A control system and method for intelligent manufacturing production line of non-woven breathable membrane

Abstract

The present invention relates to the technical field of production intelligent control, and discloses a control system and method for an intelligent manufacturing production line of a non-woven breathable film, comprising collecting material attribute data of a breathable film production line, and constructing a digital twin model of a breathable film production process; collecting visual appearance images and near-infrared spectrum data of waste scraps in a sorting area of ​​the production line in real time; dividing the waste scraps into Class A scraps, Class B scraps, and Class C scraps according to preset grading judgment standards, and constructing a waste scrap grading decision model; replacing part of the raw materials with Class A scraps, physically regenerating Class B waste, and biodegrading Class C waste; based on the digital twin model, integrating Class A and Class B waste recovery data, constructing a multi-objective optimization model for the breathable film production line, and solving to obtain the production control target.

Description

Technical Field

[0001] The present invention relates to the field of intelligent production control technology, and more specifically, to a control system and method for an intelligent manufacturing production line of a non-woven breathable membrane. Background Art

[0002] With the widespread application of non-woven breathable membranes in the fields of medical treatment, nursing, hygiene, protection, etc., breathable membrane production faces challenges such as high product quality requirements, high production efficiency requirements, and strict cost control requirements. In order to improve the intelligent level of breathable membrane production, optimize the production process, and achieve lean production, domestic and foreign scholars have carried out a lot of research work.

[0003] The Chinese patent with the authorization announcement number CN113850538B discloses an intelligent management system for the production of antibacterial flame-retardant boards based on full-process tracking of production. The system tracks and manages the production process quality of the antibacterial flame-retardant boards, determines whether the production process quality of each production process meets the standards, and stops the production flow of the semi-finished boards of the corresponding process in the production process when a production process does not meet the standards, and performs correction processing, thus solving the problems of the current production quality management method of antibacterial flame-retardant boards, such as the inability to trace quality and the inability to conduct targeted control of key production processes.

[0004] A Chinese patent with the authorization announcement number CN113408800B discloses a method for predicting the quality of cross-border renewable resource industrial products. The method determines the cross-border use environment and use duration of renewable resource industrial products, uses big data to find the use data of similar products, establishes a loss model, evaluates the loss of products in different time periods and different use environments, and calculates and predicts the service life of products in different environments. The method can derive the loss of renewable resource industrial products in different use environments and use durations, which is conducive to the rational use of renewable resource industrial products and reduces waste.

[0005] Although the above patents propose some intelligent management and quality prediction methods, the existing breathable membrane production line control systems and methods lack a systematic classification and recycling solution for the waste and scraps generated during the production process, resulting in waste of resources and further improvement in sustainable development. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, the present invention provides a control system and method for an intelligent manufacturing production line of a non-woven breathable membrane.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A control method for a non-woven breathable film intelligent manufacturing production line, comprising:

[0009] Collect material attribute data of the breathable membrane production line to form a first data set, and build a digital twin model of the breathable membrane production process based on the first data set; collect visual appearance images and near-infrared spectral data of waste scraps in the sorting area of ​​the non-woven breathable membrane intelligent manufacturing production line in real time to obtain a second data set;

[0010] According to the preset classification judgment standard, the waste scraps are divided into three grades, including grade A scraps, grade B scraps and grade C scraps; a classification judgment standard database is established, and a waste scrap classification decision model is constructed based on the classification judgment standard database; based on the second data set collected in real time and the waste scrap classification decision model, the classification grade corresponding to the waste scraps is obtained;

[0011] Replace some of the original raw materials with Class A scraps to obtain Class A scrap recycling data; physically regenerate Class B waste to obtain Class B waste recycling data; biodegrade Class C waste to convert it into valuable energy and fertilizer products;

[0012] Based on the digital twin model of the breathable membrane production process, the A-level scrap recycling data and the B-level waste recycling data are integrated to construct a multi-objective optimization model of the breathable membrane production line. The production control target is obtained by solving the multi-objective optimization model of the breathable membrane production line.

[0013] Further, the method comprises:

[0014] The appearance feature data of the waste scraps are extracted according to the visual appearance image, and the material attribute data of the waste scraps are obtained by analyzing the near infrared spectrum data; the appearance feature data and the material attribute data are fused to obtain a second data set.

[0015] Furthermore, the method comprises:

[0016] The classification judgment standard database is used to store the corresponding relationship between the key attribute parameters of waste and scraps and the classification levels;

[0017] The key property parameters of the waste scraps are property parameters of the waste scraps used to determine the classification of the waste scraps;

[0018] For each key attribute parameter, divide the value range or level and set the classification judgment threshold;

[0019] The classification level is determined by the value range or level of the key attribute parameter and the classification determination threshold.

[0020] Further, the method comprises:

[0021] Replace part of the original raw materials with grade A scraps and control the proportion of grade A scraps added; perform quality inspection on the raw material mixture after adding grade A scraps, establish a quantitative relationship model between the quality and the proportion of grade A scraps added, maximize the reuse rate of grade A scraps while ensuring the quality of the raw material mixture, and obtain grade A scrap recycling data;

[0022] Put Class B waste into the physical recycling system to convert Class B waste into plasticized material; conduct quality inspection on the plasticized material, establish a mathematical model between the quality of plasticized material and the amount of Class B waste input, maximize the recovery rate of Class B waste while ensuring the quality of plasticized material, and obtain Class B waste recycling data.

[0023] Furthermore, the quantitative relationship model between the quality and the proportion of A-grade scraps added includes:

[0024]

[0025] in, It is the quality index of the raw material mixture; is the proportion of A-grade scraps added, , where A is the amount of grade A scrap, is the amount of the main ingredient; is the adjustment factor: is the exponential coefficient; is the nonlinear adjustment coefficient; is the Gaussian attenuation coefficient; This is the ideal proportion of grade A scraps added.

[0026] Furthermore, the mathematical model between the plasticized material quality and the input amount of Class B waste includes:

[0027]

[0028] in, is the plasticized material quality coefficient, is the input amount of Class B waste, is the optimal input amount of Class B waste, is the maximum potential coefficient for improving the quality of plasticized materials, is the impact intensity coefficient of waste input, is the nonlinear impact index of waste input, is the mass loss coefficient when the input quantity deviates from the optimal one.

[0029] Further, the method comprises:

[0030] Use the digital twin model to generate simulation data of the breathable membrane production process and integrate it with the actual production data to construct a training sample set for multi-objective optimization;

[0031] Taking product quality and production efficiency as constraints, minimizing cost and energy consumption, maximizing the recycling rate of Class A scraps and maximizing the recycling rate of Class B waste as optimization goals, a multi-objective optimization model for the breathable membrane production line was constructed;

[0032] Based on the training sample set, the multi-objective optimization model of the breathable membrane production line is trained;

[0033] Solve the multi-objective optimization model of the breathable membrane production line, obtain the optimal static process parameter combination, and generate a feasible solution set;

[0034] Based on the digital twin model and the feasible solution set obtained, the optimal dynamic process parameter combination is obtained as the production control target through simulation experiments and production verification.

[0035] A control system for a non-woven breathable film intelligent manufacturing production line, which is used to implement the above-mentioned control method for a non-woven breathable film intelligent manufacturing production line, the system comprising:

[0036] Data acquisition module: used to collect material attribute data of the breathable film production line to form a first data set; real-time collection of visual appearance images and near-infrared spectral data of waste scraps in the sorting area of ​​the non-woven breathable film intelligent manufacturing production line to obtain a second data set;

[0037] A digital twin model building module: used for building a digital twin model of the breathable membrane production process according to the first data set;

[0038] The scrap material classification module is used to classify the scrap materials into three grades according to the preset classification judgment standard, including grade A scrap materials, grade B scrap materials and grade C scrap materials; establish a classification judgment standard database, and build a scrap material classification decision model based on the classification judgment standard database; obtain the classification grade corresponding to the scrap materials based on the second data set collected in real time and the scrap material classification decision model;

[0039] Waste scrap recycling module: used to replace part of the original raw materials with Class A scraps to obtain Class A scrap recycling data; to physically regenerate Class B waste to obtain Class B waste recycling data; to biodegrade Class C waste to convert it into valuable energy and fertilizer products;

[0040] Production control target solving module: It is used to build a multi-objective optimization model of the breathable membrane production line based on the digital twin model of the breathable membrane production process, integrate the A-level scrap recycling data and the B-level waste recycling data, and obtain the production control target by solving the multi-objective optimization model of the breathable membrane production line.

[0041] An electronic device comprises a memory, a central processing unit and a computer program stored in the memory and executable on the central processing unit. When the central processing unit executes the computer program, the above-mentioned control method for an intelligent manufacturing production line of a non-woven breathable membrane is implemented.

[0042] A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed, implements the above-mentioned method for controlling a non-woven breathable film intelligent manufacturing production line.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] The present invention constructs a digital twin model of the breathable membrane production process by collecting and analyzing the material attribute data of the production line, realizing real-time monitoring, simulation optimization and prediction of the production process, greatly improving the intelligent level of production management. The digital twin model can dynamically present the material flow of each process of the production line, optimize material scheduling and equipment utilization, provide a visual and quantifiable basis for production decision-making, and improve production efficiency and product quality.

[0045] The present invention uses machine vision and near-infrared spectroscopy technology to intelligently collect and analyze the appearance characteristics and material property data of waste scraps, build a scientific and complete waste property data set, and automatically and accurately classify waste scraps based on classification criteria and decision models, replacing manual sorting and improving sorting efficiency and quality. After classification, a recycling plan can be formulated specifically for waste materials, with Class A scraps directly replacing raw materials, Class B waste physically regenerated, and Class C waste biodegradable, maximizing resource utilization efficiency and reducing waste disposal costs and environmental impacts.

[0046] Under the premise of ensuring the quality of the raw material mixture and recycled plastics, the present invention optimizes the replacement ratio of Class A scraps and the recycling input of Class B waste through a quantitative relationship model of quality, blending ratio and input amount, maximizes the recycling rate of waste materials at the source and in the process, realizes closed-loop optimization of the production process, promotes transparent production, and at the same time reduces dependence on virgin raw materials and reduces production costs.

[0047] The present invention integrates digital twin simulation data and actual production data, takes product quality and production efficiency as constraints, and takes minimizing cost, energy consumption and maximizing waste recycling rate as goals, to construct a multi-objective optimization model for the breathable membrane production line. By solving the optimization model, the optimal process parameter combination is obtained, and actual production is guided on the basis of dynamic simulation verification. While ensuring product quality, resource consumption is minimized, economic and environmental benefits are maximized, and energy saving, material saving, emission reduction and efficiency improvement are achieved in the breathable membrane production process.

[0048] The production line control system adopts a modular design, and the functional modules are flexibly combined to achieve rapid deployment and iterative optimization of waste scrap classification and recycling solutions for different production scenarios. Through distributed edge computing, data processing and control decisions are decentralized, improving the real-time and reliability of the system. The replicable and popularizable system architecture provides a demonstration for the intelligent upgrading and green development of non-woven fabric material industries such as breathable membranes. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1 It is a flow chart of a control method of a non-woven breathable film intelligent manufacturing production line in the present invention;

[0051] Figure 2 It is a flow chart of a method for obtaining the classification grade corresponding to waste and scrap materials in a non-woven breathable film intelligent manufacturing production line control method of the present invention;

[0052] Figure 3 A flowchart of a method for constructing a multi-objective optimization model for a breathable film production line to obtain production control objectives in a non-woven breathable film intelligent manufacturing production line control method of the present invention;

[0053] Figure 4 This is a functional module diagram of a control system for a non-woven breathable membrane intelligent manufacturing production line in the present invention. DETAILED DESCRIPTION

[0054] 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.

[0055] Example 1

[0056] See also Figure 1 As shown, this embodiment provides a control method for a non-woven breathable film intelligent manufacturing production line, including:

[0057] Step S1000, collecting material attribute data of the breathable membrane production line to form a first data set, and constructing a digital twin model of the breathable membrane production process based on the first data set; collecting visual appearance images and near-infrared spectral data of waste scraps in the sorting area of ​​the non-woven breathable membrane intelligent manufacturing production line in real time to obtain a second data set;

[0058] Furthermore, step S1000 includes:

[0059] Step S1100, collecting material attribute data of the breathable membrane production line to form a first data set, constructing a digital twin model of the breathable membrane production process based on the first data set, and presenting the material flow of each process of the production line in real time, including raw material input, work-in-progress transfer, finished product output, and waste and scrap collection;

[0060] Specifically, select appropriate material flow sensor types, such as weight sensors, infrared sensors, radio frequency identification (RFID) sensors, etc., and arrange sensor networks according to the characteristics and requirements of each process of the production line to collect material attribute information such as quantity, location, material, etc. of raw materials, work-in-progress, finished products, and scraps in real time to form the first data set. Weight sensors are used to measure the quality of materials; infrared sensors are used to detect the presence and location of materials; RFID sensors are used to identify and track materials with electronic tags. The data collected by the material flow sensor is transmitted to the data center in real time through industrial Ethernet or wireless communication protocols. The collected data is cleaned, filtered and fused to eliminate redundant and abnormal data and improve data quality. A digital twin model of the breathable membrane production process is constructed, and the first data set collected by the material flow sensor is imported into the digital twin model. Through three-dimensional visualization technology, the material flow of each process of the production line is presented in real time, including raw material input, work-in-progress transfer, finished product output, and scrap collection. The digital twin model can dynamically simulate the production process and optimize material scheduling and equipment utilization.

[0061] Material flow sensors are the basis for realizing the digitalization and intelligence of breathable membrane production lines. By rationally selecting and arranging sensors, the flow of materials in the production process can be fully sensed. Different types of sensors, such as weight sensors, infrared sensors, and RFID sensors, can collect material attribute data from multiple dimensions to form a comprehensive first data set. The real-time collection and preprocessing of material flow sensor data ensures the accuracy and reliability of the data, and provides high-quality data support for the subsequent construction and optimization control of digital twin models. The digital twin model is a virtual mapping of the breathable membrane production line. By importing the first data set, the operating status of the production line can be reflected in real time. The digital twin model can not only visualize the material flow, but also optimize material scheduling and equipment utilization through simulation, thereby improving production efficiency and product quality. At the same time, the digital twin model also provides a data basis for the graded recycling of waste scraps. By simulating different recycling schemes, the best waste treatment strategy can be selected.

[0062] Step S1200, collecting visual appearance images and near-infrared spectrum data of waste scraps in the sorting area of ​​the non-woven breathable film intelligent manufacturing production line in real time, extracting appearance feature data of the waste scraps according to the visual appearance images, analyzing the near-infrared spectrum data to obtain material attribute data of the waste scraps; fusing the appearance feature data and the material attribute data to obtain a second data set;

[0063] Specifically, at the end of the cutting, punching, welding and other processes of the breathable film production line, a waste scrap collection device, such as a vibrating conveyor, a pneumatic conveying pipeline, etc., is set up to collect and transport the waste scraps to the sorting area. A high-resolution industrial camera and light source are installed in the sorting area to build a machine vision system to collect the visual appearance images of the waste scraps. Using image processing algorithms, the visual appearance images of the waste scraps are extracted and analyzed for appearance features, such as edge detection, shape recognition, color classification, etc., to obtain the appearance feature data such as the size, shape and color of the waste scraps. A near-infrared spectrometer is installed in the sorting area to collect near-infrared spectral data and perform non-destructive testing on the material composition of the waste scraps. The spectral data includes the absorption and reflection characteristics of the waste scraps for light of different wavelengths within the near-infrared spectrum. These spectral data can reflect the molecular structure and composition of the material. Using spectral analysis technology, the material attribute data of the waste scraps, such as polyethylene, polypropylene, nylon and other material categories, are identified according to the absorption and reflection characteristics of different materials for near-infrared light.

[0064] The scrap collection device is the hardware foundation for realizing waste classification and recycling. Devices such as vibrating conveyors and pneumatic conveying pipelines can efficiently and automatically collect and transport scraps, reducing manual operations and pollution. The machine vision system uses industrial cameras and image processing algorithms to intelligently identify the appearance characteristics of scraps and replaces human eyes for classification. The near-infrared spectrometer uses the spectral characteristics of materials to quickly and accurately detect the material composition of scraps and provide material data support for the subsequent formulation of recycling plans. The second data set combines the results of machine vision and spectral detection, characterizes the properties of scraps from multiple dimensions, and is a scientific and complete set of waste physical property data sets. Based on the second data set, scraps can be intelligently classified and targeted recycling plans can be formulated, which not only improves resource utilization efficiency but also reduces waste disposal costs. At the same time, by optimizing production process parameters and improving product design, the generation of scraps can be reduced from the source, realizing closed-loop optimization of the production process.

[0065] Step S1300, according to the preset classification judgment standard, the waste scraps are divided into three grades, namely, grade A, grade B and grade C, and a classification judgment standard database is established; a waste scrap classification decision model is constructed based on the classification judgment standard database; based on the second data set including the appearance feature data and material attribute data of the waste scraps collected in real time and the waste scrap classification decision model, the classification grade corresponding to the waste scraps is obtained;

[0066] Furthermore, if Figure 2 As shown, step S1300 includes:

[0067] Step S1310, establishing a scrap material classification judgment standard database for storing the correspondence between the key attribute parameters of scrap materials and the classification levels; the key attribute parameters of scrap materials are scrap material attribute parameters used to determine the classification of scrap materials; for each key attribute parameter, a value interval or level is divided, and a classification judgment threshold is set; the classification level is determined by the value interval or level of the key attribute parameter and the classification judgment threshold;

[0068] Specifically, the scrap attribute parameters include the material type, size, shape and other attribute data of the scrap. Based on industry standards and expert experience, through the analysis of a large amount of historical production data and quality inspection reports, the scrap attribute parameters that have a significant impact on the recycling of scrap, such as material type, size range, shape characteristics, color grade, etc., are screened out and marked as the key attribute parameters of scrap. These key attribute parameters constitute the basic dimensions for the classification and determination of scrap. For each key attribute parameter, a reasonable value range or level is divided, and a classification determination threshold is set. The material type can be divided into polyethylene, polypropylene, nylon, etc.; the size range can be divided into large (>1000cm²), medium (100-1000cm²), and small (<100cm²) according to the area size; the shape characteristics can be divided into regular shapes (rectangles, circles, etc.) and irregular shapes (complex curved edges); the color grade can be divided into white, transparent, and other colors. By reasonably dividing the value range or level, the attributes of scrap can be described in a standardized manner.

[0069] Taking into account the product quality requirements and production process parameters, the corresponding grading level is determined for each combination of waste attributes based on the value range or level of the key attribute parameters. For example, polyethylene scraps with large size, regular shape, white or transparent color can be classified as Class A, which means they can be directly reused; while nylon scraps with small size, irregular shape, and other colors are classified as Class B, which means they need to be reprocessed; and waste with degraded materials or serious pollution are classified as Class C, which means they cannot be recycled. The determination of grading levels requires a balance between product quality and recycling benefits. For products with higher quality requirements, the standards for Class A scraps will be more stringent. A grading determination standard database is established to store the correspondence between the key attribute parameters of waste scraps and grading levels. The database adopts a flexible data structure and supports dynamic expansion of attribute dimensions and grading rules. The grading determination knowledge is organized and managed in a structured manner to provide data support for subsequent intelligent decision-making.

[0070] The formulation of grading standards also requires a balance between short-term and long-term benefits. Increasing the recycling ratio of waste materials can bring direct cost savings, but if the recycling rate is blindly pursued while ignoring product quality, it may damage the company's brand image and market competitiveness. Therefore, the grading standards need to dynamically balance multiple goals such as production costs, product quality, and resource utilization benefits, and adjust the grading thresholds in a timely manner. The grading determination standard database digitally and structuredly represents the grading determination knowledge, realizes the rapid retrieval, sharing, and updating of the grading standards, and provides a powerful knowledge engine for intelligent grading decisions. At the same time, the establishment of the grading determination standard database also marks the transformation of waste scrap management from experience-driven to data-driven, and from passive disposal to active utilization, which is of great significance to improving the resource utilization efficiency and sustainable development capabilities of breathable membrane production lines.

[0071] Step S1320, constructing a waste scrap grading decision model, and training the waste scrap grading decision model based on historical data in the grading judgment standard database;

[0072] Step S1330, deploying the trained waste scrap grading decision model to the edge computing node of the production line, the edge computing node receiving the second data set acquired in real time, inputting the second data set into the waste scrap grading decision model, and outputting the grading level corresponding to the waste scrap;

[0073] Specifically, the development of the scrap grading decision model needs to comprehensively consider factors such as the performance, efficiency and interpretability of the model. In terms of algorithm selection, it is necessary to select a suitable machine learning algorithm based on the scale, feature dimension and data distribution characteristics of the grading judgment standard database. For example, when the grading rules are relatively simple and the feature dimension is low, the decision tree algorithm may be more suitable; when the grading rules are complex and the feature dimension is high, the support vector machine or neural network algorithm may be more advantageous. Train the scrap grading decision model based on the historical data in the grading judgment standard database. By learning the scrap attribute data with labeled grading levels, establish the mapping relationship between the key attribute parameters of the scrap and the grading level. In the model training stage, the original scrap attribute data needs to be preprocessed, including data cleaning, feature normalization, data enhancement and other operations to improve data quality and sample diversity.

[0074] For different machine learning algorithms, optimize the model's hyperparameters to improve the accuracy and generalization of grading decisions. Use methods such as cross-validation to evaluate the model's performance under different parameter settings and select the optimal model parameter combination. Through hyperparameter optimization, the grading decision model can better adapt to the complexity and variability of the actual production environment. Deploy the trained scrap grading decision model to the edge computing node of the production line to achieve real-time scrap grading decisions. Edge computing nodes refer to computing resources and service nodes close to data sources or terminal devices in the computing architecture. Compared with the traditional cloud computing model, edge computing sinks data processing, analysis, and storage functions from centralized data centers to the edge of the network, that is, close to where the data is generated. The purpose of this is to reduce data transmission delays and bandwidth consumption, and improve response speed and processing efficiency.

[0075] The edge computing node receives the second data set from the visual sensor and spectrometer, extracts the waste attribute features, inputs them into the grading decision model, and quickly outputs the corresponding grading level. By sinking the intelligent decision-making capabilities to the production site, the real-time and accuracy of waste grading can be significantly improved. An online learning mechanism for the grading decision model is established, and the model is incrementally trained and optimized by continuously collecting waste attribute data in the production process and manually verified grading results. The online learning mechanism can enable the grading decision model to continuously adapt to changes and optimizations in the production process, and improve the robustness and interpretability of the model.

[0076] Deploying the scrap grading decision model to the edge computing node can make full use of the Internet of Things technology and edge computing capabilities to achieve real-time and accurate waste grading. By processing data and making decisions at the production site, the bandwidth pressure and latency of data transmission can be reduced, and the response speed of the system can be improved. At the same time, the distributed decision model can also achieve continuous optimization of model performance under the premise of protecting data privacy through technologies such as collaborative learning and federated learning. The online learning mechanism is an important means to maintain the effectiveness of the grading decision model. By continuously collecting real-time data in the production process, especially the grading results of manual verification, and incrementally training and optimizing the model, the model can continuously adapt to changes and optimizations in the production process. Online learning can also improve learning efficiency by collecting sample data that is most helpful to improving model performance through active learning strategies.

[0077] Step S2000: for Class A scraps, replace part of the original raw materials with them to obtain Class A scrap recycling data; for Class B waste, physically regenerate them to obtain Class B waste recycling data; for Class C waste, biodegrade them to convert them into valuable energy and fertilizer products;

[0078] Differentiated recycling plans for different grades of waste and scraps can maximize resource utilization efficiency. Grade A scraps are directly reused in production to replace some virgin raw materials, which can reduce raw material costs; Grade B waste can be used as a supplement to raw materials through physical regeneration processes such as low-temperature thermoplastic plasticization and melt spinning to improve material recovery rate; Grade C waste adopts biological treatment methods such as microbial degradation to achieve waste reduction and harmlessness, and the energy generated can be reused in production to improve energy utilization efficiency.

[0079] Furthermore, step S2000 includes:

[0080] Step S2100, replacing part of the original raw materials with Class A scraps, controlling the proportion of Class A scraps added; performing quality inspection on the raw material mixture after adding Class A scraps, establishing a quantitative relationship model between the quality and the proportion of Class A scraps added, maximizing the recycling rate of Class A scraps while ensuring the quality of the raw material mixture, and obtaining Class A scraps recycling data;

[0081] Specifically, Grade A scraps refer to high-quality waste materials whose key attributes such as material, size, and shape meet the requirements of raw materials and can directly replace part of the original raw materials for reuse. Putting Grade A scraps into the raw material warehouse and accurately controlling their blending ratio through the metering system can reduce the cost of raw materials while ensuring the accuracy of the raw material ratio. In order to evaluate the impact of Grade A scraps on product quality, it is necessary to conduct quality inspections on the raw material mixture after the addition of Grade A scraps, including indicators such as the physical and chemical properties of the materials. According to the quality inspection results, the blending ratio of Grade A scraps is dynamically adjusted to maximize the reuse rate of Grade A scraps while meeting the product quality requirements.

[0082] The recycling data of Class A scraps include: the material type, size, shape and other key attribute parameters of Class A scraps; the input amount and mixing ratio of Class A scraps; the quality test results of the raw material mixture after mixing with Class A scraps; the recycling rate of Class A scraps and its impact on production costs; online near-infrared spectroscopy analysis data for real-time monitoring of the quality of raw material mixtures, etc. Quality inspection uses online near-infrared spectroscopy analysis technology to monitor the key quality attributes of the raw material mixture in real time, and by establishing a quantitative relationship model between quality attributes and raw material ratios, intelligent optimization control of the mixing ratio of Class A scraps is achieved. Through the efficient recycling of Class A scraps, not only can the cost of raw materials be reduced, but also the environmental load of waste disposal can be reduced, and resource utilization efficiency can be improved.

[0083] The quantitative relationship model between quality and the proportion of grade A scraps included:

[0084]

[0085] in:

[0086] : Raw material mixture quality index;

[0087] : The proportion of A-grade scraps added, , where A is the amount of grade A scrap, is the amount of the main ingredient;

[0088] : The adjustment coefficient is obtained by fitting the experimental data, adjusting the proportion of the overall formula so that the output of the formula better matches the actual observed quality indicators of the raw material mixture:

[0089] : Exponential coefficient, obtained by fitting experimental data, used to determine the power relationship of the influence of the proportion of A-grade scrap on quality;

[0090] : Nonlinear adjustment coefficient, obtained by fitting experimental data, used to determine the nonlinear effect of the incorporation ratio;

[0091] : Gaussian attenuation coefficient, which is used to determine the degree of influence on quality when the incorporation ratio deviates from the ideal value through fitting of experimental data;

[0092] : Ideal A-grade scrap incorporation ratio, determined through experimental data, represents the best A-grade scrap incorporation ratio.

[0093] when near When the quality Q reaches the maximum value, the deviation The larger the amplitude, the faster the quality Q decreases, especially the influence of Gaussian attenuation. Nonlinear term This makes the quality Q more sensitive and complex to the change of the mixing ratio. This formula can describe the complex nonlinear relationship between the quality and the mixing ratio of grade A scraps; by adjusting the mixing ratio of grade A scraps, the production process can be optimized and the product quality can be improved; the specific impact of different mixing ratios on the quality can be quantified to help decision-making; the parameters in the formula can be fitted and adjusted through experimental data to adapt to different production conditions and requirements.

[0094] Step S2200, putting Class B waste into a physical regeneration system, and converting Class B waste into plasticized material through a low-temperature thermoplastic plasticization process; performing quality inspection on the plasticized material, and establishing a mathematical model between the quality of the plasticized material and the amount of Class B waste input, and maximizing the recovery rate of Class B waste while ensuring the quality of the plasticized material, and obtaining Class B waste recovery data;

[0095] Specifically, Class B waste refers to waste that meets the material requirements but cannot be directly reused due to its size, shape and other properties. Physical regeneration of Class B waste can maximize the retention of material performance and achieve high-value utilization of waste. First, Class B waste is put into the physical regeneration system, and a low-temperature thermoplastic plasticization process is used to convert the waste into plasticized material at a lower temperature through the action of shear force and heat. Low-temperature thermoplastic plasticization can reduce the thermal degradation of the material and retain the molecular structure and properties of the material. Then, the plasticized material is melt-spun to prepare regenerated fibers. Regenerated fibers can be used as a supplement to raw materials for the production of breathable films and other products. The input amount of Class B waste directly affects the output and quality of plasticized materials, which in turn affects the quality of regenerated fibers and the overall benefits of waste recycling. Class B waste recycling data includes: material type, size, shape and other attribute parameters of Class B waste; input amount and recycling ratio of Class B waste; low-temperature thermoplastic plasticization process parameters, such as temperature, pressure, time, etc.; plasticized material quality test results; Class B waste recycling rate, etc. By establishing a mathematical model, we can quantitatively analyze the influence of the input of Class B waste on the quality of plasticized materials, optimize the input strategy of waste materials, improve the quality of recycled fibers and the economic and technical feasibility of waste recycling. The physical recycling of Class B waste extends the service life of the material and reduces the environmental impact caused by landfill or incineration of waste.

[0096] The mathematical model between the quality of plasticized material and the input of Class B waste includes:

[0097]

[0098] in:

[0099] : Plastic material quality coefficient, reflecting the comprehensive quality level of plastic materials, with a value range of [0,1]. The higher the value, the better the quality.

[0100] : Input amount of Class B waste;

[0101] : The optimal input amount of Class B waste, that is, the input amount to achieve the best plasticized material quality;

[0102] : The maximum potential coefficient for improving the quality of plasticized materials, with a value range of [0,1], reflecting the maximum potential of the plasticizing process for improving the quality of plasticized materials;

[0103] : The influence intensity coefficient of waste input, with a value range of (0, +∞), reflects the rate of influence of waste input on the quality of plasticized materials;

[0104] : Nonlinear influence index of waste input, with a value range of (0,1), reflecting the nonlinear influence of waste input on the quality of plasticized materials;

[0105] : The mass loss coefficient deviating from the optimal input amount, with a value range of [0,1], reflecting the rate of decrease of plasticized material quality when deviating from the optimal input amount;

[0106] , , , It is obtained by technicians in this field through a lot of experiments. Through experimental optimization or simulation analysis, the input amount of Class B waste to achieve the best plasticized material quality is determined. It shows the effect of the input of Class B waste on the quality of plasticized materials. As the input increases, the quality improvement rate is fast at first and then slows down, showing a nonlinear saturation trend. It indicates the quality loss effect when the input amount deviates from the optimal value. When the input amount deviates from the optimal value, the quality of the plasticized material will decline, and the greater the deviation, the more serious the quality loss.

[0107] when With the increase of the input of Class B waste, the quality of plasticized material showed a trend of first fast and then slow improvement, and the improvement rate was and Decide.

[0108] when As the amount of Class B waste continues to increase, the quality of plasticized materials will decrease, and the rate of decrease will be decision, indicating that excessive input of waste material will lead to quality loss.

[0109] when When , the quality of plasticized material reaches the best, indicating that reasonable control of waste input can give full play to the quality improvement potential of plasticizing process.

[0110] Plasticized material quality factor The calculation formula combines the improvement effect of waste input and the loss effect of deviation from the optimal value; quantitatively analyzes the influence of waste input on plasticized material quality, and provides a decision-making basis for optimizing waste input strategy; determines the optimal waste input to maximize the recycling rate of waste while ensuring the quality of plasticized material; predicts the quality level of plasticized material under different waste input amounts, evaluates the quality of recycled fiber and the economic and technical feasibility of waste recycling; guides the optimization of physical regeneration process parameters, and improves the stability of plasticized material quality and recycled fiber quality.

[0111] Class C waste refers to waste that is not suitable for material recycling due to material degradation or serious pollution. Class C waste can be converted into valuable energy and fertilizer products by using microbial degradation methods to realize the resource utilization of waste. First, Class C waste is sent to an anaerobic fermentation tank. Under anaerobic conditions, the organic matter in the waste is used as a carbon source and energy source for the microbial flora to promote its growth and metabolism, and the waste is degraded into small molecules. The biogas produced during the anaerobic fermentation process is mainly composed of methane, which is a clean and efficient renewable energy. By purifying biogas, it can be used for energy supply of production lines and reduce the consumption of fossil energy. The fermentation residue is rich in organic matter and nutrients and can be used as a fertilizer raw material. Through aerobic composting treatment, the residue is promoted to be decomposed and harmless, and finally a high-quality organic fertilizer product is made. The biodegradation and utilization of Class C waste not only reduces the environmental impact of the waste, but also produces valuable by-products such as energy and fertilizer, realizing the recycling of waste. The biodegradation process adopts intelligent monitoring technology. Through sensors, key parameters such as temperature, pH value, redox potential, etc. in the anaerobic fermentation tank are collected in real time. Combined with the online detection data of metabolites, a waste degradation kinetic model is established to optimize the growth environment of microbial flora and improve waste degradation efficiency and biogas yield.

[0112] Step S3000: Based on the digital twin model of the breathable membrane production process, the A-level scrap recycling data and the B-level waste recycling data are integrated to construct a multi-objective optimization model of the breathable membrane production line based on a neural network, so as to realize the intelligent optimization control of the breathable membrane production line.

[0113] Furthermore, if Figure 3 As shown, step S3000 includes:

[0114] Step S3100, using the digital twin model to generate simulation data of the breathable membrane production process, and integrating it with the actual production data to construct a training sample set for multi-objective optimization;

[0115] Specifically, the digital twin model constructed in step S1000 can simulate the production process under different combinations of process parameters and predict key indicators such as product quality, energy consumption, and cost. Using the digital twin model, a large amount of simulation data is generated to cover a wider range of process parameter spaces. At the same time, the simulation data is integrated with the actual production data, and the A-level scrap recycling data and the B-level waste recycling data are comprehensively considered to construct a training sample set for the multi-objective optimization problem. The training sample set includes input features (such as process parameters, waste recovery rate, etc.) and output targets (such as product quality, production efficiency, cost, energy consumption, etc.).

[0116] The digital twin model provides a low-cost and efficient way to generate data. Through simulation, more combinations of process parameters can be explored in the virtual space to reveal the inherent laws of the production process. The fusion of simulation data and actual production data can make up for the limitations of actual data and improve the diversity and representativeness of samples. Taking into account the A-level scrap recycling data and the B-level waste recycling data, it is possible to establish a connection between waste recycling and production process optimization, and achieve the coordinated optimization of resource utilization efficiency and product quality and production efficiency. A high-quality training sample set is the basis of the multi-objective optimization model, laying a data foundation for subsequent modeling and optimization.

[0117] Step S3200, constructing a multi-objective optimization model for a breathable membrane production line based on a neural network;

[0118] Further, step S3200 includes:

[0119] Step S3210, construct a neural network structure, determine the input layer, hidden layer and output layer of the neural network, and design the hyperparameters of the network.

[0120] Specifically, the process flow and data characteristics of the breathable membrane production line are analyzed, and a neural network structure suitable for modeling is selected. Feedforward neural networks are suitable for modeling complex nonlinear relationships between input and output, and can be used to predict continuous variables such as product quality and energy consumption. Convolutional neural networks are good at extracting local features and can be used to analyze image data in the production process, such as defect detection. According to the characteristics of the problem and the type of data, the neural network structure is flexibly selected to build the basic framework of the multi-objective optimization model. The key process parameters and waste recovery rate of the breathable membrane production line are used as the input of the neural network, and indicators such as product quality, production efficiency, cost, and energy consumption are used as outputs. Reasonably set the number of hidden layers and the number of neurons in each layer, and select suitable activation functions, such as ReLU, Sigmoid, etc. By adjusting the hyperparameters, the structure and expression ability of the neural network are optimized, and the fitting accuracy and generalization ability of the multi-objective optimization model are improved.

[0121] Step S3220, based on the neural network, taking product quality and production efficiency as constraints, and minimizing cost and energy consumption, maximizing the recycling rate of Class A scraps, and maximizing the recycling rate of Class B waste as optimization goals, constructing a multi-objective optimization model for the breathable membrane production line;

[0122] Specifically, with product quality and production efficiency as constraints, and minimizing cost and energy consumption and maximizing waste recovery rate as optimization goals, the mathematical form of the multi-objective optimization model is constructed. The neural network is used to predict the objective function value under different process parameter combinations, and the neural network is embedded in the optimization model to realize the nonlinear modeling of the objective function. At the same time, factors such as resource limitations and safety margins in actual production are used as constraints to ensure the feasibility and operability of the optimization results. Neural networks are the core of building a multi-objective optimization model for breathable membrane production lines. Through the reasonable design of neural network structure and hyperparameters, the complex nonlinear relationship in the production process can be accurately modeled, revealing the intrinsic connection between process parameters and goals such as quality, efficiency, cost, and energy consumption. Incorporating waste recovery indicators into the optimization goals can achieve a balance between resource utilization efficiency and production performance, and promote the green and sustainable development of breathable membrane production. The construction of a multi-objective optimization model provides quantitative tools and methods for intelligent decision-making and dynamic optimization of breathable membrane production lines, and helps to continuously improve and upgrade the production process.

[0123] The optimization goal is:

[0124]

[0125] The constraints are: ;

[0126] in:

[0127] : represents the optimization objective function;

[0128] : represents the cost of raw materials, obtained through purchase records and market prices;

[0129] : represents labor cost, obtained through workers' wages and working hours records;

[0130] : represents the equipment maintenance and depreciation costs, which are obtained through equipment maintenance records and depreciation policies;

[0131] : represents production cost;

[0132] : weight coefficient of production cost;

[0133] : Indicates the energy consumption of production equipment, obtained through the equipment energy consumption monitoring system;

[0134] : Energy consumption of environmental control system, obtained through energy consumption monitoring of environmental control system;

[0135] : total energy consumption;

[0136] : Weight coefficient of total energy consumption;

[0137] : The mass of recycled A-grade scraps, in kilograms;

[0138] : The total mass of grade A scraps, in kilograms;

[0139] : A-grade scrap recycling rate;

[0140] : Weight coefficient of the recycling rate of grade A scraps;

[0141] : The quality of recycled Class B waste;

[0142] : Total mass of Class B waste;

[0143] : B-grade waste recycling rate;

[0144] : Weight coefficient of B-grade waste recycling rate;

[0145] : Indicates product quality;

[0146] : Indicates the minimum product quality requirements;

[0147] : Indicates production efficiency;

[0148] : Indicates the minimum production efficiency requirement;

[0149] When the cost of raw materials, labor costs, or equipment maintenance and depreciation costs increase, the production cost increases, and the objective function F increases; when the energy consumption of production equipment or the energy consumption of environmental control systems increases, the total energy consumption increases, and the objective function F increases; when the mass of recycled scraps increases or the total mass of scraps decreases, the objective function F decreases. By minimizing production costs, the objective function F can help companies reduce expenses and improve economic benefits; by minimizing energy consumption E, companies can reduce energy consumption and improve environmental benefits; by maximizing the waste recycling rate, companies can improve resource utilization and reduce environmental pollution. By comprehensively considering costs, energy consumption, and waste recycling rates, the model can balance multiple objectives and achieve a win-win situation for corporate benefits and sustainable development.

[0150] In the breathable membrane intelligent manufacturing production line, the product refers to the non-woven breathable membrane that is finally produced. Product quality is a comprehensive indicator, which usually includes physical properties such as air permeability, tensile strength, tear strength, chemical properties such as material purity and chemical stability, and appearance quality such as surface flatness, color uniformity, and no obvious defects. Product quality in constraints You can select specific quality indicators based on actual production needs, or evaluate by combining multiple indicators.

[0151] Step S3300, training a multi-objective optimization model for a breathable membrane production line based on a training sample set;

[0152] The back propagation algorithm and gradient descent method are used to continuously adjust the weights and biases of the neural network, minimize the prediction error, and improve the fitting accuracy of the model. During the training process, regularization techniques such as cross-validation and early stopping are used to prevent overfitting and improve the generalization ability of the model. Through training, the neural network model can learn the inherent laws of the production process, achieve accurate prediction of product quality, production efficiency, cost, energy consumption and other targets, and provide reliable decision support for multi-objective optimization. Through training, the neural network can automatically extract features from a large amount of sample data and learn the complex mapping relationship of the production process. Back propagation and gradient descent algorithms are the core technologies for training neural networks. Through continuous iteration and optimization, the prediction results of the model are as close as possible to the actual value. Cross-validation and regularization techniques can effectively prevent the model from overfitting the training data and improve the applicability and robustness of the model in actual production. The trained neural network model can quickly and accurately predict and simulate the production process, provide a reliable decision-making basis for multi-objective optimization, and guide the intelligent regulation of the breathable membrane production line.

[0153] Step S3400, solving the multi-objective optimization model of the breathable membrane production line, obtaining the optimal static process parameter combination, and generating a feasible solution set;

[0154] Specifically, a suitable multi-objective optimization algorithm, such as genetic algorithm, particle swarm algorithm, etc., is selected to solve the multi-objective optimization model. In the iterative process of the optimization algorithm, the neural network model is used to predict the objective function values ​​under different process parameter combinations, such as product quality, production efficiency, cost, energy consumption, etc. The prediction results of the neural network are used as the fitness value or constraint violation of the optimization algorithm to guide the optimization algorithm to search for the optimal solution. Through the close coupling of the neural network model and the optimization algorithm, the optimal static process parameter combination can be efficiently searched in the complex parameter space to achieve multi-objective optimization of the production process. The population or particles of the optimization algorithm are initialized, and the hyperparameters of the algorithm are set, such as population size, number of iterations, crossover probability, mutation probability, etc. In each iteration, the population or particles are updated through operations such as selection, crossover, and mutation, the objective function value and constraint conditions of the new solution are evaluated, and the Pareto optimal solution set is updated. Repeat the iteration until the stop condition is reached, and the final feasible solution set, that is, the optimal process parameter combination, is output.

[0155] The combination of multi-objective optimization algorithm and neural network model realizes the efficient solution of breathable membrane production line optimization problem. The neural network model can accurately evaluate the objective function value of different process parameter combinations and provide reliable fitness evaluation for the optimization algorithm. The optimization algorithm can intelligently search in complex parameter space and quickly locate the optimal solution, overcoming the limitations of traditional optimization methods. Through the iterative search of the optimization algorithm, a series of Pareto optimal solutions can be obtained, that is, the optimal static process parameter combination that weighs multiple objectives, providing a variety of choices for production decisions. The solution of the multi-objective optimization model provides an effective method for the intelligent optimization control of the breathable membrane production line, helping to reduce costs, increase efficiency and achieve green development in the production process.

[0156] Step S3500, based on the feasible solution set and digital twin model obtained by solving, the optimal dynamic process parameter combination is obtained through simulation experiments and production verification as the production control target.

[0157] Specifically, based on the feasible solution set obtained by the multi-objective optimization algorithm, simulation experiments are carried out in the digital twin model to evaluate the impact of different process parameter combinations on key performance indicators such as production efficiency, product quality, and energy consumption cost. Through simulation experiments, one or more groups of process parameter combinations with the best performance are selected as candidate control schemes. In order to further verify the feasibility and effectiveness of the candidate control schemes, small-batch trial production is carried out on the actual production line, and different process parameter combinations are compared and tested, and production data and quality inspection results are collected. By analyzing the trial production data, the actual effect of the candidate control scheme is evaluated, and combined with expert experience and on-site operation constraints, the optimal dynamic process parameter combination is finally determined as the real-time production control target. In the production process, advanced control algorithms and actuators are used to adjust the process parameters of the equipment in real time to achieve the optimal value, ensuring that the production runs under the best conditions. At the same time, by continuously monitoring production data and product quality data, the effect of dynamic parameter optimization is evaluated, and parameter correction and control strategy update are carried out when necessary to achieve continuous optimization and adaptive control of the production process. Dynamic process parameter optimization control can automatically adjust the key process parameters of the production line according to changes in factors such as raw material properties, process requirements, and equipment status, so that the production process is always in the optimal state. Through simulation optimization and production verification supported by digital twin models, we can maximize production potential and improve production efficiency and resource utilization while ensuring product quality and production safety.

[0158] By optimizing process parameters in real time, the production process can be made more stable and controllable, product quality fluctuations can be reduced, and the consistency and reliability of product quality can be improved. Dynamic adjustment of process parameters can keep the equipment running in the best working conditions, shorten the product production cycle, and increase the output per unit time, thereby improving overall production efficiency and equipment utilization. Optimizing process parameters can reduce unnecessary energy loss and reduce the energy consumption level per unit product. At the same time, by reducing unplanned production losses such as rework and downtime, production costs can be significantly reduced. Flexible production control strategies can quickly adapt to changes in factors such as raw material fluctuations and product specification adjustments, flexibly adjust production plans and process parameters, and achieve rapid response to market demand. Dynamic process parameter optimization and control is an important means to realize smart factories. Through data-driven simulation optimization, adaptive control and other technologies, the lean level of the production process can be significantly improved, enabling the intelligent transformation and sustainable development of enterprises.

[0159] Example 2

[0160] This embodiment provides a control system for a non-woven breathable membrane intelligent manufacturing production line based on embodiment 1, such as Figure 4 As shown, including:

[0161] Data acquisition module: used to collect material attribute data of the breathable film production line to form a first data set; real-time collection of visual appearance images and near-infrared spectral data of waste scraps in the sorting area of ​​the non-woven breathable film intelligent manufacturing production line to obtain a second data set;

[0162] A digital twin model building module: used for building a digital twin model of the breathable membrane production process according to the first data set;

[0163] The scrap material classification module is used to classify the scrap materials into three grades according to the preset classification judgment standard, including grade A scrap materials, grade B scrap materials and grade C scrap materials; establish a classification judgment standard database, and build a scrap material classification decision model based on the classification judgment standard database; obtain the classification grade corresponding to the scrap materials based on the second data set collected in real time and the scrap material classification decision model;

[0164] Waste scrap recycling module: used to replace part of the original raw materials with Class A scraps to obtain Class A scrap recycling data; to physically regenerate Class B waste to obtain Class B waste recycling data; to biodegrade Class C waste to convert it into valuable energy and fertilizer products;

[0165] Production control target solving module: It is used to build a multi-objective optimization model of the breathable membrane production line based on the digital twin model of the breathable membrane production process, integrate the A-level scrap recycling data and the B-level waste recycling data, and obtain the production control target by solving the multi-objective optimization model of the breathable membrane production line.

[0166] Example 3

[0167] This embodiment discloses an electronic device, including a memory, a central processing unit, and a computer program stored in the memory and executable on the central processing unit. When the central processing unit executes the computer program, the above-mentioned non-woven breathable membrane intelligent manufacturing production line control method is implemented.

[0168] Since the electronic device introduced in this embodiment is an electronic device used to implement a non-woven breathable film intelligent manufacturing production line control method in the embodiment of this application, based on the non-woven breathable film intelligent manufacturing production line control method introduced in the embodiment of this application, the technical personnel of this field can understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of this application is not described in detail here. As long as the technical personnel of this field implement the electronic device used in the non-woven breathable film intelligent manufacturing production line control method in the embodiment of this application, it belongs to the scope of protection of this application.

[0169] Example 4

[0170] The present embodiment discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed, the above-mentioned non-woven breathable film intelligent manufacturing production line control method is implemented.

[0171] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters, weights and thresholds in the formula are set by technicians in this field according to actual conditions.

[0172] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired network or a wireless network. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD) or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0173] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0174] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0175] In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic, for example, the division of the units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0176] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0177] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0178] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

[0179] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A control method for a non-woven breathable film intelligent manufacturing production line, characterized in that: include: Collecting material attribute data of the breathable membrane production line to form a first data set, and constructing a digital twin model of the breathable membrane production process according to the first data set; Real-time collection of visual appearance images and near-infrared spectral data of waste scraps in the sorting area of ​​the non-woven breathable film intelligent manufacturing production line to obtain a second data set; According to the preset classification judgment standard, the waste scraps are divided into three grades, including grade A scraps, grade B scraps and grade C scraps; a classification judgment standard database is established, and a waste scrap classification decision model is constructed based on the classification judgment standard database; based on the second data set collected in real time and the waste scrap classification decision model, the classification grade corresponding to the waste scraps is obtained; Replace part of the original raw materials with grade A scraps to obtain grade A scrap recycling data; perform physical regeneration on grade B waste to obtain grade B waste recycling data; Biodegradation of Class C waste, converting it into valuable energy and fertilizer products; The obtaining of the A-grade scrap recycling data comprises: replacing part of the original raw materials with the A-grade scraps to control the proportion of the A-grade scraps added; performing a quality test on the raw material mixture after adding the A-grade scraps, establishing a quantitative relationship model between the quality and the proportion of the A-grade scraps added, maximizing the reuse rate of the A-grade scraps while ensuring the quality of the raw material mixture, and obtaining the A-grade scrap recycling data; The obtaining of Class B waste recycling data includes: inputting Class B waste into a physical regeneration system to convert Class B waste into plasticized material; performing quality inspection on the plasticized material, establishing a mathematical model between the quality of the plasticized material and the amount of Class B waste input, maximizing the recovery rate of Class B waste while ensuring the quality of the plasticized material, and obtaining Class B waste recycling data; The quantitative relationship model between the quality and the proportion of A-grade scraps mixed in includes: ； in, It is the quality index of the raw material mixture; is the proportion of A-grade scraps added, , where A is the amount of grade A scrap, is the amount of the main ingredient; is the adjustment factor: is the exponential coefficient; is the nonlinear adjustment coefficient; is the Gaussian attenuation coefficient; The ideal A-grade scrap mixing ratio; The mathematical model between the plasticized material quality and the input amount of Class B waste includes: ； in, is the plasticized material quality coefficient, is the input amount of Class B waste, is the optimal input amount of Class B waste, is the maximum potential coefficient for improving the quality of plasticized materials, is the impact intensity coefficient of waste input, is the nonlinear impact index of waste input, is the mass loss coefficient that deviates from the optimal input amount; Based on the digital twin model of the breathable membrane production process, the A-level scrap recycling data and the B-level waste recycling data are integrated to construct a multi-objective optimization model of the breathable membrane production line. The production control target is obtained by solving the multi-objective optimization model of the breathable membrane production line.

2. A non-woven breathable membrane intelligent manufacturing production line control method according to claim 1, characterized in that: The method comprises: The appearance feature data of the waste scraps are extracted according to the visual appearance image, and the material attribute data of the waste scraps are obtained by analyzing the near infrared spectrum data; the appearance feature data and the material attribute data are fused to obtain a second data set.

3. A non-woven breathable membrane intelligent manufacturing production line control method according to claim 1, characterized in that: The method comprises: The classification judgment standard database is used to store the corresponding relationship between the key attribute parameters of waste and scraps and the classification levels; The key property parameters of the waste scraps are property parameters of the waste scraps used to determine the classification of the waste scraps; For each key attribute parameter, divide the value range or level and set the classification judgment threshold; The classification level is determined by the value range or level of the key attribute parameter and the classification determination threshold.

4. A non-woven breathable membrane intelligent manufacturing production line control method according to claim 1, characterized in that: The method comprises: Use the digital twin model to generate simulation data of the breathable membrane production process and integrate it with the actual production data to construct a training sample set for multi-objective optimization; Taking product quality and production efficiency as constraints, minimizing cost and energy consumption, maximizing the recycling rate of Class A scraps and maximizing the recycling rate of Class B waste as optimization goals, a multi-objective optimization model for the breathable membrane production line was constructed; Based on the training sample set, the multi-objective optimization model of the breathable membrane production line is trained; Solve the multi-objective optimization model of the breathable membrane production line, obtain the optimal static process parameter combination, and generate a feasible solution set; Based on the digital twin model and the feasible solution set obtained, the optimal dynamic process parameter combination is obtained as the production control target through simulation experiments and production verification.

5. A control system for a non-woven breathable film intelligent manufacturing production line, which is used to implement a control method for a non-woven breathable film intelligent manufacturing production line according to any one of claims 1 to 4, characterized in that: The system comprises: Data acquisition module: used to collect material attribute data of the breathable film production line to form a first data set; real-time collection of visual appearance images and near-infrared spectral data of waste scraps in the sorting area of ​​the non-woven breathable film intelligent manufacturing production line to obtain a second data set; A digital twin model building module: used for building a digital twin model of the breathable membrane production process according to the first data set; The scrap material classification module is used to classify the scrap materials into three grades according to the preset classification judgment standard, including grade A scrap materials, grade B scrap materials and grade C scrap materials; establish a classification judgment standard database, and build a scrap material classification decision model based on the classification judgment standard database; obtain the classification grade corresponding to the scrap materials based on the second data set collected in real time and the scrap material classification decision model; Waste scrap recycling module: used to replace part of the original raw materials with Class A scraps to obtain Class A scrap recycling data; to physically regenerate Class B waste to obtain Class B waste recycling data; to biodegrade Class C waste to convert it into valuable energy and fertilizer products; Production control target solving module: It is used to build a multi-objective optimization model of the breathable membrane production line based on the digital twin model of the breathable membrane production process, integrate the A-level scrap recycling data and the B-level waste recycling data, and obtain the production control target by solving the multi-objective optimization model of the breathable membrane production line.

6. An electronic device comprising a memory, a central processing unit, and a computer program stored in the memory and executable on the central processing unit, characterized in that: When the central processing unit executes the computer program, a non-woven breathable membrane intelligent manufacturing production line control method described in any one of claims 1-4 is implemented.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed, the method for controlling a non-woven breathable membrane intelligent manufacturing production line according to any one of claims 1 to 4 is implemented.

Images