the real road surface and avoiding misjudgments caused by single-wheel lock-up. By fusing multi-source data such as slope, vehicle speed, and wheel speed in real time to construct two-dimensional sample points, the adaptability to operating conditions is significantly improved, and errors are reduced. The final output sample point data provides a high-precision input source for subsequent RANSAC noise reduction and nonlinear fitting, improving the road surface recognition accuracy and providing a reliable road condition perception foundation for commercial vehicle EBS systems.

[0017] Furthermore, this method dynamically collects historical slope, braking deceleration, vehicle speed, and wheel speed data over a preset time period to construct a set of historical sample points with clear physical meaning. This ensures that the slope, vehicle speed, and wheel speed data at the same time point are strictly matched, avoiding asynchronous errors. The final two-dimensional historical sample point set and the current sample point form a spatiotemporally continuous dataset, providing a sufficient and consistent input source for the RANSAC algorithm. This improves the accuracy of adhesion coefficient identification under non-steady-state conditions, enabling the commercial vehicle EBS system to make corresponding decisions based on reliable adhesion coefficients.

[0018] Furthermore, this method constructs an initial model through random sampling, effectively avoiding the local optimum trap and ensuring the globality of model exploration. Then, through a preset distance threshold mechanism, the data is divided into inliers and non-inliers, which can tolerate reasonable data fluctuations and accurately identify outliers. By traversing all point pair combinations to construct the model and counting the number of inliers, an exhaustive exploration of the data distribution characteristics is achieved. Finally, the model with the maximum number of inliers is selected as the optimal solution, ensuring the model's best fit to the main data stream and automating model selection. The operation of removing outliers purifies the dataset, and by retaining high-confidence inliers, a clean inlier dataset is constructed, achieving closed-loop optimization of noise suppression and model fitting, significantly improving the applicability and stability of the algorithm in complex noisy environments. Attached Figure Description

[0019] Figure 1 A schematic flowchart of a commercial vehicle EBS road surface adhesion identification method provided by the present invention; Figure 2 A schematic diagram of a computer device provided in an embodiment of the present invention; Figure 3 This is a block diagram of a chip provided according to an embodiment of the present invention. Detailed Implementation

[0020] In the following description, only certain exemplary embodiments are briefly described. As those skilled in the art will recognize, the described embodiments can be modified in various ways without departing from the spirit or scope of the invention. Therefore, the drawings and description are considered to be exemplary in nature and not restrictive.

[0021] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0022] This invention proposes a method for identifying the EBS road adhesion coefficient of commercial vehicles, such as... Figure 1 As shown, it includes the following steps: Under ABS triggering conditions, the current sample point is constructed based on the current slip ratio data and the current adhesion coefficient, and the historical sample point is constructed based on the acquired multiple historical slip ratios and the corresponding historical adhesion coefficients of the historical slip ratios. Specifically, the calculation of the road surface adhesion coefficient generally adopts a model-based method, which does not require expensive sensors. It only uses common low-cost sensors found in vehicles, such as wheel speed sensors and combined sensors, to measure or estimate the dynamic response changes on the wheels or vehicle body caused by changes in road surface adhesion conditions, and then calculates the road surface adhesion coefficient. ; Adhesion coefficient The formula is:

[0023] In the formula, For the driving force of the wheels, This refers to the vertical load on the wheel.

[0024] Wheel drive force When the vehicle brakes, this is converted into braking force. For the EBS system, since braking force is positively correlated with brake air pressure, theoretically, the higher the brake air pressure, the greater the braking force. Wheel vertical load. The torque is different for the front and rear wheels. Taking the torque at the contact point of the rear wheel, we can obtain:

[0025] In the formula, Let N be the normal force exerted by the ground on the front wheel; The force is the weight of the car, in N; The distance from the vehicle's center of gravity to the rear axle centerline, in meters (m). The mass of the car is expressed in kg. The height of the car's core, in meters (m). For the car's deceleration, m / s 2 .

[0026] Taking the torque about the front ground contact point, we get:

[0027] In the formula, The normal reaction force of the ground on the rear wheel; It is the distance from the center of mass to the center line of the front axle. Therefore, for the front and rear wheels, For and These are the normal reaction forces exerted by the ground on the front and rear wheels, respectively. If the Y-axis of the road is horizontal, then dividing the normal reaction forces of the front and rear wheels by 2 can be considered as the normal reaction forces exerted by the ground on each wheel.

[0028] and This is the braking force during braking. However, EBS can only measure brake air pressure, and the ratio of brake air pressure to brake force is different for each vehicle. Furthermore, braking force is affected by many factors, including the type and dimensions of the brakes, the coefficient of friction of the brake friction pairs, and the wheel radius. Therefore, braking force can be equivalent to braking deceleration. The vertical load on the wheel can be equivalent to gravitational acceleration at this point. ,in, Because of the slope, it is equivalent to the adhesion coefficient. In the formula, the numerator and denominator are both divided by the load m at each wheel end.

[0029] Therefore, the adhesion coefficient The simplified formula is:

[0030] In the formula, For slope, It is the acceleration due to gravity. This is for braking deceleration.

[0031] That is, obtain the slope of the vehicle's current location and the current braking deceleration corresponding to the slope, and calculate the current adhesion coefficient based on the slope and the current braking deceleration corresponding to the slope; The system presets the time period for acquiring data before the current moment during vehicle operation, selects the slope data of multiple time nodes within the preset time period and records them as historical slope data, acquires the braking deceleration of the corresponding time nodes and records it as historical braking deceleration, and calculates the historical adhesion coefficient through historical slope and the historical braking deceleration corresponding to historical slope. Get vehicle speed and the corresponding wheel speed By vehicle speed and the corresponding wheel speed The slip ratio was calculated. ; The formula for calculating slip ratio is:

[0032] In the formula, For vehicle speed, For wheel speed, slip ratio when the wheel is in pure rolling motion. When the wheel is in pure sliding, the slip ratio is 0. When the wheel is rolling and slipping at 100%, 0 < <100%.

[0033] That is, obtain the vehicle's speed at the current moment, and record it as the current speed; obtain the vehicle's wheel speed at the current moment, and record it as the current wheel speed; calculate the current slip ratio using the current speed and the corresponding current wheel speed. That is, the vehicle speed at a given time point during the driving process is obtained and recorded as the historical vehicle speed, and the wheel speed at the corresponding time point during the driving process is obtained and recorded as the historical wheel speed. The historical slip ratio is calculated by using the historical vehicle speed and the corresponding historical wheel speed. The current sample point is constructed by using the current slip rate as one coordinate data value within the current sample point and the current adhesion coefficient as another coordinate data value within the current sample point. The historical sample point is constructed by using the historical slip rate as one coordinate data value within the historical sample point and the historical adhesion coefficient corresponding to the historical slip rate as another coordinate data value within the historical sample point. After preprocessing the historical sample points, a two-dimensional dataset is constructed by combining it with the current sample points; Specifically, the coordinates of historical sample points with negative historical adhesion coefficients are extracted, these coordinate points are removed, and the remaining coordinate points are combined with the current sample points to obtain a two-dimensional dataset.

[0034] The RANSAC algorithm is used to denoise and fit the two-dimensional dataset, and the parameters of the first-order fitting model and the inlier dataset are calculated. Specifically, two data points are randomly selected from the two-dimensional dataset. The first straight line model is obtained by fitting one of the selected data points as the starting point and the other data point as the ending point. The vertical distance from the remaining data points in the two-dimensional dataset to the first straight line model is calculated. A preset distance threshold is set, and all vertical distances are compared with the distance threshold. Points with a vertical distance less than the distance threshold are marked as interior points, and the number of interior points is counted. Points with a vertical distance greater than or equal to the distance threshold are marked as non-interior points. Then, any two other data points in the two-dimensional dataset are selected to reconstruct the first straight line model, until any two data points in the two-dimensional dataset have constructed the first straight line model. Sort the number of interior points of all first straight line models according to their numerical values, extract the first straight line model with the maximum number of interior points, and denote it as the optimal first-fit straight line model. Calculate the slope and intercept of the optimal first-fit straight line model to obtain the parameters of the first-fit model. In a two-dimensional dataset, the non-interior points marked by the best-fit linear model are removed to obtain the interior point dataset.

[0035] The parameters of the quadratic fitting model are obtained by performing a second fitting on the parameters of the fitted line and the inlier dataset using the nonlinear least squares method. Specifically, a linear model is constructed by fitting the slope and intercept of the optimal linear model in one step. The slip ratios in the inlier dataset are input into the linear model to calculate the fitting adhesion coefficients. Based on the fitting adhesion coefficients and the corresponding slip ratios, the inlier processing dataset is constructed. Extract all slip ratios and fitting adhesion coefficients from the interior point processing dataset, and calculate the sum of slip ratios. Sum of squares of slip ratios Sum of fitted adhesion coefficients The sum of the products of slip ratio and fitted adhesion coefficient ; Sum of slip ratios The calculation formula is:

[0036] Sum of fitted adhesion coefficients The calculation formula is:

[0037] Sum of squares of slip ratios The calculation formula is:

[0038] The sum of the products of slip ratio and fitted adhesion coefficient The calculation formula is:

[0039] In the above formula, For interior points, handle the slip ratio in the dataset. For interior point processing, the adhesion coefficient in the dataset is processed. The number of slip ratios or adhesion coefficients in the dataset for interior point processing.

[0040] Through the sum of slip ratios Sum of squares of slip ratios Sum of fitted adhesion coefficients The sum of the products of slip ratio and fitted adhesion coefficient The slope of the second-order fitting was calculated. and the second-order fitting intercept Thus, the parameters of the quadratic fitting model are obtained; Among them, the slope of the second-order fitting The calculation formula is:

[0041] In the formula, For interior point processing, the sum of the products of the central slip ratio and the fitted adhesion coefficient is used. For interior point processing, the sum of adhesion coefficients in the dataset is used. For interior points, process the sum of squared slip rates in the dataset. For interior points, the sum of the central slip ratios in the dataset is processed. The number of slip ratios or fitted adhesion coefficients in the dataset for interior point processing.

[0042] Second-order fitting intercept The calculation formula is:

[0043] In the formula, For inlier processing, the sum of fitting adhesion coefficients in the dataset is used. For interior points, the sum of the central slip ratios in the dataset is processed. The number of slip ratios or fitted adhesion coefficients in the dataset for interior point processing.

[0044] By using the slope of the quadratic fitting and the second-order fitting intercept Calculate the residuals of each data point in the interior point dataset. and the sum of squared residuals And by fitting the sum of squares of the differences between the adhesion coefficient and the mean of the fitted adhesion coefficient. The confidence coefficient is calculated using the sum of squared differences and the sum of squared residuals. Through confidence coefficient Evaluate the fitting accuracy.

[0045] Among them, residual The calculation formula is:

[0046] In the formula, For interior points, handle the slip ratio in the dataset. For inlier processing, the fitting adhesion coefficients in the dataset are processed. The slope of the quadratic fit. The intercept of the second-order fit is given.

[0047] Sum of Squares of Residuals The calculation formula is:

[0048] In the formula, For interior points, process the residuals of each data point in the dataset.

[0049] Sum of squared differences The calculation formula is:

[0050] In the formula, For inlier processing, the fitting adhesion coefficients in the dataset are processed. The mean of all fitted attachment coefficients in the dataset is used for inlier processing.

[0051] Confidence coefficient The calculation formula is:

[0052] In the formula, For the sum of squared residuals, It is the sum of squared differences.

[0053] The peak pavement coefficient is calculated based on the parameters of the quadratic fitting model, and the current pavement adhesion coefficient is identified based on the peak pavement coefficient to determine the pavement adhesion status.

[0054] Specifically, by fitting the slope twice Determine the compensation coefficient That is, when the slope of the second-order fitting When the value is greater than 0.7, it is determined to be high adhesion, and the compensation coefficient is... The value is 1.05; when the slope of the second-order fit is... If the value is between 0.4 and 0.7, it is determined to be medium adhesion, and the compensation coefficient is... The value is 1.00; when the slope of the second-order fit is... When the value is less than 0.4, it is determined to be low adhesion, and the compensation coefficient is... It is 0.92.

[0055] By using the slope of the quadratic fitting and the second-order fitting intercept Peak pavement coefficient was calculated And through compensation coefficient Peak pavement coefficient Compensation is performed to identify the current road surface adhesion coefficient.

[0056] Peak pavement coefficient The calculation formula is:

[0057] In the formula, and For calibration parameters, The value is 0.62. The value is 0.28.

[0058] This invention also proposes a commercial vehicle EBS road surface adhesion coefficient identification system to implement the above-mentioned commercial vehicle EBS road surface adhesion coefficient identification method, including a data acquisition module, a sample point construction module, a dataset construction module, a first-order fitting module, a second-order fitting module, a road surface adhesion identification module, and an output module; The data acquisition module is configured to acquire current slip ratio data, current adhesion coefficient, multiple historical slip ratios, and the historical adhesion coefficients of the corresponding historical slip ratios. The sample point construction module is configured to construct a current sample point based on the current slip ratio data and the current adhesion coefficient under ABS triggering conditions, and to construct historical sample points based on the acquired multiple historical slip ratios and the corresponding historical adhesion coefficients of the historical slip ratios. The dataset construction module is configured to preprocess the historical sample points and then construct a two-dimensional dataset with the current sample points. The first-order fitting module is configured to perform noise reduction fitting on the two-dimensional dataset using the RANSAC algorithm, and calculate the first-order fitting model parameters and the inlier dataset. The quadratic fitting module is configured to perform a quadratic fitting of the first-fit model parameters and the interior point dataset using a nonlinear least squares method to calculate the quadratic fitting model parameters. The road surface adhesion identification module is configured to calculate the peak road surface coefficient based on the parameters of the quadratic fitting model, identify the current road surface adhesion coefficient based on the peak road surface coefficient, and determine the road surface adhesion status. The output module is configured to output the road surface adhesion condition and the peak pavement coefficient.

[0059] In another embodiment of the present invention, a computer device is provided, comprising a processor and a memory. The memory stores a computer program, which includes program instructions. The processor executes the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions to implement a corresponding method flow or corresponding function. The processor in this embodiment of the present invention can be used to implement the operation of the EBS road surface adhesion coefficient identification method for commercial vehicles, including: Under ABS triggering conditions, the current sample point is constructed based on the current slip ratio data and the current adhesion coefficient. Historical sample points are constructed based on multiple historical slip ratios and their corresponding historical adhesion coefficients. After preprocessing the historical sample points, a two-dimensional dataset is constructed with the current sample point. The two-dimensional dataset is then fitted with noise reduction using the RANSAC algorithm to calculate the first-order fitting model parameters and the interior point dataset. The fitted line parameters and the interior point dataset are then fitted with a second-order model using the nonlinear least squares method to calculate the second-order fitting model parameters. The peak pavement coefficient is calculated based on the second-order fitting model parameters, and the current pavement adhesion coefficient is identified based on the peak pavement coefficient to determine the pavement adhesion status.

[0060] In another embodiment of the present invention, a storage medium is also provided, specifically a computer-readable storage medium (Memory). The computer-readable storage medium is a memory device in a terminal device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the terminal device and extended storage media supported by the terminal device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, the storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device.

[0061] One or more instructions stored in a computer-readable storage medium can be loaded and executed by a processor to implement the corresponding steps of the commercial vehicle EBS road adhesion coefficient identification method in the above embodiments; one or more instructions in the computer-readable storage medium are loaded and executed by the processor in the following steps: Under ABS triggering conditions, the current sample point is constructed based on the current slip ratio data and the current adhesion coefficient. Historical sample points are constructed based on multiple historical slip ratios and their corresponding historical adhesion coefficients. After preprocessing the historical sample points, a two-dimensional dataset is constructed with the current sample point. The two-dimensional dataset is then fitted with noise reduction using the RANSAC algorithm to calculate the first-order fitting model parameters and the interior point dataset. The fitted line parameters and the interior point dataset are then fitted with a second-order model using the nonlinear least squares method to calculate the second-order fitting model parameters. The peak pavement coefficient is calculated based on the second-order fitting model parameters, and the current pavement adhesion coefficient is identified based on the peak pavement coefficient to determine the pavement adhesion status.

[0062] Please see Figure 2 The terminal device is a computer device. In this embodiment, the computer device 60 includes a processor 61, a memory 62, and a computer program 63 stored in the memory 62 and executable on the processor 61. When executed by the processor 61, the computer program 63 implements the fluid composition calculation method in the reservoir stimulation wellbore of this embodiment. To avoid repetition, these details are not elaborated here. Alternatively, when executed by the processor 61, the computer program 63 implements the functions of each model / unit in the fluid composition calculation system in the reservoir stimulation wellbore of this embodiment. To avoid repetition, these details are not elaborated here.

[0063] Computer device 60 can be a desktop computer, laptop, handheld computer, cloud server, or other computing device. Computer device 60 may include, but is not limited to, a processor 61 and a memory 62. Those skilled in the art will understand that... Figure 2 This is merely an example of computer device 60 and does not constitute a limitation on computer device 60. It may include more or fewer components than shown, or combine certain components, or different components. For example, computer device may also include input / output devices, network access devices, buses, etc.

[0064] The processor 61 may be a central processing unit (CPU), or other general-purpose processors, CPUs, graphics processing units (GPUs), digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, quantum computing-based data processing logic units, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0065] The memory 62 can be an internal storage unit of the computer device 60, such as a hard disk or RAM of the computer device 60. The memory 62 can also be an external storage device of the computer device 60, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. equipped on the computer device 60.

[0066] Furthermore, the memory 62 may include both internal storage units of the computer device 60 and external storage devices. The memory 62 is used to store computer programs and other programs and data required by the computer device. The memory 62 can also be used to temporarily store data that has been output or will be output.

[0067] Any references to memory, databases, or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0068] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0069] Please see Figure 3 The terminal device is a chip. In this embodiment, the chip 600 includes a processor 622, which may be one or more, and a memory 632 for storing computer programs executable by the processor 622. The computer program stored in the memory 632 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processor 622 may be configured to execute the computer program to perform the generalizable monocular absolute depth map estimation method described above.

[0070] Additionally, chip 600 may also include a power supply component 626 and a communication component 650. The power supply component 626 can be configured to perform power management of chip 600, and the communication component 650 can be configured to enable communication of chip 600, such as wired or wireless communication. Furthermore, chip 600 may also include an input / output interface 658. Chip 600 can operate on an operating system stored in memory 632.

[0071] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered illustrative and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the scope of the invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

[0072] Furthermore, it should be understood that although this specification describes embodiments, not every embodiment contains only one independent technical solution. This narrative style is merely for clarity. Those skilled in the art should consider the specification as a whole, and the technical solutions in each embodiment can be appropriately combined to form other embodiments that can be understood by those skilled in the art. The above content is only for illustrating the technical concept of the present invention and should not be construed as limiting the scope of protection of the present invention. Any modifications made based on the technical concept proposed in this invention shall fall within the scope of protection of the claims of this invention.

Claims

1. A method for identifying the EBS road adhesion coefficient of commercial vehicles, characterized in that, Includes the following steps: Under ABS triggering conditions, the current sample point is constructed based on the current slip ratio data and the current adhesion coefficient, and the historical sample point is constructed based on the acquired multiple historical slip ratios and the corresponding historical adhesion coefficients of the historical slip ratios. After preprocessing the historical sample points, a two-dimensional dataset is constructed by combining them with the current sample points; The two-dimensional dataset is denoised and fitted using the RANSAC algorithm to calculate the parameters of the first-order fitted model and the inlier dataset. The parameters of the second-order fitting model are obtained by performing a second-order fitting on the parameters of the first-order fitting model and the inlier dataset using the nonlinear least squares method. The peak pavement coefficient is calculated based on the parameters of the quadratic fitting model, and the current pavement adhesion coefficient is identified based on the peak pavement coefficient to determine the pavement adhesion status.

2. The method for identifying the EBS road adhesion coefficient of commercial vehicles according to claim 1, characterized in that, The process of obtaining the current slip ratio data and the current adhesion coefficient to construct the current sample point includes: The current slope of the vehicle's current location and the corresponding current braking deceleration are obtained, and the current adhesion coefficient is calculated using the slope and the corresponding current braking deceleration. The vehicle speed at the current moment is obtained and recorded as the current vehicle speed. The wheel speed of the vehicle at the current moment is obtained and recorded as the current wheel speed. The current slip ratio is calculated using the current vehicle speed and the current wheel speed. The current sample point is constructed by using the current slip rate as one coordinate data value within the current sample point and the current adhesion coefficient as another coordinate data value within the current sample point.

3. The method for identifying the EBS road adhesion coefficient of commercial vehicles according to claim 1, characterized in that, The historical sample points are constructed by obtaining multiple historical slip rates and corresponding historical adhesion coefficients of the historical slip rates, including: A time period for acquiring data is preset to be located before the current time. Slope data of multiple time nodes within the time period are selected and recorded as historical slope data. The braking deceleration of the corresponding time node is acquired and recorded as historical braking deceleration. The historical adhesion coefficient is calculated by the historical slope and the historical braking deceleration corresponding to the historical slope. The vehicle speed at the time node is obtained and recorded as the historical vehicle speed, and the wheel speed of vehicle Wang Wenyu at the corresponding time node is obtained and recorded as the historical wheel speed. The historical slip ratio is calculated by the historical vehicle speed and the historical wheel speed. The historical sample point is constructed by using the historical slip rate as one coordinate data value within the historical sample point and the historical adhesion coefficient corresponding to the historical slip rate as another coordinate data value within the historical sample point.

4. The method for identifying the EBS road adhesion coefficient of commercial vehicles according to claim 1, characterized in that, The denoising and fitting of the two-dimensional dataset using the RANSAC algorithm includes: Two data points are randomly selected from the two-dimensional dataset. A first straight line model is obtained by fitting one of the selected data points as the starting point and the other data point as the ending point. Calculate the vertical distance from the remaining data points in the two-dimensional dataset to the first straight line model; A preset distance threshold is used to compare all the vertical distances with the preset distance threshold; Points whose vertical distance is less than the distance threshold are recorded as interior points, and the number of interior points is counted; points whose vertical distance is greater than or equal to the distance threshold are recorded as non-interior points. Then select any two other data points in the two-dimensional dataset to reconstruct the first straight line model, until any two data points in the two-dimensional dataset have completed the construction of the first straight line model; The number of interior points is sorted according to their numerical values. The first straight line model corresponding to the maximum number of interior points is extracted and denoted as the optimal straight line model of the first fitting. The slope and intercept of the optimal straight line model of the first fitting are calculated to obtain the parameters of the first fitting model. In the two-dimensional dataset, the non-interior points marked by the first-fit optimal straight line model are removed to obtain the interior point dataset.

5. The method for identifying the EBS road adhesion coefficient of commercial vehicles according to claim 1, characterized in that, The step of performing a second-order fitting of the first-order fitting model parameters and the interior point dataset using the nonlinear least squares method includes: A linear model is constructed by fitting the slope and intercept of the optimal linear model in one step. The in-point dataset is processed based on a linear model to obtain the in-point processed dataset; Extract all slip ratios and fitted adhesion coefficients from the in-point processing dataset, and calculate the sum of slip ratios, the sum of squared slip ratios, the sum of fitted adhesion coefficients, and the sum of the products of slip ratios and fitted adhesion coefficients; Based on the sum of slip ratios, the sum of squared slip ratios, the sum of fitted adhesion coefficients, and the sum of the products of slip ratios and fitted adhesion coefficients, the quadratic fitting slope and the quadratic fitting intercept are calculated, thus obtaining the parameters of the quadratic fitting model.

6. The method for identifying the EBS road adhesion coefficient of commercial vehicles according to claim 5, characterized in that, The process of processing the interior point dataset based on a linear model to obtain an interior point processed dataset includes: The slip ratios in the inlier dataset are input into the linear model to calculate the fitting adhesion coefficients. The inlier processing dataset is then constructed based on the fitting adhesion coefficients and the corresponding slip ratios.

7. The method for identifying the EBS road adhesion coefficient of commercial vehicles according to claim 1, characterized in that, The peak pavement coefficient is calculated based on the parameters of the quadratic fitting model, and the current pavement adhesion coefficient is identified based on the peak pavement coefficient, including: The compensation coefficient and peak pavement coefficient are determined based on the parameters of the quadratic fitting model. The peak pavement coefficient is compensated based on the compensation coefficient, and the current pavement adhesion coefficient is identified.

8. A commercial vehicle EBS road surface adhesion coefficient identification system, used to implement the commercial vehicle EBS road surface adhesion coefficient identification method according to any one of claims 1 to 9, characterized in that, include: The data acquisition module is configured to acquire current slip ratio data, current adhesion coefficient, multiple historical slip ratios, and the historical adhesion coefficients of the corresponding historical slip ratios. The sample point construction module is configured to, under ABS triggering conditions, construct a current sample point based on the acquired current slip ratio data and the current adhesion coefficient, and construct historical sample points based on the acquired multiple historical slip ratios and the corresponding historical adhesion coefficients of the historical slip ratios. The dataset construction module is configured to preprocess the historical sample points and then construct a two-dimensional dataset with the current sample points. The first-order fitting module is configured to perform noise reduction fitting on the two-dimensional dataset using the RANSAC algorithm, and calculate the first-order fitting model parameters and the inlier dataset. The quadratic fitting module is configured to perform a quadratic fitting of the first-fit model parameters and the interior point dataset using a nonlinear least squares method to calculate the quadratic fitting model parameters. The road surface adhesion identification module is configured to calculate the peak road surface coefficient based on the parameters of the quadratic fitting model, identify the current road surface adhesion coefficient based on the peak road surface coefficient, and determine the road surface adhesion status. The output module is configured to output the road surface adhesion condition and the peak pavement coefficient.

9. A computer device, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory and executable in the processor, wherein the processor executes the computer program to implement the steps of the commercial vehicle EBS road adhesion coefficient identification method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the commercial vehicle EBS road adhesion coefficient identification method according to any one of claims 1 to 7.

Images