Intelligent control system for precise coating and curing production of spunbond non-woven fabric production line

Abstract

The invention relates to the technical field of coating production control, in particular to an intelligent control system for precise coating and curing production of a spun-bonded non-woven fabric production line, which comprises a data collection module, a data analysis module and a production and optimization module, and is characterized in that the data collection module collects historical coating data and current coating image data; the data analysis module calculates a current uniformity score according to the current coating image data; obtaining a current smoothness score; the data analysis module calculates an optimal uniformity score and a smoothness score according to historical coating data, and performs classification based on the optimal uniformity score and the smoothness score according to a current uniformity score and a current smoothness score obtained through current coating image data; and the production and optimization module performs prior production and execution of an optimized production parameter instruction according to the classification result, and if the current coating image data belongs to coating to be optimized, the optimized production parameter instruction is generated according to the current uniformity score and the current smoothness score.

Description

Technical Field

[0001] The invention relates to the technical field of coating production control, and in particular to an intelligent control system for precise coating and curing production of a spunbond nonwoven fabric production line. Background Art

[0002] Traditional coating production control systems usually rely on preset production parameters and fixed processes during operation, and lack real-time data collection and analysis capabilities; first, traditional systems usually determine a set of production parameters through historical experience and preliminary tests before starting production, and perform continuous coating production based on these parameters. However, such systems lack the ability to respond to changes in variables that may occur during the production process, such as changes in material properties, environmental conditions, or equipment status. From a quality control perspective, traditional systems may evaluate production quality at predetermined checkpoints, but these evaluations are usually intermittent rather than continuous. Due to the lack of real-time thickness mean and standard deviation calculations, traditional systems have difficulty accurately controlling the uniformity of coating, which may lead to inconsistent thickness problems.

[0003] In addition, for smoothness indicators, traditional methods usually rely on simple measuring tools for inspection, which cannot detect and correct subtle changes in surface roughness in advance, which may cause the smoothness of the final product to fail to meet the standard. Due to the inability to optimize based on real-time data, the process of adjusting production parameters becomes slow and inaccurate, and quality problems on the production line are often not solved in a timely and effective manner. For example, when the problem is found, the parameters are adjusted. This delayed adjustment process causes a large number of products to be reworked or scrapped, resulting in waste of resources and reduced production efficiency. Traditional systems have obvious disadvantages in quality control and production efficiency because they lack data-driven intelligent decision-making capabilities and continuous optimization mechanisms, and ultimately it is difficult to stably produce high-quality products. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent control system for precision coating and curing production of a spunbond nonwoven fabric production line to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solution: an intelligent control system for precision coating and curing production of spunbond nonwoven production line, characterized in that it includes a data collection module, a data analysis module and a production and optimization module, wherein: The data collection module collects historical coating data and current coating image data generated by the coating production equipment; The data analysis module calculates the mean and standard deviation according to the current coating image data, and calculates the current uniformity score according to the mean and standard deviation; and calculates the root mean square roughness of the current coating image data, and reversely maps the root mean square roughness to the current smoothness score; The data analysis module calculates the best uniformity score and smoothness score based on the historical coating data using the quantile statistics method, and classifies based on the best uniformity score and smoothness score using the current uniformity score and current smoothness score obtained from the current coating image data; The production and optimization module performs the execution of the instructions for prioritizing production and optimizing production parameters according to the classification results in the data analysis module, wherein: If the current coating image data belongs to the coating to be shipped, the coating corresponding to the current coating image data will be prioritized for shipment; If the current coating image data belongs to the coating to be optimized, an optimization production parameter instruction is generated according to the current uniformity score and the current smoothness score, and the production parameters of the coating equipment are adjusted. After the adjustment, the data collection module re-collects the current coating image data and executes the data analysis module and the production and optimization module through the same logical loop as above.

[0006] As a further improvement of the present technical solution, the data collected by the data collection module include historical coating data and current coating image data, wherein the historical coating data includes past equipment production parameters, historical quality scores and production conditions, wherein the quality scores are historical uniformity scores and historical smoothness scores; and the current coating image data are coating thickness data at different positions.

[0007] As a further improvement of the technical solution, the data analysis module includes a current scoring unit, which calculates the thickness mean and standard deviation corresponding to the current coating image data according to the current coating image data, and calculates the current uniformity score according to the thickness mean and standard deviation, specifically including: The calculation formula of the mean thickness is: ; Thickness standard deviation calculation formula: ;in It is The thickness of the position, is the number of samples of coating thickness data at different locations; Calculate the current uniformity score using the mean and standard deviation , the formula is .

[0008] As a further improvement of the technical solution, the process of calculating the root mean square roughness of the current coating image data by the current scoring unit is as follows: Filter the image to remove noise; Compute the gradient of an image to detect surface texture and uneven areas; Calculate the root mean square roughness of the gray value in the image, the formula is ,in, is the image at point The gray value at is the average gray value of the image, and are the width and height of the image; Back-map the RMS roughness to the current smoothness score , the formula is: .

[0009] As a further improvement of the technical solution, the data analysis module includes a best scoring unit, which calculates the best uniformity score and the best smoothness score range based on the historical coating data using the quantile statistics method, and classifies the current uniformity score and the current smoothness score obtained by the current coating image data based on the range of the best uniformity score and the smoothness score. The classification results include coatings to be shipped and coatings to be optimized. The calculation and classification process specifically includes: Extract the historical coating data of the produced products, sort the historical coating data of the produced products in descending order according to the historical uniformity score and the historical smoothness score, and select the 50% quantile and the 75% quantile as the range of the best uniformity score and the best smoothness score; The current coating image data whose current uniformity score is within the optimal uniformity score range and whose current smoothness score is within the optimal uniformity score range is regarded as the coating to be shipped, otherwise it is regarded as the coating to be optimized.

[0010] As a further improvement of the technical solution, the production and optimization module generates an optimized production parameter instruction according to the classification result of the best scoring unit and the current uniformity score and the current smoothness score, wherein: If the current coating image data belongs to the coating to be optimized, an optimized production parameter instruction is generated according to the current uniformity score and the current smoothness score, specifically including: The optimization target is determined based on the current uniformity score and the current smoothness score corresponding to the current coating image data, wherein: if only the current uniformity score exceeds the optimal uniformity score range, then improving the uniformity score is determined as the optimization target; if only the current smoothness score exceeds the optimal smoothness score range, then improving the smoothness score is determined as the optimization target; if both exceed the corresponding optimal scores, then improving the uniformity score and the smoothness score are determined as the optimization targets.

[0011] As a further improvement of the technical solution, the production and optimization module selects a corresponding optimization model according to the optimization target, wherein the optimization model includes a uniformity optimization model and a smoothness optimization model, specifically including: Establishment of uniformity optimization model: extract the historical coating data of the products, take the historical uniformity score as the target variable, and the equipment production parameters as the input variables, and use the multivariate regression algorithm to establish the uniformity optimization model; Establishment of smoothness optimization model: extract the historical coating data of the products, take the historical smoothness score as the target variable, and the equipment production parameters as the input variables, and use the multivariate regression algorithm to establish the smoothness optimization model; According to the established optimization model and the determined optimization model, the corresponding equipment production parameters are determined, the optimization parameter instructions are generated, and the coating equipment production parameters are adjusted. After the adjustment, the data collection module re-collects the current coating image data, and executes the data analysis module and the production and optimization module through the same logical loop as above until all the coating corresponding to the current coating image data is completed and belongs to the coating to be shipped.

[0012] Compared with the prior art, the present invention has the following beneficial effects: 1. The spunbond nonwoven production line precision coating and curing production intelligent control system calculates the best uniformity score and smoothness score based on historical coating data using quantile statistics. It can not only classify the current coating image data, but also determine the optimization target. This process is based on a large amount of historical data. By extracting the historical coating data that has been produced and sorting these data according to the historical quality scores, the 50% quantile and 75% quantile are used to determine the best score range, forming a scientific and reliable standard. Such quantitative standards play an important role in the current coating image data evaluation. It not only clarifies which products can be shipped immediately and which need further optimization, but also provides clear goals for the optimization process. This data-driven approach enhances the intelligence of the system and the accuracy of decision-making through digitalization and statistical methods, enabling the production line to better cope with variable changes in the production process. 2. The intelligent control system for precision coating and curing production of the spunbond nonwoven production line classifies products based on the current uniformity score and the current smoothness score, and the best uniformity score and smoothness score; and generates optimized production parameter instructions based on the current uniformity score and the current smoothness score, and selects the corresponding optimization model by determining the corresponding optimization target. This method enables the system to perform real-time quality monitoring and dynamic adjustment during the production process; specifically, during the coating production process, the system obtains the current coating image data in real time and calculates the thickness mean and standard deviation, thereby generating the current uniformity score and calculating the smoothness score; then, based on the comparison between the current score and the historical best score range, the product is automatically classified as coating to be shipped or coating to be optimized; when the product is classified as coating to be optimized, the system will determine whether it is necessary to improve the uniformity or smoothness, or the dual optimization target, based on the current quality score, and then apply the corresponding optimization model to generate new production parameters to ensure that the product quality is stable at a high level; 3. The overall method and cycle process used by the intelligent control system for precision coating and curing production of the spunbond nonwoven production line include data collection, real-time quality evaluation, production parameter optimization and cycle adjustment. Through a closed-loop control system, the production line can continue to maintain the optimal state. The data collection module regularly extracts historical data and current real-time production data from the public database. The data analysis module generates a detailed quality score after the current coating quality evaluation and classifies the current product. At the same time, the production and optimization module executes priority production and optimization commands according to the classification results, and adjusts production parameters to achieve the best production effect. After each adjustment, the system restarts data collection and analysis, and repeats this process to form an automated intelligent control cycle. This method not only improves production efficiency, but also ensures the consistency and stability of product quality, greatly reduces the possibility of human intervention, and achieves high intelligence and high-precision control of precision coating and curing production in the production process of spunbond nonwovens. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 It is a schematic diagram of the overall module of the present invention; Figure 2 It is a schematic diagram of the data analysis module unit of the present invention.

[0014] In the figure: 100, data collection module; 200, data analysis module; 201, current scoring unit; 202, best scoring unit; 300, production and optimization module. DETAILED DESCRIPTION

[0015] The following will be combined with the accompanying drawings in 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.

[0016] See also Figure 1-2 The present invention provides a technical solution: an intelligent control system for precision coating and curing production of a spunbond nonwoven fabric production line, comprising a data collection module 100, a data analysis module 200 and a production and optimization module 300.

[0017] The data collection module 100 uses a public database to collect historical coating data, which includes past equipment production parameters, historical quality scores and production conditions, where the quality scores are historical uniformity scores and historical smoothness scores; and collects current coating image data generated by coating production equipment through visual sensors, where the current coating image data is coating thickness data at different positions.

[0018] The current scoring unit 201 in the data analysis module 200 calculates the thickness mean and standard deviation corresponding to the current coating image data according to the current coating image data, and calculates the current uniformity score according to the thickness mean and standard deviation, specifically including: The calculation formula of the mean thickness is: ; Thickness standard deviation calculation formula: ;in It is The thickness of the position, is the number of samples of coating thickness data at different locations; Calculate the current uniformity score using the mean and standard deviation , the formula is , the formula shows that the smaller the standard deviation, the more consistent the thickness, the better the current uniformity score. Approaching 1.

[0019] The current scoring unit 201 calculates the root mean square roughness of the current coating image data and reversely maps the root mean square roughness into the current smoothness score, specifically including: Filter the image (e.g., Gaussian filtering) to remove noise; Compute the gradient of the image (e.g., via the Sobel operator) to detect surface texture and uneven areas; Calculate the root mean square roughness of the gray value in the image, the formula is ,in, is the image at point The gray value at is the average gray value of the image, and are the width and height of the image; Back-map the RMS roughness to the current smoothness score , the formula is: , which indicates that the lower the roughness, the higher the current smoothness score. Approaching 1.

[0020] The best scoring unit 202 in the data analysis module 200 calculates the best uniformity score and the best smoothness score range based on the historical coating data using the quantile statistics method, and classifies the current uniformity score and the current smoothness score obtained from the current coating image data based on the range of the best uniformity score and the smoothness score. The classification results include coatings to be shipped and coatings to be optimized. The calculation and classification process specifically includes: Extract the historical coating data of the produced products, sort the historical coating data of the produced products in descending order according to the historical uniformity score and the historical smoothness score, and select the 50% quantile and the 75% quantile as the range of the best uniformity score and the best smoothness score; The current coating image data whose current uniformity score is within the optimal uniformity score range and whose current smoothness score is within the optimal uniformity score range is regarded as the coating to be shipped, otherwise it is regarded as the coating to be optimized.

[0021] The data analysis module 200 integrates the current scoring unit 201 and the best scoring unit 202. The current scoring unit 201 calculates the thickness mean and standard deviation of the current coating image data, and the system can generate a uniformity score for the current coating. At the same time, the image's smoothness is evaluated by calculating its root mean square roughness and gradient analysis. The best scoring unit 202 uses historical coating data to calculate the best uniformity score and the best smoothness score range based on the quantile statistics method. By comparing the current score with the historical best range, the current product is accurately classified as a coating to be shipped or a coating to be optimized, ensuring that the product quality is at the optimal level. This module greatly improves the product's qualification rate and consistency through sophisticated data analysis and scientific classification methods.

[0022] The production and optimization module 300 performs the execution of the instructions of prioritizing production and optimizing production parameters according to the classification results in the best scoring unit 202, wherein: If the current coating image data belongs to the coating to be shipped, the coating corresponding to the current coating image data will be prioritized for shipment; If the current coating image data belongs to the coating to be optimized, an optimized production parameter instruction is generated according to the current uniformity score and the current smoothness score, specifically including: According to the current uniformity score and the current smoothness score corresponding to the current coating image data, an optimization target is determined, wherein: if only the current uniformity score exceeds the optimal uniformity score range, then improving the uniformity score is determined as the optimization target; if only the current smoothness score exceeds the optimal smoothness score range, then improving the smoothness score is determined as the optimization target; if both exceed the corresponding optimal scores, then improving the uniformity score and the smoothness score is determined as the optimization target; According to the optimization target, select the corresponding optimization model, where the optimization model includes uniformity optimization model and smoothness optimization model, and analyze the influence of equipment production parameters on uniformity and smoothness, including: Establishment of uniformity optimization model: extract the historical coating data of the products, take the historical uniformity score as the target variable, and the equipment production parameters as the input variables, and use the multivariate regression algorithm to establish the uniformity optimization model; Establishment of smoothness optimization model: extract the historical coating data of the products, take the historical smoothness score as the target variable, and the equipment production parameters as the input variables, and use the multivariate regression algorithm to establish the smoothness optimization model; According to the established optimization model and the determined optimization model, the corresponding equipment production parameters are determined, the optimization parameter instructions are generated, and the coating equipment production parameters are adjusted. After the adjustment, the data collection module 100 re-collects the current coating image data, and executes the data analysis module 200 and the production and optimization module 300 through the same logical loop as above until all the coatings corresponding to the current coating image data are completed and are ready for shipment.

[0023] The production and optimization module 300 executes the corresponding production instructions according to the classification results. For the coating to be shipped, the system gives priority to production to ensure timely delivery; for the coating to be optimized, the module determines the optimization target and selects the appropriate optimization model (such as uniformity optimization model or smoothness optimization model) by analyzing the current uniformity score and smoothness score; through the multivariate regression algorithm, the module can accurately analyze the impact of equipment production parameters on coating quality, generate optimized production parameter instructions, and adjust the production equipment; this process forms a closed-loop control system, through continuous data collection, analysis, classification and optimization, to achieve real-time monitoring and dynamic adjustment of production quality, and continuously improve the overall quality of products and production efficiency.

[0024] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. Intelligent control system for precision coating and curing production of spunbond nonwoven production line, characterized by: It comprises a data collection module (100), a data analysis module (200) and a production and optimization module (300), wherein: The data collection module (100) collects historical coating data and current coating image data generated by coating production equipment; The data analysis module (200) calculates a mean value and a standard deviation based on the current coating image data, and calculates a current uniformity score based on the mean value and the standard deviation; and calculates a root mean square roughness of the current coating image data, and reversely maps the root mean square roughness into a current smoothness score; The data analysis module (200) calculates the best uniformity score and smoothness score based on the historical coating data using a quantile statistics method, and performs classification based on the best uniformity score and smoothness score using the current uniformity score and current smoothness score obtained from the current coating image data; The production and optimization module (300) performs the execution of the instructions for prioritizing production and optimizing production parameters according to the classification results in the data analysis module (200), wherein: If the current coating image data belongs to the coating to be shipped, the coating corresponding to the current coating image data will be prioritized for shipment; If the current coating image data belongs to the coating to be optimized, an optimization production parameter instruction is generated according to the current uniformity score and the current smoothness score, and the production parameters of the coating equipment are adjusted. After the adjustment, the data collection module (100) re-collects the current coating image data, and executes the data analysis module (200) and the production and optimization module (300) through the same logical loop as above.

2. According to claim 1, the intelligent control system for precision coating and curing production of spunbond nonwoven production line is characterized in that: The data collected by the data collection module (100) include historical coating data and current coating image data, wherein the historical coating data includes past equipment production parameters, historical quality scores and production conditions, wherein the quality scores are historical uniformity scores and historical smoothness scores; and the current coating image data are coating thickness data at different locations.

3. According to claim 1, the intelligent control system for precision coating and curing production of spunbond nonwoven production line is characterized in that: The data analysis module (200) comprises a current scoring unit (201), wherein the current scoring unit (201) calculates the thickness mean and standard deviation corresponding to the current coating image data according to the current coating image data, and calculates the current uniformity score according to the thickness mean and standard deviation, specifically comprising: The calculation formula of the mean thickness is: ; Thickness standard deviation calculation formula: ;in It is The thickness of the position, is the number of samples of coating thickness data at different locations; Calculate the current uniformity score using the mean and standard deviation , the formula is .

4. According to claim 3, the intelligent control system for precision coating and curing production of spunbond nonwoven production line is characterized in that: The process of the current scoring unit (201) calculating the root mean square roughness of the current coating image data is as follows: Filter the image to remove noise; Compute the gradient of an image to detect surface texture and uneven areas; Calculate the root mean square roughness of the gray value in the image, the formula is ,in, is the image at point The gray value at is the average gray value of the image, and are the width and height of the image; Back-map the RMS roughness to the current smoothness score , the formula is: .

5. According to claim 3, the intelligent control system for precision coating and curing production of spunbond nonwoven production line is characterized in that: The data analysis module (200) includes a best scoring unit (202), wherein the best scoring unit (202) calculates the best uniformity score and the best smoothness score range based on the historical coating data using a quantile statistics method, and classifies the coating based on the best uniformity score and the smoothness score range obtained from the current coating image data. The classification results include coatings to be shipped and coatings to be optimized. The calculation and classification process specifically includes: Extract the historical coating data of the produced products, sort the historical coating data of the produced products in descending order according to the historical uniformity score and the historical smoothness score, and select the 50% quantile and the 75% quantile as the range of the best uniformity score and the best smoothness score; The current coating image data whose current uniformity score is within the optimal uniformity score range and whose current smoothness score is within the optimal uniformity score range is regarded as the coating to be shipped, otherwise it is regarded as the coating to be optimized.

6. The intelligent control system for precision coating and curing production of spunbond nonwoven production line according to claim 1 is characterized in that: The production and optimization module (300) generates an optimized production parameter instruction according to the classification result of the best scoring unit (202) and the current uniformity score and the current smoothness score, wherein: If the current coating image data belongs to the coating to be optimized, an optimized production parameter instruction is generated according to the current uniformity score and the current smoothness score, specifically including: The optimization target is determined based on the current uniformity score and the current smoothness score corresponding to the current coating image data, wherein: if only the current uniformity score exceeds the optimal uniformity score range, then improving the uniformity score is determined as the optimization target; if only the current smoothness score exceeds the optimal smoothness score range, then improving the smoothness score is determined as the optimization target; if both exceed the corresponding optimal scores, then improving the uniformity score and the smoothness score are determined as the optimization targets.

7. The intelligent control system for precision coating and curing production of spunbond nonwoven production line according to claim 6 is characterized in that: The production and optimization module (300) selects a corresponding optimization model according to the optimization target, wherein the optimization model includes a uniformity optimization model and a smoothness optimization model, specifically including: Establishment of uniformity optimization model: extract the historical coating data of the products, take the historical uniformity score as the target variable, and the equipment production parameters as the input variables, and use the multivariate regression algorithm to establish the uniformity optimization model; Establishment of smoothness optimization model: extract the historical coating data of the products, take the historical smoothness score as the target variable, and the equipment production parameters as the input variables, and use the multivariate regression algorithm to establish the smoothness optimization model; According to the established optimization model and the determined optimization model, the corresponding equipment production parameters are determined, the optimization parameter instructions are generated, and the coating equipment production parameters are adjusted. After the adjustment, the data collection module (100) re-collects the current coating image data, and executes the data analysis module (200) and the production and optimization module (300) through the same logical loop as above until all the coatings corresponding to the current coating image data are completed and are ready for shipment.

Images