Intelligent control system for production line

Abstract

The invention discloses an intelligent control system for a production line, and relates to the technical field of intelligent control systems, and the system comprises a monitoring collection terminal which is used for collecting a product image after processing of a processing node on the production line, delimiting a processing region on the product image based on the processing information of a target processing node, and obtaining a processing region image of the target processing node; and the image multi-dimensional processing module is used for carrying out contour detection processing on the processing area image to obtain a contour deviation detection image, carrying out analysis based on the contour deviation detection image to obtain a contour precision deviation coefficient, and carrying out area distribution processing on the processing area image to obtain a plurality of sub-area deviation detection images. According to the method, the product processing condition is accurately analyzed and evaluated from two dimensions in a distributed manner, so that inferior-quality products and waste products are accurately recognized, the inferior-quality products and the waste products are automatically controlled to be removed and prevented from entering the next processing node, the processing efficiency of a production line is remarkably improved, and resource waste is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control systems, and particularly to an intelligent control system for a production line. Background Art

[0002] Intelligent control systems and control methods for production lines are important components of modern manufacturing. They are of great significance for improving production efficiency, ensuring product quality, and reducing production costs. An intelligent control system for a production line is a highly integrated system that usually includes multiple levels and modules, such as an enterprise management level, a production management level, a process control level, an equipment control level, and a detection and drive level. Information sharing and collaborative work are achieved between these levels and modules through advanced communication technologies and network technologies. Using intelligent control technologies and engineering methods, the production process is controlled and optimized in real time to ensure the stability and efficiency of the production process.

[0003] For example, in the Chinese patent with the authorization announcement number CN212160443U, the authorization announcement date is December 15, 2020, and the name is "A Product Processing Quality Monitoring System for a Machining Line". It includes a monitoring gantry, a central processor, an AI recognition module, and a wireless transmission module. A conveyor belt is arranged at the bottom inside the monitoring gantry. Monitoring probes are arranged at the top inside the monitoring gantry and on the left and right inner side walls. The central processor is arranged on the top of the monitoring gantry. The central processor is electrically connected to a data storage module and an image comparison module in a two-way manner. The central processor is electrically connected to the monitoring probes in an input manner. The central processor is electrically connected to the AI recognition module in a two-way manner. The central processor is electrically connected to the wireless transmission module in a two-way manner. The wireless transmission module is electrically connected to a terminal service desk in a two-way manner.

[0004] The deficiencies of the prior art including the above application are that when the existing production line detects products at each processing node, it mostly collects product photos by setting up monitoring modules, and then evaluates and analyzes the product processing status of the collected photos through an AI recognition module or a machine learning model. When analyzing and processing the collected images, there are many features on the images, which affects the efficiency and accuracy of the analysis and cannot meet the requirements of the accuracy and timeliness of the production line processing. Summary of the Invention

[0005] The purpose of the present invention is to provide an intelligent control system for a production line to solve the above deficiencies in the prior art.

[0006] To achieve the above purpose, the present invention adopts the following technical solutions: An intelligent control system for a production line, comprising:

[0007] The monitoring and acquisition terminal is used to acquire the product images after processing at the processing nodes on the production line. Based on the processing information of the target processing node, it demarcates the processing area on the product image and obtains the processing area image of the target processing node.

[0008] The image multi-dimensional processing module performs contour detection processing on the processing area image to obtain a contour deviation detection image, analyzes the contour deviation monitoring image to obtain a contour accuracy deviation coefficient, performs regional distribution processing on the processing area image to obtain multiple sub-region deviation detection images, calculates the sub-region deviation defect coefficients based on each sub-region deviation detection image, and integrates and calculates to obtain the regional accuracy deviation coefficient.

[0009] The processing status analysis unit is used to integrate and calculate the product processing defect coefficient and evaluate the current processing status of the product based on the product processing defect coefficient.

[0010] The rejection processing unit is used to retrieve the current processing status of the product and perform a rejection operation on the product based on the current processing status of the product.

[0011] As a further description of the above technical solution:

[0012] Specifically, performing contour detection processing on the processing area image to obtain a contour deviation detection image is as follows:

[0013] Perform image edge detection and extraction on the processing area image to obtain an edge image, and obtain the contour line of the current processing area image based on the edge image.

[0014] Map the contour line of the current processing area image on the blank image background layer.

[0015] Construct a detection contour line, map the detection contour line on the blank image background layer and cover the contour line of the current processing area image, and crop and remove the detection contour line area to obtain a contour deviation monitoring image.

[0016] As a further description of the above technical solution:

[0017] Specifically, analyzing the contour deviation monitoring image to obtain a contour accuracy deviation coefficient is as follows:

[0018] Mark the standard contour line of the processing area on the contour deviation monitoring image.

[0019] Extract the pixels located outside the standard contour line in the contour deviation monitoring image, calculate the gray values of these pixels, and mark them as the external contour deviation value Pw.

[0020] Extract the pixels located inside the standard contour line in the contour deviation monitoring image, calculate the gray values of these pixels, and mark them as the internal contour deviation value Pn.

[0021] Integrate and calculate the external contour deviation value and the internal contour deviation value to obtain the contour accuracy deviation coefficient PL.

[0022] As a further description of the above technical solution:

[0023] Perform regional distribution processing on the machining area image to obtain multiple sub-region deviation detection images, calculate the deviation defect coefficient of each sub-region based on each sub-region deviation detection image, and integrate and calculate to obtain the regional accuracy deviation coefficient specifically as follows:

[0024] Retrieve the machining area image, map the contour line of the current machining area image onto the machining area image, and crop and remove the contour line area of the current machining area image to obtain the standard area detection image;

[0025] Based on the machining information of the target machining node, divide the areas with the same machining standard on the standard area detection image to obtain multiple sub-region deviation detection images, and distributively calculate the deviation defect coefficient of each sub-region deviation detection image, and then sum the deviation defect coefficients of each sub-region deviation detection image to obtain the regional accuracy deviation coefficient.

[0026] As a further description of the above technical solution:

[0027] Specifically, distributively calculate the deviation defect coefficient of each sub-region deviation detection image as follows:

[0028] Construct m pixel detection regions with different sizes on each sub-region deviation detection image, and calculate the pixel gray value of each pixel detection region to obtain the gray value data set U ∈ (X 1 、X 2 、X 3 ...X m ) of the sub-region deviation detection image, where X m represents the pixel gray value of the m-th pixel detection region of the sub-region deviation detection image;

[0029] Calculate the self-deviation coefficient and the standard deviation coefficient respectively through the gray value data set of the sub-region deviation detection image;

[0030] Sum the self-deviation coefficient and the standard deviation coefficient to calculate the deviation defect coefficient of the sub-region deviation detection image.

[0031] As a further description of the above technical solution:

[0032] Specifically, calculate the self-deviation coefficient and the standard deviation coefficient respectively through the gray value data set of the sub-region deviation detection image as follows:

[0033] Retrieve the gray value data set U ∈ (X 1 、X 2 、X3 ...X m );

[0034] Calculate the self-deviation coefficient P z represents the self-deviation coefficient of the sub-region deviation detection image, X m represents the pixel gray value of the m-th pixel detection region of the sub-region deviation detection image, δ 1 is a preset weight coefficient and δ 1 > 0;

[0035] Calculate the standard deviation coefficient represents the standard deviation coefficient of the sub-region deviation detection image, X e represents the standard pixel gray value of the sub-region deviation detection image, δ 2 is a preset weight coefficient and δ 2 > 0.

[0036] As a further description of the above technical solution:

[0037] Constructing the detection contour line specifically is: obtaining the standard contour line of the processing area based on the processing information of the target processing node, and constructing the detection contour line by extending 0.5Le length to both sides with the standard contour line as the reference line, where Le is the contour line error compensation parameter of the current processing area image.

[0038] As a further description of the above technical solution:

[0039] The processing status includes qualified products, defective products, and waste products.

[0040] As a further description of the above technical solution:

[0041] Integrate and calculate the product processing defect coefficient, and evaluate the current processing status of the product based on the product processing defect coefficient specifically as:

[0042] Retrieve the contour accuracy deviation coefficient and the regional accuracy deviation coefficient to calculate the product processing defect coefficient, P Q = P L *β 1 + P Y *β 2 where P Q represents the product processing defect coefficient, P L represents the contour deviation defect factor, P Y represents the regional accuracy deviation coefficient, β 1 、β 2 represents the weight coefficient, and β 1 ,β 2 are both greater than 0;

[0043] Preset product processing defect coefficient evaluation index P g1 、P g2 where P g1 >P g2 >0;

[0044] When P Q >P g1 it indicates that the current product processing status is defective;

[0045] When P Q <P g2 it indicates that the current product processing status is qualified;

[0046] When P g1 ≥P Q ≥P g2 it indicates that the current product processing status is substandard.

[0047] As a further description of the above technical solution:

[0048] The rejection processing unit is used to retrieve the current product processing status and perform a rejection operation on the product based on the current product processing status. Specifically:

[0049] Collect the image of the processing area at the target processing node for the current product processing status,

[0050] When the current product processing status is substandard, generate a first control instruction and control it to the actuator. The actuator rejects the currently processed product and places it in the substandard product recycling bin;

[0051] When the current product processing status is defective, generate a second control instruction and control it to the actuator. The actuator rejects the currently processed product and places it in the defective product recycling bin;

[0052] When the current product processing status is qualified, no rejection operation is performed on the currently processed product at this time.

[0053] The present invention provides an intelligent control system for a production line. It has the following beneficial effects:

[0054] This intelligent control system for the production line calculates the contour accuracy deviation coefficient and the area accuracy deviation coefficient by independently performing distributed calculations on the contour and the processing area of the processing area, and integrates the calculations to obtain the product processing defect coefficient. By evaluating the current processing state of the product based on the product processing defect coefficient, it realizes accurate analysis and evaluation of the product processing situation from two dimensions in a distributed manner, so as to accurately identify substandard and defective products, and automatically control the rejection of substandard and defective products to prevent them from entering the next processing node, significantly improving the processing efficiency of the production line and reducing resource waste. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 Schematic diagram of modules of an intelligent control system for a production line proposed by the present invention;

[0056] Figure 2 Schematic diagram of the processing flow of an intelligent control system for a production line proposed by the present invention. Specific implementation manners

[0057] 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 of the embodiments.

[0058] Referring to Figure 1-2 , an intelligent control system for a production line, wherein the production line includes a plurality of processing nodes, and the processing nodes are interconnected through a conveyor line. The products to be processed are sequentially conveyed to each processing node through the conveyor line, and the products are processed in a pipeline manner by each processing node. The intelligent control system for the production line includes: a monitoring and acquisition terminal. Optionally, the monitoring and acquisition terminal is an industrial camera, which is arranged at the positions of each processing node of the production line and is used to acquire the images of the products after being processed at the processing nodes on the production line. The acquired product images include the image information of the processing area of the products by the target processing node. Based on the processing information of the target processing node, the processing information includes processing drawings, process documents or other data sources, so as to determine the position, size and shape of the working area of the target processing node, and then delimit the processing area on the product image to obtain the image of the processing area of the target processing node; by sliding the processing area on the product image and acquiring the image of the processing area, the interference of the image features of the product image itself can be removed, the complexity of subsequent image analysis can be reduced, and the efficiency of image analysis and processing can be improved.

[0059] An image multi-dimensional processing module performs contour detection processing on the processing area image to obtain a contour deviation detection image, and analyzes and obtains a contour accuracy deviation coefficient based on the contour deviation monitoring image. The contour accuracy deviation coefficient is used to evaluate the processing accuracy of the contour of the processing area corresponding to the target processing node. The larger the contour defect deviation coefficient, the worse the processing accuracy of the contour; performs area distribution processing on the processing area image to obtain a plurality of sub-area deviation detection images, calculates and obtains the sub-area deviation defect coefficients based on the sub-area deviation detection images, and integrates and calculates to obtain the area accuracy deviation coefficient; the area accuracy deviation coefficient is used to evaluate the processing accuracy of the processing area corresponding to the target processing node. The larger the area accuracy deviation coefficient, the worse the processing accuracy of the processing area.

[0060] The processing status analysis unit is used to integrate and calculate the product processing defect coefficient, and evaluate the current processing status of the product based on the product processing defect coefficient; where the processing status includes qualified products, defective products, and waste products. A qualified product means that the current processing of the product is qualified and can enter the next processing node for processing. A defective product means that the current processing of the product is unqualified and needs to be reworked and repaired. A waste product means that the current processing of the product is unqualified and cannot be reworked and repaired.

[0061] The rejection processing unit is arranged in the conveying system between each processing node of the production line, and the rejection processing unit includes a controller and an actuator. The controller is used to retrieve the current processing status of the product, generate a control instruction based on the current processing status of the product, and transmit the control instruction to the actuator. The actuator performs a rejection operation on the product. Optionally, the actuator is a manipulator. That is, when the controller retrieves the current processing status of the product and the processing status is a defective product or a waste product, a control instruction is generated to control the manipulator, and the defective or waste processed product is removed from the production line by the manipulator, so that the defective products and waste products do not enter the next processing node of the production line.

[0062] This embodiment provides an intelligent control system for a production line. By separately calculating the contour accuracy deviation coefficient and the regional accuracy deviation coefficient for the contour of the processing area and the processing area in a distributed manner, and integrating and calculating to obtain the product processing defect coefficient, and evaluating the current processing state of the product based on the product processing defect coefficient, accurate analysis and evaluation of the product processing situation are realized from two dimensions in a distributed manner, achieving accurate identification of defective products and waste products, and automatically controlling the rejection of defective products and waste products to prevent them from entering the next processing node, significantly improving the processing efficiency of the production line and reducing resource waste.

[0063] In another embodiment provided by the present invention, the specific process of obtaining the contour deviation detection image by performing contour detection processing on the processing area image is as follows:

[0064] Perform image edge detection and extraction on the processing area image to obtain an edge image, and construct a contour line by tracking continuous edge pixels based on the edge image to obtain the contour line of the current processing area image;

[0065] Map the contour line of the current processing area image onto the blank image background layer;

[0066] Construct a detection contour line. Specifically, the construction of the detection contour line is as follows: obtain the standard contour line of the machining area based on the machining information of the target machining node, use the standard contour line as the reference line and extend it by 0.5Le on both sides to construct the detection contour line, where Le is the error compensation parameter of the image contour line in the current machining area. Map the detection contour line onto the blank image background layer and cover the image contour line of the current machining area, and crop and remove the detection contour line area to obtain the contour deviation monitoring image. Thus, the standard contour line area that meets the error requirements is removed, so that the contour deviation monitoring image only retains the contour lines with machining deviations.

[0067] Further, the specific method for analyzing and obtaining the contour accuracy deviation coefficient based on the contour deviation monitoring image is as follows:

[0068] Mark the standard contour line of the machining area on the contour deviation monitoring image;

[0069] Extract the pixels located outside the standard contour line in the contour deviation monitoring image, and calculate the gray values of these pixels, which are marked as the external contour deviation value Pw.

[0070] Extract the pixels located inside the standard contour line in the contour deviation monitoring image, and calculate the gray values of these pixels, which are marked as the internal contour deviation value Pn.

[0071] Integrate and calculate the external contour deviation value and the internal contour deviation value to obtain the contour accuracy deviation coefficient PL. The calculation logic of the contour accuracy deviation coefficient PL is as follows: preset the external contour deviation value weight coefficient S1 and the internal contour deviation value weight coefficient S2, where S1 > S2 > 0. Optionally, S1 = 0.62 and S2 = 0.38. The calculation logic of the contour accuracy deviation coefficient PL is PL = Pw * S1 + Pn * S2.

[0072] This embodiment provides an intelligent control system for a production line. When calculating the contour accuracy deviation coefficient, the detected contour line is constructed to process the extracted image contour line of the current machining area, and only the contour lines with machining deviations are retained, significantly reducing the subsequent calculation amount. At the same time, by calculating the external contour deviation value and the internal contour deviation value based on the distribution of the standard contour line, and setting weights for the external contour deviation value and the internal contour deviation value according to the influence degree and performing weighted summation to calculate the contour accuracy deviation coefficient, the accuracy and comprehensiveness of the contour accuracy deviation analysis are significantly improved, and the accuracy of the product machining state evaluation is improved.

[0073] In another embodiment provided by the present invention, the area distribution processing of the machining area image is performed to obtain multiple sub-region deviation detection images, and the specific method for calculating the sub-region deviation defect coefficients based on each sub-region deviation detection image and integrating and calculating to obtain the region accuracy deviation coefficient is as follows:

[0074] Retrieve the image of the processing area, map the contour line of the current processing area image onto the processing area image, and crop and remove the area of the current processing area image contour line to obtain a standard area detection image; achieve removing the contour on the processing area image and only retaining the standard area detection image inside the processing area;

[0075] Based on the processing information of the target processing node, divide the areas with the same processing standard on the standard area detection image to obtain multiple sub-area deviation detection images. In an ideal state, the pixel gray values of the sub-area deviation detection images in the areas with the same processing standard are the same, and distribute the calculation of the deviation defect coefficient of each sub-area deviation detection image, and then sum the deviation defect coefficients of each sub-area deviation detection image to obtain the area accuracy deviation coefficient.

[0076] Furthermore, the specific method for distributing the calculation of the deviation defect coefficient of each sub-area deviation detection image is as follows:

[0077] Construct m pixel detection areas with different sizes on each sub-area deviation detection image, and calculate the pixel gray value of each pixel detection area to obtain the gray value data set U∈(X 1 、X 2 、X 3 ...X m ) of the sub-area deviation detection image, where X m represents the pixel gray value of the m-th pixel detection area of the sub-area deviation detection image;

[0078] Calculate the self-deviation coefficient and the standard deviation coefficient respectively through the gray value data set of the sub-area deviation detection image; among them, the self-deviation coefficient represents the processing accuracy deviation between different pixel detection areas on the same sub-area deviation detection image, and the standard deviation coefficient represents the deviation between the processing accuracy of the sub-area deviation detection image and the accuracy in the standard accuracy processing state.

[0079] Sum the self-deviation coefficient and the standard deviation coefficient to calculate the deviation defect coefficient of the sub-area deviation detection image.

[0080] In another embodiment provided by the present invention, the specific method for calculating the self-deviation coefficient and the standard deviation coefficient respectively through the gray value data set of the sub-area deviation detection image is as follows:

[0081] Retrieve the gray value data set U∈(X 1 、X 2 、X 3 ...X m ) of the sub-area deviation detection image;

[0082] Calculate the self-deviation coefficient, P z represents the self-deviation coefficient of the sub-area deviation detection image, Xm denotes the pixel gray value of the m-th pixel detection area of the sub-region deviation detection image, δ 1 is a preset weight coefficient and δ 1 > 0;

[0083] Calculate the standard deviation coefficient, denotes the standard deviation coefficient of the sub-region deviation detection image, X e denotes the standard pixel gray value of the sub-region deviation detection image, δ 2 is a preset weight coefficient and δ 2 > 0.

[0084] This embodiment provides an intelligent control system for a production line. When calculating the regional accuracy deviation coefficient, the areas with the same processing standard on the standard region detection image are divided into independent sub-region deviation detection images, and the processing accuracy deviation between different pixel detection areas on the same sub-region deviation detection image and the deviation between the processing accuracy of the sub-region deviation detection image and the accuracy in the standard accuracy processing state are calculated through multiple indicators to obtain the regional accuracy deviation coefficient, significantly enhancing the accuracy and comprehensiveness of the regional accuracy deviation analysis, and further improving the accuracy of the product processing status evaluation.

[0085] In another embodiment provided by the present invention, the integration calculation of the product processing defect coefficient and the evaluation of the current product processing status based on the product processing defect coefficient are specifically as follows:

[0086] Retrieve the profile accuracy deviation coefficient and the regional accuracy deviation coefficient to calculate the product processing defect coefficient, P Q = P L *β 1 + P Y *β 2 , where P Q denotes the product processing defect coefficient, P L denotes the profile deviation defect coefficient, P Y denotes the regional accuracy deviation coefficient, β 1 , β 2 denote weight coefficients, and β 1 , β 2 are both greater than 0;

[0087] Preset the product processing defect coefficient evaluation indicators P g1 , P g2 , where P g1 > P g2 > 0;

[0088] When P Q > P g1 , it indicates that the current product processing status is a defective product;

[0089] When P Q <P g2 , it indicates that the current processing status of the product is qualified;

[0090] When P g1 ≥P Q ≥P g2 , it indicates that the current processing status of the product is defective.

[0091] In another embodiment provided by the present invention, the rejection processing unit is used to retrieve the current processing status of the product, and the specific rejection operation on the product based on the current processing status of the product is as follows:

[0092] Collect the image of the processing area of the target processing node for the current processing status of the product,

[0093] When the current processing status of the product is defective, generate a first control instruction and control it to the actuator, and the actuator rejects the currently processed product and places it in the defective product recycling bin;

[0094] When the current processing status of the product is a scrap, generate a second control instruction and control it to the actuator, and the actuator rejects the currently processed product and places it in the scrap recycling bin;

[0095] By setting the defective product recycling bin and the scrap recycling bin, the rejection unit can classify and store defective products and scraps when rejecting them, which is convenient for subsequent staff to classify and process defective products and scraps.

[0096] When the current processing status of the product is qualified, no rejection operation is performed on the currently processed product at this time. That is, the qualified products are conveyed through the conveyor line between the processing nodes and enter the next processing node for pipeline processing. Among them, monitoring and acquisition terminals, image multi-processing modules, processing status analysis units, and rejection processing units are set at the positions of each processing node of the production line to realize the acquisition, analysis, and evaluation of the processing status of the products after processing at each processing node, and to realize the rejection of defective products and scraps, so that defective products and scraps will not flow into the adjacent next processing node, avoiding continuous processing of defective products and scraps by subsequent processing nodes, improving the processing efficiency of the production line, and reducing resource waste.

[0097] In the description of this specification, the descriptions referring to terms such as "one embodiment", "example", "specific example", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0098] The above are only the preferred specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, making equivalent substitutions or changes, shall be covered by the protection scope of the present invention.

Claims

1. An intelligent control system for a production line, characterized in that: include: The monitoring and acquisition terminal is used to collect images of products processed by the processing nodes on the production line, delineate processing areas on the product images based on the processing information of the target processing nodes, and obtain images of the processing areas of the target processing nodes; The image multi-dimensional processing module performs contour detection processing on the processing area image to obtain a contour deviation detection image, obtains a contour accuracy deviation coefficient based on contour deviation monitoring image analysis, performs regional distribution processing on the processing area image to obtain multiple sub-region deviation detection images, calculates and obtains the deviation defect coefficient of each sub-region based on the deviation detection image of each sub-region, and integrates the calculation to obtain the regional accuracy deviation coefficient; A processing status analysis unit is used to integrate and calculate the product processing defect coefficient and evaluate the current processing status of the product based on the product processing defect coefficient; The rejection processing unit is used to retrieve the current processing status of the product and perform rejection operations on the product based on the current processing status of the product.

2. According to claim 1, the intelligent control system of a production line is characterized in that: The contour detection process of the processing area image is performed to obtain the contour deviation detection image as follows: Performing image edge detection and extraction on the processing area image to obtain an edge image, and obtaining the image contour line of the current processing area based on the edge image; Map the image contour of the current processing area onto the blank image background layer; Construct the detection contour line, map the detection contour line on the blank image background layer and cover the image contour line of the current processing area, and crop and remove the detection contour line area to obtain the contour deviation monitoring image.

3. The intelligent control system of a production line according to claim 2, characterized in that: The contour accuracy deviation coefficient obtained based on contour deviation monitoring image analysis is specifically: Mark the standard contour line of the processing area on the contour deviation monitoring image; Extract pixels outside the standard contour line in the contour deviation monitoring image, and calculate the grayscale values ​​of these pixels, which are marked as external contour deviation values ​​Pw; Extract the pixels located inside the standard contour line in the contour deviation monitoring image, and calculate the grayscale values ​​of these pixels, which are marked as the internal contour deviation value Pn; The external contour deviation value and the internal contour deviation value are integrated and calculated to obtain the contour accuracy deviation coefficient PL.

4. The intelligent control system of a production line according to claim 1, characterized in that: Perform regional distribution processing on the processing area image to obtain multiple sub-region deviation detection images, calculate and obtain the deviation defect coefficient of each sub-region based on the deviation detection image of each sub-region, and integrate and calculate to obtain the regional accuracy deviation coefficient, which is specifically: Retrieve the processing area image, map the contour line of the current processing area image onto the processing area image, and cut out the contour line area of ​​the current processing area image to obtain the standard area detection image; Based on the processing information of the target processing node, the area with the same processing standard is divided on the standard area detection image to obtain multiple sub-area deviation detection images, and the deviation defect coefficient of each sub-area deviation detection image is calculated in a distributed manner. Then, the deviation defect coefficient of each sub-area deviation detection image is summed to obtain the regional accuracy deviation coefficient.

5. The intelligent control system of a production line according to claim 4, characterized in that: The distributed calculation of the deviation defect coefficient of each sub-region deviation detection image is specifically: Construct m pixel detection regions of the same size on each sub-region deviation detection image, and calculate the pixel grayscale value of each pixel detection region to obtain the grayscale value dataset U∈(X1, X2, X3...X m ), X m represents the pixel gray value of the mth pixel detection area of ​​the sub-region deviation detection image; The self-deviation coefficient and the standard deviation coefficient are calculated respectively through the gray value data set of the sub-region deviation detection image; The self-deviation coefficient and the standard deviation coefficient are summed to obtain the deviation defect coefficient of the sub-region deviation detection image.

6. The intelligent control system of a production line according to claim 5, characterized in that: The gray value data set of the sub-region deviation detection image is used to calculate the self-deviation coefficient and the standard deviation coefficient respectively as follows: Retrieve the gray value dataset U∈(X1, X2, X3...X m ); Calculate the self-bias coefficient, P z represents the self-bias coefficient of the sub-region deviation detection image, X m represents the pixel grayscale value of the mth pixel detection area of ​​the sub-region deviation detection image, δ1 is a preset weight coefficient and δ1>0; Calculate the coefficient of standard deviation, represents the standard deviation coefficient of the sub-region deviation detection image, X e Represents the standard pixel grayscale value of the sub-region deviation detection image, δ2 is the preset weight coefficient and δ2>0.

7. An intelligent control system for a production line according to claim 2 or 4, characterized in that: The specific steps of constructing the detection contour line are as follows: based on the processing information of the target processing node, the standard contour line of the processing area is obtained, and the detection contour line is constructed by taking the standard contour line as the baseline and extending it by 0.5Le to both sides, where Le is the error compensation parameter of the image contour line of the current processing area.

8. The intelligent control system of a production line according to claim 1, characterized in that: The processing status includes qualified products, defective products and waste products.

9. The intelligent control system of a production line according to claim 1, characterized in that: The integrated calculation of the product processing defect coefficient and the evaluation of the current processing status of the product based on the product processing defect coefficient are specifically as follows: Retrieve the contour accuracy deviation coefficient and the regional accuracy deviation coefficient to calculate the product processing defect coefficient, P Q =P L *β1+P Y *β2, where P Q Represents the product processing defect coefficient, P L Indicates contour deviation defect, P Y represents the regional accuracy deviation coefficient, β1 and β2 represent weight coefficients, and both β1 and β2 are greater than 0; Preset product processing defect coefficient evaluation index P g1 , P g2 , where P g1 >P g2 >0; When P Q >P g1 When , it means that the current product processing status is waste; When P Q <P g2 When , it means the current product processing status is qualified; When P g1 ≥P Q ≥P g2 , it indicates that the current product processing status is defective.

10. The intelligent control system of a production line according to claim 1, characterized in that: The rejection processing unit is used to retrieve the current processing status of the product and perform rejection operations on the product based on the current processing status of the product. Specifically: Collect the current processing status of the target processing node processing area image product, When the current processing status of the product is defective, a first control instruction is generated and controlled to the execution mechanism, and the execution mechanism removes the currently processed product and places it in the defective product recovery box; When the current processing status of the product is waste, a second control instruction is generated and controlled to the execution mechanism, and the execution mechanism removes the currently processed product and places it in the waste recycling box; When the current processing status of the product is qualified, the current processed product will not be rejected.

Images