Intelligent control method and system for asphalt mixing equipment based on machine vision

Abstract

The invention relates to the technical field of intelligent control, and discloses an asphalt stirring equipment intelligent control method and system based on machine vision, and the method comprises the steps: obtaining a to-be-processed asphalt image, and carrying out the image preprocessing of the to-be-processed asphalt image, and obtaining a binary asphalt image; performing image segmentation according to the binarized asphalt image to obtain a preset number of area images; performing gray gravity center calculation on the regional image and the binarized asphalt image to obtain a total image gravity center and a regional gravity center; according to the gravity center of the total image and the gravity center of the region, determining a caking region by combining a preset caking judgment rule; performing component characteristic analysis on the caking area to obtain a component characteristic value and a uniform mixing degree; and optimizing equipment parameters according to the component characteristic values and the uniform mixing degree to obtain optimal operation parameters, and controlling the asphalt stirring equipment according to the optimal operation parameters. The method can improve the control efficiency of the asphalt stirring equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control, and particularly to an intelligent control method and system for asphalt mixing equipment based on machine vision. Background Art

[0002] In recent years, the rapid development of transportation infrastructure construction and the construction industry has greatly promoted the demand for high-quality road paving materials. Among them, asphalt, as one of the main road paving materials, has also seen a corresponding significant increase in demand. With the continuous improvement of the requirements for high-performance and environmentally friendly asphalt mixtures, asphalt mixing equipment, as a key link in the production process, faces various challenges such as improving product quality, increasing production efficiency, and reducing energy consumption. At the same time, in order to meet the increasingly strict construction standards and environmental protection requirements, the intelligent control of asphalt mixing equipment has become a research hotspot, aiming to ensure the continuity and stability of production through advanced control technologies, reduce errors caused by human factors, and thus guarantee the quality of the final product.

[0003] In an existing method, in a modern asphalt mixing plant, a series of sensors are installed to monitor the process parameters at various stages. These sensors cover types such as temperature sensors, pressure sensors, humidity sensors, weighing sensors, etc., and are used to precisely monitor the input quantity of raw materials, environmental conditions, and the quality of the finished product. For example, the temperature sensor can track the temperature change of asphalt during the heating process in real time; the pressure sensor can detect the pressure situation inside the mixing drum to ensure that the materials are fully mixed under appropriate pressure; the humidity sensor is used to detect the influence of the external environment on the mixing process; and the weighing sensor can accurately measure the input quantity of various components to ensure that the formulation ratio is correct. In addition to sensors, actuators such as motor drivers or valve controllers are also set at key positions to directly control the physical process. For example, the motor driver can adjust the working state of the mixer according to the set speed; the valve controller is responsible for regulating the direction and speed of the material flow to optimize the entire production process. All the above-mentioned devices are connected to one or more programmable logic controllers (PLCs). As a local controller, the PLC receives data from each sensor and sends instructions to the actuators according to a preset program, thereby completing the data acquisition and preliminary processing of the asphalt mixing process.

[0004] However, the existing technical solutions are limited to the simple collection and recording of data, lacking effective integration and in-depth automatic analysis functions for the collected data. This limitation results in the inability to fully utilize these data to guide actual operations even with abundant raw information, restricting the overall operating efficiency of asphalt mixing equipment. Summary of the Invention

[0005] The present invention provides an intelligent control method and system for asphalt mixing equipment based on machine vision to improve the control efficiency of asphalt mixing equipment.

[0006] In a first aspect, to solve the above technical problems, the present invention provides an intelligent control method for asphalt mixing equipment based on machine vision, including:

[0007] Obtain the asphalt image to be processed, and perform image preprocessing on the asphalt image to be processed to obtain a binary asphalt image;

[0008] Perform image segmentation on the binary asphalt image to obtain a preset number of regional images;

[0009] Calculate the gray center of gravity of the regional image and the binary asphalt image to obtain the full-image center of gravity and the regional center of gravity;

[0010] Determine the caking area according to the full-image center of gravity and the regional center of gravity in combination with a preset caking determination rule;

[0011] Perform component feature analysis on the caking area to obtain component feature values and the degree of uniform mixing;

[0012] Optimize the equipment parameters according to the component feature values and the degree of uniform mixing to obtain the optimal equipment operation parameters, and control the asphalt mixing equipment according to the optimal operation parameters.

[0013] In an alternative embodiment, the step of obtaining the asphalt image to be processed and performing image preprocessing on the asphalt image to be processed to obtain a binary asphalt image includes:

[0014] Perform gray-scale processing on the asphalt image to be processed to obtain a gray-scale asphalt image;

[0015] Input the gray-scale asphalt image into a Gaussian filter to obtain a noise-reduced asphalt image;

[0016] Perform an image erosion operation on the noise-reduced asphalt image to obtain a binary asphalt image.

[0017] In an alternative embodiment, the step of performing image segmentation on the binary asphalt image to obtain a preset number of regional images includes:

[0018] Segment the binary asphalt image according to a preset regional side length to obtain a preset number of regional images;

[0019] Wherein, the regional image is a square with a side length of the regional side length.

[0020] In an alternative embodiment, calculating the gray center of gravity of the regional image and the binarized asphalt image to obtain the full-image center of gravity and the regional center of gravity includes:

[0021] Calculating the gray center of gravity through the following formula:

[0022]

[0023] where X S is the abscissa of the gray center of gravity, Y S is the ordinate of the gray center of gravity, N fS is the total number of pixel points in the image, (x i , y i ) is the coordinate of the i-th pixel point, S is the set of all pixel points in the image, x i is the abscissa of the i-th pixel point, y i is the ordinate of the i-th pixel point, and I(x i , y i ) is the binarized pixel value of the i-th pixel point;

[0024] where the full-image center of gravity is the gray center of gravity of the binarized asphalt image, and the regional center of gravity is the gray center of gravity of the regional image.

[0025] In an alternative embodiment, determining the caking area according to the full-image center of gravity and the regional center of gravity in combination with a preset caking determination rule includes:

[0026] Calculating the distance between the full-image center of gravity and each regional center of gravity to obtain the regional distance;

[0027] Extracting the regional images of a preset caking number with the largest regional distance as the caking area according to the regional distance.

[0028] In an alternative embodiment, performing component feature analysis on the caking area to obtain component feature values and the degree of uniform mixing includes:

[0029] Calculating the component feature values through the following formula:

[0030]

[0031] where j is the number of the caking area, A j is the original area of the caking area, A j' is the area of the caking area after erosion operation, and Q(j) is the component feature value of the j-th caking area;

[0032] Calculating the degree of uniform mixing through the following formula:

[0033]

[0034] Wherein, U is the degree of uniform mixing, N is the total number of agglomerated regions, and Q' is the average value of the component characteristic values.

[0035] In an alternative embodiment, optimizing the device parameters according to the component characteristic values and the degree of uniform mixing to obtain the optimal device operating parameters, and controlling the asphalt mixing device according to the optimal operating parameters includes:

[0036] Calculating an optimization coefficient through the following formula:

[0037]

[0038] Wherein, R is the optimization coefficient, α and β are proportionality coefficients, Q' is the average value of the component characteristic values, and Q max is the maximum value of the component characteristic values, and U is the degree of uniform mixing;

[0039] Calculating the optimized drum eccentricity through the following formula:

[0040] e optimal = e·R

[0041] Wherein, e is the preset standard drum eccentricity, and e optimal is the optimized drum eccentricity, and R is the optimization coefficient;

[0042] Calculating the optimized time through the following formula:

[0043] t optimal = t0·R

[0044] Wherein, t optimal represents the optimized time, t0 represents the preset standard time, and R is the optimization coefficient;

[0045] Wherein, the optimal operating parameters include the optimized time and the optimized drum eccentricity.

[0046] In a second aspect, the present invention provides an intelligent control system for an asphalt mixing device based on machine vision, including:

[0047] A data acquisition module, configured to acquire an asphalt image to be processed and perform image preprocessing on the asphalt image to be processed to obtain a binary asphalt image;

[0048] An image segmentation module, configured to perform image segmentation on the binary asphalt image to obtain a preset number of regional images;

[0049] A centroid calculation module, configured to perform gray centroid calculation on the regional image and the binary asphalt image to obtain the full-image centroid and the regional centroid;

[0050] The caking determination module is used to determine the caking area according to the overall image centroid and the regional centroid in combination with a preset caking determination rule;

[0051] The component analysis module is used to perform component feature analysis on the caking area to obtain component feature values and the degree of uniform mixing;

[0052] The equipment control module is used to optimize the equipment parameters according to the component feature values and the degree of uniform mixing to obtain the optimal operating parameters, and control the asphalt mixing equipment according to the optimal operating parameters.

[0053] In a third aspect, the present invention further provides an electronic device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the intelligent control method for asphalt mixing equipment based on machine vision described in any one of the above.

[0054] In a fourth aspect, the present invention further provides a computer-readable storage medium. The computer-readable storage medium includes a stored computer program. When the computer program runs, it controls the device where the computer-readable storage medium is located to execute the intelligent control method for asphalt mixing equipment based on machine vision described in any one of the above.

[0055] Compared with the prior art, the present invention has the following beneficial effects: The present invention discloses an intelligent control method and system for asphalt mixing equipment based on machine vision. The method includes obtaining a to-be-processed asphalt image, performing image preprocessing on the to-be-processed asphalt image to obtain a binary asphalt image; performing image segmentation on the binary asphalt image to obtain a preset number of regional images; calculating the gray center of gravity of the regional images and the binary asphalt image to obtain the overall image centroid and the regional centroid; determining the caking area according to the overall image centroid and the regional centroid in combination with a preset caking determination rule; performing component feature analysis on the caking area to obtain component feature values and the degree of uniform mixing; optimizing the equipment parameters according to the component feature values and the degree of uniform mixing to obtain the optimal operating parameters, and controlling the asphalt mixing equipment according to the optimal operating parameters. This method can improve the control efficiency of asphalt mixing equipment.

[0056] Specifically, this method uses quantification means to evaluate the quality of asphalt mixtures without the need to use complex mathematical formulas. The component feature analysis focuses on the compactness or component distribution of the internal structure within each agglomerate region. By means of an operation called "erosion" in image processing technology, the size of the object can be reduced, and then the changes of the agglomerates before and after this operation can be observed. If the agglomerates are very dense, the erosion operation has little effect on their area; on the contrary, if the agglomerates are relatively loose, the erosion operation will significantly reduce their area. This method can help determine the component characteristics of each agglomerate region.

[0057] For the evaluation of the degree of uniform mixing, it focuses on the consistency of components between each agglomerate region in the whole asphalt mixture. By comparing the component characteristics of multiple agglomerate regions, the similarity between these regions can be understood. When the component characteristics of all agglomerate regions are close, this indicates a better state of uniform mixing; while obvious differences indicate non-uniform mixing. This method combines mathematical models with image processing technology, providing a new way to quantitatively analyze the component characteristics and mixing uniformity of asphalt mixtures. Compared with the traditional methods that only rely on visual inspection or simple physical tests, this method can more accurately capture the changes in the internal structure of the mixture and improve the operating efficiency of asphalt mixing equipment.

[0058] Furthermore, this method performs a series of image preprocessing steps on the obtained asphalt image to be processed, and finally obtains a binary asphalt image. First, the gray-scale processing is performed on the asphalt image to be processed, converting the color image into a gray-scale image, which reduces the data volume and simplifies the subsequent processing process. Then, the gray-scale asphalt image is smoothed by a Gaussian filter to reduce noise interference and improve the image quality. Finally, the erosion operation is performed on the denoised asphalt image. This morphological processing means can eliminate small noise points and help separate closely contacted objects, so as to obtain a binary asphalt image, that is, each pixel in the image is marked as black or white for further analysis.

[0059] Furthermore, for the obtained binary asphalt image, image segmentation is performed according to preset rules, aiming to obtain a preset number of regional images. Specifically, according to the preset regional side length standard, the binary asphalt image is divided into multiple small square regions, and the side length of each small region is equal to the set regional side length. This segmentation method ensures that each regional image is a square with the same size, which is convenient for subsequent more detailed analysis and processing of each regional image, such as component feature analysis, etc., helps to more accurately evaluate the quality of asphalt mixtures, and improves the efficiency of asphalt mixing equipment management.

[0060] Furthermore, this method uses the gray centroid distance to determine the agglomeration area. Gray centroid calculation is a mathematical method in image processing used to describe the central position of the image brightness distribution. For the binary asphalt image and its segmented regional images, this process can provide important information about the position distribution of non-zero pixels (i.e., foreground objects) in the image. First of all, gray centroid calculation helps to extract the key features of the image and is very useful for understanding the central tendency of the image content. Especially in binary images, it can accurately reflect the position distribution of foreground objects. Secondly, using the gray centroid for analysis can assist in judging whether the asphalt mixture is evenly distributed during the mixing process, and whether there are abnormal aggregations or dispersions. This is crucial for ensuring the quality consistency of the asphalt mixture.

[0061] Compared with traditional detection methods, this machine vision-based method provides more objective and accurate data support, reducing the influence of human factors. In addition, it has a higher degree of automation, can complete the processing of a large amount of image data in a short time, and improves the efficiency. At the same time, since a mathematical model is used for calculation, the stability and repeatability of the results are guaranteed, which helps to improve the reliability and accuracy of the intelligent control system of the asphalt mixing equipment. Brief Description of the Drawings

[0062] Figure 1 is a schematic flow chart of an intelligent control method for an asphalt mixing equipment based on machine vision provided by the first embodiment of the present invention;

[0063] Figure 2 is a schematic structural diagram of an intelligent control system for an asphalt mixing equipment based on machine vision provided by the second embodiment of the present invention. Detailed Embodiments

[0064] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without making creative efforts shall fall within the protection scope of the present invention.

[0065] In recent years, the rapid development of transportation infrastructure construction and the construction industry has greatly promoted the demand for high-quality road paving materials. Among them, asphalt, as one of the main road paving materials, has correspondingly seen a significant increase in demand. With the continuous improvement of requirements for high-performance and environmentally friendly asphalt mixtures, asphalt mixing equipment, as a key link in the production process, faces challenges in multiple aspects such as improving product quality, increasing production efficiency, and reducing energy consumption. At the same time, in order to meet the increasingly strict construction standards and environmental protection requirements, the intelligent control of asphalt mixing equipment has become a research hotspot, aiming to ensure the continuity and stability of production through advanced control technologies, reduce errors caused by human factors, and thus guarantee the quality of the final product.

[0066] In an existing method, in a modern asphalt mixing plant, a series of sensors are installed to monitor the process parameters at various stages. These sensors cover types such as temperature sensors, pressure sensors, humidity sensors, weighing sensors, etc., and are used to precisely monitor the input quantity of raw materials, environmental conditions, and the quality of the finished product. For example, the temperature sensor can track the temperature change of asphalt in real time during the heating process; the pressure sensor can detect the pressure situation inside the mixing drum to ensure that the materials are fully mixed under appropriate pressure; the humidity sensor is used to detect the influence of the external environment on the mixing process; and the weighing sensor can accurately measure the input quantity of various components to ensure that the formula ratio is correct. In addition to sensors, actuators such as motor drivers or valve controllers are also set at key positions to directly control the physical process. For example, the motor driver can adjust the working state of the mixer according to the set speed; the valve controller is responsible for adjusting the direction and speed of material flow to optimize the entire production process. All the above-mentioned devices are connected to one or more programmable logic controllers (PLCs). As a local controller, the PLC receives data from each sensor and sends instructions to the actuators according to the preset program to complete the data acquisition and preliminary processing of the asphalt mixing process.

[0067] However, the existing technical solutions are limited to the simple collection and recording of data and lack the effective integration and in-depth automatic analysis functions for the collected data. This limitation leads to the inability to fully utilize these data to guide actual operations even though there is abundant raw information, restricting the overall operating efficiency of asphalt mixing equipment.

[0068] To solve the above problems, referring to Figure 1 , the first embodiment of the present invention provides an intelligent control method for asphalt mixing equipment based on machine vision, including the following steps:

[0069] S11, obtain the asphalt image to be processed, and perform image preprocessing on the asphalt image to be processed to obtain a binary asphalt image;

[0070] S12. Perform image segmentation on the binary asphalt image to obtain a preset number of regional images;

[0071] S13. Calculate the gray - level centroids of the regional images and the binary asphalt image to obtain the full - image centroid and the regional centroids;

[0072] S14. Determine the caking area according to the full - image centroid and the regional centroids in combination with a preset caking determination rule;

[0073] S15. Analyze the component characteristics of the caking area to obtain component characteristic values and the degree of uniform mixing;

[0074] S16. Optimize the equipment parameters according to the component characteristic values and the degree of uniform mixing to obtain the optimal equipment operating parameters, and control the asphalt mixing equipment according to the optimal operating parameters.

[0075] In step S11, obtain the asphalt image to be processed, and perform image pre - processing on the asphalt image to be processed to obtain a binary asphalt image.

[0076] In one implementation, an industrial - grade CCD is used to obtain the asphalt image to be processed. The automatic shooting function is triggered at a fixed time interval through programming, or synchronized with the operation cycle of the mixer to ensure that each shot is taken when the material is in a stable state. Further, the camera should be installed at a key position where the asphalt mixture can be clearly captured, such as inside the mixer or near the discharge port. Ensure that the camera's view covers the entire area to be monitored while avoiding obstacles. At the same time, good lighting is crucial for obtaining high - quality images. Appropriate light sources (such as LED lights) should be used to ensure sufficient brightness and uniform light distribution, reducing the influence of shadows and reflections.

[0077] In one implementation, perform gray - level processing on the asphalt image to be processed to obtain a gray - level asphalt image; input the gray - level asphalt image into a Gaussian filter to obtain a noise - reduced asphalt image; perform an image erosion operation on the noise - reduced asphalt image to obtain a binary asphalt image.

[0078] In one implementation, gray - level processing refers to the process of converting a color image into a gray - level image, and the color information of each pixel is simplified into a brightness value. Gray - level processing is performed through the following formula:

[0079] Y = 0.299R+0.587G + 0.114B

[0080] where Y is the pixel gray - level value, and R, G, and B represent the red, green, and blue channel intensities of the pixel respectively;

[0081] In one implementation, Gaussian filtering is a linear smoothing filter, which is suitable for removing Gaussian noise in an image. It is achieved by calculating the weighted average of pixels in the neighborhood, and the weights are determined by a two-dimensional Gaussian distribution.

[0082] It should be noted that the erosion operation is part of morphological image processing and is used to remove small objects in the image or disconnect the connection between objects. The basic idea of erosion is to slide a structuring element (a small matrix) over the image and only retain those pixels that are completely surrounded by non-zero values. For a binary image, erosion can be defined as follows: if a pixel and all its surrounding pixels (defined by the structuring element) are foreground, then the pixel remains unchanged; otherwise, the pixel becomes background. This can effectively reduce the size of the foreground area, thereby achieving the effect of removing isolated noise points. For a grayscale image, erosion reduces the brightness of brighter areas, making them appear darker, and also makes the boundaries thinner. In practical applications, erosion can be achieved by applying a minimum filter pixel by pixel, that is, selecting the minimum pixel value in the window as the new value at the corresponding position of the output image.

[0083] In step S12, image segmentation is performed on the binary asphalt image to obtain a preset number of regional images.

[0084] In one implementation, the binary asphalt image is segmented according to a preset regional side length to obtain a preset number of regional images; wherein, the regional image is a square with the side length of the regional side length.

[0085] In one implementation, the purpose of image segmentation is to divide the binary asphalt image into multiple smaller and more manageable regions (or sub-images). This can simplify subsequent processing tasks, such as centroid calculation and agglomerate detection. Each region is a square and has a preset side length. First, a suitable square side length is set according to actual needs. For example, for a large image with an original size of 1024x1024 pixels, a smaller side length such as 64 pixels can be selected, so that each region is a small square of 64x64 pixels.

[0086] In step S13, the gray centroid of the regional image and the binary asphalt image is calculated to obtain the global centroid and the regional centroid.

[0087] In one implementation, the gray centroid is calculated by the following formula:

[0088]

[0089] where X S is the abscissa of the gray centroid, Y S is the ordinate of the gray centroid, and N fSis the total number of pixel points in the image, (x i , y i ) is the coordinate of the i-th pixel point, S is the set of all pixel points in the image, x i is the abscissa of the i-th pixel point, y i is the ordinate of the i-th pixel point, I(x i , y i ) is the binary pixel value of the i-th pixel point;

[0090] Among them, the center of gravity of the whole image is the gray center of gravity of the binary asphalt image, and the center of gravity of the region is the gray center of gravity of the region image.

[0091] It should be noted that the gray center of gravity is a mathematical concept used to describe the central position of the brightness distribution in an image, which can help understand the concentration trend of the image content. For a binary image, the gray center of gravity actually reflects the position distribution of non-zero pixels (i.e., foreground objects) in the image.

[0092] In step S14, according to the center of gravity of the whole image and the center of gravity of the region, combined with a preset caking determination rule, the caking area is determined.

[0093] It should be noted that during the asphalt mixing process, if some components are not fully mixed, local aggregation will occur, that is, the so-called "caking". Through the analysis of the gray center of gravity and other features, the caking in the image can be effectively identified. When the gray center of gravity of a certain area significantly deviates from the expected position or the number of non-zero pixel points in this area is extremely high, this is a sign of caking formation.

[0094] In one implementation, calculate the distance between the center of gravity of the whole image and the center of gravity of each region to obtain the region distance; according to the region distance, extract the region images with the largest preset caking number of the region distance as the caking area.

[0095] It should be noted that the region distance is calculated by the following formula:

[0096]

[0097] Among them, d k is the distance from the center of gravity of the k-th region to the center of gravity of the whole image, X Sc is the abscissa of the center of gravity of the whole image, Y Sc is the ordinate of the center of gravity of the whole image, X k is the abscissa of the center of gravity of the k-th region, Y kis the ordinate of the centroid of the k-th region. Set the preset number of lumps to 100, and find the largest 100 regions among them. Since the centroids of these regions are at a relatively large distance, there is a greater probability of containing lumps. Selecting 100 as the preset number of lumps not only ensures a sufficient sample size for subsequent analysis but also is not too large to be difficult to manage and process.

[0098] In step S15, perform a component feature analysis on the lump regions to obtain component feature values and the degree of uniform mixing.

[0099] In one implementation, the component feature values are calculated through the following formula:

[0100]

[0101] where j is the number of the lump region, A j is the original area of the lump region, A j' is the area of the lump region after the erosion operation, and Q(j) is the component feature value of the j-th lump region;

[0102] The degree of uniform mixing is calculated through the following formula:

[0103]

[0104] where U is the degree of uniform mixing, N is the total number of lump regions, and Q' is the average value of the component feature values.

[0105] It should be noted that the component eigenvalue provides a specific value for the internal structural compactness of each caking area, which helps to locate areas with insufficient mixing. The degree of uniform mixing, from a global perspective, evaluates the consistency of caking within the entire sample. This not only helps to detect local anomalies but also reflects the quality control effect of the entire mixing process. The number of the caking area is used to distinguish different caking areas. The original area of the caking area, that is, the area before any image processing (such as erosion operation) is performed. It reflects the initial size of the caking. Erosion is a morphological image processing technique that reduces the size of foreground objects, especially for objects with irregular edges or relatively loose internal structures. Therefore, if a caking is very dense, the erosion has little effect on its area; while if the caking is relatively loose, the erosion will cause a larger reduction in area. The absolute difference represents the difference between the component eigenvalue of a single caking area and the average component eigenvalue. The larger this difference, the greater the difference in compactness between this caking and other cakings. Summing and then dividing by the total number of caking areas is to calculate the degree to which the component eigenvalues of all caking areas deviate from the average value and normalize the result to an average value. The smaller the final degree of uniform mixing value obtained, the more consistent the compactness between caking areas and the more uniform the overall mixing; conversely, a larger degree of uniform mixing value represents uneven mixing.

[0106] In step S16, the equipment parameters are optimized according to the component eigenvalue and the degree of uniform mixing to obtain the optimal equipment operating parameters, and the asphalt mixing equipment is controlled according to the optimal operating parameters.

[0107] In one implementation, the optimization coefficient is calculated by the following formula:

[0108]

[0109] where R is the optimization coefficient, α and β are proportionality coefficients, Q' is the average value of the component eigenvalues, and Q max is the maximum value of the component eigenvalues, and U is the degree of uniform mixing;

[0110] The optimized drum eccentricity is calculated by the following formula:

[0111] e optimal = e·R

[0112] where e is the preset standard drum eccentricity, and e optimal is the optimized drum eccentricity, and R is the optimization coefficient;

[0113] The optimized time is calculated by the following formula:

[0114] t optimal = t0·R

[0115] Among them, t optimal represents the optimization time, t0 represents the preset standard time, and R is the optimization coefficient;

[0116] Among them, the optimal operating parameters include the optimization time and the eccentricity of the optimization drum.

[0117] It should be noted that the optimization coefficient is a comprehensive factor used to adjust the eccentricity of the drum and the mixing time. It reflects the gap between the current mixing state and the ideal state. The proportionality coefficients respectively correspond to the influence weights of the component characteristic value part and the uniform mixing degree part. These two coefficients can be adjusted to balance their contributions to the optimization result. The sum of the two is 1. The optimized eccentricity of the drum, that is, the new drum eccentricity distance after adjustment. The eccentricity of the drum affects the magnitude and distribution of the force received by the material during the mixing process, thereby changing the mixing efficiency. The standard drum eccentricity is set to 50 mm.

[0118] In summary, the present invention discloses an intelligent control method and system for asphalt mixing equipment based on machine vision, aiming to improve the intelligent level of asphalt mixing equipment during the production process. Through a series of image processing techniques, including image acquisition, preprocessing, segmentation, gray center-of-gravity calculation, caking determination, and component characteristic analysis, etc., the quality of the asphalt mixture is evaluated, and the operating parameters of the mixing equipment are optimized according to the evaluation results.

[0119] First, in the image acquisition stage, an industrial-grade CCD camera is used to automatically capture key positions of the asphalt material at set time intervals, such as inside the mixer or near the discharge port, ensuring that each captured image can capture the material in a stable state. To obtain high-quality images, sufficient brightness and uniform light distribution should also be ensured to reduce the influence of shadows and reflections. The acquired color asphalt images will then undergo a series of image preprocessing operations: first, they are converted into grayscale images to simplify the subsequent processing process; then, they are smoothed by a Gaussian filter to reduce noise interference; finally, an erosion operation is implemented to further eliminate small noise points and separate closely contacted objects, thereby forming a binary asphalt image.

[0120] Next, based on the binary asphalt image, the system divides the entire image into multiple small square regions with the same side length according to preset rules, and each region is used as an independent unit for more detailed analysis. This segmentation method helps to calculate the gray center of gravity for each region separately in the subsequent process to determine the center of gravity of the entire image and the center of gravity positions of each region. The gray center of gravity is an important parameter describing the center position of the brightness distribution in the image. For a binary image, it reflects the position distribution of non-zero pixels (i.e., foreground objects) in the image and can help identify abnormal caking phenomena in the image.

[0121] In the caking determination step, by comparing the distances between the center of gravity of the whole image and the centers of gravity of each region, the regions with caking can be screened out. Specifically, when the gray center of gravity of a certain region significantly deviates from the expected position or the number of non-zero pixel points in this region is extremely high, it means that there is caking in this region. Through further analysis of the component characteristics of these suspected caking regions, specific values regarding the compactness of the internal structure of the caking can be obtained, and at the same time, the consistency of caking within the entire sample, that is, the degree of uniform mixing, can be evaluated from a global perspective. The calculation of the component characteristic value and the degree of uniform mixing relies on specific formulas, which not only provide a method for quantitatively analyzing the quality of asphalt mixtures but also provide a basis for adjusting the working parameters of the mixing equipment.

[0122] Finally, based on the component characteristic value and the degree of uniform mixing, the equipment parameters are optimized to obtain the optimal operating parameters, such as optimizing the drum eccentricity and the mixing time. This process involves calculating the optimization coefficient, which is a comprehensive factor used to adjust the drum eccentricity and the mixing time, reflecting the gap between the current mixing state and the ideal state. By introducing a proportional coefficient to balance the contributions of the component characteristic value part and the degree of uniform mixing part to the optimization result, more precise parameter adjustment can be achieved. Finally, according to the optimized parameter settings, the control system issues commands to the asphalt mixing equipment to ensure its operation in the most favorable way for product quality.

[0123] To sum up, the present invention provides a complete intelligent control method for asphalt mixing equipment based on machine vision, integrating a variety of advanced image processing technologies and mathematical models, and improving the control efficiency of asphalt mixing equipment.

[0124] Referring to Figure 2 , the second embodiment of the present invention provides an intelligent control system for asphalt mixing equipment based on machine vision, including:

[0125] A data acquisition module, used to acquire the asphalt image to be processed and perform image preprocessing on the asphalt image to be processed to obtain a binary asphalt image;

[0126] An image segmentation module, used to perform image segmentation according to the binary asphalt image to obtain a preset number of regional images;

[0127] A center of gravity calculation module, used to calculate the gray center of gravity of the regional image and the binary asphalt image to obtain the center of gravity of the whole image and the center of gravity of the region;

[0128] A caking determination module, used to determine the caking region according to the center of gravity of the whole image and the center of gravity of the region in combination with the preset caking determination rule;

[0129] The component analysis module is used to analyze the component characteristics of the caking area to obtain component characteristic values and the degree of uniform mixing;

[0130] The equipment control module is used to optimize the equipment parameters according to the component characteristic values and the degree of uniform mixing to obtain the optimal operating parameters, and control the asphalt mixing equipment according to the optimal operating parameters.

[0131] Preferably, the data acquisition module is used to:

[0132] Obtain the asphalt image to be processed, and perform image preprocessing on the asphalt image to be processed to obtain a binary asphalt image, including:

[0133] Perform grayscale processing on the asphalt image to be processed to obtain a grayscale asphalt image;

[0134] Input the grayscale asphalt image into a Gaussian filter to obtain a noise-reduced asphalt image;

[0135] Perform image erosion operation on the noise-reduced asphalt image to obtain a binary asphalt image.

[0136] Preferably, the image segmentation module is used to:

[0137] Perform image segmentation according to the binary asphalt image to obtain a preset number of regional images, including:

[0138] Segment the binary asphalt image according to a preset regional side length to obtain a preset number of regional images;

[0139] Among them, the regional image is a square with a side length of the regional side length.

[0140] Preferably, the centroid calculation module is used to:

[0141] Perform grayscale centroid calculation on the regional image and the binary asphalt image to obtain the full-image centroid and the regional centroid, including:

[0142] Calculate the grayscale centroid through the following formula:

[0143]

[0144] Among them, X S is the abscissa of the grayscale centroid, Y S is the ordinate of the grayscale centroid, N fS is the total number of pixel points in the image, (x i , y i ) is the coordinate of the i-th pixel point, S is the set of all pixel points in the image, x i is the abscissa of the i-th pixel point, y iis the vertical coordinate of the i-th pixel point, and I(x i , y i ) is the binarized pixel value of the i-th pixel point;

[0145] wherein the center of gravity of the whole image is the gray center of gravity of the binarized asphalt image, and the center of gravity of the region is the gray center of gravity of the region image.

[0146] Preferably, the caking determination module is used for:

[0147] Determine the caking area according to the center of gravity of the whole image and the center of gravity of the region in combination with a preset caking determination rule, including:

[0148] Calculate the distance between the center of gravity of the whole image and the center of gravity of each region to obtain the regional distance;

[0149] Extract the regional images of the preset number of cakings with the largest regional distance as the caking area according to the regional distance.

[0150] Preferably, the component analysis module is used for:

[0151] Conduct component feature analysis on the caking area to obtain component feature values and the degree of uniform mixing, including:

[0152] Calculate the component feature value through the following formula:

[0153]

[0154] where j is the number of the caking area, A j is the original area of the caking area, A j' is the area of the caking area after corrosion operation, and Q(j) is the component feature value of the j-th caking area;

[0155] Calculate the degree of uniform mixing through the following formula:

[0156]

[0157] where U is the degree of uniform mixing, N is the total number of caking areas, and Q' is the average value of the component feature values.

[0158] Preferably, the equipment control module is used for:

[0159] Optimize the equipment parameters according to the component feature value and the degree of uniform mixing to obtain the best operating parameters, and control the asphalt mixing equipment according to the best operating parameters, including:

[0160] Calculate the optimization coefficient through the following formula:

[0161]

[0162] Among them, R is the optimization coefficient, α and β are proportionality coefficients, Q' is the average value of the component characteristic values, and Q max is the maximum value of the component characteristic value, and U is the degree of uniform mixing;

[0163] The optimized drum eccentricity is calculated through the following formula:

[0164] e optimal = e·R

[0165] Among them, e is the preset standard drum eccentricity, and e optimal is the optimized drum eccentricity, and R is the optimization coefficient;

[0166] The optimized time is calculated through the following formula:

[0167] t optimal = t0·R

[0168] Among them, t optimal represents the optimized time, t0 represents the preset standard time, and R is the optimization coefficient;

[0169] Among them, the optimal operating parameters include the optimized time and the optimized drum eccentricity.

[0170] It should be noted that an intelligent control system for an asphalt mixing equipment based on machine vision provided by an embodiment of the present invention is used to execute all the process steps of an intelligent control method for an asphalt mixing equipment based on machine vision in the above embodiment. The working principles and beneficial effects of the two correspond one by one, and thus will not be elaborated here.

[0171] An embodiment of the present invention also provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a data program. When the processor executes the computer program, the steps in the above embodiments of various intelligent control methods for an asphalt mixing equipment based on machine vision are implemented, such as Figure 1 the step S11 shown. Or, when the processor executes the computer program, the functions of each module / unit in the above device embodiments are implemented, such as the data acquisition module.

[0172] Exemplarily, the computer program can be divided into one or more modules / units. The one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device.

[0173] The electronic device can be a computing device such as a desktop computer, notebook, handheld computer, and smart tablet, etc. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the above components are only examples of the electronic device and do not constitute a limitation on the electronic device. It may include more or fewer components than the above, or combine some components, or different components. For example, the electronic device may further include input / output devices, network access devices, a bus, etc.

[0174] The so-called processor may be a central processing unit (CPU), or may also be 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. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor is the control center of the electronic device and connects various parts of the entire electronic device through various interfaces and lines.

[0175] The memory can be used to store the computer programs and / or modules. The processor realizes various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory may mainly include a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the mobile phone (such as audio data, phone book, etc.). In addition, the memory may include high-speed random access memory and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one magnetic disk storage device, flash device, or other volatile solid-state storage devices.

[0176] Among them, if the modules / units integrated in the electronic device are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-described embodiment methods of the present invention, it can also be completed by a computer program instructing relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0177] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art can understand and implement without creative efforts.

[0178] The specific embodiments described above further elaborate on the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only the specific embodiments of the present invention and is not used to limit the protection scope of the present invention. In particular, for those skilled in the art, any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent control method for asphalt mixing equipment based on machine vision, characterized in that, Including: Obtain the asphalt image to be processed, and perform image preprocessing on the asphalt image to be processed to obtain a binary asphalt image; Perform image segmentation according to the binary asphalt image to obtain a preset number of regional images; Perform gray center of gravity calculation on the regional image and the binary asphalt image to obtain the full-image center of gravity and the regional center of gravity; Determine the caking area according to the full-image center of gravity and the regional center of gravity in combination with a preset caking determination rule; Perform component feature analysis on the caking area to obtain component feature values and the degree of uniform mixing; Optimize the equipment parameters according to the component feature values and the degree of uniform mixing to obtain the optimal operating parameters, and control the asphalt mixing equipment according to the optimal operating parameters.

2. The intelligent control method of the asphalt mixing equipment based on machine vision according to claim 1, wherein The obtaining the asphalt image to be processed, and performing image preprocessing on the asphalt image to be processed to obtain a binary asphalt image includes: Perform gray processing on the asphalt image to be processed to obtain a gray asphalt image; Input the gray asphalt image into a Gaussian filter to obtain a noise-reduced asphalt image; Perform image erosion operation on the noise-reduced asphalt image to obtain a binary asphalt image.

3. The intelligent control method for asphalt mixing equipment based on machine vision according to claim 1, characterized in that, The performing image segmentation according to the binary asphalt image to obtain a preset number of regional images includes: Segment the binary asphalt image according to a preset regional side length to obtain a preset number of regional images; Wherein, the regional image is a square with the side length of the regional side length.

4. The intelligent control method for an asphalt mixing plant based on machine vision according to claim 1, wherein, The performing gray center of gravity calculation on the regional image and the binary asphalt image to obtain the full-image center of gravity and the regional center of gravity includes: Calculate the gray center of gravity through the following formula: Among them, X S is the abscissa of the gray - level centroid, Y S is the ordinate of the gray - level centroid, N fS is the total number of pixel points in the image, (x i , y i ) is the coordinate of the i - th pixel point, S is the set of all pixel points in the image, x i is the abscissa of the i - th pixel point, y i is the ordinate of the i - th pixel point, I(x i , y i ) is the binarized pixel value of the i - th pixel point; Wherein the full-image center of gravity is the gray center of gravity of the binary asphalt image, and the regional center of gravity is the gray center of gravity of the regional image.

5. The intelligent control method of the asphalt mixing equipment based on machine vision according to claim 1, characterized in that, The determining the caking area according to the full-image center of gravity and the regional center of gravity in combination with a preset caking determination rule includes: Calculate the distance between the full-image center of gravity and each regional center of gravity to obtain the regional distance; According to the regional distance, extract the regional images with the largest preset caking number of the regional distance as the caking area.

6. The intelligent control method for an asphalt mixing plant based on machine vision according to claim 1, characterized in that The performing component feature analysis on the caking area to obtain component feature values and the degree of uniform mixing includes: Calculate the component feature values through the following formula: Among them, j is the number of the agglomerated area, A j is the original area of the agglomerated area, A j' is the area of the agglomerated area after the erosion operation, and Q(j) is the component characteristic value of the j-th agglomerated area; Calculate the degree of uniform mixing through the following formula: Wherein, U is the degree of uniform mixing, N is the total number of caking areas, and Q' is the average value of the component feature values.

7. The intelligent control method for asphalt mixing equipment based on machine vision according to claim 1, characterized in that The optimizing the equipment parameters according to the component feature values and the degree of uniform mixing to obtain the optimal operating parameters, and controlling the asphalt mixing equipment according to the optimal operating parameters includes: Calculate the optimization coefficient through the following formula: wherein, R is an optimization coefficient, α and β are proportionality coefficients, Q' is the average value of component characteristic values, Q max is the maximum value of component characteristic values, and U is the degree of uniform mixing; Calculate the optimized drum eccentricity through the following formula: e optimal = e·R where e is the preset standard drum eccentricity, e optimal is the optimized drum eccentricity, and R is the optimization coefficient; Calculate the optimized time through the following formula: t optimal = t0·R where t optimal represents the optimization time, t0 represents the preset standard time, and R is the optimization coefficient; Wherein, the optimal operating parameters include the optimized time and the optimized drum eccentricity.

8. An intelligent control system for asphalt mixing equipment based on machine vision, characterized in that, Including: A data acquisition module, configured to obtain the asphalt image to be processed, and perform image preprocessing on the asphalt image to be processed to obtain a binary asphalt image; An image segmentation module, configured to perform image segmentation according to the binary asphalt image to obtain a preset number of regional images; The centroid calculation module is used to perform gray centroid calculation on the regional image and the binary asphalt image to obtain the full-image centroid and the regional centroid; The caking determination module is used to determine the caking area according to the full-image centroid and the regional centroid in combination with a preset caking determination rule; The component analysis module is used to perform component feature analysis on the caking area to obtain component feature values and the degree of uniform mixing; The equipment control module is used to optimize the equipment parameters according to the component feature values and the degree of uniform mixing to obtain the optimal operating parameters, and control the asphalt mixing equipment according to the optimal operating parameters.

9. An electronic device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the intelligent control method for asphalt mixing equipment based on machine vision according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein when the computer program runs, it controls the device where the computer-readable storage medium is located to execute the intelligent control method for asphalt mixing equipment based on machine vision according to any one of claims 1 to 7.

Images