Home textile product production method and system based on PLC programming automatic control

Abstract

The present invention relates to the field of home textile product production control technology, and in particular to a home textile product production method and system based on PLC programming automatic control. The method comprises the following steps: performing target home textile product raw material scanning data acquisition according to a monitoring scanning device to obtain target home textile product raw material scanning data; performing real-time collection and processing of home textile product production data according to a sensor integrated device to generate home textile product production data; performing data matching processing on target home textile product raw material scanning data and home textile product production data to generate home textile product raw material-production matching data; establishing an optimized home textile product production quality prediction model according to a preset support vector machine algorithm and home textile product raw material-production matching data; designing PLC production control logic according to the optimized home textile product production quality prediction model. The present invention realizes the automated control production of home textile products and improves the production quality of home textile products.

Description

Technical Field

[0001] The present invention relates to the technical field of home textile product production control, and in particular to a home textile product production method and system based on PLC programming automatic control. Background Art

[0002] PLC, the full name of Programmable Logic Controller, is an electronic device designed for digital computing operations in industrial environments. It uses a programmable memory to store instructions such as logical operations, sequential control, timing, counting and arithmetic operations, and can control various types of mechanical equipment or production processes through digital or analog input / output interfaces. By connecting PLC to home textile production equipment, automatic control of each process on the production line is achieved, including raw material processing, weaving, dyeing, shaping, cutting and packaging. PLC executes instructions according to preset programs, and dynamically adjusts equipment parameters by collecting real-time data from sensors to ensure efficient and stable operation of the production process. However, the traditional home textile production method requires manual observation of home textile raw materials for screening, which makes the screening effect of home textile raw materials poor and consumes human resources, and requires manual control of the control parameters of the production equipment during the production of home textile products, which makes the production cost too high and cannot guarantee the product quality of home textile products and the response speed of the production process. Summary of the invention

[0003] Based on this, the present invention provides a method and system for producing home textile products based on PLC programming and automatic control to solve at least one of the above technical problems.

[0004] To achieve the above object, a method for producing home textile products based on PLC programming and automatic control comprises the following steps:

[0005] Step S1: Scanning the home textile product raw material according to the monitoring scanning device to generate home textile product raw material scanning data; collecting target home textile product raw material scanning data on the home textile product raw material scanning data to obtain the target home textile product raw material scanning data;

[0006] Step S2: collecting and processing the home textile product production data in real time according to the sensor integrated device to generate the home textile product production data, wherein the home textile product production data includes the production equipment status data and the home textile product status data;

[0007] Step S3: performing data matching processing on the target home textile product raw material scanning data and the home textile product production data to generate home textile product raw material-production matching data;

[0008] Step S4: Establish an optimization prediction model for the production quality of home textile products based on the preset support vector machine algorithm and the home textile product raw material-production matching data, and generate an optimized home textile product production quality prediction model; design PLC production control logic based on the optimized home textile product production quality prediction model, generate PLC production control logic data, and feed back the PLC production control logic data to the terminal to execute the automatic control production operation of home textile products.

[0009] The present invention scans and processes the raw materials of home textile products through monitoring scanning equipment, thereby realizing rapid and accurate collection of raw material information, ensuring that the quality and specifications of the raw materials used in the production process meet the predetermined standards. Through the accurate collection of raw material data, production defects caused by raw material problems can be effectively avoided, and the quality of the final product can be improved. Accurate raw material data also supports material tracking, supply chain management and cost control in the production process, and provides data support for efficient and sustainable production. Using sensor integrated equipment to collect production data of home textile products in real time, including the status of production equipment and home textile products, can achieve real-time monitoring and control of the production process, which helps to immediately discover any anomalies or deviations in the production process, such as equipment failures or product quality problems, so as to quickly take measures to adjust or correct them. Real-time data collection and analysis can also optimize production scheduling and resource allocation, improve production efficiency and flexibility, reduce waste, and ultimately achieve cost savings and productivity improvements. The target home textile product raw material scanning data and home textile product production data are accurately matched, and the generated home textile product raw material-production matching data can provide more accurate data support for the production process. This matching process ensures the best match between raw material selection and actual production needs, reduces the decline in production efficiency and product quality problems caused by raw material mismatch, and supports more refined production management, such as the optimal utilization of raw materials and fine regulation of the production process, thereby improving resource utilization efficiency and controllability of the production process. Through the preset support vector machine (SVM) algorithm and home textile product raw material-production matching data, the optimized home textile product production quality prediction model established can effectively predict and optimize production quality, which not only significantly improves product quality and production efficiency, but also reduces waste through accurate quality control, and improves the overall production economic benefits. The model is used to design PLC production control logic, and the control logic data is fed back to the production terminal, realizing the automation and intelligent control of the production process. This data-driven control logic makes the production process more flexible and responsive, and can effectively respond to various changes and uncertainties in the production process, ensuring the stability of the production process and the consistency of product quality.

[0010] Preferably, step S1 comprises the following steps:

[0011] Step S11: Scanning the raw materials of home textile products according to the monitoring scanning device to generate scanning data of the raw materials of home textile products;

[0012] Step S12: performing multi-dimensional raw material quality detection processing on the home textile product raw material scanning data to generate multi-dimensional raw material quality detection data;

[0013] Step S13: performing PLC raw material screening logic analysis according to the multi-dimensional raw material quality detection data to generate PLC raw material screening logic data;

[0014] Step S14: Screening the effective raw material quality detection data of the multi-dimensional raw material quality detection data based on the PLC raw material screening logic data to obtain effective raw material quality detection data;

[0015] Step S15: collecting target home textile product raw material scanning data on the home textile product raw material scanning data based on the effective raw material quality detection data to obtain the target home textile product raw material scanning data.

[0016] The present invention performs scanning processing of home textile product raw materials through monitoring scanning equipment, directly generates home textile product raw material scanning data, automatically collects detailed information of raw materials, including type, quality, size, etc., provides first-hand data for subsequent raw material screening and quality inspection, and such automated scanning reduces human errors and improves the efficiency and accuracy of data collection. Multidimensional raw material quality inspection data is subjected to multidimensional raw material quality inspection processing, and the generated multidimensional raw material quality inspection data can fully reflect the quality status of raw materials. By evaluating raw materials from multiple angles and multiple indicators, the comprehensive quality of raw materials can be revealed, including but not limited to various important parameters such as strength, purity, color, etc., to ensure that the screened raw materials meet production requirements in all important dimensions. PLC raw material screening logic analysis is performed according to multidimensional raw material quality inspection data to generate PLC raw material screening logic data, realizes the automation and intelligence of raw material screening, makes the raw material screening process more accurate and efficient, and automatically excludes raw materials that do not meet quality standards through preset screening logic, ensuring that the raw materials used in production meet the requirements, thereby directly improving product quality and production efficiency. Based on the PLC raw material screening logic data, the multi-dimensional raw material quality inspection data is screened for effective raw material quality inspection data to obtain effective raw material quality inspection data, which improves the accuracy and efficiency of raw material quality inspection. This screening mechanism reduces production problems and finished product defects caused by substandard raw material quality. Based on the effective raw material quality inspection data, the home textile product raw material scanning data is collected for target home textile product raw material scanning data, further refining and ensuring the target and effectiveness of the collected raw material data, ensuring that raw material data that meets production requirements will be used in subsequent production processes, optimizing the raw material selection process, thereby improving production efficiency while maximizing product quality.

[0017] Preferably, step S12 comprises the following steps:

[0018] The multi-dimensional raw material quality inspection data is processed by dimensional indicator weighting to generate raw material quality dimensional indicator weight data; the PLC raw material screening logic is designed according to the preset multi-dimensional raw material quality assessment decision and raw material quality dimensional indicator weight data to generate PLC raw material screening logic data.

[0019] The present invention performs dimensional index weighting processing on multi-dimensional raw material quality detection data, and the generated raw material quality dimensional index weight data reasonably reflects the degree of influence of each quality index on the quality of the final product. By specifying different weights for different quality dimensions, it is ensured that the applicability and quality of the raw materials can be more accurately evaluated during the raw material screening process. The PLC raw material screening logic design based on the preset multi-dimensional raw material quality assessment decision and the raw material quality dimensional index weight data realizes the automation and intelligence of the raw material screening process, which not only improves the efficiency and accuracy of the screening, but also makes the raw material selection process more objective and reasonable. By accurately controlling the quality of the raw materials, it can directly affect the smooth progress of the production process and the stability of the product quality, ensuring that the produced home textile products can meet high-standard quality requirements.

[0020] Preferably, step S2 comprises the following steps:

[0021] Step S21: Analyze sensor configuration data according to preset home textile product production monitoring decisions to generate sensor configuration data;

[0022] Step S22: performing configuration adjustment on the sensor integrated device based on the sensor configuration data, and performing real-time monitoring and processing of initial home textile product production data through the sensor integrated device after the configuration adjustment to generate initial home textile product production data, wherein the initial home textile product production data includes initial production device status data and initial home textile product status data;

[0023] Step S23: performing production equipment abnormal pattern recognition processing according to the initial home textile product production data to generate production equipment abnormal pattern data;

[0024] Step S24: Analyzing and processing the production equipment repair parameters according to the production equipment abnormality mode data to generate the production equipment repair parameters;

[0025] Step S25: performing iterative updating processing on the initial home textile product production data based on the production equipment repair parameters to generate home textile product production data.

[0026] The present invention analyzes sensor configuration data according to preset home textile production monitoring decisions, can accurately guide the configuration of sensor integrated equipment, ensure that the sensor layout best matches the production requirements, optimize the configuration of the sensor, and enable it to more accurately monitor the key parameters in the production process, thereby improving the monitoring efficiency and accuracy of the production process. Appropriate sensor configuration is crucial to achieving high-quality production because it directly affects the quality and comprehensiveness of data collection. Based on the sensor configuration data, the sensor integrated equipment is configured and adjusted, and the initial home textile production data is monitored in real time by the sensor integrated equipment after configuration adjustment, ensuring that the production process is monitored in real time from the beginning, allowing any potential production problems to be discovered and handled in a timely manner, thereby reducing the risk of production interruption, and improving the stability of the production line and the consistency of the product. The initial home textile production data is processed by abnormal pattern recognition of production equipment, which helps to timely identify abnormal situations in the production process, such as equipment failure or performance degradation, improves the response speed and processing efficiency to production problems, and ensures the continuity of the production process and the stability of product quality. The production equipment repair parameter analysis and processing is performed based on the abnormal mode data of the production equipment. The generated production equipment repair parameters guide the timely maintenance and adjustment of the equipment, which not only reduces the equipment downtime, but also ensures that the equipment can operate in the best state after resuming production, thereby improving production efficiency and the service life of the equipment. The initial home textile product production data is iteratively updated based on the production equipment repair parameters, reflecting the production status after equipment maintenance and adjustment, ensuring the continuous updating and optimization of production data, providing data support for the continuous improvement of the production process, better monitoring of each link of the production process, and achieving fine control of the production process, thereby improving the overall production quality and efficiency.

[0027] Preferably, step S23 includes the following steps:

[0028] Extracting and processing abnormal home textile product status data according to the initial home textile product status data to generate abnormal home textile product status data;

[0029] Based on the abnormal home textile product status data, the initial production equipment status data is subjected to abnormal production equipment status data marking processing to generate abnormal production equipment status data;

[0030] Perform periodic abnormal analysis and processing of production equipment based on abnormal production equipment status data to generate periodic abnormal data of production equipment;

[0031] The abnormal pattern recognition processing of the production equipment is performed based on the periodic abnormal data of the production equipment to generate the abnormal pattern data of the production equipment.

[0032] The present invention performs abnormal data extraction processing on the initial home textile product status data, quickly identifies quality problems in the production process, and helps to timely discover product quality deviations, such as inconsistent size, excessive color difference or other quality defects, thereby realizing early identification of problem products. Based on the abnormal home textile product status data, the initial production equipment status data is subjected to abnormal status marking processing to accurately locate the source of the production problem. This process provides important clues for diagnosing and solving production problems by marking the abnormal equipment status associated with product quality problems, ensuring that the problems can be quickly identified and located, reducing the time for problem solving, and improving the stability and efficiency of the production line. Periodic abnormal analysis processing is performed based on the abnormal production equipment status data to reveal the periodic pattern of equipment failure or performance degradation, identify problems that may be caused by equipment wear or insufficient regular maintenance, thereby realizing preventive maintenance and optimization adjustment of production equipment, and significantly reducing the risk of production interruption by identifying and solving periodic problems in advance, ensuring the continuity of the production process and the improvement of production efficiency. Abnormal pattern recognition processing is performed based on the periodic abnormal data of production equipment, which can provide clear guidance for the maintenance and repair of production equipment and reduce production losses caused by equipment failure. This data-based recognition and prediction mechanism greatly improves the reliability of production equipment and the stable operation of the production line.

[0033] Preferably, step S3 comprises the following steps:

[0034] Step S31: performing home textile product data matching processing according to the target home textile product raw material scanning data and the home textile product status data to generate home textile product matching data;

[0035] Step S32: Perform production timing matching processing according to the target home textile product raw material scanning data and the production equipment status data to generate production timing matching data;

[0036] Step S33: performing home textile product production matching node analysis and processing according to the home textile product matching data and the production time sequence matching data to generate home textile product production matching node data;

[0037] Step S34: performing data matching processing on the target home textile product raw material scanning data and the home textile product production data according to the home textile product production matching node data to generate home textile product raw material-production matching data.

[0038] The present invention performs home textile product data matching processing according to the target home textile product raw material scanning data and home textile product status data, ensures a high degree of consistency between raw material selection and final product status, effectively connects the characteristics of the raw materials with the quality requirements of the product, ensures that the raw materials used are most suitable for the predetermined product standards, thereby improving product quality and the ability to meet customer needs. Production timing matching processing is performed according to the target home textile product raw material scanning data and production equipment status data, optimizes the time arrangement and resource allocation of the production process, ensures the synchronization of production activities and equipment status, thereby maximizing production efficiency and achieving smoother and more efficient production scheduling. By performing home textile product production matching node analysis and processing according to home textile product matching data and production timing matching data, key nodes in the production process, such as raw material input, processing process, and quality control points, are identified, and by accurately analyzing and optimizing key production nodes, the management efficiency of the production process and the accuracy of product quality control are improved, providing important support for the smooth completion of production tasks. The final data matching processing is performed on the target home textile product raw material scanning data and home textile product production data according to the home textile product production matching node data, which provides comprehensive data support for the production process and can ensure that production decisions and control logic are based on accurate and comprehensive information, thereby maximizing the efficiency of the production process and product quality, while reducing resource waste and optimizing production costs.

[0039] Preferably, step S4 comprises the following steps:

[0040] Step S41: establishing a mapping relationship between the production equipment status and the home textile product status according to a preset support vector machine algorithm to generate a preliminary home textile product production quality prediction model;

[0041] Step S42: Designing a model training sample according to the production equipment status data in the home textile product raw material-production matching data as input data and the home textile product status data in the home textile product raw material-production matching data as output data, so as to generate a model training sample;

[0042] Step S43: performing model training optimization processing on the preliminary home textile product production quality prediction model according to the model training samples to generate an optimized home textile product production quality prediction model;

[0043] Step S44: Design the PLC production control logic according to the optimized home textile product production quality prediction model, generate PLC production control logic data, and feed back the PLC production control logic data to the terminal to execute the automatic control production operation of home textile products.

[0044] The present invention uses a preset support vector machine (SVM) algorithm to establish a mapping relationship between the state of production equipment and the state of home textile products. The generated preliminary home textile product production quality prediction model accurately predicts the quality changes in the production process. The establishment of this mapping relationship allows the prediction and identification of potential product quality problems in the early stage of production, which provides the possibility for taking improvement measures in advance, thereby improving the quality of the final product. By designing model training samples, the production equipment state data in the home textile product raw material-production matching data is used as input, and the corresponding home textile product state data is used as output. This process provides an accurate data basis for in-depth training and optimization of the quality prediction model, ensuring that the model can accurately capture the key features and laws in the production process, thereby improving the accuracy and reliability of the prediction model. By performing model training optimization processing on the preliminary home textile product production quality prediction model, the generated optimized home textile product production quality prediction model can more accurately predict the production quality, especially in a complex production environment. This optimization processing makes the prediction model more refined and adaptable through continuous learning and adjustment, and can effectively guide the adjustment of the production process to ensure continuous optimization of product quality. The PLC production control logic design and its data feedback based on the optimized home textile product production quality prediction model realize the automation and intelligent control of the production process. By precisely controlling the production parameters and processes, it ensures that production activities can automatically adjust the control parameters of production equipment according to the guidance of the prediction model and the PLC automation program, thereby maximizing production efficiency and product quality. This data and model-based intelligent production control mechanism provides the manufacturing industry with an efficient, flexible and sustainable production solution.

[0045] Preferably, step S43 includes the following steps:

[0046] Divide the model training samples into data to generate model training set, model verification set, and model test set respectively;

[0047] Using the model training set to perform model training processing on the preliminary home textile product production quality prediction model, to generate the home textile product production quality prediction model;

[0048] Based on the model validation set, the model validation and evaluation processing of the home textile product production quality prediction model is carried out to generate model validation and evaluation data;

[0049] Divide the model validation evaluation data into stages of production link evaluation data to generate production link stage evaluation data;

[0050] Analyze the bottleneck optimization parameters of the production link based on the production link stage evaluation data, and generate the bottleneck optimization parameters of the production link;

[0051] The home textile product production quality prediction model is optimized and adjusted by optimizing the production link bottleneck parameters to generate an optimized home textile product production quality prediction model. The optimized home textile product production quality prediction model is tested using a model test set to generate an optimized home textile product production quality prediction model.

[0052] The present invention divides the model training samples into data, generates the model training set, model verification set, and model test set, ensures that the training, verification, and test processes of the machine learning model do not interfere with each other, fairly evaluates the model performance, helps to effectively avoid model overfitting, and ensures that the model has good generalization ability. The model training set is used to perform model training processing on the preliminary home textile product production quality prediction model, so that the model can learn the key quality influencing factors and their internal relationships in the production process, thereby improving the accuracy of the model prediction production quality. Based on the model verification set, the home textile product production quality prediction model is subjected to model verification and evaluation processing, and the performance of the model is tested without affecting the final test results. The generated model verification and evaluation data helps to adjust and optimize the model parameters, and further improves the accuracy and reliability of the model. The stage division of the production link evaluation data for the model verification evaluation data can carefully identify the various stages in the production process and their impact on product quality, help locate the root cause of quality problems, and provide guidance for subsequent optimization. The production link bottleneck optimization parameter analysis based on the production link stage evaluation data can clearly point out the bottlenecks and inefficient links in the production process, which is crucial for improving production processes, improving production efficiency and product quality. The home textile product production quality prediction model is optimized and adjusted by optimizing the production link bottleneck parameters and tested using the model test set. This not only improves the model's prediction accuracy, but also ensures the model's applicability and effectiveness in the actual production environment, guides production more accurately, and effectively improves production quality and efficiency.

[0053] Preferably, the performing of production link bottleneck optimization parameter analysis according to the production link stage evaluation data comprises the following steps:

[0054] Identify decision factors at the production link stage based on the production link stage evaluation data and generate decision factor data at the production link stage;

[0055] Perform tree node parameter analysis based on the decision factor data of the production link stage to generate tree node parameters; establish a production link optimization decision tree model based on the tree node parameters to generate a production link optimization decision tree model;

[0056] According to the production link optimization decision tree model, the production link bottleneck optimization parameter analysis is performed to generate the production link bottleneck optimization parameters.

[0057] The present invention identifies production link stage decision factors based on production link stage evaluation data, can accurately point out the key factors that affect production link efficiency and product quality, helps to clarify the optimization focus in the production process, provides data support and directional guidance for the improvement of the production link, and ensures that the optimization activities can solve practical problems in a targeted manner. The tree node parameter analysis and generated tree node parameters based on the production link stage decision factor data provide basic parameters for constructing a production link optimization decision tree model. These parameters reflect the decision logic and possible optimization paths of each stage of the production link, and help to accurately simulate and analyze the production process, thereby discovering and optimizing key nodes in the production process. The production link optimization decision tree model established based on the tree node parameters systematically analyzes and evaluates each link and decision point of the production link, provides an intuitive and systematic method for identifying and analyzing the bottleneck problem of the production link, helps to more deeply understand the complex relationships and influencing factors in the production process, and provides scientific decision-making for the optimization of the production process. The production chain bottleneck optimization parameter analysis based on the production chain optimization decision tree model can accurately identify the bottleneck links in the production process and put forward specific optimization suggestions and parameters, which helps to solve the inefficiency and quality problems in the production process in a targeted manner, improve the efficiency and product quality of the entire production chain, and ensure that production activities can be carried out more smoothly and efficiently. Through the application of these optimization parameters, continuous improvement and optimization of the production process can be achieved.

[0058] This specification provides a home textile product production system based on PLC programming automatic control, which is used to execute the home textile product production method based on PLC programming automatic control as described above. The home textile product production system based on PLC programming automatic control includes:

[0059] The target home textile product raw material scanning module is used to perform home textile product raw material scanning processing according to the monitoring scanning device to generate home textile product raw material scanning data; and collect target home textile product raw material scanning data from the home textile product raw material scanning data to obtain the target home textile product raw material scanning data;

[0060] A home textile product production data acquisition module, which is used to collect and process home textile product production data in real time according to the sensor integrated device to generate home textile product production data, wherein the home textile product production data includes production equipment status data and home textile product status data;

[0061] A home textile product raw material-production matching module is used to perform data matching processing on target home textile product raw material scanning data and home textile product production data to generate home textile product raw material-production matching data;

[0062] The PLC production control logic analysis module is used to establish an optimization prediction model for the production quality of home textile products based on the preset support vector machine algorithm and the home textile product raw material-production matching data, and generate an optimized home textile product production quality prediction model; design the PLC production control logic based on the optimized home textile product production quality prediction model, generate PLC production control logic data, and feed back the PLC production control logic data to the terminal to execute the automatic control production operation of home textile products.

[0063] The beneficial effects of the present application lie in that the home textile product production method based on PLC programming and automatic control of the present invention can automatically screen out target home textile product raw materials through PLC, thereby ensuring the screening effect and objectivity of the home textile product raw materials, and accurately matching the collected raw material scanning data and production data for analyzing the control parameters of the production equipment, and analyzing the production bottlenecks corresponding to the control parameters of each stage in the production equipment according to the decision tree model, so as to accurately adjust the control parameters of the production equipment in the production process of home textile products, and design the control logic parameters of the PLC through the analyzed control parameters of the production equipment to realize the automatic control of home textile product production, thereby improving the intelligence level of home textile product production, reducing manual intervention, and reducing production costs, and being able to improve production flexibility and response speed while ensuring product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 This is a schematic flow chart of the steps of a method for producing home textile products based on PLC programming and automatic control of the present invention;

[0065] Figure 2 for Figure 1 Detailed implementation steps of step S4 in FIG.

[0066] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0067] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are 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 technicians in this field without creative work are within the scope of protection of the present invention.

[0068] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0069] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0070] To achieve this, please refer to Figure 1 to Figure 2 The present invention provides a method for producing home textile products based on PLC programming and automatic control, comprising the following steps:

[0071] Step S1: scanning the home textile product raw material according to the monitoring scanning device to generate home textile product raw material scanning data; collecting target home textile product raw material scanning data on the home textile product raw material scanning data to obtain the target home textile product raw material scanning data;

[0072] Step S2: collecting and processing the home textile product production data in real time according to the sensor integrated device to generate the home textile product production data, wherein the home textile product production data includes the production equipment status data and the home textile product status data;

[0073] Step S3: performing data matching processing on the target home textile product raw material scanning data and the home textile product production data to generate home textile product raw material-production matching data;

[0074] Step S4: Establish an optimization prediction model for the production quality of home textile products based on the preset support vector machine algorithm and the home textile product raw material-production matching data, and generate an optimized home textile product production quality prediction model; design PLC production control logic based on the optimized home textile product production quality prediction model, generate PLC production control logic data, and feed back the PLC production control logic data to the terminal to execute the automatic control production operation of home textile products.

[0075] The present invention scans and processes the raw materials of home textile products through monitoring scanning equipment, thereby realizing rapid and accurate collection of raw material information, ensuring that the quality and specifications of the raw materials used in the production process meet the predetermined standards. Through the accurate collection of raw material data, production defects caused by raw material problems can be effectively avoided, and the quality of the final product can be improved. Accurate raw material data also supports material tracking, supply chain management and cost control in the production process, and provides data support for efficient and sustainable production. Using sensor integrated equipment to collect production data of home textile products in real time, including the status of production equipment and home textile products, can achieve real-time monitoring and control of the production process, which helps to immediately discover any anomalies or deviations in the production process, such as equipment failures or product quality problems, so as to quickly take measures to adjust or correct them. Real-time data collection and analysis can also optimize production scheduling and resource allocation, improve production efficiency and flexibility, reduce waste, and ultimately achieve cost savings and productivity improvements. The target home textile product raw material scanning data and home textile product production data are accurately matched, and the generated home textile product raw material-production matching data can provide more accurate data support for the production process. This matching process ensures the best match between raw material selection and actual production needs, reduces the decline in production efficiency and product quality problems caused by raw material mismatch, and supports more refined production management, such as the optimal utilization of raw materials and fine regulation of the production process, thereby improving resource utilization efficiency and controllability of the production process. Through the preset support vector machine (SVM) algorithm and home textile product raw material-production matching data, the optimized home textile product production quality prediction model established can effectively predict and optimize production quality, which not only significantly improves product quality and production efficiency, but also reduces waste through accurate quality control, and improves the overall production economic benefits. The model is used to design PLC production control logic, and the control logic data is fed back to the production terminal, realizing the automation and intelligent control of the production process. This data-driven control logic makes the production process more flexible and responsive, and can effectively respond to various changes and uncertainties in the production process, ensuring the stability of the production process and the consistency of product quality.

[0076] As an embodiment of the present invention, refer to Figure 1 The above is a schematic diagram of the steps of a method for producing home textile products based on PLC programming and automatic control of the present invention. In this embodiment, the intelligent medication management method includes the following steps:

[0077] Step S1: scanning the home textile product raw material according to the monitoring scanning device to generate home textile product raw material scanning data; collecting target home textile product raw material scanning data on the home textile product raw material scanning data to obtain the target home textile product raw material scanning data;

[0078] In the embodiment of the present invention, monitoring scanning equipment is installed during the raw material storage stage, including a barcode scanner, an image recognition camera, etc., to capture detailed information of the raw materials, such as type, size, color, texture, etc. When the home textile product raw materials pass through the scanning area, the scanning equipment is started to automatically scan and capture the raw material information, and the information is digitized into home textile product raw material scanning data. Based on the pre-defined raw material demand standards (such as quality, size range, etc.), the target home textile product raw material scanning data that meets the production requirements is screened from the scanned data, and the data is saved in the database for subsequent use.

[0079] Step S2: collecting and processing the home textile product production data in real time according to the sensor integrated device to generate the home textile product production data, wherein the home textile product production data includes the production equipment status data and the home textile product status data;

[0080] In an embodiment of the present invention, sensors are installed at key positions of a home textile product production line, including temperature and humidity sensors, speed sensors, pressure sensors, etc., for real-time monitoring of key parameters of the production environment and the production process. The sensor integration equipment monitors the operating status of the production equipment (such as speed, temperature, pressure, etc.) and the status of the home textile products (such as size, weight, texture, etc.) in real time, and transmits these data to a central data processing system in real time. The central data processing system receives data from each sensor, organizes and analyzes the data, and generates structured home textile product production data, including specific production equipment status data and home textile product status data, which is used to monitor the quality and efficiency of the production process and provide a basis for subsequent data matching and production quality optimization.

[0081] Step S3: performing data matching processing on the target home textile product raw material scanning data and the home textile product production data to generate home textile product raw material-production matching data;

[0082] In an embodiment of the present invention, the screened target home textile product raw material scanning data and the home textile product production data are integrated together, including detailed information of the raw materials (such as material, size, etc.) and corresponding production process information (such as equipment status, product quality inspection data, etc.), and the integrated data are matched and analyzed using data processing software or a custom-developed algorithm to identify the correlation between raw material properties and production process parameters, with the aim of finding out key raw material characteristics and production conditions that affect product quality. Based on the results of the matching analysis, home textile product raw material-production matching data is generated, which describes in detail which raw material characteristics are closely related to which parameters in the production process, providing a basis for production quality prediction and optimization.

[0083] Step S4: Establish an optimization prediction model for the production quality of home textile products based on the preset support vector machine algorithm and the home textile product raw material-production matching data, and generate an optimized home textile product production quality prediction model; design PLC production control logic based on the optimized home textile product production quality prediction model, generate PLC production control logic data, and feed back the PLC production control logic data to the terminal to execute the automatic control production operation of home textile products.

[0084] In the embodiment of the present invention, a preliminary home textile product production quality prediction model is established based on the home textile product raw material-production matching data using a support vector machine (SVM) algorithm. It is necessary to program the SVM algorithm, select a suitable kernel function, adjust parameters to optimize model performance, train the model, and use a part of the data with known results as a training set to adjust the model parameters to ensure that the model can accurately predict production quality. Use another part of the data as a validation set to evaluate the accuracy and generalization ability of the model, and perform optimization when necessary to improve the prediction accuracy. After completing the model optimization, use the test set data to perform a final test on the model to confirm that the model's prediction performance meets production requirements, and finally generate an optimized home textile product production quality prediction model. Based on the optimization of the home textile product production quality prediction model, the production control logic of the PLC (programmable logic controller) is designed, including defining how to automatically adjust the production parameters (such as equipment speed, temperature, pressure, etc.) according to the new monitoring data and the corresponding model prediction results to optimize product quality. The designed PLC production control logic is programmed into the PLC control system and deployed to the production line to ensure that the control logic can be accurately executed and realize automatic control of the production process. During the production process, production data is collected in real time and fed back to the PLC control system. The production conditions are continuously optimized according to the prediction model and control logic to ensure product quality.

[0085] Preferably, step S1 comprises the following steps:

[0086] Step S11: Scanning the raw materials of home textile products according to the monitoring scanning device to generate scanning data of the raw materials of home textile products;

[0087] Step S12: performing multi-dimensional raw material quality detection processing on the home textile product raw material scanning data to generate multi-dimensional raw material quality detection data;

[0088] Step S13: performing PLC raw material screening logic analysis according to the multi-dimensional raw material quality detection data to generate PLC raw material screening logic data;

[0089] Step S14: Screening the effective raw material quality detection data of the multi-dimensional raw material quality detection data based on the PLC raw material screening logic data to obtain effective raw material quality detection data;

[0090] Step S15: collecting target home textile product raw material scanning data on the home textile product raw material scanning data based on the effective raw material quality detection data to obtain the target home textile product raw material scanning data.

[0091] The present invention performs scanning processing of home textile product raw materials through monitoring scanning equipment, directly generates home textile product raw material scanning data, automatically collects detailed information of raw materials, including type, quality, size, etc., provides first-hand data for subsequent raw material screening and quality inspection, and such automated scanning reduces human errors and improves the efficiency and accuracy of data collection. Multidimensional raw material quality inspection data is subjected to multidimensional raw material quality inspection processing, and the generated multidimensional raw material quality inspection data can fully reflect the quality status of raw materials. By evaluating raw materials from multiple angles and multiple indicators, the comprehensive quality of raw materials can be revealed, including but not limited to various important parameters such as strength, purity, color, etc., to ensure that the screened raw materials meet production requirements in all important dimensions. PLC raw material screening logic analysis is performed according to multidimensional raw material quality inspection data to generate PLC raw material screening logic data, realizes the automation and intelligence of raw material screening, makes the raw material screening process more accurate and efficient, and automatically excludes raw materials that do not meet quality standards through preset screening logic, ensuring that the raw materials used in production meet the requirements, thereby directly improving product quality and production efficiency. Based on the PLC raw material screening logic data, the multi-dimensional raw material quality inspection data is screened for effective raw material quality inspection data to obtain effective raw material quality inspection data, which improves the accuracy and efficiency of raw material quality inspection. This screening mechanism reduces production problems and finished product defects caused by substandard raw material quality. Based on the effective raw material quality inspection data, the home textile product raw material scanning data is collected for target home textile product raw material scanning data, further refining and ensuring the target and effectiveness of the collected raw material data, ensuring that raw material data that meets production requirements will be used in subsequent production processes, optimizing the raw material selection process, thereby improving production efficiency while maximizing product quality.

[0092] In an embodiment of the present invention, a monitoring scanning device, such as a barcode scanner, an RFID reader, a visual recognition system, etc., is installed in the raw material processing area to automatically identify and record raw material information. When the home textile raw material passes through the scanning area, the scanning device is automatically triggered to collect basic information of the raw material, such as type, batch, specification, etc., and generate home textile product raw material scanning data. Multidimensional quality detection equipment is configured in the raw material detection area, including detection instruments such as weight, size, color, texture, etc. When the raw material passes through the detection area, multidimensional quality detection is automatically performed, and the detection results are recorded to generate multidimensional raw material quality detection data. According to production requirements, the quality screening standards of the raw materials are pre-set, such as weight range, color consistency standard, etc., and the PLC system is used to perform logical analysis on the multidimensional raw material quality detection data, and PLC raw material screening logic data is generated according to the screening standards. Based on the PLC raw material screening logic data, data that meets the quality standard is automatically screened out from the multidimensional raw material quality detection data, and unqualified data is eliminated. The screened data is determined as effective raw material quality detection data for subsequent production processes. Match and integrate the effective raw material quality inspection data with the original home textile product raw material scanning data. Based on the integrated data, further screen out the raw material data that meets the specific production target requirements as the target home textile product raw material scanning data to prepare accurate raw material information for specific production batches.

[0093] Preferably, step S12 comprises the following steps:

[0094] The multi-dimensional raw material quality inspection data is processed by dimensional indicator weighting to generate raw material quality dimensional indicator weight data; the PLC raw material screening logic is designed according to the preset multi-dimensional raw material quality assessment decision and raw material quality dimensional indicator weight data to generate PLC raw material screening logic data.

[0095] The present invention performs dimensional index weighting processing on multi-dimensional raw material quality detection data, and the generated raw material quality dimensional index weight data reasonably reflects the degree of influence of each quality index on the quality of the final product. By specifying different weights for different quality dimensions, it is ensured that the applicability and quality of the raw materials can be more accurately evaluated during the raw material screening process. The PLC raw material screening logic design based on the preset multi-dimensional raw material quality assessment decision and the raw material quality dimensional index weight data realizes the automation and intelligence of the raw material screening process, which not only improves the efficiency and accuracy of the screening, but also makes the raw material selection process more objective and reasonable. By accurately controlling the quality of the raw materials, it can directly affect the smooth progress of the production process and the stability of the product quality, ensuring that the produced home textile products can meet high-standard quality requirements.

[0096] In the embodiment of the present invention, according to the production requirements and quality standards, the influence of each dimension of raw material quality (such as weight, size, color, texture, etc.) on the quality of the final product is evaluated, the importance of each dimension is determined, and a weight is assigned to each dimensional indicator according to the evaluation results to ensure that the indicator with a greater impact on product quality has a higher decision weight in the raw material screening process, and all dimensional indicators and their corresponding weights are integrated into a raw material quality dimensional indicator weight data table for subsequent raw material screening logic design. According to the product quality requirements and raw material characteristics, a set of raw material evaluation decision rules including all quality dimensions is formulated, and the set of rules should consider the interaction between the dimensions and their comprehensive impact on the quality of the final product, and the raw material quality dimensional indicator weight data is integrated into the multidimensional raw material quality evaluation decision rules to ensure that the raw material screening logic can reflect the importance of each quality dimension. Using PLC programming language and tools, according to the above evaluation decision rules and weight data, the PLC raw material screening logic is designed, including writing a program that can automatically calculate the comprehensive quality score of each batch of raw materials, and a logic control process that automatically decides whether to accept the batch of raw materials according to the score. After completing the PLC program design, a set of raw material screening logic data that can be executed by PLC is generated, which will be directly applied to the PLC system on the production line to realize the automated quality screening of raw materials.

[0097] Preferably, step S2 comprises the following steps:

[0098] Step S21: Analyze sensor configuration data according to preset home textile product production monitoring decisions to generate sensor configuration data;

[0099] Step S22: performing configuration adjustment on the sensor integrated device based on the sensor configuration data, and performing real-time monitoring and processing of initial home textile product production data through the sensor integrated device after the configuration adjustment to generate initial home textile product production data, wherein the initial home textile product production data includes initial production device status data and initial home textile product status data;

[0100] Step S23: performing production equipment abnormal pattern recognition processing according to the initial home textile product production data to generate production equipment abnormal pattern data;

[0101] Step S24: Analyzing and processing the production equipment repair parameters according to the production equipment abnormality mode data to generate the production equipment repair parameters;

[0102] Step S25: performing iterative updating processing on the initial home textile product production data based on the production equipment repair parameters to generate home textile product production data.

[0103] The present invention analyzes sensor configuration data according to preset home textile production monitoring decisions, can accurately guide the configuration of sensor integrated equipment, ensure that the sensor layout best matches the production requirements, optimize the configuration of the sensor, and enable it to more accurately monitor the key parameters in the production process, thereby improving the monitoring efficiency and accuracy of the production process. Appropriate sensor configuration is crucial to achieving high-quality production because it directly affects the quality and comprehensiveness of data collection. Based on the sensor configuration data, the sensor integrated equipment is configured and adjusted, and the initial home textile production data is monitored in real time by the sensor integrated equipment after configuration adjustment, ensuring that the production process is monitored in real time from the beginning, allowing any potential production problems to be discovered and handled in a timely manner, thereby reducing the risk of production interruption, and improving the stability of the production line and the consistency of the product. The initial home textile production data is processed by abnormal pattern recognition of production equipment, which helps to timely identify abnormal situations in the production process, such as equipment failure or performance degradation, improves the response speed and processing efficiency to production problems, and ensures the continuity of the production process and the stability of product quality. The production equipment repair parameter analysis and processing is performed based on the abnormal mode data of the production equipment. The generated production equipment repair parameters guide the timely maintenance and adjustment of the equipment, which not only reduces the equipment downtime, but also ensures that the equipment can operate in the best state after resuming production, thereby improving production efficiency and the service life of the equipment. The initial home textile product production data is iteratively updated based on the production equipment repair parameters, reflecting the production status after equipment maintenance and adjustment, ensuring the continuous updating and optimization of production data, providing data support for the continuous improvement of the production process, better monitoring of each link of the production process, and achieving fine control of the production process, thereby improving the overall production quality and efficiency.

[0104] In the embodiment of the present invention, the production process of home textile products is reviewed, and the key parameters that need to be monitored, such as temperature, humidity, speed, pressure, etc., are determined. According to the monitoring requirements, suitable sensor types are selected, and their optimal installation positions on the production line are determined to ensure that the required data can be effectively collected. The determined sensor type and installation position and other information are organized into sensor configuration data to provide guidance for the next step of sensor installation and adjustment. According to the sensor configuration data, the sensor integrated equipment on the production line is installed and configured to ensure that each sensor can accurately capture data. The adjusted sensor integrated equipment is started, the production process is monitored in real time, and the initial production equipment status data and home textile product status data are collected. The collected data is organized into structured initial home textile product production data to provide a basis for subsequent analysis and optimization. The collected initial home textile product production data is analyzed to identify possible abnormal modes of production equipment, such as unstable equipment operation, performance degradation, etc., and the identified abnormal modes are organized into production equipment abnormal mode data for further analysis and processing. According to the production equipment abnormal mode data, the cause of the abnormality is analyzed and determined, and corresponding repair measures are formulated. According to the repair measures, the production equipment parameters that need to be adjusted are determined, such as adjusting the temperature setting, changing the production speed, etc., and the production equipment repair parameters are generated. According to the production equipment repair parameters, the equipment on the production line is adjusted or repaired to solve the identified abnormal problems. After the repair parameters are applied, the production process is monitored again through the sensor integrated equipment to collect updated production data, and the updated monitoring data is sorted and updated to generate home textile product production data reflecting the equipment repair and parameter adjustment, providing a basis for continuous production monitoring and quality control.

[0105] Preferably, step S23 includes the following steps:

[0106] Extracting and processing abnormal home textile product status data according to the initial home textile product status data to generate abnormal home textile product status data;

[0107] Based on the abnormal home textile product status data, the initial production equipment status data is subjected to abnormal production equipment status data marking processing to generate abnormal production equipment status data;

[0108] Perform periodic abnormal analysis and processing of production equipment based on abnormal production equipment status data to generate periodic abnormal data of production equipment;

[0109] The abnormal pattern recognition processing of the production equipment is performed based on the periodic abnormal data of the production equipment to generate the abnormal pattern data of the production equipment.

[0110] The present invention performs abnormal data extraction processing on the initial home textile product status data, quickly identifies quality problems in the production process, and helps to timely discover product quality deviations, such as inconsistent size, excessive color difference or other quality defects, thereby realizing early identification of problem products. Based on the abnormal home textile product status data, the initial production equipment status data is subjected to abnormal status marking processing to accurately locate the source of the production problem. This process provides important clues for diagnosing and solving production problems by marking the abnormal equipment status associated with product quality problems, ensuring that the problems can be quickly identified and located, reducing the time for problem solving, and improving the stability and efficiency of the production line. Periodic abnormal analysis processing is performed based on the abnormal production equipment status data to reveal the periodic pattern of equipment failure or performance degradation, identify problems that may be caused by equipment wear or insufficient regular maintenance, thereby realizing preventive maintenance and optimization adjustment of production equipment, and significantly reducing the risk of production interruption by identifying and solving periodic problems in advance, ensuring the continuity of the production process and the improvement of production efficiency. Abnormal pattern recognition processing is performed based on the periodic abnormal data of production equipment, which can provide clear guidance for the maintenance and repair of production equipment and reduce production losses caused by equipment failure. This data-based recognition and prediction mechanism greatly improves the reliability of production equipment and the stable operation of the production line.

[0111] In an embodiment of the present invention, data related to the status of home textile products are extracted from the initial home textile product production data, the home textile product status data is analyzed, and according to the preset normal operating parameter range (such as size, weight, color difference and other standards), abnormal data that does not meet the standards is identified, and the identified abnormal home textile product status data is sorted and summarized to generate an abnormal home textile product status data report. The abnormal home textile product status data is deeply analyzed to determine the production equipment status problems that cause these abnormalities. Based on the analysis results, the initial production equipment status data is checked and marked, and it is accurately pointed out which equipment status data is associated with the abnormal status of home textile products to obtain abnormal production equipment status data. All marked abnormal production equipment status data within a period of time are sorted and collected, and the occurrence pattern of these abnormal data is analyzed using statistical analysis tools or software to identify whether there are periodic abnormalities, such as identifying that the production equipment has sudden abnormal conditions and continuous abnormal conditions, and the periodic abnormal patterns obtained by analysis are sorted into reports to generate periodic abnormal data of production equipment. Conduct a detailed analysis of the periodic abnormal data of production equipment, combine the production process and the working principle of the equipment to determine the root cause of the abnormal pattern. Based on the analysis results, identify the specific abnormal pattern of the production equipment, such as wear of a certain component, inaccurate temperature control, etc., record the identified abnormal pattern of the production equipment in detail, and generate a production equipment abnormal pattern data report to provide a basis for subsequent equipment repair and parameter adjustment.

[0112] Preferably, step S3 comprises the following steps:

[0113] Step S31: performing home textile product data matching processing according to the target home textile product raw material scanning data and the home textile product status data to generate home textile product matching data;

[0114] Step S32: Perform production timing matching processing according to the target home textile product raw material scanning data and the production equipment status data to generate production timing matching data;

[0115] Step S33: performing home textile product production matching node analysis and processing according to the home textile product matching data and the production time sequence matching data to generate home textile product production matching node data;

[0116] Step S34: performing data matching processing on the target home textile product raw material scanning data and the home textile product production data according to the home textile product production matching node data to generate home textile product raw material-production matching data.

[0117] The present invention performs home textile product data matching processing according to the target home textile product raw material scanning data and home textile product status data, ensures a high degree of consistency between raw material selection and final product status, effectively connects the characteristics of the raw materials with the quality requirements of the product, ensures that the raw materials used are most suitable for the predetermined product standards, thereby improving product quality and the ability to meet customer needs. Production timing matching processing is performed according to the target home textile product raw material scanning data and production equipment status data, optimizes the time arrangement and resource allocation of the production process, ensures the synchronization of production activities and equipment status, thereby maximizing production efficiency and achieving smoother and more efficient production scheduling. By performing home textile product production matching node analysis and processing according to home textile product matching data and production timing matching data, key nodes in the production process, such as raw material input, processing process, and quality control points, are identified, and by accurately analyzing and optimizing key production nodes, the management efficiency of the production process and the accuracy of product quality control are improved, providing important support for the smooth completion of production tasks. The final data matching processing is performed on the target home textile product raw material scanning data and home textile product production data according to the home textile product production matching node data, which provides comprehensive data support for the production process and can ensure that production decisions and control logic are based on accurate and comprehensive information, thereby maximizing the efficiency of the production process and product quality, while reducing resource waste and optimizing production costs.

[0118] In an embodiment of the present invention, the target home textile product raw material scanning data and home textile product status data are imported into the data analysis platform. These data include detailed information of the raw materials (such as type, quality, etc.) and various status data of the home textile products during the production process (such as finished product size, quality, etc.). The imported raw material data and home textile product status data are compared and analyzed using data analysis tools. The purpose of the analysis is to find out the correlation between the raw material properties and the finished product status, such as the relationship between a certain raw material characteristic and the quality of the finished product. Based on the results of the matching analysis, a set of home textile product matching data is generated, which describes in detail the correlation between the raw material characteristics and the final state of the home textile products, and provides a basis for the selection and use of raw materials in the production process. The target home textile product raw material scanning data and production equipment status data are processed together. The data involved include the time point of raw material use, the batch of raw materials used, and the status information of the production equipment matching these time points (such as equipment running speed, temperature, etc.). The time series analysis method is used to study the relationship between the timing of raw material use and the change of equipment status, and identify whether the use of certain specific raw materials can bring better production results under specific equipment status. According to the results of the timing analysis, the production timing matching data is generated, which shows which raw materials have a strong match with which equipment status in different production periods, providing a reference for optimizing the production process and improving production efficiency. The home textile product matching data and the production timing matching data are collected together to identify the key matching nodes in the production process. These nodes refer to the production links where the raw material characteristics have a high degree of match with the equipment status and have a significant impact on the quality of the final product. For example, the home textile product matching data corresponds to the production timing matching data of each stage in the production process to establish a matching node. The matching node contains the products produced in the middle and the control parameters in the corresponding production equipment. The specific information of these key matching nodes is extracted and recorded to generate the home textile product production matching node data. These data describe the characteristics of each matching node in detail, including raw material type, equipment status, time point, etc. The home textile product production matching node data is further integrated with the target home textile product raw material scanning data and home textile product production data, and the specific information of the matching node is combined with the detailed characteristics of the raw materials and the actual data of the production process. The integrated data is deeply analyzed, focusing on identifying which raw material characteristics and which production conditions are at specific matching nodes to ensure the accuracy and reliability of the analysis results. Based on the results of the matching analysis, the home textile product raw material-production matching data is generated, which records the information on the use of key raw materials and the adjustment of production conditions in the production process, providing data support for formulating production strategies and optimizing production processes.

[0119] Preferably, step S4 comprises the following steps:

[0120] Step S41: establishing a mapping relationship between the production equipment status and the home textile product status according to a preset support vector machine algorithm to generate a preliminary home textile product production quality prediction model;

[0121] Step S42: Designing a model training sample according to the production equipment status data in the home textile product raw material-production matching data as input data and the home textile product status data in the home textile product raw material-production matching data as output data, so as to generate a model training sample;

[0122] Step S43: performing model training optimization processing on the preliminary home textile product production quality prediction model according to the model training samples to generate an optimized home textile product production quality prediction model;

[0123] Step S44: Design the PLC production control logic according to the optimized home textile product production quality prediction model, generate PLC production control logic data, and feed back the PLC production control logic data to the terminal to execute the automatic control production operation of home textile products.

[0124] The present invention uses a preset support vector machine (SVM) algorithm to establish a mapping relationship between the state of production equipment and the state of home textile products. The generated preliminary home textile product production quality prediction model accurately predicts the quality changes in the production process. The establishment of this mapping relationship allows the prediction and identification of potential product quality problems in the early stage of production, which provides the possibility for taking improvement measures in advance, thereby improving the quality of the final product. By designing model training samples, the production equipment state data in the home textile product raw material-production matching data is used as input, and the corresponding home textile product state data is used as output. This process provides an accurate data basis for in-depth training and optimization of the quality prediction model, ensuring that the model can accurately capture the key features and laws in the production process, thereby improving the accuracy and reliability of the prediction model. By performing model training optimization processing on the preliminary home textile product production quality prediction model, the generated optimized home textile product production quality prediction model can more accurately predict the production quality, especially in a complex production environment. This optimization processing makes the prediction model more refined and adaptable through continuous learning and adjustment, and can effectively guide the adjustment of the production process to ensure continuous optimization of product quality. The PLC production control logic design and its data feedback based on the optimized home textile product production quality prediction model realize the automation and intelligent control of the production process. By precisely controlling the production parameters and processes, it ensures that production activities can automatically adjust the control parameters of production equipment according to the guidance of the prediction model and the PLC automation program, thereby maximizing production efficiency and product quality. This data and model-based intelligent production control mechanism provides the manufacturing industry with an efficient, flexible and sustainable production solution.

[0125] As an embodiment of the present invention, refer to Figure 2 As shown, Figure 1 Detailed implementation step flow chart of step S4 in the embodiment, step S4 in this embodiment includes:

[0126] Step S41: establishing a mapping relationship between the production equipment status and the home textile product status according to a preset support vector machine algorithm to generate a preliminary home textile product production quality prediction model;

[0127] In the embodiment of the present invention, the production equipment status data and the home textile product status data are analyzed to determine the relationship between the two. This includes identifying which equipment status parameters have a significant impact on product quality, using software tools or programming languages ​​(such as Python, R, etc.) to pre-design a support vector machine algorithm, including defining the kernel function and penalty parameters of the model, and establishing a preliminary production quality prediction model that can predict the quality status of home textile products based on the input production equipment status data.

[0128] Step S42: Designing a model training sample according to the production equipment status data in the home textile product raw material-production matching data as input data and the home textile product status data in the home textile product raw material-production matching data as output data, so as to generate a model training sample;

[0129] In the embodiment of the present invention, the production equipment status data is extracted from the home textile product raw material-production matching data as the input data (feature vector) of the model, and the corresponding home textile product status data (such as quality grade) is used as the output data (label), and the training samples are designed according to the extracted data. Ensure that the samples cover various combinations of equipment status and product quality to improve the generalization ability of the model, perform necessary preprocessing on the training samples, such as standardization and normalization, to meet the requirements of SVM model training, divide the sorted data set into training set, validation set and test set, the training set is used for model training, the validation set is used for model parameter tuning, and the test set is used to evaluate model performance, so as to generate model training samples, ready for model training and optimization process.

[0130] Step S43: performing model training optimization processing on the preliminary home textile product production quality prediction model according to the model training samples to generate an optimized home textile product production quality prediction model;

[0131] In an embodiment of the present invention, the model training samples designed in step S42 are used to train a preliminary home textile product production quality prediction model through a software tool or a programming environment (such as Python's scikit-learn library), including inputting training set data to allow the model to learn how to predict the quality status of home textile products based on the status of production equipment. During the training process, the performance of the model is evaluated through a validation set, and the model parameters (such as the C parameter and kernel parameter of SVM) are adjusted according to the validation results. The decision tree algorithm is used to find the optimal parameter combination, and the model is finally evaluated using the test set data to confirm that the prediction performance of the model reaches the expected goal. The evaluation indicators may include accuracy, recall rate, F1 score, etc. After completing training, parameter tuning and performance evaluation, an optimized home textile product production quality prediction model is obtained, which is used for quality control and prediction in the actual production process.

[0132] Step S44: Design the PLC production control logic according to the optimized home textile product production quality prediction model, generate PLC production control logic data, and feed back the PLC production control logic data to the terminal to execute the automatic control production operation of home textile products.

[0133] In an embodiment of the present invention, the output results of the optimized prediction model are analyzed to determine the accuracy and reliability of the model's prediction of the quality status of home textile products. Based on this information, a PLC control logic is designed to achieve automated adjustment of the production process. According to the model prediction results and production quality requirements, the PLC control logic is designed, including formulating rules and procedures so that the operating parameters of the production equipment can be automatically adjusted according to the quality status predicted by the model during the production process, such as adjusting the speed and temperature. The designed control logic is programmed into the PLC system, and a PLC programming tool is used to encode according to the designed logic, configure the PLC system on the production line, and deploy the configured PLC control logic to the actual operation of the production line to ensure that the production line can automatically adjust the production parameters according to the control logic and the model prediction results, optimize the production process and product quality, and continuously monitor the execution effect of the PLC control logic during the production process, such as real-time monitoring of new raw material data, and predicting the optimal production equipment control parameters based on the new raw material data, so that the automated home textile product production products can meet excellent standards.

[0134] Preferably, step S43 includes the following steps:

[0135] Divide the model training samples into data to generate model training set, model verification set, and model test set respectively;

[0136] Using the model training set to perform model training processing on the preliminary home textile product production quality prediction model, to generate the home textile product production quality prediction model;

[0137] Based on the model validation set, the model validation and evaluation processing of the home textile product production quality prediction model is carried out to generate model validation and evaluation data;

[0138] Divide the model validation evaluation data into stages of production link evaluation data to generate production link stage evaluation data;

[0139] Analyze the bottleneck optimization parameters of the production link based on the production link stage evaluation data, and generate the bottleneck optimization parameters of the production link;

[0140] The home textile product production quality prediction model is optimized and adjusted by optimizing the production link bottleneck parameters to generate an optimized home textile product production quality prediction model. The optimized home textile product production quality prediction model is tested using a model test set to generate an optimized home textile product production quality prediction model.

[0141] The present invention divides the model training samples into data, generates the model training set, model verification set, and model test set, ensures that the training, verification, and test processes of the machine learning model do not interfere with each other, fairly evaluates the model performance, helps to effectively avoid model overfitting, and ensures that the model has good generalization ability. The model training set is used to perform model training processing on the preliminary home textile product production quality prediction model, so that the model can learn the key quality influencing factors and their internal relationships in the production process, thereby improving the accuracy of the model prediction production quality. Based on the model verification set, the home textile product production quality prediction model is subjected to model verification and evaluation processing, and the performance of the model is tested without affecting the final test results. The generated model verification and evaluation data helps to adjust and optimize the model parameters, and further improves the accuracy and reliability of the model. The stage division of the production link evaluation data for the model verification evaluation data can carefully identify the various stages in the production process and their impact on product quality, help locate the root cause of quality problems, and provide guidance for subsequent optimization. The production link bottleneck optimization parameter analysis based on the production link stage evaluation data can clearly point out the bottlenecks and inefficient links in the production process, which is crucial for improving production processes, improving production efficiency and product quality. The home textile product production quality prediction model is optimized and adjusted by optimizing the production link bottleneck parameters and tested using the model test set. This not only improves the model's prediction accuracy, but also ensures the model's applicability and effectiveness in the actual production environment, guides production more accurately, and effectively improves production quality and efficiency.

[0142] In an embodiment of the present invention, the sorted model training samples are divided into three parts: a model training set, a model validation set, and a model test set. The proportions are usually allocated according to 70% (training set), 15% (validation set), and 15% (test set) to ensure that the model can be trained and evaluated on various data, and the model training set data is used to train the preliminary home textile product production quality prediction model. This step usually involves selecting appropriate hyperparameters such as learning rate and number of iterations. After completing the training process, a home textile product production quality prediction model is obtained. The trained model is verified and evaluated using the model validation set, the prediction performance and accuracy of the model are analyzed, and model validation evaluation data is generated. According to the model validation evaluation data, it is determined whether the model is overfitting or underfitting, and its performance on unseen data is evaluated. The model validation evaluation data is divided according to different stages of the production process to identify which production stage the model has the best or worst prediction performance, and the production link stage evaluation data is generated. According to the evaluation data of the production chain stage, the bottleneck link in the production process is analyzed and determined, that is, the part with poor model prediction performance. For the identified bottleneck link, how to adjust the model parameters or production process parameters to optimize the production process is analyzed to generate the production chain bottleneck optimization parameters. According to the production chain bottleneck optimization parameters, the home textile product production quality prediction model is optimized and adjusted, including adjusting the model structure, optimizing algorithm parameters, etc. The optimized and adjusted model is finally tested using the model test set to verify whether the prediction performance of the model is improved after optimization, and the optimized home textile product production quality prediction model is generated.

[0143] Preferably, the performing of production link bottleneck optimization parameter analysis according to the production link stage evaluation data comprises the following steps:

[0144] Identify decision factors at the production link stage based on the production link stage evaluation data and generate decision factor data at the production link stage;

[0145] Perform tree node parameter analysis based on the decision factor data of the production link stage to generate tree node parameters; establish a production link optimization decision tree model based on the tree node parameters to generate a production link optimization decision tree model;

[0146] According to the production link optimization decision tree model, the production link bottleneck optimization parameter analysis is performed to generate the production link bottleneck optimization parameters.

[0147] The present invention identifies production link stage decision factors based on production link stage evaluation data, can accurately point out the key factors that affect production link efficiency and product quality, helps to clarify the optimization focus in the production process, provides data support and directional guidance for the improvement of the production link, and ensures that the optimization activities can solve practical problems in a targeted manner. The tree node parameter analysis and generated tree node parameters based on the production link stage decision factor data provide basic parameters for constructing a production link optimization decision tree model. These parameters reflect the decision logic and possible optimization paths of each stage of the production link, and help to accurately simulate and analyze the production process, thereby discovering and optimizing key nodes in the production process. The production link optimization decision tree model established based on the tree node parameters systematically analyzes and evaluates each link and decision point of the production link, provides an intuitive and systematic method for identifying and analyzing the bottleneck problem of the production link, helps to more deeply understand the complex relationships and influencing factors in the production process, and provides scientific decision-making for the optimization of the production process. The production chain bottleneck optimization parameter analysis based on the production chain optimization decision tree model can accurately identify the bottleneck links in the production process and put forward specific optimization suggestions and parameters, which helps to solve the inefficiency and quality problems in the production process in a targeted manner, improve the efficiency and product quality of the entire production chain, and ensure that production activities can be carried out more smoothly and efficiently. Through the application of these optimization parameters, continuous improvement and optimization of the production process can be achieved.

[0148] In an embodiment of the present invention, the production link stage evaluation data is analyzed, and these data reflect the different stages and their performance in the production process. Based on the production link stage evaluation data, the key decision factors affecting the performance of the production link stage, such as raw material quality, equipment efficiency, operating parameters, etc., are identified, and the identified decision factors are sorted out to generate production link stage decision factor data. These data describe the key influencing factors of each production stage in detail. The collected production link stage decision factor data are analyzed in detail to identify the key factors affecting production efficiency and product quality, and each decision factor is evaluated for its degree of influence on the production process, and a weight is assigned to each factor based on this evaluation. The weight allocation can be based on expert experience or data analysis results, and each decision factor and its weight are integrated into tree node parameters. These parameters will be used to construct a production link optimization decision tree model to reflect the importance of different decision factors in the production process. Based on the tree node parameters, the structure of the optimized decision tree is designed, including determining the depth of the tree, the decision factors represented by each node, the conditions for node splitting, etc. For each node in the decision tree, the corresponding tree node parameters (including decision factors and weights) are used to determine its split path. The splitting condition is based on the specific impact of the decision factors on production efficiency and quality. For example, when a parameter exceeds the threshold, it is split to a specific sub-node. According to the designed structure and splitting conditions, a decision tree algorithm (may involve programming implementation) is used to build a production chain optimization decision tree model. The model structure needs to be iteratively adjusted to ensure that the model can accurately reflect the decision path of the production process. After completing the construction and verification of the decision tree, the final production chain optimization decision tree model is obtained. This model can guide how to make optimization decisions according to different production conditions to improve the efficiency and product quality of the production chain. Using the established production chain optimization decision tree model, the entire production process is analyzed, especially those stages indicated as key influencing points by the model, and the production bottlenecks pointed out in the model are identified, that is, the stages where the decision factors that have the greatest impact on production quality and efficiency are located. For the identified production bottlenecks, the parameters that need to be adjusted or optimized are analyzed. These optimization parameters are aimed at improving the production efficiency and product quality of the bottleneck stage to generate the production chain bottleneck optimization parameters, which provides specific guidance for the implementation of production process optimization.

[0149] This specification provides a home textile product production system based on PLC programming automatic control, which is used to execute the home textile product production method based on PLC programming automatic control as described above. The home textile product production system based on PLC programming automatic control includes:

[0150] The target home textile product raw material scanning module is used to perform home textile product raw material scanning processing according to the monitoring scanning device to generate home textile product raw material scanning data; and collect target home textile product raw material scanning data from the home textile product raw material scanning data to obtain the target home textile product raw material scanning data;

[0151] A home textile product production data acquisition module, which is used to collect and process home textile product production data in real time according to the sensor integrated device to generate home textile product production data, wherein the home textile product production data includes production equipment status data and home textile product status data;

[0152] A home textile product raw material-production matching module is used to perform data matching processing on target home textile product raw material scanning data and home textile product production data to generate home textile product raw material-production matching data;

[0153] The PLC production control logic analysis module is used to establish an optimization prediction model for the production quality of home textile products based on the preset support vector machine algorithm and the home textile product raw material-production matching data, and generate an optimized home textile product production quality prediction model; design the PLC production control logic based on the optimized home textile product production quality prediction model, generate PLC production control logic data, and feed back the PLC production control logic data to the terminal to execute the automatic control production operation of home textile products.

[0154] The beneficial effects of the present application lie in that the home textile product production method based on PLC programming and automatic control of the present invention can automatically screen out target home textile product raw materials through PLC, thereby ensuring the screening effect and objectivity of the home textile product raw materials, and accurately matching the collected raw material scanning data and production data for analyzing the control parameters of the production equipment, and analyzing the production bottlenecks corresponding to the control parameters of each stage in the production equipment according to the decision tree model, so as to accurately adjust the control parameters of the production equipment in the production process of home textile products, and design the control logic parameters of the PLC through the analyzed control parameters of the production equipment to realize the automatic control of home textile product production, thereby improving the intelligence level of home textile product production, reducing manual intervention, and reducing production costs, and being able to improve production flexibility and response speed while ensuring product quality.

[0155] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0156] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for producing home textile products based on PLC programming and automatic control, characterized in that: The following steps are involved: Step S1: Scanning the raw materials of home textile products according to the monitoring scanning equipment to generate scanning data of the raw materials of home textile products; The target home textile product raw material scanning data is collected for the home textile product raw material scanning data to obtain the target home textile product raw material scanning data; wherein step S1 includes: Step S11: Scanning the raw materials of home textile products according to the monitoring scanning device to generate scanning data of the raw materials of home textile products; Step S12: Perform multi-dimensional raw material quality detection processing on the home textile product raw material scanning data to generate multi-dimensional raw material quality detection data; wherein step S12 includes: Perform dimensional indicator weighting processing on multi-dimensional raw material quality inspection data to generate raw material quality dimensional indicator weight data; perform PLC raw material screening logic design based on preset multi-dimensional raw material quality assessment decisions and raw material quality dimensional indicator weight data to generate PLC raw material screening logic data; Step S13: performing PLC raw material screening logic analysis according to the multi-dimensional raw material quality detection data to generate PLC raw material screening logic data; Step S14: Screening the effective raw material quality detection data of the multi-dimensional raw material quality detection data based on the PLC raw material screening logic data to obtain effective raw material quality detection data; Step S15: collecting target home textile product raw material scanning data on the home textile product raw material scanning data based on the effective raw material quality detection data to obtain the target home textile product raw material scanning data; Step S2: collecting and processing the home textile product production data in real time according to the sensor integrated device to generate the home textile product production data, wherein the home textile product production data includes the production equipment status data and the home textile product status data; Step S3: performing data matching processing on the target home textile product raw material scanning data and the home textile product production data to generate home textile product raw material-production matching data; wherein step S3 includes: Step S31: performing home textile product data matching processing according to the target home textile product raw material scanning data and the home textile product status data to generate home textile product matching data; Step S32: Perform production timing matching processing according to the target home textile product raw material scanning data and the production equipment status data to generate production timing matching data; Step S33: performing home textile product production matching node analysis and processing according to the home textile product matching data and the production time sequence matching data to generate home textile product production matching node data; Step S34: performing data matching processing on the target home textile product raw material scanning data and the home textile product production data according to the home textile product production matching node data to generate home textile product raw material-production matching data; Step S4: Establish an optimization prediction model for the production quality of home textile products according to the preset support vector machine algorithm and the home textile product raw material-production matching data, and generate an optimized home textile product production quality prediction model; perform PLC production control logic design according to the optimized home textile product production quality prediction model, generate PLC production control logic data, and feed back the PLC production control logic data to the terminal to execute the automatic control production operation of home textile products; wherein, step S4 includes: Step S41: establishing a mapping relationship between the production equipment status and the home textile product status according to a preset support vector machine algorithm to generate a preliminary home textile product production quality prediction model; Step S42: Designing a model training sample according to the production equipment status data in the home textile product raw material-production matching data as input data and the home textile product status data in the home textile product raw material-production matching data as output data, so as to generate a model training sample; Step S43: performing model training optimization processing on the preliminary home textile product production quality prediction model according to the model training samples to generate an optimized home textile product production quality prediction model; wherein step S43 includes: Divide the model training samples into data to generate model training set, model verification set, and model test set respectively; Using the model training set to perform model training processing on the preliminary home textile product production quality prediction model, to generate the home textile product production quality prediction model; Based on the model validation set, the model validation and evaluation processing of the home textile product production quality prediction model is carried out to generate model validation and evaluation data; Divide the model validation evaluation data into stages of production link evaluation data to generate production link stage evaluation data; The production link bottleneck optimization parameter analysis is performed according to the production link stage evaluation data to generate the production link bottleneck optimization parameter; wherein the production link bottleneck optimization parameter analysis according to the production link stage evaluation data comprises the following steps: Identify decision factors at the production link stage based on the production link stage evaluation data and generate decision factor data at the production link stage; Perform tree node parameter analysis based on the decision factor data of the production link stage to generate tree node parameters; establish a production link optimization decision tree model based on the tree node parameters to generate a production link optimization decision tree model; According to the production link optimization decision tree model, the production link bottleneck optimization parameter analysis is performed to generate the production link bottleneck optimization parameters; The home textile product production quality prediction model is optimized and adjusted by optimizing the production link bottleneck parameters to generate an optimized home textile product production quality prediction model, and the optimized home textile product production quality prediction model is tested by using the model test set to generate an optimized home textile product production quality prediction model; Step S44: Design the PLC production control logic according to the optimized home textile product production quality prediction model, generate PLC production control logic data, and feed back the PLC production control logic data to the terminal to execute the automatic control production operation of home textile products.

2. The method for producing home textile products based on PLC programming automatic control according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: Analyze sensor configuration data according to preset home textile product production monitoring decisions to generate sensor configuration data; Step S22: performing configuration adjustment on the sensor integrated device based on the sensor configuration data, and performing real-time monitoring and processing of initial home textile product production data through the sensor integrated device after the configuration adjustment to generate initial home textile product production data, wherein the initial home textile product production data includes initial production device status data and initial home textile product status data; Step S23: performing production equipment abnormal pattern recognition processing according to the initial home textile product production data to generate production equipment abnormal pattern data; Step S24: Analyzing and processing the production equipment repair parameters according to the production equipment abnormality mode data to generate the production equipment repair parameters; Step S25: performing iterative updating processing on the initial home textile product production data based on the production equipment repair parameters to generate home textile product production data.

3. The method for producing home textile products based on PLC programming automatic control according to claim 2 is characterized in that: Step S23 includes the following steps: Extracting and processing abnormal home textile product status data according to the initial home textile product status data to generate abnormal home textile product status data; Based on the abnormal home textile product status data, the initial production equipment status data is subjected to abnormal production equipment status data marking processing to generate abnormal production equipment status data; Perform periodic abnormal analysis and processing of production equipment based on abnormal production equipment status data to generate periodic abnormal data of production equipment; The abnormal pattern recognition processing of the production equipment is performed based on the periodic abnormal data of the production equipment to generate the abnormal pattern data of the production equipment.

4. A home textile product production system based on PLC programming and automatic control, characterized in that: Used to execute the home textile product production method based on PLC programming automatic control according to any one of claims 1 to 3, the home textile product production system based on PLC programming automatic control comprises: The target home textile product raw material scanning module is used to perform home textile product raw material scanning processing according to the monitoring scanning device to generate home textile product raw material scanning data; and collect target home textile product raw material scanning data from the home textile product raw material scanning data to obtain the target home textile product raw material scanning data; A home textile product production data acquisition module, which is used to collect and process home textile product production data in real time according to the sensor integrated device to generate home textile product production data, wherein the home textile product production data includes production equipment status data and home textile product status data; A home textile product raw material-production matching module is used to perform data matching processing on target home textile product raw material scanning data and home textile product production data to generate home textile product raw material-production matching data; The PLC production control logic analysis module is used to establish an optimization prediction model for the production quality of home textile products based on the preset support vector machine algorithm and the home textile product raw material-production matching data, and generate an optimized home textile product production quality prediction model; design the PLC production control logic based on the optimized home textile product production quality prediction model, generate PLC production control logic data, and feed back the PLC production control logic data to the terminal to execute the automatic control production operation of home textile products.

Images