Pavement skid resistance detection system based on multi-feature fusion

Abstract

The invention relates to the technical field of road surface detection, in particular to a road surface skid resistance detection system based on multi-feature fusion, which comprises the following steps: applying broadband sweep frequency excitation by using a frequency modulation vibration sensor, matching with the inherent frequency of road surface texture to generate local resonance, and collecting the temperature, humidity and rainfall of a road surface in real time; performing fast Fourier transform on the collected vibration signals to obtain a resonance response spectrum, extracting key parameters through Gaussian fitting, and fusing frequency domain, material and environment data to form a comprehensive feature set; the frequency domain features are converted into three-dimensional energy distribution of pavement microtextures, the actual contact area ratio is calculated according to the three-dimensional energy distribution, an environment temperature and humidity compensation factor is introduced, and a dynamic friction attenuation coefficient is calculated; and comparing the calculated dynamic friction attenuation coefficient with a third-level safety threshold, and outputting a corresponding anti-skid performance level. Multi-source data fusion enables a detection result to be more fit with an actual driving scene, and misjudgment caused by single data is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of road surface detection, and in particular to a road surface anti-skid performance detection system based on multi-feature fusion. Background Art

[0002] The anti-skid performance of a road surface refers to the friction characteristics generated by the relative motion between the vehicle tire and the road surface. It is characterized by the friction coefficient or structural depth. Its essence is the result of the coupling of multiple factors such as tire rubber and road material, texture structure, and environmental conditions. Insufficient anti-skid performance will lead to longer braking distance and increased skidding risk, which is especially prone to traffic accidents under complex working conditions such as high speed and rainy days.

[0003] Existing methods typically divide road surface texture into macrostructure and microtexture and measure them separately. However, under actual driving conditions, the friction between tires and roads is the result of the synergistic effect of macro and micro textures. Traditional detection methods mostly use static tests such as pendulum instruments and sand spreading methods, or friction coefficient measurements based on fixed working conditions. These cannot adapt to dynamic environmental changes such as rainy days and high temperatures. In addition, the impact of long-term factors such as aging and wear of road materials on anti-skid performance cannot be monitored in real time. Summary of the Invention

[0004] The present invention aims to solve the technical problems existing in the prior art and provides a road surface anti-skid performance detection system based on multi-feature fusion.

[0005] The present invention solves the above-mentioned technical problems with the following technical solutions: a road surface anti-skid performance detection system based on multi-feature fusion, comprising: Frequency-adjustable vibration module: uses a frequency-modulated vibration sensor to apply a wide-band sweep excitation, matching the natural frequency of the road surface texture to produce local resonance, and uses the sensor to collect road surface temperature, humidity, and rainfall in real time; Feature extraction and preprocessing module: This module performs fast Fourier transform on the collected vibration signals to obtain the resonance response spectrum, extracts key parameters through Gaussian fitting, identifies the road surface material by comparing it with a template library, and integrates frequency domain, material, and environmental data to form a comprehensive feature set. Friction coupling model building module: This module converts frequency domain features into three-dimensional energy distribution of road surface microtexture, calculates the actual contact area ratio based on the three-dimensional energy distribution, introduces ambient temperature and humidity compensation factors, quantifies the impact of environmental factors on anti-slip performance, and calculates the dynamic friction attenuation coefficient. Anti-skid performance evaluation module: compares the calculated dynamic friction attenuation coefficient with the three-level safety threshold and outputs the corresponding anti-skid performance level.

[0006] In a preferred embodiment, the frequency-adjustable vibration module mounts the frequency-adjustable vibration sensor on the bottom of the vehicle to ensure that the piezoelectric ceramic exciter is in stable contact with the road surface. At the same time, a temperature and humidity sensor and a rainfall sensor are deployed on the vehicle. The detection vehicle is started and driven on the road surface to be detected. During driving, a wide-band swept frequency excitation is continuously applied to the road surface through the piezoelectric ceramic exciter. This frequency band covers the characteristic vibration mode of the micro-texture of the road surface. When the excitation frequency matches the natural frequency of the road surface texture and causes local resonance, the amplitude of the vibration acceleration signal at the corresponding frequency point suddenly changes. The three-axis MEMS accelerometer synchronously collects the normal and tangential vibration responses to obtain the resonance response spectrum. The temperature and humidity sensor and the rainfall sensor synchronously collect road surface environmental parameters, including road surface temperature, humidity and rainfall. All collected data are synchronously transmitted to the on-board data processing terminal for temporary storage.

[0007] In a preferred embodiment, the feature extraction and preprocessing module converts the collected vibration acceleration signal into the frequency domain using a fast Fourier transform algorithm. The specific calculation formula is as follows: Where k=0,1,...,N-1, Represents the time domain vibration acceleration signal, n represents the sampling number, represents the complex number result after frequency domain transformation, k represents the frequency point number, N represents the number of sampling points, determines the frequency resolution, calculates and extracts the relative energy value of each frequency point, and thus constructs the resonance response spectrum. The specific calculation formula is as follows: in, Indicates the relative energy value of the kth frequency point, Represents the amplitude of the frequency domain signal. In the process of constructing the resonance response spectrum, the sweep frequency interval is strictly controlled within 1kHz to ensure that the resolution of the road texture characteristics meets the analysis requirements. Based on the generated resonance response spectrum, the Gaussian fitting algorithm is used to process the obtained resonance response spectrum. The specific calculation formula is as follows: in, Indicates the frequency value, Represents the energy value of the corresponding frequency point, A represents the peak height of the characteristic peak, represents the center frequency of the characteristic peak, represents the half-height width of the characteristic peak, b represents the baseline offset, and key parameters are obtained, including the characteristic peak position and half-height width; After obtaining the key parameters of the resonance response spectrum, compare it with the constructed typical road surface benchmark resonance spectrum feature template library. The correlation coefficient between the measured resonance spectrum and each benchmark spectrum in the template library is calculated. The specific calculation formula is as follows: in, represents the correlation coefficient between the measured resonance spectrum and the jth reference spectrum of the i-th type of pavement material, Represents the relative energy value of the kth frequency point of the measured resonance spectrum, Indicates the relative energy value of the kth frequency point of the jth reference spectrum of the i-th type material, 、 Represents the energy mean of the measured spectrum and the reference spectrum, M represents the number of frequency points involved in the matching, and measures the similarity between them. The matching degree is then optimized based on the least squares method. The specific calculation formula is as follows: Among them, Loss represents the matching error loss function, and the smaller the value, the higher the matching degree. represents the scale factor. Finally, the optimal matching pavement material type i is determined by minimizing the Loss. At the same time, the acoustic impedance correction factor is introduced. The specific calculation formula is as follows: in, represents the correction factor, represents the acoustic impedance of the reference material, represents the estimated acoustic impedance of the measured material, Indicates the corrected frequency energy value, eliminating the interference of the material's intrinsic characteristics on the resonance spectrum. Based on the acoustic impedance correction factor, the interference of the material's intrinsic characteristics on the result is eliminated, thereby determining the material type of the road surface. After completing the vibration response frequency domain feature extraction and road material identification, these data are integrated with the real-time collected road environment parameters to form a comprehensive feature set including vibration frequency domain features, road material information and environmental parameters, which can be specifically expressed as , where F={ }, represents the characteristic peak frequency set, E={ }, represents the characteristic peak energy intensity set, It represents the anisotropy coefficient, which reflects the texture direction characteristics, M represents the pavement material type label, T represents the real-time temperature, H represents the real-time humidity, and R represents the real-time rainfall.

[0008] In a preferred embodiment, the friction coupling model building module obtains the frequency domain characteristics of the processed vibration response data and converts the energy value of each frequency point into the activity level of the texture at a specific scale according to the physical relationship between the resonant frequency and the texture wavelength. The specific calculation formula is as follows: in, Indicates a specific texture wavelength The corresponding activity level, Represents the frequency in the frequency domain characteristics f represents the vibration frequency, represents the environmental correction factor, Indicates the density of the pavement material, through the frequency f and wavelength The reciprocal relationship of the frequency domain energy Mapped to the texture scale, using the environment correction factor k and material density Eliminate physical property interference to ensure To truly reflect the activity level of the texture, the converted results are described from three dimensions. In the texture space frequency dimension, textures of different frequencies are divided and classified according to a certain interval. The specific calculation formula is as follows: in, Indicates the center frequency of the spatial frequency division interval, Indicates the texture wavelength division interval, corresponding to the spatial frequency range of 0.5-20cycle / mm, represents the upper limit of the spatial frequency range, Indicates the lower limit of the spatial frequency range, N indicates the number of divided intervals, Represents the frequency division interval, and evenly divides the spatial frequency according to the inverse of the wavelength to ensure that textures of different scales are effectively captured. In the energy intensity dimension, the energy value corresponding to each texture is normalized. The specific calculation formula is as follows: in, represents the normalized energy intensity, 、 Indicates the minimum and maximum energy activity corresponding to all texture wavelengths in the current sample. By normalizing, the dimension difference of energy value is eliminated, which facilitates the horizontal comparison of texture energy intensity between different samples, highlights the relative contribution of high-frequency or low-frequency texture, and clearly presents the relative strength of different texture energies. In the dimension of anisotropy coefficient, by calculating the ratio of tangential to normal energy, the characteristic differences of texture in different directions are quantified. The specific calculation formula is as follows: in, Represents the anisotropy coefficient, reflecting the difference in energy distribution between the tangential and normal directions of the texture. Indicates the texture activity corresponding to the tangential vibration response, Indicates the texture activity corresponding to the normal vibration response, if =1, indicating that the texture is isotropic. or , reflects the energy advantage of the texture in the tangential or normal direction, affecting the force transmission characteristics during the friction process. The three-dimensional information is integrated and expressed in the form of a tensor to construct the three-dimensional energy distribution of the road surface microtexture, which can be expressed as: ST=[ ( ) ( ) ( )], this tensor can intuitively and comprehensively display the topological characteristics of the road surface texture, providing accurate and intuitive key input data for subsequent friction calculations. Based on the comprehensive feature data set of the feature extraction and preprocessing module, the friction coupling model construction process is started, and the three-dimensional energy distribution data is called. Through the pre-established mapping relationship between energy distribution and actual contact area, the actual contact area ratio of the contact interface between the road surface and the detection equipment is calculated. The specific calculation formula is as follows: in, represents the actual contact area ratio, The smaller the value, the rougher the road surface. Indicates the actual contact area, which is determined by the micro texture of the road surface. Represents the apparent contact area, the macro-geometric area where the testing equipment contacts the road surface, Represents the mapping function between energy distribution and contact area, represents the three-dimensional energy distribution tensor, Indicates the texture spatial frequency, which represents the texture frequency in the x and y directions respectively. Represents the anisotropy coefficient, reflecting the difference in texture direction, It represents the environmental correction factor, which includes the comprehensive influencing factors of environmental factors such as temperature (T), humidity (H), and rainfall (R). This ratio reflects the roughness of the road surface microtexture and the effective contact state; Based on the temperature and humidity data and the real-time environmental parameters, the temperature and humidity compensation factor calculation formula is substituted. The specific calculation formula is as follows: in, represents the comprehensive temperature and humidity compensation factor, represents the temperature compensation factor, It represents the humidity compensation factor. The calculation of the temperature and humidity compensation factor quantifies the impact of temperature and humidity changes on the physical properties of the pavement material, and then adjusts the baseline parameters of the friction calculation. The LuGre model is used. The specific calculation formula is as follows: in, represents the dynamic friction force, represents the elastic stiffness of the bristles, which is related to the contact stiffness of the road surface texture. represents the average deformation of the bristles, characterizing the microscopic deformation of the actual contact area, represents the damping coefficient, reflecting the speed-related energy dissipation, represents the viscous friction coefficient, which characterizes the viscous friction effect at low speeds. v represents the relative sliding velocity. The actual contact area ratio, the temperature and humidity compensation factor, and the energy distribution parameters in the vibration frequency domain characteristics are used as inputs. By solving the model differential equation, the dynamic friction attenuation coefficient is calculated. The specific calculation formula is as follows: in, represents the dynamic friction attenuation coefficient, Represents the normal load, which is related to the vertical pressure on the road surface. Indicates the texture contact area ratio, reflecting the ratio of the actual contact area to the nominal area. Represents the comprehensive temperature compensation factor, which corrects the influence of the environment on friction.

[0009] In a preferred embodiment, the anti-slip performance evaluation module sets three levels of safety thresholds, and compares the dynamic friction attenuation coefficient with the three levels of safety thresholds one by one. The preset three levels of safety thresholds are , the boundary width of the hysteresis comparison strategy is , the anti-slip performance level judgment logic can be expressed as: If , then the anti-skid performance level is excellent anti-skid pavement, if , and the last judgment grade was excellent anti-skid road surface, then maintain the excellent anti-skid road surface grade, otherwise proceed to the next judgment, if , then the anti-skid performance level is qualified pavement, if , and the last judgment grade is qualified road surface, then maintain qualified road surface grade, otherwise proceed to the next judgment, if , then the slip warning is triggered. If If the last judgment was that the slip warning was triggered, the slip warning will be kept triggered; otherwise, it will be judged as a qualified road surface. During the comparison process, if the dynamic friction attenuation coefficient falls within a certain threshold boundary ±0.05, the previous level judgment result will be maintained and no level adjustment will be made. This will avoid frequent jumps in the anti-skid performance level due to slight fluctuations in real-time measurement data. After the comparison is completed, the system will output the corresponding anti-skid performance level according to the judgment result.

[0010] The beneficial effects of the present invention are: the present invention combines vibration response data with environmental parameters, not only considering the texture characteristics of the road surface itself, but also adding environmental factors such as temperature, humidity, and rainfall. Environmental changes will significantly affect the friction performance of the road surface. Multi-source data fusion makes the detection results more in line with the actual driving scene, avoiding misjudgment caused by single data. Starting from the resonance principle of vibration excitation and road surface texture, a model is constructed based on the mechanical properties of materials, so that the detection process is based on reliable physical laws, which can more accurately reflect the essence of the road surface's anti-skid performance. A hierarchical modeling strategy is adopted in the model calculation layer. First, a three-dimensional energy distribution model is constructed to quantify the road surface texture characteristics, and then the friction attenuation coefficient is calculated by integrating multiple factors through the friction coupling model. Through the collaborative work of texture contact, temperature and humidity influence, and dynamic friction, the real friction process is simulated, multi-physical field coupling is realized, and the evaluation of the road surface's anti-skid ability is more in line with actual working conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 is a flow chart of the present invention; Figure 2 This is a system block diagram of the present invention. DETAILED DESCRIPTION

[0012] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0013] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the described features. In the description of this application, "plurality" means two or more, unless otherwise specifically specified.

[0014] In the description of this application, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any person skilled in the art to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art will recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in this application.

[0015] like Figure 1-2 This embodiment provides: a road surface anti-skid performance detection system based on multi-feature fusion, including: Frequency-adjustable vibration module: uses a frequency-modulated vibration sensor to apply a wide-band sweep excitation, matching the natural frequency of the road surface texture to produce local resonance, and uses the sensor to collect road surface temperature, humidity, and rainfall in real time; In this embodiment, what needs to be specifically explained is the adjustable frequency vibration module. The adjustable frequency vibration module mounts the adjustable frequency vibration sensor on the bottom of the vehicle to ensure that the piezoelectric ceramic exciter is in stable contact with the road surface. At the same time, a temperature and humidity sensor and a rainfall sensor are deployed on the vehicle. The detection vehicle is started and driven on the road surface to be detected. During driving, a wide-band swept frequency excitation of 5-50kHz is continuously applied to the road surface through the piezoelectric ceramic exciter. This frequency band covers the characteristic vibration mode of the micro-texture of the road surface. When the excitation frequency matches the natural frequency of the road surface texture and causes local resonance, the amplitude of the vibration acceleration signal at the corresponding frequency point suddenly changes. The three-axis MEMS accelerometer synchronously collects the normal and tangential vibration responses to obtain the resonance response spectrum. The temperature and humidity sensor and the rainfall sensor synchronously collect road environmental parameters, including road surface temperature, humidity and rainfall. All collected data are synchronously transmitted to the on-board data processing terminal for temporary storage.

[0016] It should be noted that before conducting the road anti-skid performance test, the frequency-adjustable vibration sensor is rigidly fixed to the center of the test vehicle chassis through an electromagnetic clamp to ensure that the excitation direction is perpendicular to the road surface. The three-axis MEMS accelerometer is installed at the center of the contact surface of the exciter, and the temperature and humidity sensor and rainfall sensor are installed in an unobstructed place on the roof. The time base of all equipment is calibrated by the on-board synchronous clock to ensure data synchronization.

[0017] Feature extraction and preprocessing module: This module performs fast Fourier transform on the collected vibration signals to obtain the resonance response spectrum, extracts key parameters through Gaussian fitting, identifies the road surface material by comparing it with a template library, and integrates frequency domain, material, and environmental data to form a comprehensive feature set. In this embodiment, the feature extraction and preprocessing module needs to be specifically explained. The feature extraction and preprocessing module uses the fast Fourier transform algorithm to convert the collected vibration acceleration signal from the time domain signal to the frequency domain. The specific calculation formula is as follows: Where k=0,1,...,N-1, Represents the time domain vibration acceleration signal, n represents the sampling number, represents the complex number result after frequency domain transformation, k represents the frequency point number, N represents the number of sampling points, determines the frequency resolution, calculates and extracts the relative energy value of each frequency point, and thus constructs the resonance response spectrum. The specific calculation formula is as follows: in, Indicates the relative energy value of the kth frequency point, Represents the amplitude of the frequency domain signal. In the process of constructing the resonance response spectrum, the sweep frequency interval is strictly controlled within 1kHz to ensure that the resolution of the road texture characteristics meets the analysis requirements. Based on the generated resonance response spectrum, the Gaussian fitting algorithm is used to process the obtained resonance response spectrum. The specific calculation formula is as follows: in, Indicates the frequency value, Represents the energy value of the corresponding frequency point, A represents the peak height of the characteristic peak, represents the center frequency of the characteristic peak, represents the half-height width of the characteristic peak, b represents the baseline offset, and key parameters are obtained, including the characteristic peak position and half-height width; After obtaining the key parameters of the resonance response spectrum, compare it with the constructed typical road surface benchmark resonance spectrum feature template library. The correlation coefficient between the measured resonance spectrum and each benchmark spectrum in the template library is calculated. The specific calculation formula is as follows: in, represents the correlation coefficient between the measured resonance spectrum and the jth reference spectrum of the i-th type of pavement material, Represents the relative energy value of the kth frequency point of the measured resonance spectrum, Indicates the relative energy value of the kth frequency point of the jth reference spectrum of the i-th type material, 、 Represents the energy mean of the measured spectrum and the reference spectrum, M represents the number of frequency points involved in the matching, and measures the similarity between them. The matching degree is then optimized based on the least squares method. The specific calculation formula is as follows: Among them, Loss represents the matching error loss function, and the smaller the value, the higher the matching degree. represents the scale factor. Finally, the optimal matching pavement material type i is determined by minimizing the Loss. At the same time, the acoustic impedance correction factor is introduced. The specific calculation formula is as follows: in, represents the correction factor, represents the acoustic impedance of the reference material, represents the estimated acoustic impedance of the measured material, Indicates the corrected frequency energy value, eliminating the interference of the material's intrinsic characteristics on the resonance spectrum. Based on the acoustic impedance correction factor, the interference of the material's intrinsic characteristics on the result is eliminated, thereby determining the material type of the road surface. After completing the vibration response frequency domain feature extraction and road material identification, these data are integrated with the real-time collected road environment parameters to form a comprehensive feature set including vibration frequency domain features, road material information and environmental parameters, which can be specifically expressed as , where F={ }, represents the characteristic peak frequency set, E={ }, represents the characteristic peak energy intensity set, It represents the anisotropy coefficient, which reflects the texture direction characteristics, M represents the pavement material type label, T represents the real-time temperature, H represents the real-time humidity, and R represents the real-time rainfall.

[0018] First, a 50Hz low-pass filter is used to eliminate vehicle engine vibration interference. A wavelet denoising algorithm is then used to remove high-frequency noise. The preprocessed vibration signal is then subjected to a fast Fourier transform, extracting the energy values ​​of 63 frequency points in the 5-50kHz frequency band at 800Hz intervals. A standardized resonance response spectrum is constructed, and characteristic peaks are fitted using a Gaussian mixture model. The center frequency, half-width at half-maximum, and peak energy of the main and secondary peaks are automatically identified. When matching materials, the dynamic time warping distance is calculated between the measured spectrum and 32 typical pavement types in the template library (including asphalt pavements with different aggregate gradations and oil-to-stone ratios, and concrete pavements with different aggregate types). This is combined with an acoustic impedance correction factor (calculated based on the measured material density ρ ± 0.01g / cm³ and the elastic wave velocity c ± 0.5m / s) to achieve fuzzy matching of material types.

[0019] It should be noted that the update of the template library requires the collection of typical road surface samples from 20 climate distributions across the country every quarter, the establishment of a benchmark data set through a pendulum tester and a dynamic friction coefficient tester, and the use of a transfer learning algorithm to update the material matching model.

[0020] Friction coupling model building module: This module converts frequency domain features into three-dimensional energy distribution of road surface microtexture, calculates the actual contact area ratio based on the three-dimensional energy distribution, introduces ambient temperature and humidity compensation factors, quantifies the impact of environmental factors on anti-slip performance, and calculates the dynamic friction attenuation coefficient. In this embodiment, the friction coupling model construction module needs to be specifically explained. Based on the frequency domain characteristics of the processed vibration response data, the friction coupling model construction module converts the energy value of each frequency point into the activity level of the texture at a specific scale according to the physical relationship between the resonant frequency and the texture wavelength. The specific calculation formula is as follows: in, Indicates a specific texture wavelength The corresponding activity level, Represents the frequency in the frequency domain characteristics f represents the vibration frequency, represents the environmental correction factor, Indicates the density of the pavement material, through the frequency f and wavelength The reciprocal relationship of the frequency domain energy Mapped to the texture scale, using the environment correction factor k and material density Eliminate physical property interference to ensure To truly reflect the activity level of the texture, the converted results are described from three dimensions. In the texture space frequency dimension, textures of different frequencies are divided and classified according to a certain interval. The specific calculation formula is as follows: in, Indicates the center frequency of the spatial frequency division interval, Indicates the texture wavelength division interval, corresponding to the spatial frequency range of 0.5-20cycle / mm, represents the upper limit of the spatial frequency range, Indicates the lower limit of the spatial frequency range, N indicates the number of divided intervals, Represents the frequency division interval, and evenly divides the spatial frequency according to the inverse of the wavelength to ensure that textures of different scales are effectively captured. In the energy intensity dimension, the energy value corresponding to each texture is normalized. The specific calculation formula is as follows: in, represents the normalized energy intensity, 、 Indicates the minimum and maximum energy activity corresponding to all texture wavelengths in the current sample. By normalizing, the dimension difference of energy value is eliminated, which facilitates the horizontal comparison of texture energy intensity between different samples, highlights the relative contribution of high-frequency or low-frequency texture, and clearly presents the relative strength of different texture energies. In the dimension of anisotropy coefficient, by calculating the ratio of tangential to normal energy, the characteristic differences of texture in different directions are quantified. The specific calculation formula is as follows: in, Represents the anisotropy coefficient, reflecting the difference in energy distribution between the tangential and normal directions of the texture. Indicates the texture activity corresponding to the tangential vibration response, Indicates the texture activity corresponding to the normal vibration response, if =1, indicating that the texture is isotropic. or , reflects the energy advantage of the texture in the tangential or normal direction, affecting the force transmission characteristics during the friction process. The three-dimensional information is integrated and expressed in the form of a tensor to construct the three-dimensional energy distribution of the road surface microtexture, which can be expressed as: ST=[ ( ) ( ) ( )], this tensor can intuitively and comprehensively display the topological characteristics of the road surface texture, providing accurate and intuitive key input data for subsequent friction calculations. Based on the comprehensive feature data set of the feature extraction and preprocessing module, the friction coupling model construction process is started, and the three-dimensional energy distribution data is called. Through the pre-established mapping relationship between energy distribution and actual contact area, the actual contact area ratio of the contact interface between the road surface and the detection equipment is calculated. The specific calculation formula is as follows: in, represents the actual contact area ratio, The smaller the value, the rougher the road surface. Indicates the actual contact area, which is determined by the micro texture of the road surface. Represents the apparent contact area, the macro-geometric area where the testing equipment contacts the road surface, Represents the mapping function between energy distribution and contact area, represents the three-dimensional energy distribution tensor, Indicates the texture spatial frequency, which represents the texture frequency in the x and y directions respectively. Represents the anisotropy coefficient, reflecting the difference in texture direction, It represents the environmental correction factor, which includes the comprehensive influencing factors of environmental factors such as temperature (T), humidity (H), and rainfall (R). This ratio reflects the roughness of the road surface microtexture and the effective contact state; Based on the temperature and humidity data and the real-time environmental parameters, the temperature and humidity compensation factor calculation formula is substituted. The specific calculation formula is as follows: in, represents the comprehensive temperature and humidity compensation factor, represents the temperature compensation factor, It represents the humidity compensation factor. The calculation of the temperature and humidity compensation factor quantifies the impact of temperature and humidity changes on the physical properties of the pavement material, and then adjusts the baseline parameters of the friction calculation. The LuGre model is used. The specific calculation formula is as follows: in, represents the dynamic friction force, represents the elastic stiffness of the bristles, which is related to the contact stiffness of the road surface texture. represents the average deformation of the bristles, characterizing the microscopic deformation of the actual contact area, represents the damping coefficient, reflecting the speed-related energy dissipation, represents the viscous friction coefficient, which characterizes the viscous friction effect at low speeds. v represents the relative sliding velocity. The actual contact area ratio, the temperature and humidity compensation factor, and the energy distribution parameters in the vibration frequency domain characteristics are used as inputs. By solving the model differential equation, the dynamic friction attenuation coefficient is calculated. The specific calculation formula is as follows: in, represents the dynamic friction attenuation coefficient, Represents the normal load, which is related to the vertical pressure on the road surface. Indicates the texture contact area ratio, reflecting the ratio of the actual contact area to the nominal area. Represents the comprehensive temperature compensation factor, which corrects the influence of the environment on friction.

[0021] Anti-skid performance evaluation module: compares the calculated dynamic friction attenuation coefficient with the three-level safety threshold and outputs the corresponding anti-skid performance level; In this embodiment, the anti-skid performance evaluation module needs to be specifically explained. The anti-skid performance evaluation module sets three levels of safety thresholds and compares the dynamic friction attenuation coefficient with the three levels of safety thresholds one by one. The preset three levels of safety thresholds are , the boundary width of the hysteresis comparison strategy is , the anti-slip performance level judgment logic can be expressed as: If , then the anti-skid performance level is excellent anti-skid pavement, if , and the last judgment grade was excellent anti-skid road surface, then maintain the excellent anti-skid road surface grade, otherwise proceed to the next judgment, if , then the anti-skid performance level is qualified pavement, if , and the last judgment grade is qualified road surface, then maintain qualified road surface grade, otherwise proceed to the next judgment, if , then the slip warning is triggered. If If the last judgment was that the slip warning was triggered, the slip warning will be kept triggered; otherwise, it will be judged as a qualified road surface. During the comparison process, if the dynamic friction attenuation coefficient falls within a certain threshold boundary ±0.05, the previous level judgment result will be maintained and no level adjustment will be made. This will avoid frequent jumps in the anti-skid performance level due to slight fluctuations in real-time measurement data. After the comparison is completed, the system will output the corresponding anti-skid performance level according to the judgment result.

[0022] It should be noted that, in the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0023] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0024] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0025] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0026] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0027] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0028] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. The road surface anti-skid performance detection system based on multi-feature fusion is characterized by: include: Frequency-adjustable vibration module: uses a frequency-modulated vibration sensor to apply a wide-band sweep excitation, matching the natural frequency of the road surface texture to produce local resonance, and uses the sensor to collect road surface temperature, humidity, and rainfall in real time; Feature extraction and preprocessing module: This module performs fast Fourier transform on the collected vibration signals to obtain the resonance response spectrum, extracts key parameters through Gaussian fitting, identifies the road surface material by comparing it with a template library, and integrates frequency domain, material, and environmental data to form a comprehensive feature set. Friction coupling model building module: This module converts frequency domain features into three-dimensional energy distribution of road surface microtexture, calculates the actual contact area ratio based on the three-dimensional energy distribution, introduces ambient temperature and humidity compensation factors, quantifies the impact of environmental factors on anti-slip performance, and calculates the dynamic friction attenuation coefficient. Anti-skid performance evaluation module: compares the calculated dynamic friction attenuation coefficient with the three-level safety threshold and outputs the corresponding anti-skid performance level.

2. The road surface anti-skid performance detection system based on multi-feature fusion according to claim 1 is characterized in that: The frequency-adjustable vibration module mounts the frequency-adjustable vibration sensor on the bottom of the vehicle to ensure stable contact between the piezoelectric ceramic exciter and the road surface. At the same time, temperature and humidity sensors and rainfall sensors are deployed on the vehicle. The detection vehicle is started and driven on the road to be detected. During driving, the piezoelectric ceramic exciter continuously applies wide-band swept frequency excitation to the road surface. This frequency band covers the characteristic vibration modes of the road surface microtexture. When the excitation frequency matches the natural frequency of the road surface texture and causes local resonance, the amplitude of the vibration acceleration signal at the corresponding frequency point suddenly changes. The three-axis MEMS accelerometer synchronously collects the normal and tangential vibration responses to obtain the resonance response spectrum. The temperature and humidity sensor and rainfall sensor synchronously collect road environmental parameters, including road surface temperature, humidity and rainfall. All collected data are synchronously transmitted to the on-board data processing terminal for temporary storage.

3. The road surface anti-skid performance detection system based on multi-feature fusion according to claim 1 is characterized in that: The feature extraction and preprocessing module uses the fast Fourier transform algorithm to convert the collected vibration acceleration signal from the time domain to the frequency domain, calculates and extracts the relative energy value of each frequency point, and thus constructs the resonance response spectrum. Based on the generated resonance response spectrum, the Gaussian fitting algorithm is used to process the obtained resonance response spectrum. The specific calculation formula is as follows: in, Indicates the frequency value, Represents the energy value of the corresponding frequency point, A represents the peak height of the characteristic peak, represents the center frequency of the characteristic peak, represents the half-height width of the characteristic peak, b represents the baseline offset, and key parameters are obtained, including the characteristic peak position and half-height width.

4. The road surface anti-skid performance detection system based on multi-feature fusion according to claim 3 is characterized in that: After obtaining the key parameters of the resonance response spectrum, compare it with the constructed typical road surface benchmark resonance spectrum feature template library. The correlation coefficient between the measured resonance spectrum and each benchmark spectrum in the template library is calculated. The specific calculation formula is as follows: in, represents the correlation coefficient between the measured resonance spectrum and the jth reference spectrum of the i-th type of pavement material, Represents the relative energy value of the kth frequency point of the measured resonance spectrum, Indicates the relative energy value of the kth frequency point of the jth reference spectrum of the i-th type material, 、 Represents the energy mean of the measured spectrum and the reference spectrum, M represents the number of frequency points involved in the matching, and measures the similarity between them. The matching degree is then optimized based on the least squares method. The specific calculation formula is as follows: Among them, Loss represents the matching error loss function, and the smaller the value, the higher the matching degree. represents the scale factor, and ultimately the optimal matching pavement material type i is determined by minimizing the Loss. At the same time, the acoustic impedance correction factor is introduced to eliminate the interference of the material's intrinsic characteristics on the resonance spectrum. Based on the acoustic impedance correction factor, the interference of the material's intrinsic characteristics on the result is eliminated, thereby determining the material type of the pavement.

5. The road surface anti-skid performance detection system based on multi-feature fusion according to claim 4 is characterized in that: After completing the vibration response frequency domain feature extraction and pavement material identification, these data are integrated with the real-time collected pavement environmental parameters to form a comprehensive feature set including vibration frequency domain features, pavement material information and environmental parameters.

6. The road surface anti-skid performance detection system based on multi-feature fusion according to claim 1 is characterized in that: The friction coupling model construction module obtains the frequency domain characteristics of the vibration response data after processing. Based on the physical relationship between the resonant frequency and the texture wavelength, the energy value of each frequency point is converted into the activity level of the texture of a specific scale. The converted results are described from three dimensions. In the texture spatial frequency dimension, textures of different frequencies are divided and classified according to a certain interval, and the spatial frequency is evenly divided according to the inverse of the wavelength to ensure that textures of different scales are effectively captured. In the energy intensity dimension, the energy value corresponding to each texture is normalized to eliminate the dimensional difference of the energy value through normalization. In the anisotropy coefficient dimension, the characteristic differences of the texture in different directions are quantified by calculating the tangential to normal energy ratio. The specific calculation formula is as follows: in, Represents the anisotropy coefficient, reflecting the difference in energy distribution between the tangential and normal directions of the texture. Indicates the texture activity corresponding to the tangential vibration response, The texture activity level corresponding to the normal vibration response affects the force transmission characteristics during the friction process. The three-dimensional information is integrated and expressed in the form of a tensor to construct the three-dimensional energy distribution of the road surface microtexture. This tensor can intuitively and comprehensively display the topological characteristics of the road surface texture, providing accurate and intuitive key input data for subsequent friction calculations. Based on the comprehensive feature data set of the feature extraction and preprocessing module, the friction coupling model construction process is started, and the three-dimensional energy distribution data is called. Through the pre-established mapping relationship between the energy distribution and the actual contact area, the actual contact area ratio of the contact interface between the road surface and the detection equipment is calculated. This ratio reflects the roughness of the road surface microtexture and the effective contact state.

7. The road surface anti-skid performance detection system based on multi-feature fusion according to claim 6 is characterized in that: Based on the temperature and humidity data and the real-time environmental parameters, the temperature and humidity compensation factor calculation formula is substituted. The specific calculation formula is as follows: in, Represents the comprehensive temperature and humidity compensation factor, represents the temperature compensation factor, represents the temperature compensation factor. Based on the calculation of the temperature and humidity compensation factor, the influence of temperature and humidity changes on the physical properties of the pavement material is quantified, and the reference parameters of the friction calculation are adjusted. The LuGre model is used, and the actual contact area ratio, temperature and humidity compensation factor, and energy distribution parameters in the vibration frequency domain characteristics are used as input. By solving the model differential equation, the dynamic friction attenuation coefficient is calculated. The specific calculation formula is as follows: in, represents the dynamic friction attenuation coefficient, Represents the normal load, which is related to the vertical pressure on the road surface. Indicates the texture contact area ratio, reflecting the ratio of the actual contact area to the nominal area. Represents the comprehensive temperature compensation factor, which corrects the influence of the environment on friction.

8. The road surface anti-skid performance detection system based on multi-feature fusion according to claim 1 is characterized in that: The anti-slip performance evaluation module sets three levels of safety thresholds and compares the dynamic friction attenuation coefficient with the three levels of safety thresholds one by one. The preset three levels of safety thresholds are , the boundary width of the hysteresis comparison strategy is , the anti-slip performance level judgment logic can be expressed as: If , then the anti-skid performance level is excellent anti-skid pavement, if , and the last judgment grade was excellent anti-skid road surface, then maintain the excellent anti-skid road surface grade, otherwise proceed to the next judgment, if , then the anti-skid performance level is qualified pavement, if , and the last judgment grade is qualified road surface, then maintain qualified road surface grade, otherwise proceed to the next judgment, if , then the slip warning is triggered. If If the last judgment was that the slip warning was triggered, the slip warning will be kept triggered; otherwise, it will be judged as a qualified road surface. During the comparison process, if the dynamic friction attenuation coefficient falls within a certain threshold boundary ±0.05, the previous level judgment result will be maintained and no level adjustment will be made. This will avoid frequent jumps in the anti-skid performance level due to slight fluctuations in real-time measurement data. After the comparison is completed, the system will output the corresponding anti-skid performance level according to the judgment result.

Images