A pavement leveling quality analysis and management system based on a leveling device

Abstract

The present invention provides a pavement leveling quality analysis and management system based on a leveling device. By combining the first device parameters of the leveling device, the first pavement leveling image parameters collected by the imaging function module of the leveling device, and the first environmental parameters, a first leveling analysis feature is obtained. According to the first leveling analysis feature and the corresponding first pavement leveling quality grade, a leveling quality analysis model is constructed. The second leveling analysis feature obtained by processing the pavement to be analyzed for leveling is input into the leveling quality analysis model to obtain the target second pavement leveling quality grade. According to the second pavement leveling quality grade, it helps engineering managers to arrange the pavement leveling adjustment work and conduct pavement leveling quality management. By effectively processing the pavement leveling image parameter data and combining environmental parameters, the accuracy of the pavement leveling quality analysis of the model is improved, so as to assist in leveling quality management, reduce labor costs, shorten the pavement leveling analysis time, and improve the level of fine management of the project.

Description

Technical Field

[0001] The present invention belongs to the technical field of automatic management of construction engineering, and particularly relates to a pavement leveling quality analysis and management system based on a leveling device. Background Art

[0002] A leveling machine is a special equipment widely used in the field of road traffic construction, and is used for the leveling and repair of road surfaces. It measures the height difference of the road surface through sensors, and automatically adjusts the height and length of the cutting tools by using a system to achieve the flatness and smoothness of the road surface. In road traffic construction, the flatness and smoothness of the road surface have extremely important impacts on driving comfort, safety and service life. Therefore, it is crucial to analyze and evaluate the pavement leveling quality of the leveling machine.

[0003] The existing pavement leveling quality analysis technology of leveling machines mainly focuses on the monitoring of road surface parameters after the concrete has dried, so as to evaluate the pavement leveling quality. Although it meets the existing requirements to a certain extent, due to the single analysis purpose and limited analysis indicators, there are still great limitations, which are specifically manifested in:

[0004] The existing technology ignores the important impact of the parameter settings of the leveling machine on the leveling operation of different road surfaces on the pavement leveling quality. The leveling speed, power, width of the leveling knife and the surrounding climate environment of the leveling machine all have certain limitations on the pavement leveling quality. In particular, the color and soil quality of the concrete need to be adjusted in a timely manner to ensure the uniform compaction and flatness of the concrete in the area to be leveled. However, the lack of compliance analysis of the leveling operation of the leveling machine for the area to be leveled in the existing technology makes the pavement leveling operation process blurred, and thus is not conducive to the accurate and detailed analysis of the pavement leveling quality. It can be seen that the existing technology has the following problems:

[0005] Firstly, there is a lack of collection, processing and consideration of the image data of the leveled road surface, and the use of environmental factors to evaluate the quality of the pavement leveling, so as to conduct corresponding analysis and management of the pavement leveling quality. Secondly, the classification and management analysis of different leveled road surfaces cannot be well separated from a relatively simple evaluation model for analysis and management, and machine learning algorithms are not fully utilized for accurate quality analysis. Finally, in model selection, the adaptive classification of the model is not well carried out by using the color of the leveled road surface. Summary of the Invention

[0006] To solve the above technical problems, the present invention proposes a pavement leveling quality analysis and management system based on a leveling device.

[0007] In the first aspect of the present invention, a pavement leveling quality analysis and management method based on a leveling device is provided, characterized in that the method includes:

[0008] A1. Obtain the first device parameters of the leveling device, collect the first image parameters of the leveled road surface by the leveling device, and collect the first environmental parameters of the environment where the leveled road surface is located;

[0009] A2. Integrate the first device parameters, the first image parameters of the leveled road surface, and the first environmental parameters to obtain the first leveling analysis feature;

[0010] A3. Construct a leveling quality analysis model according to the first leveling analysis feature and the corresponding first road surface leveling quality level;

[0011] A4. Obtain the second device parameters of the leveling device, collect the second image parameters of the leveled road surface by the leveling device, and collect the second environmental parameters of the environment where the leveled road surface is located; Integrate the second device parameters, the second image parameters of the leveled road surface, and the second environmental parameters to obtain the second leveling analysis feature;

[0012] A5. Input the second leveling analysis feature obtained by processing the leveling road surface to be analyzed into the leveling quality analysis model to obtain the target second road surface leveling quality level, and help engineering managers arrange the road surface leveling adjustment work according to the second road surface leveling quality level to carry out road surface leveling quality management.

[0013] Further, perform feature processing on the first image parameters of the leveled road surface or the second image parameters of the leveled road surface to obtain the first optimized image parameters of the leveled road surface or the second optimized image parameters of the leveled road surface. The first step S1 is as follows:

[0014] Use a color camera to capture the first image of the leveled road surface or the second image of the leveled road surface, and perform segmented regional processing on the captured image. Divide the captured equal-area pictures into T equal parts. The first image parameters of the leveled road surface or the second image parameters of the leveled road surface are the feature processing values of the color images of each region after the first image of the leveled road surface or the second image of the leveled road surface is divided into T equal parts.

[0015] Further, perform feature processing on the first image parameters of the leveled road surface or the second image parameters of the leveled road surface to obtain the first optimized image parameters of the leveled road surface or the second optimized image parameters of the leveled road surface. The last step S2 is as follows:

[0016] Process the first image parameters of the leveled road surface or the second image parameters of the leveled road surface by using the method of image simplification processing.

[0017] Further, the leveling quality analysis model includes a classifier based on the Fisher criterion, a support vector machine, and a neural network model.

[0018] Further, the first device parameter or the second device parameter is the power of the leveling device, the leveling width, and the operating speed of the leveling device.

[0019] Further, the first environmental parameter or the second environmental parameter includes the temperature, humidity, and rainfall around the road surface to be leveled.

[0020] A road surface leveling quality analysis and management system based on a leveling device is also provided, including a leveling quality analysis data acquisition terminal and a quality analysis and management terminal, characterized in that:

[0021] The leveling quality analysis data acquisition terminal includes a leveling parameter acquisition module, an environmental parameter acquisition module, and a camera function module, and the quality analysis and management terminal includes a leveling data processing module, a leveling quality analysis module, and a leveling quality management module, where:

[0022] The leveling parameter acquisition module: acquires the first device parameter of the leveling device and also acquires the second device parameter of the leveling device;

[0023] The environmental parameter acquisition module: performs networking processing, receives the first environmental parameter from the local Internet, and also receives the second environmental parameter;

[0024] The camera function module: is a color camera device, and the device acquires the first road surface leveling image parameter and also acquires the second road surface leveling image parameter;

[0025] The leveling data processing module: receives the first road surface leveling image parameter or the first road surface leveling image parameter to perform feature processing to obtain the first road surface optimized image parameter or the second road surface optimized image parameter, receives the first device parameter, the first environmental parameter, combines with the first road surface optimized image parameter and performs effective feature extraction to obtain the first leveling analysis feature, and also receives the second device parameter, the second environmental parameter obtained from the environmental parameter acquisition module, and the second road surface optimized image parameter acquired and processed by the camera function module, and performs feature extraction to obtain the second leveling analysis feature;

[0026] The leveling quality analysis module: receives the first leveling analysis feature and the corresponding first road surface leveling quality grade given by an expert according to the road surface condition, constructs a leveling quality analysis model according to the first leveling analysis feature and the first road surface leveling quality grade, and also processes according to the second leveling analysis feature model to obtain the second road surface leveling quality grade;

[0027] The leveling quality management module: performs road surface leveling quality analysis according to the second road surface leveling quality grade for different road surfaces to be leveled, and performs leveling quality management.

[0028] Furthermore, the leveling quality analysis model includes a classifier based on the Fisher criterion, a support vector machine, and a neural network model.

[0029] The present invention uses a color imaging device on the leveling device to collect image data of the leveled road surface, and performs regional and single processing. Considering the image data of the leveled road surface to analyze the leveling quality, and fully utilizing environmental factors to evaluate the quality of road leveling, so as to perform corresponding analysis and management on the road leveling quality. Secondly, for the classification and management analysis of different leveled road surfaces, it is not possible to well use machine learning evaluation models for different road scenarios for analysis and management, which improves the accuracy of quality analysis. Finally, in model selection, the color of the leveled road surface is well utilized for adaptive classification of the model, and an accurate and effective road leveling quality grade is obtained, so as to assist in leveling quality management, reduce labor costs, shorten the analysis time of road leveling, and improve the level of fine management of the project. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 is a flowchart of a method for analyzing and managing the quality of road leveling based on a leveling device according to the present invention;

[0031] Figure 2 is a schematic diagram of a leveling quality analysis data acquisition terminal of a road leveling quality analysis and management system based on a leveling device according to the present invention;

[0032] Figure 3 is a schematic diagram of a quality analysis and management terminal of a road leveling quality analysis and management system based on a leveling device according to the present invention;

[0033] Figure 4 is a nine-equal-part road leveling image in the present invention;

[0034] Figure 5 is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0035] Next, with reference to the drawings and specific embodiments, the invention will be further described.

[0036] In a first aspect of the present invention, there is provided a method for analyzing and managing the quality of road leveling based on a leveling device, characterized in that the method includes:

[0037] A1. Obtain the first device parameters of the leveling device, collect the first leveled road surface image parameters of the road surface leveled by the leveling device, and collect the first environmental parameters of the environment where the leveled road surface is located;

[0038] A2. Integrate the first device parameters, the first leveled road surface image parameters, and the first environmental parameters to obtain a first leveling analysis feature;

[0039] A3. Construct a leveling quality analysis model based on the first leveling analysis feature and the corresponding first road surface leveling quality level;

[0040] A4. Obtain the second device parameters of the leveling device, collect the second leveling road surface image parameters of the road surface after leveling by the leveling device, and collect the second environmental parameters of the environment where the leveling road surface is located; integrate the second device parameters, the second leveling road surface image parameters, and the second environmental parameters to obtain the second leveling analysis feature;

[0041] A5. Input the second leveling analysis feature obtained by processing the leveling road surface to be analyzed into the leveling quality analysis model to obtain the target second road surface leveling quality level, and help engineering managers arrange the road surface leveling adjustment work according to the second road surface leveling quality level to carry out road surface leveling quality management.

[0042] Furthermore, perform feature processing on the first leveling road surface image parameters or the second leveling road surface image parameters to obtain the first optimized leveling road surface image parameters or the second optimized leveling road surface image parameters. The steps of S1 are as follows:

[0043] Use a color camera to capture the first leveling road surface image or the second leveling road surface image, and perform segmented regional processing on the captured image. Divide the captured equal-area pictures into T equal parts. The first leveling road surface image parameters or the second leveling road surface image parameters are the feature processing values of the color images of each region after the first leveling road surface image or the second leveling road surface image is divided into T equal parts. The processing formula is:

[0044]

[0045] F s =(R(i,j), G(i,j), B(i,j))

[0046] In the formula, R(i,j), R(i,j), B(i,j) are the gray-scale feature values of the three channels of the color image, k R , k G , k B are correction coefficients, T is the number of equal parts, R n , G n , B n are the image feature values of the three channels of the nth color image after equal division.

[0047] In this embodiment, the picture can be divided into nine equal parts, and the obtained RGB image feature is the average value of the RGB feature values after coefficient adjustment after nine equal divisions, where k R , k G , k BIn this embodiment, it is selected to be between 0.1 and 0.5, specifically determined according to the condition of the levelled road surface. If the levelled road surface is black, then k R is 0.25, k G is 0.25, k B is 0.1. The levelled road surface can also be light yellow and red. For yellow, k R is 0.25, k G is 0.1, k B is 0.25. For red, k R is 0.1, k G is 0.25, k B is 0.25.

[0048] Further, perform feature processing on the first levelled road surface image parameter or the second levelled road surface image parameter to obtain the first optimized levelled road surface image parameter or the second optimized levelled road surface image parameter. The last step S2 is as follows:

[0049] Process the first levelled road surface image parameter or the second levelled road surface image parameter by using the method of image simplification. The formula of the method of image simplification is:

[0050] F = A * R(i, j) + S * G(i, j) + C * B(i, j)

[0051] In the formula, F is the image feature value after image simplification processing, R(i, j), R(i, j), B(i, j) are the gray feature values of the three channels of the color image, i and j are both pixel values, and A, S, C are the image simplification feature weight coefficients.

[0052] In this embodiment, the value ranges of A, S, and C are 0.1 - 0.3, 0.3 - 0.5, and 0.1 - 0.2 respectively. The optimal values in this embodiment are where A = 0.299, S = 0.578, and C = 0.114.

[0053] Further, the levelling quality analysis model includes a classifier based on the Fisher criterion, a support vector machine, and a neural network model.

[0054] Further, the calculation formula of the classifier based on the Fisher criterion is as follows:

[0055]

[0056] M is the first levelling analysis feature or the second levelling analysis feature, L(M) is the output first road surface levelling quality grade or the second road surface levelling quality grade, W Tis the normal vector perpendicular to the hyperplane, obtained by training using the first leveling analysis feature and the first road surface leveling quality grade; |X| is one of the A, S, C image simplification feature weight coefficients selected according to the color change of the leveled road surface.

[0057] In this embodiment, if the road surface is black, the calculation formula of the classifier based on the Fisher criterion is as follows:

[0058]

[0059] If there are also yellow and red, then |X| are 0.578 and 0.299 respectively.

[0060] Furthermore, the first device parameter or the second device parameter is the power of the leveling device, the leveling width, and the operating speed of the leveling device.

[0061] In this embodiment, the expression of this parameter is (P, D, V)

[0062] Furthermore, the first environmental parameter or the second environmental parameter includes the air temperature, humidity, and rainfall around the leveled road surface.

[0063] In this embodiment, the environmental parameter (25, 75, 50) means that the surrounding air temperature is 25°C, the humidity is 75%, and the rainfall is 50 mm.

[0064] Then the first leveling analysis feature or the second leveling analysis feature input into the classifier based on the Fisher criterion is the feature quantity (F, P, D, V, 25, 75, 50).

[0065] The obtained first road surface leveling quality grade or the second road surface leveling quality grade can be divided into three levels, namely L(M) < 0, L(M) = 0, and L(M) > 0, corresponding to low, high, and medium three leveling quality grades.

[0066] There is also provided a road surface leveling quality analysis and management system based on a leveling device, including a leveling quality analysis data acquisition terminal and a quality analysis management terminal, characterized in that:

[0067] The leveling quality analysis data acquisition terminal includes a leveling parameter acquisition module, an environmental parameter acquisition module, and a camera function module, and the quality analysis management terminal includes a leveling data processing module, a leveling quality analysis module, and a leveling quality management module, where:

[0068] The leveling parameter acquisition module: acquires the first device parameter of the leveling device and also acquires the second device parameter of the leveling device;

[0069] The environmental parameter acquisition module: performs networking processing, receives the first environmental parameter from the local Internet, and also receives the second environmental parameter;

[0070] The camera function module: is a color camera device that collects the first flat road surface image parameter and also collects the second flat road surface image parameter;

[0071] The flatness data processing module: receives the first flat road surface image parameter or the first flat road surface image parameter to perform feature processing to obtain the first flat road surface optimized image parameter or the second flat road surface optimized image parameter, receives the first device parameter, the first environmental parameter, combines with the first flat road surface optimized image parameter and performs effective feature extraction to obtain the first flatness analysis feature, and also receives the second device parameter, the second environmental parameter obtained from the environmental parameter acquisition module, and the second flat road surface optimized image parameter collected and processed by the camera function module, and performs feature extraction to obtain the second flatness analysis feature;

[0072] The flatness quality analysis module: receives the first flatness analysis feature and the corresponding first road surface flatness quality grade given by an expert according to the road surface condition, constructs a flatness quality analysis model based on the first flatness analysis feature and the first road surface flatness quality grade, and also processes according to the second flatness analysis feature model to obtain the second road surface flatness quality grade;

[0073] The flatness quality management module: for different flat road surfaces, performs road surface flatness quality analysis according to the second road surface flatness quality grade and conducts flatness quality management.

[0074] Further, the flatness quality analysis model includes a classifier based on the Fisher criterion, a support vector machine, and a neural network model.

[0075] Further, the calculation formula of the classifier based on the Fisher criterion is as follows:

[0076]

[0077] M is the first flatness analysis feature or the second flatness analysis feature, L(M) is the output first road surface flatness quality grade or the second road surface flatness quality grade, W T is the normal vector perpendicular to the hyperplane, obtained by training using the first flatness analysis feature and the first road surface flatness quality grade, and |X| is one of the A, S, C image single feature weight coefficients selected according to the color change of the flat road surface.

[0078] The present invention utilizes the color imaging device on the leveling device to collect the image data of the leveled road surface, and performs regionalization and simplification processing. Considering the image data of the leveled road surface to analyze the leveling quality, and making full use of environmental factors to evaluate the quality of road surface leveling, so as to perform corresponding analysis and management on the road surface leveling quality. Secondly, for the classification and management analysis of different leveled road surfaces, it is not possible to well adopt machine learning evaluation models for different road surface scenarios for analysis and management, which improves the level of precise quality analysis. Finally, in model selection, the color of the leveled road surface is well utilized for adaptive classification of the model, and the accurate and effective road surface leveling quality grade is obtained, so as to assist in leveling quality management, reduce labor costs, shorten the road surface leveling analysis time, and improve the level of engineering refinement management.

[0079] Of course, it can be understood that each embodiment of the present invention can achieve one of the effects alone, and the combination of multiple embodiments of the present invention can achieve all the above effects. However, it is not required that each embodiment of the present invention achieves all the above advantages and effects, because each embodiment of the present invention can form an independent technical solution and make one or more contributions to the prior art.

[0080] For the part of the module structure not specifically defined in the present invention, it shall be subject to the content recorded in the prior art. The prior art mentioned in the foregoing background art part and the specific embodiment part of the present invention can be used as a part of the present invention to understand the meaning of some technical features or parameters. The protection scope of the present invention shall be subject to the content actually recorded in the claims.

Claims

1. A road surface leveling quality analysis and management method based on a leveling device, characterized in that: The method comprises: A1. Obtaining the first device parameters of the leveling device, collecting the first leveling road surface image parameters of the road surface after the leveling device is leveled, and collecting the first environmental parameters of the environment in which the leveling road surface is located; A2. Integrate the first device parameter, the first leveling road surface image parameter and the first environmental parameter to obtain the first leveling analysis feature; A3. Constructing a leveling quality analysis model based on the first leveling analysis characteristics and the corresponding first road surface leveling quality grade; A4. Obtaining a second device parameter of the leveling device, collecting a second leveling road surface image parameter of the road surface after the leveling device has leveled the road surface, and collecting a second environmental parameter of the environment in which the leveling road surface is located; integrating the second device parameter, the second leveling road surface image parameter, and the second environmental parameter to obtain a second leveling analysis feature; A5. Input the second leveling analysis features obtained by the leveling process to be analyzed into the leveling quality analysis model to obtain the target second road leveling quality grade, and help the engineering management personnel to arrange the road leveling adjustment work and perform road leveling quality management according to the second road leveling quality grade; The first leveled road surface image parameter or the second leveled road surface image parameter is subjected to feature processing to obtain the first leveled road surface optimized image parameter or the second leveled road surface optimized image parameter, and step S1 is first as follows: Using a color camera to shoot a leveled road surface image, and performing segmentation and regionalization processing on the shot image, the shot equal-area image is divided into T equal parts, and the leveled road surface image parameter is a feature processing value of the color image of each area after the shot leveled road surface image is divided into T equal parts; The processing formula is: F s =(R(i,j),G(i,j),B(i,j)) In the formula, R(i,j), R(i,j), and B(i,j) are the grayscale eigenvalues ​​of the three channels of the color image, and k R , k G , k B is the correction coefficient, T is the equal fraction, R n , G n , B n are the image feature values ​​of the three channels of the nth color image after equal division; The final step S2 is as follows: The image parameters of the leveled road surface are processed using an image simplification method, and the image simplification method formula is: F=A*R(i,j)+S*G(i,j)+C*B(i,j) Where F is the image feature value after image simplification, R(i,j), R(i,j), B(i,j) are the grayscale feature values ​​of the three channels of the color image, i and j are both pixel values, and A, S, and C are the image simplification feature weight coefficients.

2. A road surface leveling quality analysis and management method based on a leveling device as claimed in claim 1, characterized in that: The leveling quality analysis model includes a classifier based on Fisher criterion, a support vector machine and a neural network model.

3. A road surface leveling quality analysis and management method based on a leveling device as claimed in claim 2, characterized in that: The first device parameter or the second device parameter is the power, the leveling width and the running speed of the leveling device.

4. A road surface leveling quality analysis and management method based on a leveling device as claimed in claim 3, characterized in that: The first environmental parameter or the second environmental parameter includes the temperature, humidity and rainfall around the screed road surface.

5. A road surface leveling quality analysis and management system based on a leveling device, the system implementing the method according to claim 1, comprising a leveling quality analysis data acquisition terminal and a quality analysis management terminal, characterized in that: The leveling quality analysis data acquisition terminal includes a leveling parameter acquisition module, an environmental parameter acquisition module and a camera function module, and the quality analysis management terminal includes a leveling data processing module, a leveling quality analysis module and a leveling quality management module.

6. A road surface leveling quality analysis and management system based on a leveling device as claimed in claim 5, characterized in that: The leveling parameter acquisition module is used to acquire a first device parameter of the leveling device and a second device parameter of the leveling device; The environmental parameter acquisition module performs networking processing to receive the first environmental parameter and the second environmental parameter from the local Internet; The camera function module is a color camera device, which collects the first leveled road surface image parameters and the second leveled road surface image parameters; The leveling data processing module: receives the first leveled pavement image parameter or performs feature processing on the first leveled pavement image parameter to obtain the first leveled pavement optimized image parameter or the second leveled pavement optimized image parameter, receives the first device parameter, the first environmental parameter and the first leveled pavement optimized image parameter and performs effective feature extraction to obtain the first leveling analysis feature, and also receives the second device parameter, the second environmental parameter obtained from the environmental parameter acquisition module, the second leveled pavement optimized image parameter collected and processed by the camera function module, and extracts features to obtain the second leveling analysis feature.

7. A road surface leveling quality analysis and management method based on a leveling device as claimed in claim 6, characterized in that: The leveling quality analysis module receives the first leveling analysis feature and the corresponding first road surface leveling quality grade given by the expert according to the road surface condition, constructs a leveling quality analysis model according to the first leveling analysis feature and the first road surface leveling quality grade, and further processes according to the second leveling analysis feature model to obtain a second road surface leveling quality grade; The leveling quality management module: for different leveled road surfaces, performs road surface leveling quality analysis according to the second road surface leveling quality grade, and performs leveling quality management.

8. A road surface leveling quality analysis and management system based on a leveling device as claimed in claim 7, characterized in that: The leveling quality analysis model includes a classifier based on Fisher criterion, a support vector machine and a neural network model.

Images