Self-adaptive high-uniformity powder spraying intelligent control method and system based on machine vision

Abstract

The invention relates to the technical field of powder spraying intelligent control, and discloses a self-adaptive high-uniformity powder spraying intelligent control method and system based on machine vision, and the method comprises the steps: obtaining image information needed by powder spraying uniformity detection; performing data preprocessing according to the image information to obtain image pixel data and image information entropy data, and weighting the product feature information according to the image information entropy data to obtain product information weight data; performing gray scale equalization processing on the image information based on the image pixel data to obtain gray scale equalization data; calculating a uniformity index of powder spraying uniformity according to the equalization data to obtain powder spraying uniformity data; performing weighted summation according to product information weight data and the powder spraying uniformity data to obtain an actual powder spraying uniformity index of the product surface; and according to the actual powder spraying uniformity index and a preset target powder spraying uniformity index, a self-adaptive powder spraying adjustment instruction is formulated. According to the method, intelligent control over high-uniformity powder spraying is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of powder spraying intelligent control, and in particular to a machine vision-based adaptive high-uniformity powder spraying intelligent control method and system. Background Art

[0002] At present, in the industrial field, in order to ensure product quality, there are extremely strict requirements for the uniformity of coating on the surface of materials; whether it is automobile manufacturing, home appliance production or aerospace industries, the uniformity of coating directly affects the appearance quality and performance of products; therefore, the quality inspection and control of uniform distribution of powder has always been the focus and difficulty of research; in recent years, with the rapid development of automation and intelligent technology, automatic powder spraying system based on machine vision has gradually become a hot spot for research and application. Machine vision technology captures images through cameras, uses image processing algorithms to analyze and identify features in images, and can realize real-time monitoring and automatic control of the powder spraying process; compared with traditional methods, the detection method based on machine vision has higher accuracy, faster speed and stronger stability, which can significantly improve the quality and efficiency of the powder spraying process.

[0003] In an existing technology, an innovative method based on image processing technology is used to monitor and evaluate the uniformity of the powder spraying process. Specifically, this technology captures the atomized spray images during the powder spraying process and performs grayscale histogram analysis on these images to determine the uniformity of the powder spraying distribution. The grayscale histogram can reflect the distribution of pixels of different grayscale levels in the image. When the number of peaks in the image grayscale histogram meets the preset standard, the system will determine that the powder sprayed by the spray gun has achieved an ideal uniform atomization state, which means that the coating can evenly cover the target surface and ensure the quality and performance of the final product. On the contrary, if the number of peaks in the grayscale histogram does not reach or exceed the preset threshold, this indicates that non-uniform atomization has occurred during the powder spraying process, which will affect the consistency and durability of the coating. At this time, the operator can adjust the spray gun parameters such as injection pressure, flow rate, etc. according to the system feedback to optimize the powder spraying effect and ensure the coating quality.

[0004] However, in the above-mentioned prior art, the unevenness of powder spraying is analyzed by image grayscale histogram, and the characteristics of powder spraying uniformity are ignored, which will lead to the inability to accurately analyze the specific situation of powder spraying uniformity, thereby making it impossible to achieve high-uniformity powder spraying intelligent control. Summary of the invention

[0005] The present invention provides a machine vision-based adaptive high-uniformity powder spraying intelligent control method and system, which can accurately analyze the specific situation of powder spraying uniformity and realize high-uniformity powder spraying intelligent control.

[0006] In the first aspect, in order to solve the above technical problems, the present invention provides an adaptive high-uniformity powder spraying intelligent control method based on machine vision, comprising:

[0007] Obtain image information required for powder spraying uniformity detection;

[0008] Performing data preprocessing according to the image information to obtain image pixel data and image information entropy data, wherein the image pixel data includes the total number of image pixels and the total number of regional pixels;

[0009] Weighting product feature information according to the image information entropy data to obtain product information weight data;

[0010] Performing grayscale equalization processing on the image information based on the image pixel data to obtain grayscale equalization data;

[0011] Calculate the uniformity index of powder spraying uniformity according to the equalization data to obtain powder spraying uniformity data;

[0012] Performing weighted summation according to the product information weight data and the powder spraying uniformity data to obtain an actual powder spraying uniformity index on the product surface;

[0013] An adaptive powder spraying adjustment instruction is formulated according to the actual powder spraying uniformity index and a predetermined target powder spraying uniformity index.

[0014] In an optional implementation, performing data preprocessing according to the image information to obtain image pixel data and image information entropy data includes:

[0015] Digitally processing the image information to obtain digital image information, wherein the digital image information includes surface image data and powder spraying coverage area data;

[0016] Perform pixel calculation according to the surface image data to obtain the total number of image pixels;

[0017] Pixel calculation and powder particle calculation are performed according to the powder spraying coverage area data to obtain the total number of pixels in the area and the total number of powder spraying particles;

[0018] Calculate the total area of ​​the powder spraying area according to the total number of pixels in the area and the total number of powder spraying particles to obtain the total area of ​​the powder spraying area;

[0019] The image information entropy is calculated according to the total number of image pixels, the total area of ​​the powder spraying region and the total number of powder spraying particles by the following formula to obtain image information entropy data;

[0020] x1=-k×ln(ln(N)×ln(M / S))

[0021] Among them, x1 represents the image information entropy, k represents the image information entropy correction coefficient, N represents the total area of ​​the powder spraying area, M represents the total number of image pixels, and S represents the total number of powder spraying particles.

[0022] In an optional implementation, weighting product feature information according to the image information entropy data to obtain product information weight data includes:

[0023] Set the product feature information to:

[0024] p=(x1,x2,x3,x4,x5)

[0025] Among them, p represents product feature information, x1 represents image information entropy, x2 represents image uniformity, x3 represents image continuity, x4 represents image integrity, and x5 represents image distribution;

[0026] According to the product feature information, the weight of each item in the product feature information is determined by a hierarchical analysis algorithm to obtain the following product information weight data:

[0027] w=(w1,w2,w3,w4,w5)

[0028] Among them, w1 represents the weight of image information entropy, w2 represents the weight of image uniformity, w3 represents the weight of image continuity, w4 represents the weight of image integrity, and w5 represents the weight of image distribution.

[0029] In an optional implementation, performing grayscale equalization processing on the image information based on the image pixel data to obtain grayscale equalization data includes:

[0030] Performing block processing on the image pixel data to obtain block pixel data, wherein the block pixel data includes the number of block pixels and the average grayscale value of the block;

[0031] Calculate the gray value distribution coefficient according to the block pixel data and the image pixel data to obtain the gray value distribution coefficient;

[0032] According to the block pixel data and the gray value distribution coefficient, gray equalization processing is performed on the block pixel data by the following formula to obtain gray equalization data;

[0033]

[0034] Among them, G j Represents grayscale equalization data, Y j Indicates the average grayscale value of each block, g j Represents the gray value distribution coefficient.

[0035] In an optional embodiment, the step of calculating the uniformity index of the powder spraying uniformity according to the equalization data to obtain the powder spraying uniformity data includes:

[0036] Calculate the grayscale difference of the divided images according to the equalization data to obtain grayscale difference data;

[0037] According to the grayscale difference data, the average value and the variance of the grayscale difference are calculated to obtain grayscale difference average value data and grayscale difference variance data;

[0038] The uniformity index of powder spraying uniformity is calculated according to the grayscale difference average value data and the grayscale difference variance data to obtain powder spraying uniformity data.

[0039] In an optional embodiment, performing weighted summation on the product information weight data and the powder spraying uniformity data to obtain an actual powder spraying uniformity index on the product surface includes:

[0040] The product information weight data and the powder spraying uniformity data are weighted and summed by the following formula:

[0041] P=x1×w1+x2×w2+x3×w3+x4×w4+x5×w5+Q×w Q

[0042] Among them, P represents the actual powder spraying uniformity index, x1 represents the image information entropy, x2 represents the image uniformity, x3 represents the image continuity, x4 represents the image integrity, x5 represents the image distribution, w1 represents the weight of the image information entropy, w2 represents the weight of the image uniformity, w3 represents the weight of the image continuity, w4 represents the weight of the image integrity, w5 represents the weight of the image distribution, Q represents the powder spraying uniformity data, w Q Indicates the weight of powder spraying uniformity data.

[0043] In an optional embodiment, formulating an adaptive powder spraying adjustment instruction according to the actual powder spraying uniformity index and a predetermined target powder spraying uniformity index includes:

[0044] The actual powder spraying uniformity index and the predetermined target powder spraying uniformity index are subtracted and the absolute value is obtained to obtain the absolute value data;

[0045] When the absolute value data is not within the preset adjustment range, the following judgment is made:

[0046] When the actual powder spraying uniformity index is less than a preset first threshold value, the powder spraying quality control parameter is set to the first parameter;

[0047] When the actual powder spraying uniformity index is greater than or equal to a preset first threshold value and less than a preset second threshold value, the powder spraying quality control parameter is set to the second parameter;

[0048] When the actual powder spraying uniformity index is greater than or equal to the preset second threshold value and less than the preset third threshold value, the powder spraying quality control parameter is kept unchanged;

[0049] When the actual powder spraying uniformity index is greater than or equal to a preset third threshold value and less than a preset fourth threshold value, the powder spraying quality control parameter is set to the third parameter;

[0050] When the actual powder spraying uniformity index is greater than or equal to a preset fourth threshold value, the powder spraying quality control parameter is set to a fourth parameter; wherein the setting values ​​of the first parameter, the second parameter, the third parameter, and the fourth parameter satisfy a decreasing order from large to small;

[0051] When the absolute value data is within the preset adjustment range, the parameter adjustment of the powder spraying process is finished.

[0052] In a second aspect, the present invention provides an adaptive high-uniformity powder spraying intelligent control system based on machine vision, comprising:

[0053] A data acquisition module is used to obtain image information required for powder spraying uniformity detection;

[0054] A data preprocessing module, used to perform data preprocessing according to the image information to obtain product feature information, image pixel data and image information entropy data, wherein the image pixel data includes the total number of image pixels and the total number of regional pixels;

[0055] A weighting module, used to weight the product feature information according to the image information entropy data to obtain product information weight data;

[0056] A grayscale equalization module, used for performing grayscale equalization processing on the image information based on the image pixel data to obtain grayscale equalization data;

[0057] A uniformity index calculation module, used to calculate the uniformity index of powder spraying uniformity according to the equalization data to obtain powder spraying uniformity data;

[0058] A process performance calculation module, used for performing weighted summation according to the product information weight data and the powder spraying uniformity data to obtain an actual powder spraying uniformity index;

[0059] The adjustment module is used to formulate an adaptive powder spray adjustment instruction according to the actual powder spray uniformity index and the predetermined target powder spray uniformity index.

[0060] In a third aspect, the present invention further provides an electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements any one of the above-mentioned adaptive high-uniformity powder spraying intelligent control methods based on machine vision.

[0061] In a fourth aspect, the present invention further provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned adaptive high-uniformity powder spraying intelligent control methods based on machine vision.

[0062] Compared with the prior art, the present invention has the following beneficial effects:

[0063] The present invention obtains image information required for powder spraying uniformity detection and performs data preprocessing, weights product feature information in combination with image information entropy data, calculates the uniformity index of powder spraying uniformity after grayscale equalization processing on image information based on image pixel data, and then performs weighted summation according to product information weight data and powder spraying uniformity data to obtain the actual powder spraying uniformity index. Finally, adaptive powder spraying adjustment instructions are formulated according to the comparison between the actual powder spraying uniformity index and the predetermined target powder spraying uniformity index, thereby realizing accurate analysis of the powder spraying uniformity and automatically adjusting the powder spraying amount according to the analysis result, effectively improving the quality and efficiency of the powder spraying process, and solving the problem in the prior art that high-uniformity powder spraying intelligent control cannot be achieved due to ignoring the powder spraying uniformity characteristics. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 It is a schematic flow chart of an adaptive high-uniformity powder spraying intelligent control method based on machine vision provided by the first embodiment of the present invention;

[0065] Figure 2 It is a schematic structural diagram of an adaptive high-uniformity powder spraying intelligent control system based on machine vision provided in the second embodiment of the present invention. DETAILED DESCRIPTION

[0066] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0067] Reference Figure 1 The first embodiment of the present invention provides an adaptive high-uniformity powder spraying intelligent control method based on machine vision, comprising the following steps:

[0068] S11, obtaining image information required for powder spraying uniformity detection;

[0069] S12, performing data preprocessing according to the image information to obtain image pixel data and image information entropy data, wherein the image pixel data includes the total number of image pixels and the total number of regional pixels.

[0070] S13, weighting the product feature information according to the image information entropy data to obtain product information weight data;

[0071] S14, performing grayscale equalization processing on the image information based on the image pixel data to obtain grayscale equalization data;

[0072] S15, calculating a uniformity index of powder spraying uniformity according to the equalization data to obtain powder spraying uniformity data;

[0073] S16, performing weighted summation according to the product information weight data and the powder spraying uniformity data to obtain an actual powder spraying uniformity index of the product surface;

[0074] S17, formulating an adaptive powder spraying adjustment instruction according to the actual powder spraying uniformity index and a predetermined target powder spraying uniformity index.

[0075] In step S11, image information required for powder spraying uniformity detection is obtained.

[0076] The images required for powder uniformity detection in high-uniformity powder spraying systems are captured by industrial CCD cameras, and the captured image information is stored in a storage device through a network or wireless transmission for subsequent data processing and analysis. This process includes not only acquiring the image itself, but also ensuring the quality of the image so that it can accurately reflect product characteristics, such as image uniformity, image continuity, image integrity, and image distribution.

[0077] In step S12, data preprocessing is performed according to the image information to obtain image pixel data and image information entropy data, wherein the image pixel data includes the total number of image pixels and the total number of regional pixels.

[0078] In a specific implementation, performing data preprocessing according to the image information to obtain image pixel data and image information entropy data includes:

[0079] Digitally processing the image information to obtain digital image information, wherein the digital image information includes surface image data and powder spraying coverage area data;

[0080] Perform pixel calculation according to the surface image data to obtain the total number of image pixels;

[0081] Pixel calculation and powder particle calculation are performed according to the powder spraying coverage area data to obtain the total number of pixels in the area and the total number of powder spraying particles;

[0082] Calculate the total area of ​​the powder spraying area according to the total number of pixels in the area and the total number of powder spraying particles to obtain the total area of ​​the powder spraying area;

[0083] The image information entropy is calculated according to the total number of image pixels, the total area of ​​the powder spraying region and the total number of powder spraying particles by the following formula to obtain image information entropy data;

[0084] x1=-k×ln(ln(N)×ln(M / S))

[0085] Among them, x1 represents the image information entropy, k represents the image information entropy correction coefficient, N represents the total area of ​​the powder spraying area, M represents the total number of image pixels, and S represents the total number of powder spraying particles.

[0086] In a specific implementation, the digitalizing the image information to obtain digital image information includes:

[0087] The captured analog signal is converted into a digital signal through an image acquisition card, and then the digital signal is sampled and quantized, that is, the image is discretized into pixels in space, and the brightness or color information of each pixel is converted into a finite number of discrete values, thereby forming a digital image matrix composed of pixels. Finally, the digital image data is compressed by a preset encoding method, such as using the JPEG format for lossy compression, which removes redundant information in the image through discrete cosine transform (DCT), quantization, and Huffman coding, thereby reducing the file size without significantly reducing the image quality; or using the PNG format for lossless compression, which utilizes the LZ77 algorithm and Huffman coding, and can reduce the file size without losing any information.

[0088] In a specific implementation, performing pixel calculation according to the surface image data to obtain the total number of image pixels includes:

[0089] The surface image data is loaded using an image processing library (such as OpenCV or PIL), and then the height and width of the image are obtained by accessing the attribute information of the image. These two attributes represent the number of pixels of the image in the vertical direction and the horizontal direction, respectively; then the height and width of the image are multiplied to calculate the total number of pixels of the image, that is, the number of all pixels in the image.

[0090] In a specific implementation, the pixel calculation and powder particle calculation are performed according to the powder coverage area data to obtain the total number of regional pixels and the total number of powder particles, including:

[0091] The image is loaded through image processing software or programming language (such as Python combined with OpenCV library) and converted into a grayscale image for easy processing; then threshold processing or edge detection technology is applied to identify the specific area covered by the powder spraying, and accurately distinguish the powder spraying area from the background, so as to ensure the accuracy of the calculation; then, based on the identified powder spraying area, the number of all pixels in the area is calculated, that is, the total number of pixels in the area; for the calculation of powder spraying particles, morphological operations (such as corrosion and expansion) can be further applied to the powder spraying area to separate individual particles, and then the number of particles is counted through the connected domain analysis method, and finally the total number of powder spraying particles is obtained.

[0092] In a specific implementation, the total area of ​​the powder spraying region is calculated according to the total number of pixels in the region and the total number of powder spraying particles to obtain the total area of ​​the powder spraying region, including:

[0093] The total area of ​​the powder coating area is obtained by multiplying the total number of pixels in the powder coating area calculated previously by the actual area of ​​each pixel. At the same time, the powder coating area can also be indirectly verified by the total number of powder coating particles and the average number of pixels occupied by a single particle. This process can not only accurately measure the total area of ​​the powder coating area, but also evaluate the uniformity and coverage of the powder coating.

[0094] In step S13, the product feature information is weighted according to the image information entropy data to obtain product information weight data.

[0095] In a specific implementation, weighting product feature information according to the image information entropy data to obtain product information weight data includes:

[0096] Set the product feature information to:

[0097] p=(x1,x2,x3,x4,x5)

[0098] Among them, p represents product feature information, x1 represents image information entropy, x2 represents image uniformity, x3 represents image continuity, x4 represents image integrity, and x5 represents image distribution;

[0099] According to the product feature information, the weight of each item in the product feature information is determined by a hierarchical analysis algorithm to obtain the following product information weight data:

[0100] w=(w1,w2,w3,w4,w5)

[0101] Among them, w1 represents the weight of image information entropy, w2 represents the weight of image uniformity, w3 represents the weight of image continuity, w4 represents the weight of image integrity, and w5 represents the weight of image distribution.

[0102] Specifically, first, a hierarchical model is established. In this hierarchical evaluation model, it is necessary to confirm the target layer, criterion layer, and solution layer of the entire decision event. The target layer is to evaluate the overall quality of the product, the criterion layer is the product feature information p = (x1, x2, x3, x4, x5) mentioned above, and the solution layer depends on the specific evaluation object. There is no need to specify the solution layer here because the focus is on the weight distribution of product features.

[0103] Secondly, construct a judgment matrix. According to the five indicators in the criterion layer (image information entropy, image uniformity, image continuity, image integrity, image distribution), construct a 5x5 judgment matrix A. The elements in the judgment matrix A satisfy: where a ij Indicates the importance of the i-th indicator relative to the j-th indicator, a ji Indicates the importance of the jth indicator relative to the ith indicator, usually given using Saaty's 1-9 scale method. For example, if it is considered that image information entropy x1 is significantly more important than image uniformity x2, the value can be 5, that is, a 12 =5, then

[0104] Next, perform hierarchical single sorting and its consistency check. Hierarchical single sorting means comparing all elements in this layer with an element in the previous layer, and performing hierarchical sorting to arrange the order of importance. The specific calculation can be performed based on the judgment matrix A, and the calculation ensures that it can meet the characteristic root and characteristic vector conditions of AW = λW. Among them, the largest characteristic root of A is λ max , corresponding to λ max The normalized eigenvector of is W, and the components of W are weights, corresponding to the single order of their corresponding elements.

[0105] The consistency check is achieved by calculating the consistency ratio CR, where CI is the consistency index, and RI is the random consistency index. The consistency index CI is calculated by the formula Calculate, where n is the order of the matrix. When CR<0.1, it indicates that the consistency of the judgment matrix A is considered to be within the allowable range, and the eigenvector of A can be used to calculate the weight vector; if CR>0.1, the judgment matrix A should be modified.

[0106] Finally, the weight vector w calculated by the above steps is w = (w1, w2, w3, w4, w5), where each w i Indicates the corresponding product feature information x i ’s weight, thereby completing the task of determining the weight of each item in the product feature information through the hierarchical analysis algorithm.

[0107] In step S14, grayscale equalization processing is performed on the image information based on the image pixel data to obtain grayscale equalization data.

[0108] In a specific implementation, performing grayscale equalization processing on the image information based on the image pixel data to obtain grayscale equalization data includes:

[0109] Performing block processing on the image pixel data to obtain block pixel data, wherein the block pixel data includes the number of block pixels and the average grayscale value of the block;

[0110] Calculate the gray value distribution coefficient according to the block pixel data and the image pixel data to obtain the gray value distribution coefficient;

[0111] According to the block pixel data and the gray value distribution coefficient, gray equalization processing is performed on the block pixel data by the following formula to obtain gray equalization data;

[0112]

[0113] Among them, G j Represents grayscale equalization data, Y j Indicates the average grayscale value of each block, g j Represents the gray value distribution coefficient.

[0114] Specifically, first, the pixel data of the original image is processed in blocks. This means that the entire image is divided into several small blocks, each of which contains a certain number of pixels. This can improve processing efficiency and better preserve local details. After block processing, the number of block pixels and the average grayscale value of each block can be obtained. The average grayscale value of the block can be calculated using the following formula:

[0115]

[0116] Among them, Y j Represents the grayscale average of the jth block, N j represents the number of pixels in the jth block, I ij Represents the grayscale value of each pixel.

[0117] Next, the gray value distribution coefficient g is calculated based on the block pixel data and the original image pixel data. The purpose of calculating the gray value distribution coefficient g is to adjust the contribution of each block in the grayscale equalization process to ensure that the final output image has better contrast and visual effects.

[0118] The specific calculation process is as follows:

[0119] The global grayscale average is calculated using the following formula:

[0120]

[0121] Among them, Y avg represents the global grayscale average, N represents the number of blocks, I i Represents the gray value of each pixel;

[0122] The difference between the average grayscale value of each block and the average grayscale value of the whole block is calculated by the following formula:

[0123] D j =|Y j -Y avg |

[0124] Among them, D j Indicates the difference between the average grayscale value of each block and the average grayscale value of the whole block, Y j represents the grayscale average value of the jth block, Y avg Represents the global grayscale average;

[0125] The grayscale standard deviation of the block is calculated by the following formula:

[0126]

[0127] Among them, S j Indicates the grayscale standard deviation of the block, Y j Represents the grayscale average of the jth block, N j represents the number of pixels in the jth block, I ij Represents the gray value of each pixel;

[0128] The gray value distribution coefficient is calculated by the following formula:

[0129]

[0130] Among them, g j Denotes the gray value distribution coefficient of the jth block, D j Represents the difference between the average grayscale value of each block and the average grayscale value of the whole block, S j Represents the grayscale standard deviation of the block, ∈ is a preset constant used to prevent the denominator from being zero.

[0131] Finally, according to the grayscale average value Y of the block j and gray value distribution coefficient g j , grayscale equalization is performed on each pixel of each block through the following formula to obtain grayscale equalization data G j :

[0132]

[0133] Among them, Gj Represents grayscale equalization data, Y j Indicates the average grayscale value of each block, g j Represents the gray value distribution coefficient.

[0134] In step S15, a uniformity index of powder spraying uniformity is calculated according to the equalization data to obtain powder spraying uniformity data.

[0135] In a specific embodiment, the uniformity index of powder spraying uniformity is calculated according to the equalization data to obtain the powder spraying uniformity data, including:

[0136] Calculate the grayscale difference of the divided images according to the equalization data to obtain grayscale difference data;

[0137] According to the grayscale difference data, the average value and the variance of the grayscale difference are calculated to obtain grayscale difference average value data and grayscale difference variance data;

[0138] The uniformity index is calculated according to the grayscale difference average value data and the grayscale difference variance data to obtain the powder spraying uniformity data.

[0139] Specifically, for each block, the grayscale difference of the block image is calculated by the following formula:

[0140] ΔG j =|G j -Y j |

[0141] For each block, the average grayscale difference is calculated using the following formula:

[0142]

[0143] For each block, the variance of the grayscale difference is calculated by the following formula:

[0144]

[0145] The global average of the grayscale differences of all blocks is calculated using the following formula:

[0146]

[0147] The global variance of the grayscale differences of all blocks is calculated using the following formula:

[0148]

[0149] The evenness index is calculated by the following formula:

[0150]

[0151] Among them, Yj represents the grayscale average value of the jth block, G j Represents grayscale equalization data, ΔG j represents the grayscale difference of the jth block, Represents the average grayscale difference of the jth block, N j represents the number of pixels in the jth block, represents the grayscale difference variance of the jth block, represents the global average value of grayscale difference, It represents the global variance of grayscale difference, and U represents the uniformity index.

[0152] In step S16, a weighted sum is performed based on the product information weight data and the powder spraying uniformity data to obtain an actual powder spraying uniformity index of the product surface.

[0153] In a specific implementation, the weighted summation of the product information weight data and the powder spraying uniformity data to obtain an actual powder spraying uniformity index includes:

[0154] The product information weight data and the powder spraying uniformity data are weighted and summed by the following formula:

[0155] P=x1×w1+x2×w2+x3×w3+x4×w4+x5×w5+Q×w Q

[0156] Among them, P represents the actual powder spraying uniformity index, x1 represents the image information entropy, x2 represents the image uniformity, x3 represents the image continuity, x4 represents the image integrity, x5 represents the image distribution, w1 represents the weight of the image information entropy, w2 represents the weight of the image uniformity, w3 represents the weight of the image continuity, w4 represents the weight of the image integrity, w5 represents the weight of the image distribution, Q represents the powder spraying uniformity data, w Q Indicates the weight of powder spraying uniformity data.

[0157] The actual powder spraying uniformity index is obtained by weighted summing the product information weight data and powder spraying uniformity data through a formula. This method can comprehensively consider the product characteristics and the actual situation of powder spraying uniformity, so that the final powder spraying uniformity index can more accurately reflect the quality status of the product surface powder spraying; by assigning appropriate weights to different characteristic information, those factors that have a greater impact on the powder spraying quality can be highlighted, thereby ensuring that the powder spraying control strategy is more scientific and reasonable, and effectively improving the accuracy of the powder spraying process and product quality.

[0158] In step S17, an adaptive powder spraying adjustment instruction is formulated according to the actual powder spraying uniformity index and a predetermined target powder spraying uniformity index.

[0159] In a specific implementation, formulating an adaptive powder spraying adjustment instruction according to the actual powder spraying uniformity index and a predetermined target powder spraying uniformity index includes:

[0160] The actual powder spraying uniformity index and the predetermined target powder spraying uniformity index are subtracted and the absolute value is obtained to obtain the absolute value data;

[0161] When the absolute value data is not within the preset adjustment range, the following judgment is made:

[0162] When the actual powder spraying uniformity index is less than a preset first threshold value, the powder spraying quality control parameter is set to the first parameter;

[0163] When the actual powder spraying uniformity index is greater than or equal to a preset first threshold value and less than a preset second threshold value, the powder spraying quality control parameter is set to the second parameter;

[0164] When the actual powder spraying uniformity index is greater than or equal to the preset second threshold value and less than the preset third threshold value, the powder spraying quality control parameter is kept unchanged;

[0165] When the actual powder spraying uniformity index is greater than or equal to a preset third threshold value and less than a preset fourth threshold value, the powder spraying quality control parameter is set to the third parameter;

[0166] When the actual powder spraying uniformity index is greater than or equal to a preset fourth threshold value, the powder spraying quality control parameter is set to a fourth parameter; wherein the setting values ​​of the first parameter, the second parameter, the third parameter, and the fourth parameter satisfy a decreasing order from large to small;

[0167] When the absolute value data is within the preset adjustment range, the parameter adjustment of the powder spraying process is finished.

[0168] The setting values ​​of the first threshold, the second threshold, the third threshold, and the fourth threshold meet the requirement of increasing from small to large, and the specific values ​​can be adjusted according to actual conditions;

[0169] The setting values ​​of the first parameter, the second parameter, the third parameter, and the fourth parameter decrease from large to small, and the specific values ​​can be adjusted according to actual conditions.

[0170] First, the system calculates the absolute value of the difference between the actual powder spraying uniformity index (i.e. the actual measured value of the powder spraying uniformity) and the preset target powder spraying uniformity index to obtain an absolute value data. This absolute value data is an important indicator used to measure whether the current powder spraying uniformity has reached the expected target.

[0171] An allowable adjustment range is predefined. When the absolute value data mentioned above exceeds this allowable range, it indicates that the current powder spraying uniformity is significantly different from the target value, and corresponding adjustments are required to optimize the powder spraying uniformity. On the contrary, if the absolute value data is within the allowable range, it is considered that the current powder spraying uniformity meets the requirements and no further adjustments are required.

[0172] When the absolute value data exceeds the preset adjustment range, the system will further determine whether the gap between the actual process performance index and the preset process performance index tends to be stable or fluctuating, and then formulate specific process adjustment instructions based on the gap, the stability of the gap and the changing state of the gap, as well as the preset performance parameter control range of the product.

[0173] For example, in an adaptive high-uniformity powder spraying intelligent control system based on machine vision, the preset target powder spraying uniformity index is 100, and the allowable adjustment range is ±10. When the absolute value of the difference between the actual powder spraying uniformity index and the target value is less than 10, the system considers that the current powder spraying uniformity meets the requirements and no further adjustment is required. However, when the absolute value data exceeds 10, it indicates that there is a significant difference between the current powder spraying uniformity and the target value, and corresponding adjustment measures need to be taken to optimize the powder spraying uniformity. For example, if the actual powder spraying uniformity index is lower than 90, the system will increase the powder spraying amount or adjust the position and angle of the powder spraying equipment; if the actual powder spraying uniformity index is higher than 110, the system will reduce the powder spraying amount or adjust the position and angle of the powder spraying equipment to bring the powder spraying uniformity back to the target range.

[0174] Specifically, when the actual powder spraying uniformity index is less than 80, the system will set the powder spraying quality control parameter to 20g / cm 2 , to significantly increase the amount of powder spraying; when the actual powder spraying uniformity index is between 80 and 90, the system will set the powder spraying quality control parameter to 15g / cm 2 , to moderately increase the powder spraying amount; when the actual powder spraying uniformity index is between 90 and 110, the system keeps the powder spraying quality control parameters unchanged and continues to monitor the powder spraying uniformity; when the actual powder spraying uniformity index is between 110 and 120, the system will set the powder spraying quality control parameters to 10g / cm 2 , in order to moderately reduce the amount of powder spraying; when the actual powder spraying uniformity index is greater than 120, the system will set the powder spraying quality control parameter to 5g / cm 2 , to significantly reduce the amount of powder sprayed. Through this dynamic adjustment mechanism, the system can ensure that the uniformity of powder spraying is always within the preset target range, thereby improving the quality and efficiency of the powder spraying process.

[0175] In summary, the preset adjustment range is a comprehensive criteria system that includes the allowable range of absolute value data, the judgment of gap stability, and the formulation of corresponding adjustment measures based on this information. It aims to ensure that the powder spraying process can operate in the most optimized state, improve the uniformity of powder spraying, reduce waste, and improve product quality.

[0176] The following describes the working process of the present invention using a relatively common scenario as an example. Figure 1 , an adaptive high-uniformity powder spraying intelligent control method based on machine vision, comprising the following steps:

[0177] The data acquisition module first obtains the image information required for powder spraying uniformity detection, and transmits the image information to the processor through the data transmission and conversion module. After the processor reads the image information, the computer program calculates the information entropy of the product surface image and determines the maximum particle radius and the total area of ​​the particles. According to the product type input by the user, the product information weighting parameter is set, and then the image information entropy, the image information entropy correction coefficient and the product information weighting parameter are calculated to obtain the product feature information weight. Next, the computer program divides the image into blocks and calculates the information entropy of each image block, the grayscale average value of the pixels in the image block, and the grayscale variance of the pixels in the image block. By establishing the equalization condition, the computer program performs grayscale equalization on the image blocks, calculates the grayscale value of each block after the image block equalization processing, and calculates the grayscale difference of the image blocks.

[0178] The computer program calculates the uniformity index based on the grayscale difference variance and grayscale difference mean of the image blocks. Then, the product feature information weight and the uniformity index are weighted to obtain the actual process performance index. The actual process performance index is compared with the preset process performance index to calculate the absolute value of the difference between the two. If the difference between the actual and preset process performance indicators exceeds the preset adjustment range, the computer program will obtain the absolute value of the difference between the actual process performance indicator and the preset process performance indicator based on the product feature information weight and the uniformity index, and determine whether the difference between the actual process performance indicator and the preset process performance indicator tends to be stable or fluctuating. According to the gap, the stability of the gap and the change state of the gap, as well as the preset performance parameter control range of the product, the process adjustment instruction is obtained, and the adjustment command is sent to the powder spray adjustment module.

[0179] The powder spraying adjustment module adjusts the parameters according to the adjustment command, including product type, powder spraying parameters, process environment, powder spraying process parameters, etc. Then, the image information of the powder spraying uniformity is re-acquired, the product feature information weight and uniformity index are recalculated according to the new image information, and the difference between the process performance index and the preset process performance index is re-judged. If the gap is within the preset adjustment range, the adjustment of the powder spraying process parameters is ended. If the gap still exceeds the preset range, repeat the above steps until the gap is within the preset range. When the gap between the actual process performance index and the preset process performance index is within the preset adjustment range, the powder spraying adjustment module stops adjusting. In this way, through the above steps, adaptive high-uniformity powder spraying intelligent control based on machine vision can be realized to ensure the uniformity and quality of the powder spraying process.

[0180] In summary, the adaptive high-uniformity powder spraying intelligent control method and system based on machine vision obtains the image information required for powder spraying uniformity detection through the data acquisition module, and the data transmission and conversion module transmits the image information to the processor. The processor calculates the image information entropy and the product feature information weight, performs block processing and grayscale equalization on the image, calculates the uniformity index, and compares the actual process performance index with the preset index. The powder spraying parameters are adjusted according to the gap and the preset adjustment range until the gap between the actual and preset indicators is within the preset range, thereby realizing accurate analysis and intelligent control of powder spraying uniformity, effectively improving the quality and efficiency of the powder spraying process, and solving the problem of the inability to realize high-uniformity powder spraying intelligent control due to ignoring the powder spraying uniformity characteristics in the prior art.

[0181] Reference Figure 2 The second embodiment of the present invention provides an adaptive high-uniformity powder spraying intelligent control system based on machine vision, comprising:

[0182] A data acquisition module is used to obtain image information required for powder spraying uniformity detection;

[0183] A data preprocessing module, used to perform data preprocessing according to the image information to obtain product feature information, image pixel data and image information entropy data, wherein the image pixel data includes the total number of image pixels and the total number of regional pixels;

[0184] A weighting module, used to weight the product feature information according to the image information entropy data to obtain product information weight data;

[0185] A grayscale equalization module, used for performing grayscale equalization processing on the image information based on the image pixel data to obtain grayscale equalization data;

[0186] A uniformity index calculation module, used to calculate the uniformity index of powder spraying uniformity according to the equalization data to obtain powder spraying uniformity data;

[0187] A process performance calculation module, used for performing weighted summation according to the product information weight data and the powder spraying uniformity data to obtain an actual powder spraying uniformity index;

[0188] The adjustment module is used to formulate an adaptive powder spray adjustment instruction according to the actual powder spray uniformity index and the predetermined target powder spray uniformity index.

[0189] It should be noted that an adaptive high-uniformity powder spraying intelligent control device based on machine vision provided in an embodiment of the present invention is used to execute all the process steps of an adaptive high-uniformity powder spraying intelligent control method based on machine vision in the above-mentioned embodiment. The working principles and beneficial effects of the two correspond one to one, and therefore will not be repeated here.

[0190] The embodiment of the present invention further 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 an adaptive high-uniformity powder spraying intelligent control program based on machine vision. When the processor executes the computer program, the steps in the above-mentioned embodiments of the adaptive high-uniformity powder spraying intelligent control method based on machine vision are implemented, such as Figure 1 Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are realized, such as a self-adaptive high-uniformity powder spraying intelligent control module based on machine vision.

[0191] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the electronic device.

[0192] The electronic device may be a computing device such as a desktop computer, a notebook, a PDA, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. The electronic device may include more or fewer components than the above components, or may combine certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0193] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the electronic device, and uses various interfaces and lines to connect various parts of the entire electronic device.

[0194] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the electronic device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0195] Wherein, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained 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, computer-readable media do not include electric carrier signals and telecommunication signals.

[0196] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme 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 may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0197] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. An adaptive high-uniformity powder spraying intelligent control method based on machine vision, characterized in that: Executed by a computer, including: Obtain image information required for powder spraying uniformity detection; Performing data preprocessing according to the image information to obtain image pixel data and image information entropy data, wherein the image pixel data includes the total number of image pixels and the total number of regional pixels; Weighting product feature information according to the image information entropy data to obtain product information weight data; Performing grayscale equalization processing on the image information based on the image pixel data to obtain grayscale equalization data; Calculate the uniformity index of powder spraying uniformity according to the equalization data to obtain powder spraying uniformity data; Performing weighted summation according to the product information weight data and the powder spraying uniformity data to obtain an actual powder spraying uniformity index on the product surface; An adaptive powder spraying adjustment instruction is formulated according to the actual powder spraying uniformity index and a predetermined target powder spraying uniformity index.

2. The adaptive high-uniformity powder spraying intelligent control method based on machine vision according to claim 1 is characterized in that: The performing data preprocessing according to the image information to obtain image pixel data and image information entropy data includes: Digitally processing the image information to obtain digital image information, wherein the digital image information includes surface image data and powder spraying coverage area data; Perform pixel calculation according to the surface image data to obtain the total number of image pixels; Pixel calculation and powder particle calculation are performed according to the powder spraying coverage area data to obtain the total number of pixels in the area and the total number of powder spraying particles; Calculate the total area of ​​the powder spraying area according to the total number of pixels in the area and the total number of powder spraying particles to obtain the total area of ​​the powder spraying area; The image information entropy is calculated according to the total number of image pixels, the total area of ​​the powder spraying region and the total number of powder spraying particles by the following formula to obtain image information entropy data; x1=-k×ln(ln(N)×ln(M / S)) Among them, x1 represents the image information entropy, k represents the image information entropy correction coefficient, N represents the total area of ​​the powder spraying area, M represents the total number of image pixels, and S represents the total number of powder spraying particles.

3. The adaptive high-uniformity powder spraying intelligent control method based on machine vision according to claim 1 is characterized in that: The step of weighting product feature information according to the image information entropy data to obtain product information weight data includes: Set the product feature information to: p=(x1,x2,x3,x4,x5) Among them, p represents product feature information, x1 represents image information entropy, x2 represents image uniformity, x3 represents image continuity, x4 represents image integrity, and x5 represents image distribution; According to the product feature information, the weight of each item in the product feature information is determined by a hierarchical analysis algorithm to obtain the following product information weight data: w=(w1,w2,w3,w4,w5) Among them, w1 represents the weight of image information entropy, w2 represents the weight of image uniformity, w3 represents the weight of image continuity, w4 represents the weight of image integrity, and w5 represents the weight of image distribution.

4. The adaptive high-uniformity powder spraying intelligent control method based on machine vision according to claim 1 is characterized in that: The performing grayscale equalization processing on the image information based on the image pixel data to obtain grayscale equalization data includes: Performing block processing on the image pixel data to obtain block pixel data, wherein the block pixel data includes the number of block pixels and the average grayscale value of the block; Calculate the gray value distribution coefficient according to the block pixel data and the image pixel data to obtain the gray value distribution coefficient; According to the block pixel data and the gray value distribution coefficient, gray equalization processing is performed on the block pixel data by using the following formula to obtain gray equalization data; Among them, G j Represents grayscale equalization data, Y j Indicates the average grayscale value of each block, g j Represents the gray value distribution coefficient.

5. The adaptive high-uniformity powder spraying intelligent control method based on machine vision according to claim 1 is characterized in that: The step of calculating the uniformity index of powder spraying uniformity according to the equalization data to obtain powder spraying uniformity data comprises: Calculate the grayscale difference of the divided images according to the equalization data to obtain grayscale difference data; According to the grayscale difference data, the average value and the variance of the grayscale difference are calculated to obtain grayscale difference average value data and grayscale difference variance data; The uniformity index of powder spraying uniformity is calculated according to the grayscale difference average value data and the grayscale difference variance data to obtain powder spraying uniformity data.

6. The adaptive high-uniformity powder spraying intelligent control method based on machine vision according to claim 3 is characterized in that: The weighted summation of the product information weight data and the powder spraying uniformity data to obtain the actual powder spraying uniformity index of the product surface includes: The product information weight data and the powder spraying uniformity data are weighted and summed by the following formula: P=x1×w1+x2×w2+x3×w3+x4×w4+x5×w5+Q×w Q Among them, P represents the actual powder spraying uniformity index, x1 represents the image information entropy, x2 represents the image uniformity, x3 represents the image continuity, x4 represents the image integrity, x5 represents the image distribution, w1 represents the weight of the image information entropy, w2 represents the weight of the image uniformity, w3 represents the weight of the image continuity, w4 represents the weight of the image integrity, w5 represents the weight of the image distribution, Q represents the powder spraying uniformity data, w Q Indicates the weight of powder spraying uniformity data.

7. The adaptive high-uniformity powder spraying intelligent control method based on machine vision according to claim 1 is characterized in that: The step of formulating an adaptive powder spray adjustment instruction according to the actual powder spray uniformity index and a predetermined target powder spray uniformity index comprises: The actual powder spraying uniformity index and the predetermined target powder spraying uniformity index are subtracted and the absolute value is obtained to obtain the absolute value data; When the absolute value data is not within the preset adjustment range, the following judgment is made: When the actual powder spraying uniformity index is less than a preset first threshold value, the powder spraying quality control parameter is set to the first parameter; When the actual powder spraying uniformity index is greater than or equal to a preset first threshold value and less than a preset second threshold value, the powder spraying quality control parameter is set to the second parameter; When the actual powder spraying uniformity index is greater than or equal to the preset second threshold value and less than the preset third threshold value, the powder spraying quality control parameter is kept unchanged; When the actual powder spraying uniformity index is greater than or equal to a preset third threshold value and less than a preset fourth threshold value, the powder spraying quality control parameter is set to the third parameter; When the actual powder spraying uniformity index is greater than or equal to a preset fourth threshold value, the powder spraying quality control parameter is set to a fourth parameter; wherein the setting values ​​of the first parameter, the second parameter, the third parameter, and the fourth parameter satisfy a decreasing order from large to small; When the absolute value data is within the preset adjustment range, the parameter adjustment of the powder spraying process is finished.

8. An adaptive high-uniformity powder spraying intelligent control system based on machine vision, characterized in that: include: A data acquisition module is used to obtain image information required for powder spraying uniformity detection; A data preprocessing module, used to perform data preprocessing according to the image information to obtain product feature information, image pixel data and image information entropy data, wherein the image pixel data includes the total number of image pixels and the total number of regional pixels; A weighting module, used to weight the product feature information according to the image information entropy data to obtain product information weight data; A grayscale equalization module, used for performing grayscale equalization processing on the image information based on the image pixel data to obtain grayscale equalization data; A uniformity index calculation module, used to calculate the uniformity index of powder spraying uniformity according to the equalization data to obtain powder spraying uniformity data; A process performance calculation module, used for performing weighted summation according to the product information weight data and the powder spraying uniformity data to obtain an actual powder spraying uniformity index; The adjustment module is used to formulate an adaptive powder spray adjustment instruction according to the actual powder spray uniformity index and the predetermined target powder spray uniformity index.

9. An electronic device, characterized in that: It comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the adaptive high-uniformity powder spraying intelligent control method based on machine vision as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the adaptive high-uniformity powder spraying intelligent control method based on machine vision as described in any one of claims 1 to 7.

Images