Method and system for monitoring and managing whole production process of polyester fabric

Abstract

The invention provides a polyester fabric production whole process monitoring management method and system. The method belongs to the technical field of production process monitoring. The method comprises the following steps: deploying various types of sensors at each key node of a polyester fabric production line; various physical parameters and environment information related to polyester fabric production are collected in real time; meanwhile, an operation state monitoring system of the production equipment is integrated to obtain equipment data; carrying out deep fusion processing on multi-source heterogeneous data obtained from the polyester fabric production holographic sensing architecture; constructing a data association model; comprehensively evaluating the production situation based on the model in combination with the technological process and the quality standard of polyester fabric production; generating a production situation assessment report through production situation assessment; the whole-process data tracing system provides a traceable basis for quality disputes, raw material problems and the like, enhances the capability of controlling supply chain risks, meets the requirements of downstream customers on product traceability, and improves the brand credibility.

Description

Technical Field

[0001] The invention provides a method and system for monitoring and managing the entire polyester cloth production process, belonging to the technical field of production process monitoring. Background Art

[0002] As an important synthetic fiber, polyester fabric has been widely used in a variety of fields, including clothing, home textiles, and industrial textiles, thanks to its advantages such as high strength, good abrasion resistance, strong wrinkle resistance, and relatively low price. In recent years, with the steady growth of the global economy and the continuous upgrading of the consumer market, the market demand for polyester fabric has continued to expand, and the production scale has also been growing.

[0003] Traditional production decisions are often based on empirical judgment and simple statistical analysis, lacking in-depth mining and analysis of large amounts of historical and real-time data. Production planning is often based solely on past production experience and rough forecasts of market demand. This makes it difficult to accurately predict dynamic changes in market demand, which can easily lead to a disconnect between production plans and actual demand, resulting in production gaps or overproduction. Regarding production process parameter optimization, due to the lack of scientific optimization methods and real-time data feedback, process parameter adjustments are often blind and lagging, making it impossible to achieve optimal control of the production process, affecting product quality and production efficiency. Summary of the Invention

[0004] The present invention provides a method and system for monitoring and managing the entire polyester fabric production process, which is used to solve the problems mentioned in the above background technology:

[0005] The present invention provides a method for monitoring and managing the entire polyester fabric production process, the method comprising:

[0006] S1. Deploy various types of sensors at key nodes of the polyester fabric production line to collect various physical parameters and environmental information related to polyester fabric production in real time. At the same time, integrate the operating status monitoring system of production equipment to obtain equipment data. Initially integrate the data from different sensors and equipment monitoring systems to build a holographic perception architecture for polyester fabric production.

[0007] S2. Perform deep fusion processing on multi-source heterogeneous data obtained from the polyester fabric production holographic perception architecture; construct a data association model; based on this model, conduct a comprehensive assessment of the production situation in combination with the polyester fabric production process and quality standards; and generate a production situation assessment report based on the production situation assessment.

[0008] S3. Collect historical multi-dimensional data on polyester fabrics; use machine learning algorithms to train and learn the multi-dimensional data to build a dynamic production demand forecasting model; compare and analyze the dynamic production demand forecast results with the current production plan to identify potential production gaps or surpluses;

[0009] S4. Based on the dynamic production demand forecast results and production situation assessment report, combined with the process knowledge of polyester fabric production, the production process parameters are adaptively optimized using intelligent optimization algorithms. During the optimization process, the quality indicators and equipment operating status of the production process are monitored in real time, and the optimization strategy is adjusted in a timely manner based on the feedback information.

[0010] S5. During the polyester fabric production process, each batch of products is assigned a unique identification code, and all relevant data from the production process is associated and stored with the identification code. A real-time quality traceability system is established to query the entire life cycle information of a batch of products by scanning the identification code. At the same time, historical quality data is analyzed using data mining and machine learning techniques to establish a quality defect early warning model.

[0011] S6. Comprehensively consider the dynamic prediction results of production demand, production situation assessment reports, process parameter optimization results, quality traceability and defect warning information, and use operations research and intelligent scheduling algorithms to intelligently allocate production resources.

[0012] The present invention proposes a monitoring and management system for the entire polyester fabric production process, comprising:

[0013] one or more processors;

[0014] a memory for storing one or more programs,

[0015] When the one or more programs are executed by the one or more processors, the one or more processors implement any one of the methods described above.

[0016] The present invention achieves beneficial effects by enabling real-time data collection throughout the entire production process through a holographic perception architecture. Combined with data fusion and intelligent analysis technologies, this technology eliminates the "information silos" inherent in traditional production, enabling visualization and transparency of production status (such as equipment operation, process parameters, and environmental conditions). Production managers can intuitively grasp the overall situation through situation assessment reports, significantly improving decision-making and response speed, shifting from an "experience-driven" approach to a "data-driven" one, and significantly enhancing the intelligence and refinement of the production process.

[0017] The adaptive process parameter optimization function continuously searches for the optimal parameter combination through intelligent algorithms and dynamically adjusts it based on real-time quality feedback, effectively reducing parameter fluctuations in key links such as spinning, weaving, printing and dyeing, and reducing quality defects caused by parameter deviations (such as color difference, insufficient strength, uneven texture, etc.).

[0018] The quality traceability and defect warning system realizes the "one item, one code" full life cycle traceability, which can quickly locate the root cause of quality problems; the defect warning function can identify anomalies in advance, avoid batch quality problems, improve product qualification rate, and significantly enhance quality stability.

[0019] The dynamic production demand forecasting model accurately predicts market demand, avoids "overproduction" or "supply shortage", and reduces inventory backlogs and the additional costs of emergency production replenishment; combined with intelligent resource allocation, the utilization rate of raw materials, equipment, manpower and other resources is improved, and problems such as equipment idleness and manpower waste are reduced.

[0020] The synergy between process parameter optimization and equipment status monitoring reduces equipment failure rate and energy consumption (such as precise control of spinning temperature to reduce energy waste), shortens production cycle, and significantly reduces production cost per unit product.

[0021] Real-time quality defect warning and equipment operation status monitoring functions can detect potential risks (such as equipment failure and quality abnormalities) in advance, facilitate timely intervention, avoid risk expansion, and reduce production interruption losses.

[0022] The full-process data traceability system provides a traceable basis for quality disputes, raw material problems, etc., enhances the ability to control supply chain risks, and at the same time meets the downstream customers' demand for product traceability and enhances brand trust.

[0023] Through a dynamic production demand forecasting and plan adjustment mechanism, we can quickly respond to changes in market demand for polyester fabrics of varying specifications and varieties, and flexibly adjust production plans (e.g., switching varieties and adjusting output). Combined with intelligent resource allocation, this enables efficient coordination of small-batch, multi-variety production, enhancing the company's adaptability to market fluctuations and improving the timeliness and accuracy of order delivery. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A diagram showing the steps of the method of the present invention;

[0025] Figure 2 The present invention Figure 1 Detailed step diagram of S1. DETAILED DESCRIPTION

[0026] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0027] One embodiment of the present invention, as Figure 1 As shown, the method includes:

[0028] S1. Deploy various types of sensors at key nodes of the polyester fabric production line to collect various physical parameters and environmental information related to polyester fabric production in real time. At the same time, integrate the operating status monitoring system of production equipment to obtain equipment data. Initially integrate the data from different sensors and equipment monitoring systems to build a holographic perception architecture for polyester fabric production.

[0029] S2. Perform deep fusion processing on multi-source heterogeneous data obtained from the polyester fabric production holographic perception architecture; construct a data association model; based on this model, conduct a comprehensive assessment of the production situation in combination with the polyester fabric production process and quality standards; and generate a production situation assessment report based on the production situation assessment.

[0030] S3. Collect historical multi-dimensional data on polyester fabrics; use machine learning algorithms to train and learn the multi-dimensional data to build a dynamic production demand forecasting model; compare and analyze the dynamic production demand forecast results with the current production plan to identify potential production gaps or surpluses;

[0031] S4. Based on the dynamic production demand forecast results and production situation assessment report, combined with the process knowledge of polyester fabric production, the production process parameters are adaptively optimized using intelligent optimization algorithms. During the optimization process, the quality indicators and equipment operating status of the production process are monitored in real time, and the optimization strategy is adjusted in a timely manner based on the feedback information.

[0032] S5. During the polyester fabric production process, each batch of products is assigned a unique identification code, and all relevant data from the production process is associated and stored with the identification code. A real-time quality traceability system is established to query the entire life cycle information of a batch of products by scanning the identification code. At the same time, historical quality data is analyzed using data mining and machine learning techniques to establish a quality defect early warning model.

[0033] S6. Comprehensively consider the dynamic prediction results of production demand, production situation assessment reports, process parameter optimization results, quality traceability and defect warning information, and use operations research and intelligent scheduling algorithms to intelligently allocate production resources.

[0034] The working principle of the above technical solution is as follows: various types of sensors are deployed at various key nodes of the polyester fabric production line, such as the raw material storage area, spinning workshop, weaving section, printing and dyeing area, and finished product packaging line; including but not limited to temperature sensors, humidity sensors, pressure sensors, tension sensors, color sensors, and weight sensors, etc., to collect various physical parameters and environmental information related to polyester fabric production in real time; at the same time, the operation status monitoring system of the production equipment is integrated to obtain data such as the equipment's speed, power, and operating time; these data from different sensors and equipment monitoring systems are preliminarily integrated to build a holographic perception architecture for polyester fabric production; this architecture takes data flow as the core, connects various data sources into an organic whole, and provides comprehensive and accurate basic data for subsequent data analysis and processing;

[0035] The multi-source heterogeneous data acquired from the holographic perception architecture for polyester fabric production is deeply fused and processed. Data cleaning techniques are used to remove noise and outliers, and data standardization methods are used to unify data of different dimensions to the same scale. Then, a data association analysis algorithm is used to explore potential relationships between the data and construct a data association model. Based on this model, combined with the polyester fabric production process and quality standards, a comprehensive production status assessment is conducted. The assessment includes whether the production progress is normal, whether the equipment is operating stably, and whether the product quality meets the requirements. The production status assessment report is generated through intuitive charts and detailed data analysis to display the overall status of the current polyester fabric production, providing strong support for production decision-making.

[0036] Collect multi-dimensional data such as historical polyester fabric production data, market sales data, industry dynamics, and seasonal factors. Utilize machine learning algorithms to train and learn from this multi-dimensional data to construct a dynamic production demand forecasting model. This model automatically adjusts forecast parameters based on real-time input data to accurately predict polyester fabric production demand over the next period of time. The forecast results include information such as production requirements and delivery deadlines for polyester fabrics of different specifications and varieties. Compare and analyze the dynamic production demand forecast results with the current production plan to promptly identify potential production gaps or surpluses, providing a basis for adjusting the production plan.

[0037] Based on the dynamic forecast results of production demand and the production situation assessment report, combined with the process knowledge and expert experience of polyester fabric production, the production process parameters are adaptively optimized using intelligent optimization algorithms. The optimal parameter combination is found through simulation and actual production tests for parameters such as temperature, pressure, and speed in the spinning process; parameters such as warp and weft density and tension control in the weaving process; and parameters such as dye concentration, temperature, and time in the printing and dyeing process. During the optimization process, the quality indicators and equipment operating status of the production process are monitored in real time, and the optimization strategy is adjusted promptly based on feedback information. The optimized process parameters are transmitted to the production equipment control system to achieve automatic adjustment and precise control of the process parameters, thereby improving the production quality and production efficiency of polyester fabric.

[0038] During the polyester fabric production process, each batch of products is assigned a unique identification code, and all relevant data in the production process, such as raw material information, process parameters, equipment operation data, quality inspection data, etc., are associated and stored with the identification code; a real-time quality traceability system is established, and by scanning the identification code, the entire life cycle information of the batch of products can be quickly queried; at the same time, data mining and machine learning technologies are used to analyze historical quality data and establish a quality defect early warning model; this model can monitor the quality indicators of the production process in real time, and when it is detected that the quality indicators deviate from the normal range, it will promptly issue an early warning signal and point out the possible types of quality defects and their causes. Production management personnel can quickly take measures to adjust and improve based on the early warning information to avoid the expansion of quality problems;

[0039] By comprehensively considering dynamic production demand forecasts, production status assessment reports, process parameter optimization results, and quality traceability and defect warning information, operations research and intelligent scheduling algorithms are used to intelligently allocate production resources. Production resources include raw materials, production equipment, and human resources. Based on the priority and urgency of production tasks, the system rationally arranges raw material supply plans, optimizes production equipment scheduling, and allocates human resources positions. Through intelligent allocation of production resources, efficient coordination of the production process is achieved, resource utilization is improved, and production costs are reduced. Furthermore, a production collaborative optimization mechanism is established to strengthen information communication and coordination between various production links to ensure the smooth progress of the entire polyester fabric production process.

[0040] The effect of this technical solution is that, by deploying a variety of sensors and equipment monitoring systems, various data from the production process are collected in real time, ensuring comprehensive monitoring of key production links and providing accurate, real-time basic data for subsequent data analysis and processing. This significantly reduces human intervention and delays in the production process, thereby improving production efficiency.

[0041] Leveraging deep fusion processing and data correlation analysis algorithms, we can comprehensively assess production trends and promptly identify potential issues, such as production delays and unstable equipment operation, effectively mitigating risks that may arise during the production process. Furthermore, the quality defect early warning system helps to promptly identify quality issues, avoiding rework and waste later in production.

[0042] Using machine learning algorithms to establish a dynamic production demand forecasting model and intelligent optimization algorithms, we can accurately predict future production needs and automatically adjust production process parameters. This enables more precise production planning and adjustments, reducing unnecessary losses and overproduction during the production process. During the production process, real-time monitoring of quality indicators and optimization adjustments based on feedback have effectively improved the quality of polyester fabrics. Furthermore, the establishment of a quality traceability system ensures complete quality information for each batch of products, allowing any quality issues to be quickly identified and addressed, further ensuring product consistency and stability.

[0043] Through intelligent scheduling algorithms and the optimal allocation of production resources, we rationally arrange raw material supply, production equipment utilization, and human resource allocation, reducing resource waste and lowering production costs. Furthermore, efficient coordination within the production process further improves resource utilization and avoids redundant resource waste. By combining historical data, real-time data, and external factors, the system can rapidly respond to changes in market demand and adjustments to the production environment, making production more flexible and efficient, enabling rapid response to emergencies and meeting market demands.

[0044] In one embodiment of the present invention, the S1 includes:

[0045] S11. Conduct surveys and analyses at key nodes of the polyester fabric production line and determine the type of sensors to be deployed based on the production characteristics and monitoring requirements of each node.

[0046] S12. Install and debug the sensors according to the selected sensor types and deployment locations. At the same time, configure data acquisition equipment to convert the analog signals collected by the sensors into digital signals and perform preliminary storage and processing.

[0047] S13, integrated production equipment operation status monitoring system, through equipment monitoring technology, to obtain key equipment data; using industrial Ethernet to seamlessly connect the equipment monitoring system with the data acquisition network, synchronously transmit equipment operation data and sensor collection data;

[0048] S14. Conduct preliminary integration of data collected from different sensors and equipment monitoring systems, use data fusion technology to correlate and match data from multiple data sources, and eliminate data redundancy and conflict; build a holographic perception architecture for polyester fabric production, and connect various data sources into an organic whole.

[0049] The working principle of the above technical solution is as follows: Detailed survey and analysis are carried out at each key node of the polyester fabric production line, such as the raw material storage area, spinning workshop, weaving section, printing and dyeing area, and finished product packaging line; and the type of sensor to be deployed is determined based on the production characteristics and monitoring requirements of each node; for example, in the raw material storage area, temperature and humidity sensors are deployed to monitor the temperature and humidity of the raw material storage environment to prevent the raw materials from getting damp or deteriorating; in the spinning workshop, temperature sensors, pressure sensors, and tension sensors are installed to monitor the temperature, pressure, and fiber tension during the spinning process, respectively, to ensure stable spinning quality; in the weaving section, warp and weft density sensors and tension sensors are installed to monitor the warp and weft density and tension of the fabric in real time; in the printing and dyeing area, color sensors and temperature sensors are installed to accurately control the color of the dye and the printing and dyeing temperature; and in the finished product packaging line, weight sensors are used to ensure the accuracy of the finished product packaging weight.

[0050] Install and debug sensors according to the selected sensor type and deployment location; ensure that sensors are securely installed and accurately positioned to stably and reliably collect data; configure data acquisition equipment to convert analog signals collected by sensors into digital signals and perform preliminary storage and processing; establish a data acquisition network to ensure that data from each sensor can be transmitted to the data processing center in real time and accurately;

[0051] The integrated production equipment operation status monitoring system uses equipment monitoring technology to obtain key data such as equipment speed, power, and operating time. The equipment monitoring system is seamlessly connected to the data acquisition network using industrial Ethernet, and equipment operation data and sensor data are synchronously transmitted.

[0052] The data collected from different sensors and equipment monitoring systems will be preliminarily integrated, and data fusion technology will be used to correlate and match data from multiple data sources to eliminate data redundancy and conflict; a holographic perception architecture for polyester fabric production will be constructed, which takes data flow as the core and connects various data sources into an organic whole.

[0053] The benefits of this technical solution include real-time monitoring of every aspect of the production process, ensuring that each step is performed optimally. This significantly reduces production delays and improves overall efficiency. The integration of sensors and equipment monitoring systems enables real-time identification of potential equipment failures or production schedule issues, enabling timely intervention and reducing potential production risks.

[0054] Leveraging machine learning and data analytics, production demand is predicted and process parameters are automatically adjusted. This improves the accuracy of production decisions and makes the production process more intelligent and adaptive. By monitoring quality indicators throughout the production process in real time and making adjustments based on feedback, we ensure that product quality meets standards at every stage, reducing defects.

[0055] By optimizing resource allocation and scheduling, unnecessary resource waste is reduced, while the collaborative efficiency of the production process is improved, significantly reducing production costs. The system can quickly respond to changes in market demand and production environment adjustments, enhancing production flexibility and enabling rapid response to emergencies and meeting changing market demands.

[0056] In one embodiment of the present invention, the S14 includes:

[0057] S141. Pre-process all types of collected raw data, apply data mining and association analysis techniques to deeply analyze the inherent connections between different data sources; establish a data association model based on the logical relationship of the production process and the collaborative working principle between equipment;

[0058] S142. Use a data fusion algorithm to conduct in-depth analysis on the associated and matched data; at the same time, process conflicting data from different data sources according to preset rules and priorities;

[0059] S143. Based on the processed data, a data fusion model for polyester fabric production is constructed; the data is fused and optimized;

[0060] S144. With the fused data stream as the core, a holographic perception architecture for polyester fabric production is constructed; it is connected into an organic whole through data interfaces and network protocols to carry out real-time data sharing and interaction.

[0061] The working principle of the above technical solution is as follows: pre-processing the various types of collected raw data, using data mining and association analysis techniques to deeply analyze the inherent connections between different data sources; establishing a data association model based on the logical relationship of the production process and the collaborative working principles between equipment; using this model, accurately matching data from different sensors and equipment monitoring systems to determine their corresponding relationships in time and space. For example, the temperature, pressure, and tension data of the spinning workshop can be associated with the equipment operating parameters at the corresponding time point to comprehensively analyze the impact of various factors in the production process on product quality;

[0062] Use data fusion algorithms to conduct in-depth analysis of the associated and matched data; identify and eliminate redundant information in the data, avoid repeated calculations and storage, and improve data processing efficiency; at the same time, process conflicting data from different data sources according to preset rules and priorities; for example, when multiple sensors measure the same physical quantity and the measurement results differ, the final data value to be used is determined based on factors such as the accuracy and reliability of the sensors;

[0063] Based on the processed data, a data fusion model for polyester fabric production was constructed. This model comprehensively considers various variables and factors in the production process and uses advanced algorithms such as machine learning and deep learning to fuse and optimize the data. By continuously training and adjusting model parameters, the model's ability to simulate and predict the production process is improved, providing more accurate and comprehensive data support for production decision-making. For example, the data fusion model can be used to predict the quality indicators of polyester fabric, identify potential quality issues in advance, and adjust production parameters in a timely manner.

[0064] A holographic perception architecture for polyester fabric production is constructed, centered around fused data streams. This architecture connects various data sources, including sensors and equipment monitoring systems, into an organic whole through data interfaces and network protocols, enabling real-time data sharing and interaction. This allows production managers to gain a global, real-time understanding of the status and information of every step in the production process. Furthermore, this architecture is scalable and flexible, enabling easy integration of new data sources and equipment to accommodate the continuous development and innovation of polyester fabric production technology. For example, when introducing new production equipment or monitoring technology, simply configure and integrate it into the holographic perception architecture to enable the collection and analysis of new data.

[0065] The above technical solution achieves the following results: through data fusion and preprocessing, redundant data generation is reduced, data storage and processing processes are optimized, and overall data processing efficiency is improved. By using pre-set rules and priorities to process conflicting data, errors caused by inconsistent data are effectively eliminated, ensuring data accuracy and reliability.

[0066] By building a data fusion model and combining it with machine learning and deep learning technologies, we can more accurately simulate and predict quality indicators throughout the production process, proactively identify potential issues, and reduce the occurrence of quality defects. Based on the fused data stream, production managers can gain a global, real-time understanding of production status, providing more accurate and comprehensive data support for production decisions, improving the scientific nature and efficiency of decision-making.

[0067] Automated data processing and intelligent production monitoring reduce the need for human intervention and mitigate production risks caused by human error. The holographic perception architecture offers excellent scalability and flexibility, enabling rapid adaptation to technology updates and equipment introductions while maintaining efficient system operation. This enhances production process flexibility and the ability to respond to emergencies. With technological advancements and the continuous optimization of data fusion models, production systems will become increasingly intelligent, capable of automatically adjusting and optimizing production processes, thereby achieving a more efficient and environmentally friendly production model.

[0068] In one embodiment of the present invention, the step S142 includes:

[0069] Calculate various statistical indicators for the matched data and identify highly correlated data by analyzing the statistical correlation between different data sequences. Combined with the professional knowledge base in the production field, perform semantic analysis on the data to determine whether there is semantically duplicated data.

[0070] For time series data, analyze its changing trends and cyclical characteristics. If multiple data series show similar changing trends and cyclical patterns within the same time interval, and this similarity exceeds a reasonable error range, it is determined to be redundant data. For redundant data that is statistically related or semantically repeated, use data aggregation methods to process it. Select aggregation functions based on the type and characteristics of the data, and use data sampling methods to eliminate redundant data in the time series. Determine the sampling interval based on the frequency and importance of the data changes.

[0071] Utilize the established data association model and prediction algorithm to predict and replace redundant data; establish a prediction model by analyzing the changing patterns of historical data and current data, and use the predicted values ​​to replace some redundant data;

[0072] After correlation and matching, the data is checked for consistency across different data sources. Conflicting data is identified by comparing data attributes. Conflict determination rules are developed based on the business rules and process requirements for polyester fabric production. Normal and abnormal data patterns are established using historical data. Data that does not conform to normal patterns is identified by comparing current data with historical data patterns, and is then determined to be conflicting data.

[0073] Evaluate the data sources of conflicting data and prioritize the timeliness of the data; prioritize the business importance of the data based on its importance to the polyester fabric production business; use machine learning algorithms to fuse and process the conflicting data; collect a large amount of historical conflict data and the corresponding correct processing results to build a training data set;

[0074] The training data set is trained through a neural network so that the model can learn the processing mode of conflicting data; when new conflicting data appears, the data is input into the trained model to obtain the fused result.

[0075] The working principle of the above technical solution is as follows: for the data after association matching, various statistical indicators such as mean, variance, covariance, etc. are calculated; by analyzing the statistical correlation between different data sequences, highly correlated data are identified; for example, in polyester cloth production, if the data collected by temperature sensors at two different positions show almost the same mean and very small variance difference over a long period of time, and the covariance is close to the variance value, it can be preliminarily determined that the two sets of data are redundant; combined with the professional knowledge base in the production field, the data is analyzed at the semantic level; considering the actual meaning of the data and the logical relationship in the production process, it is determined whether there is semantically repeated data; for example, when describing the operating status of the equipment, "normal operation" and "fault-free operation of the equipment" are semantically highly similar. If they appear at the same time in the data and are used to express the status of the same equipment, they can be considered as redundant information.

[0076] For time series data, analyze its changing trends and cyclical characteristics. If multiple data series exhibit similar changing trends and cyclical patterns within the same time interval, and this similarity exceeds a reasonable error range, it is considered redundant data. For example, when monitoring tension changes in polyester fabric production, if the tension data of two adjacent workstations show nearly synchronized rising and falling trends over multiple production cycles, redundancy can be considered. For statistically relevant or semantically repetitive redundant data, data aggregation methods are used to process it. Aggregation functions such as sum, average, maximum, and minimum are selected based on the type and characteristics of the data. For example, for redundant temperature data collected by multiple temperature sensors, the average value can be calculated as the representative temperature of the area, thereby reducing the data volume and retaining key information. For redundant data in time series, data sampling methods are used to eliminate it. The sampling interval is determined based on the frequency and importance of the data changes. For data that changes slowly and has little impact on production, the sampling interval can be appropriately increased; for data that changes frequently and is critical, the sampling interval can be kept smaller. For example, when monitoring the vibration data of polyester fabric production equipment, if the vibration changes are relatively stable under normal operation, a larger sampling interval can be used; when the equipment experiences abnormal vibration, the sampling interval can be immediately reduced to obtain more detailed data.

[0077] The established data association model and prediction algorithm are used to predict and replace redundant data. By analyzing the changing patterns of historical and current data, a prediction model is established, and the predicted values ​​are used to replace some redundant data, reducing the storage and calculation of actual data. For example, when predicting a process parameter in the polyester fabric production process, the prediction model is used to calculate the predicted value at the current time point based on the data of previous time points and known production conditions. If the error between the predicted value and the actual collected data is within the allowable range, the predicted value can be used to replace the actual data.

[0078] After the correlation and matching, check the consistency between different data sources; obtain the existing conflicting data by comparing the data's value range, unit, precision and other attributes; for example, in polyester fabric production, different equipment monitoring systems may have different measurement units for the same production parameter (such as spinning speed). If a unified conversion is not performed, data conflicts will occur; formulate conflict judgment rules based on the business rules and process requirements of polyester fabric production; for example, according to production process regulations, the temperature in the spinning process should fluctuate within a certain range. If the temperature data collected by a sensor exceeds this range and is inconsistent with other related data (such as heating power, cooling water flow, etc.), it can be determined as conflicting data; use historical data to establish normal data patterns and abnormal data patterns; by comparing current data with historical data patterns, find data that does not conform to the normal pattern and determine whether it is conflicting data; for example, analyze the equipment operating parameters and product quality data in the polyester fabric production process over the past period of time, and establish a data distribution range and correlation model under the normal production mode. When the current data deviates from the model, further analyze whether it is conflicting data;

[0079] Evaluate the data sources of conflicting data and prioritize data accuracy based on factors such as the accuracy, reliability, and calibration of the data acquisition equipment. Prioritize data from highly accurate data sources and discard or revise data from less accurate sources. For example, in polyester fabric production, if data collected by a regularly calibrated, high-precision sensor conflicts with data collected by an uncalibrated, low-precision sensor, the data from the high-precision sensor will be prioritized. Prioritize data timeliness based on data collection time and update frequency. For production processes with high real-time requirements, prioritize the most recently collected data. For example, when monitoring the real-time operating status of polyester fabric production equipment, if conflicting data is provided by two data sources, prioritize the most recently collected data to ensure timely and accurate production decisions. Prioritize data by business importance based on its importance to the polyester fabric production business. Prioritize data that impacts product quality, production safety, and key production indicators. For example, when controlling the fiber fineness of polyester fabric, process parameter data related to fiber fineness (such as spinneret aperture and melt temperature) has a higher business importance and should be given priority when processing conflicting data. For data that is conflicting but of equal importance, a weighted average fusion method is used for processing. Based on factors such as data accuracy, timeliness, and business importance, a corresponding weight is assigned to each data source, and the weighted average is calculated as the fused data. For example, when fusing polyester fabric thickness data collected by two different sensors, if the accuracy, timeliness, and business importance of the two sensors are similar, they can be assigned the same weight based on the actual situation, and the weighted average is calculated as the final thickness data. For complex conflicting data, the knowledge and reasoning capabilities of the expert system are utilized to process it. An expert system is established to encode the expert knowledge and experience of polyester fabric production into rules. When conflicting data arises, the expert system makes inferences and judgments based on the rules, selects the most appropriate data, or provides fusion suggestions. For example, when dealing with conflicts between multiple process parameters in the polyester fabric production process, the expert system can analyze the mutual influence between the parameters based on production process rules and historical experience to determine the optimal parameter combination; use machine learning algorithms to fuse the conflicting data; collect a large amount of historical conflict data and the corresponding correct processing results to build a training data set;

[0080] By training a training data set through a neural network, the model learns how to handle conflicting data. When new conflicting data emerges, it is fed into the trained model to generate a fused result. For example, a neural network model can be used to fuse equipment fault diagnosis data from polyester fabric production, improving the accuracy and reliability of fault diagnosis.

[0081] The above technical solution effectively reduces the storage and computational complexity of redundant data, optimizes data processing, and improves the efficiency of data analysis during production by performing statistical analysis, aggregation, sampling, and prediction on the associated and matched data. By analyzing data relevance and semantic duplication, redundant data can be identified and eliminated, ensuring data accuracy and conciseness. Furthermore, by assessing the accuracy, timeliness, and business importance of data sources, the negative impact of conflicting data on decision-making processes can be reduced.

[0082] When processing redundant and conflicting data, we prioritize high-precision, timely, and business-critical data sources to ensure more accurate and reliable final data. Furthermore, by combining the processing power of machine learning and expert systems, we can intelligently fuse conflicting data, improving the accuracy and reliability of the final results.

[0083] By establishing data association models and prediction algorithms, redundant data can be predicted and replaced, providing timely information during actual production, supporting real-time decision-making and optimizing operations, improving production efficiency and product quality. Leveraging statistical analysis and machine learning models, we can better identify abnormal data in production, reduce uncertainty caused by data conflicts, redundancy, or errors, and enhance production stability.

[0084] Expert systems and machine learning models enable intelligent data analysis and processing, improving the intelligence of production processes, enabling automated management, reducing manual intervention, and minimizing human error. Combining semantic analysis with business rules ensures that data is not only statistically accurate but also effectively interpreted from a business and production perspective, providing valuable information support for production decision-making. Trend analysis and identification of cyclical characteristics in time series data can help identify optimization opportunities for equipment and processes, reduce equipment failures and process instability, and further improve production efficiency and quality.

[0085] In one embodiment of the present invention, the S2 includes:

[0086] S21. Deeply clean the multi-source heterogeneous data obtained from the polyester fabric production holographic perception architecture; identify and remove noise data and outliers through machine learning algorithms;

[0087] S22. Use data standardization methods to unify data of different dimensions to the same scale; through data standardization, eliminate the dimensional differences between different data;

[0088] S23. Use data association analysis algorithms to mine potential relationships between data, and use association rule mining to find the intrinsic connections between data in different production links; build a data association model;

[0089] S24. Based on the constructed data association model, the production situation is evaluated in combination with the process flow and quality standards of polyester fabric production. Various data in the production process are monitored and analyzed in real time using preset evaluation indicators and thresholds.

[0090] S25. When the data exceeds the normal range, an early warning signal is issued; based on the production situation assessment results, a production situation assessment report is generated.

[0091] The working principle of the above technical solution is as follows: deep cleaning of multi-source heterogeneous data obtained from the holographic perception architecture of polyester fabric production; identification and removal of noise data and outliers through machine learning algorithms; for example, using methods such as mean filtering and median filtering to smooth the continuous data collected by sensors, removing abnormal data points caused by sensor failure or external interference; at the same time, missing value processing is performed on the data, and missing data is filled using methods such as interpolation and mean substitution to ensure data integrity and accuracy;

[0092] Use data standardization methods to unify data of different dimensions to the same scale; through data standardization, eliminate the dimensional differences between different data;

[0093] Data association analysis algorithms are used to explore potential relationships between data, and association rule mining is used to identify the inherent connections between data in different production links. For example, a data association model can be constructed by analyzing the relationship between temperature and pressure parameters in the spinning process and warp and weft density and tension parameters in the weaving section.

[0094] Based on the constructed data association model, combined with the process flow and quality standards of polyester fabric production, the production situation is evaluated. The evaluation content includes whether the production progress is normal, whether the equipment operation is stable, and whether the product quality meets the requirements. Through the preset evaluation indicators and thresholds, various data in the production process are monitored and analyzed in real time.

[0095] When the data exceeds the normal range, an early warning signal is issued; based on the production situation assessment results, a production situation assessment report is generated. The report uses intuitive charts and detailed data analysis to show the overall status of current polyester fabric production, providing strong support for production decisions.

[0096] The effectiveness of this technical solution is: by deeply cleaning multi-source heterogeneous data and using methods such as mean and median filtering to remove noise and outliers, data accuracy is ensured, providing high-quality data support for subsequent analysis and decision-making. By smoothing the continuous data collected by sensors, the impact of abnormal data points caused by equipment failures or external interference is reduced, thereby reducing the interference of these abnormal data on analysis results.

[0097] By filling missing values ​​and standardizing data, we ensure data consistency across different levels and dimensions, avoiding analytical errors caused by missing data or dimensional differences, and enhancing data comparability and stability. Building a data association model using data association analysis algorithms can deeply explore the inherent connections between different production links, making each link in the production process more transparent and helping production managers understand the interactions and impacts between them.

[0098] By monitoring and evaluating production status in real time, including production progress, equipment operating status, and product quality, potential issues can be promptly identified and effective measures can be taken, mitigating potential risks in the production process. Based on the constructed correlation models and assessment reports, managers can gain a clearer understanding of production status and make more scientific and accurate production decisions based on intuitive charts and data analysis.

[0099] Through real-time data monitoring and early warning mechanisms, anomalies can be detected and remedial measures can be taken promptly during the production process, ensuring smooth production processes, reducing downtime, optimizing resource allocation, and improving overall production efficiency. Automated data processing and evaluation reduce the need for manual intervention, lower the incidence of human error, and improve the level of automation in production management.

[0100] Real-time monitoring and data analysis of the production process effectively monitors product quality, ensuring that polyester fabrics meet quality standards and enhancing the accuracy and timeliness of quality control. Refined data processing and analysis enable rapid response to changes in the production process, providing greater flexibility and adaptability, helping production lines adjust and optimize to meet diverse needs.

[0101] In one embodiment of the present invention, the step S23 includes:

[0102] Conduct preliminary exploratory analysis on the cleaned and standardized data; quantify the degree of linear correlation between the data from a numerical perspective;

[0103] According to the characteristics and analysis requirements of polyester fabric production data, an association rule mining algorithm is selected; the optimized association rule mining algorithm is used to mine frequent item sets in polyester fabric production data;

[0104] Based on the mined frequent item sets, association rules are generated; and the generated association rule model is verified. The data set is divided into a training set and a test set using the cross-validation method. Association rules are generated on the training set, and then the validity of these rules is verified on the test set.

[0105] Calculate validation indicators to evaluate the model's performance on unknown data; if the model performance does not meet the preset requirements, analyze the reasons and adjust the algorithm parameters or reselect the algorithm for optimization.

[0106] The working principle of the above technical solution is as follows: before formally applying complex algorithms to mine data associations, a preliminary exploratory analysis is first conducted on the cleaned and standardized data; by drawing a data scatter plot matrix, the relationship between the data of different production links is intuitively presented, for example, observing the distribution trend of the spinning temperature and weaving tension data points in the graph, and judging whether there are preliminary characteristics such as linear, nonlinear or no obvious correlation; at the same time, simple correlation coefficients such as the Pearson correlation coefficient and the Spearman rank correlation coefficient are calculated between the data, quantifying the degree of linear correlation between the data from a numerical perspective, quickly locating data pairs that may have correlations, and providing directional guidance for subsequent in-depth mining; for example, if the absolute value of the correlation coefficient between spinning pressure and printing and dyeing color deviation is found to be large, it can be listed as a key correlation analysis object;

[0107] The association rule mining algorithm was selected based on the characteristics and analysis requirements of polyester fabric production data. For example, the classic Apriori algorithm is suitable for small datasets with simple rules and can efficiently identify frequent itemsets and association rules. The FP-Growth algorithm, on the other hand, is more efficient when processing large datasets, reducing the number of database scans by constructing an FP tree. Considering the multidimensional, massive, and complex nature of polyester fabric production data, the selected algorithm can be optimized. For example, the Apriori algorithm can be improved by using parallel computing technology to partition the dataset into multiple subsets. Frequent itemsets are then mined in parallel on different computing nodes, and the results are finally merged, greatly improving the algorithm's operational efficiency. The optimized association rule mining algorithm was then used to mine frequent itemsets in the polyester fabric production data. A minimum support threshold was set, representing the minimum proportion of an itemset that appears in the total data. Only itemsets that meet the minimum support requirement are considered frequent itemsets. For example, when analyzing data from the spinning workshop and weaving section, with a minimum support of 0.1, the algorithm will identify combinations of production parameters that appear simultaneously in at least 10% of the data records, such as (spinning temperature above a threshold, weaving warp and weft density within a specific range). These frequent item sets reflect the frequent co-occurrence of data from different production links and form the basis for constructing association rules.

[0108] Based on the mined frequent item sets, association rules are generated; the form of the association rule is "if A, then B," where A and B are different production parameters or events. Metrics such as support, confidence, and lift are calculated for each association rule. Support indicates the frequency with which A and B appear simultaneously; confidence indicates the probability of B appearing given the presence of A; and lift measures the effectiveness of the rule; a lift greater than 1 indicates a positive correlation between A and B. Based on preset confidence and lift thresholds, meaningful association rules are screened. For example, setting the confidence to 0.7 and the lift to 1.2, association rules such as "If the spinning pressure exceeds the standard value, the probability of an increase in the number of fiber breakages during weaving is greater than 70%, and this rule effectively reflects the relationship between the two" are screened. The generated association rule model is then validated to ensure its accuracy and reliability. Using a cross-validation method, the dataset is divided into a training set and a test set. Association rules are generated on the training set and then validated on the test set.

[0109] Calculate validation metrics, such as rule accuracy and recall, to evaluate the model's performance on unknown data. If model performance falls short of expectations, analyze the cause and adjust algorithm parameters or reselect an algorithm for optimization. For example, if the accuracy of an association rule on a test set is low, increase the minimum support threshold, reduce the number of frequent itemsets, and improve the quality of the rule. Alternatively, try using a different association rule mining algorithm, such as the Eclat algorithm, to rebuild the association model.

[0110] The benefits of this technical solution are: by conducting exploratory data analysis before formal algorithm application, relationships between production data can be visually observed, thereby discovering potential correlation patterns and providing greater accuracy and direction for subsequent in-depth analysis. Preliminary exploratory data analysis, such as calculating correlation coefficients and drawing scatter plots, can quickly identify potential correlated data pairs, thus reducing the amount of complex data that requires further exploration.

[0111] By optimizing the Apriori algorithm, employing parallel computing technology, and effectively utilizing the FP-Growth algorithm, data processing and mining efficiency can be significantly improved. This is particularly true for large, complex datasets, where the optimized algorithm can more quickly find frequent itemsets. By precisely setting metrics such as minimum support, confidence, and lift, meaningful association rules can be screened from large amounts of data, thereby improving the accuracy of data association analysis and ensuring that the mined rules have practical application value.

[0112] By calculating validation metrics such as support, confidence, and lift within the generated association rules, unreliable or invalid rules can be screened out, reducing the probability of incorrect rules being adopted. Leveraging the mined, valid association rules, managers can optimize production processes based on these rules, thereby improving the scientific nature and reliability of decision-making and ensuring the effectiveness of optimization plans for each production link.

[0113] By using cross-validation to divide the dataset into training and test sets, and then verifying the accuracy of the model on different datasets, we can ensure that the generated association rules are more robust and avoid the risk of overfitting. During the validation process, if the model performance does not meet expectations, we can quickly optimize it by adjusting the algorithm parameters or selecting a more appropriate algorithm, such as the Eclat algorithm, reducing the complexity of rebuilding the model.

[0114] By uncovering patterns in data association analysis, production managers can flexibly adjust production parameters, such as spinning temperature and weaving tension, to optimize the production process and enhance the flexibility and adaptability of the production line. By mining and applying practical and effective association rules, production parameters can be precisely adjusted to reduce the number of substandard products, thereby improving product quality control and reducing quality fluctuations during the production process.

[0115] In one embodiment of the present invention, S3 includes:

[0116] S31. Obtain multi-dimensional data of historical polyester fabrics, and use a machine learning algorithm to train and learn the multi-dimensional data;

[0117] S32. Divide historical data into training sets and test sets, continuously adjust the parameters and structure of the model, build a dynamic production demand forecasting model, automatically adjust the forecasting parameters based on real-time input data, and forecast the production demand of polyester fabric in the future;

[0118] S33. Compare and analyze the dynamic forecast results of production demand with the current production plan; calculate the difference between the forecast demand and the production plan by establishing a comparative analysis model, and adjust the production plan based on the comparative analysis results.

[0119] The above technical solution works by collecting multi-dimensional historical polyester fabric data, including time (such as polyester fabric demand by season and month), market factors (including market demand trends, competitor dynamics, and changes in consumer preferences), price information (raw material price fluctuations and polyester fabric finished product price trends), production-related data (such as historical production volume, production efficiency, equipment operating conditions), and other factors that may affect polyester fabric production demand. Machine learning algorithms are then used to train and learn from this collected multi-dimensional historical data. Machine learning algorithms automatically discover potential patterns, regularities, and relationships in the data. By continuously adjusting the algorithm's internal parameters, the model can accurately fit the characteristics reflected in the historical data. This allows the model to understand and analyze data related to polyester fabric production demand, laying the foundation for subsequent forecasting.

[0120] The collected historical data is divided into training and test sets according to a specific ratio (e.g., 70%-30% or 80%-20% are common). The training set is used to train the machine learning model, allowing it to learn patterns and regularities in the data; the test set is used to evaluate the model's performance on unseen data and verify its generalization ability. During the training process, the model's parameters and structure are continuously adjusted. Parameter adjustment aims to optimize the model's internal numerical settings to better fit the data; structural adjustment may involve changing the model's hierarchy or number of nodes to find the most optimal model architecture for polyester fabric production demand forecasting. Through repeated iterative training and adjustment, a dynamic production demand forecasting model is constructed. This model has the ability to automatically adjust its forecast parameters based on real-time input data. When new real-time data (such as the latest market trends or production data) is input, the model can quickly respond, using this new data to update and optimize the forecast parameters, thereby accurately forecasting polyester fabric production demand for a period of time. This dynamic adjustment mechanism enables the model to adapt to the ever-changing market environment and production conditions, improving the timeliness and accuracy of forecasts.

[0121] The forecast results from the dynamic production demand forecasting model are compared and analyzed with the current production plan. By establishing a specialized comparative analysis model and applying specific algorithms and rules, the discrepancy between the forecasted demand and the production plan is calculated. This discrepancy can manifest in multiple aspects, such as production quantity, production schedule, and product variety, intuitively reflecting the degree of mismatch between the current production plan and the market demand forecast. Based on the results of this comparative analysis, targeted adjustments to the production plan can be made. If the forecasted demand exceeds the current production plan, production volume may need to be increased, production schedules may need to be advanced, or product variety may need to be adjusted to meet market demand. Conversely, if the forecasted demand falls below the current production plan, production volume may need to be reduced, production resource allocation may need to be optimized, or the production cadence may need to be adjusted to avoid inventory backlogs and resource waste. This dynamic adjustment mechanism, based on data forecasts, can ensure that production plans are more aligned with market demand, improving the company's production efficiency and economic benefits.

[0122] The effect of this technical solution is that by using machine learning algorithms to train historical polyester fabric data, a more accurate dynamic production demand forecasting model can be constructed, improving the accuracy of future production demand forecasts and thus better meeting market demand. By dividing historical data into training and test sets and continuously adjusting the model's parameters and structure, the discrepancy between production demand forecasts and actual production plans can be reduced, thereby reducing the risk of planning errors and resource waste.

[0123] By adjusting the parameters of the forecasting model in real time, production demand forecasts can be dynamically adjusted based on the latest input data, thereby enhancing the flexibility and adaptability of production plans and ensuring that they can respond to changes in market demand at any time. By establishing a comparative analysis model, the discrepancy between forecasted demand and production plans can be monitored in real time, potential problems in production scheduling can be promptly identified, and adjustments can be made quickly, improving the efficiency and responsiveness of production scheduling.

[0124] Accurate production demand forecasting and production plan adjustments can optimize resource allocation, reduce unnecessary waste in the production process, and lower the consumption of resources such as raw materials, labor, and time. Accurate production demand forecasting and dynamically adjusted production plans enable companies to better meet customer needs in an ever-changing market environment, thereby enhancing their market competitiveness and customer satisfaction.

[0125] By comparing and analyzing the discrepancies between forecasted demand and production plans, decision makers can be provided with data-driven support, ensuring that production plan adjustments are based on reliable data analysis, thereby improving the scientific nature and accuracy of decision-making. By optimizing production plans and resource allocation, additional costs caused by overproduction or underproduction can be reduced, thereby lowering overall production costs.

[0126] By continuously monitoring the discrepancy between forecasts and actual demand, production schedules and quality can be better controlled, enhancing the controllability and stability of the production process. By adjusting production demand forecasts and plans in real time, companies can respond more quickly to market fluctuations, ensuring timely adjustments to production lines and improving their responsiveness to external changes.

[0127] In one embodiment of the present invention, the S4 includes:

[0128] S41. Acquire process knowledge of polyester fabric production through web crawlers, and obtain experience and skills in the production process through expert knowledge bases; integrate process knowledge, experience and skills to form a complete knowledge base for production process parameter optimization;

[0129] S42. Select an intelligent optimization algorithm based on the characteristics of polyester fabric production and the goal of process parameter optimization, and perform adaptive optimization of production process parameters;

[0130] S43. During the optimization process, simulation technology is used to conduct simulation tests on different parameter combinations; by establishing a mathematical model of the production process and using computer simulation software to conduct simulation, the production effects and quality indicators under different parameter combinations are predicted;

[0131] S44. Based on the simulation results, select the optimal parameter combination to conduct actual production tests; during the actual production process, monitor the quality indicators and equipment operating status of the production process in real time and record relevant data;

[0132] S45. Adjust the optimization strategy in a timely manner based on the feedback information from the actual production test; if there is a difference between the actual production effect and the simulation result, analyze the cause and further optimize the parameter combination;

[0133] S46. Transmit the optimized process parameters to the production equipment control system to automatically adjust and control the process parameters; and send the optimized parameters to the equipment controller in real time through the communication interface with the production equipment.

[0134] The working principle of this technical solution is to use web crawler technology to automatically search, filter, and extract process knowledge related to polyester fabric production from the vast amount of information on the internet according to preset rules and keywords. This knowledge covers theoretical knowledge, technical specifications, and key operational points for every step of the process, from raw material selection, spinning and weaving processes, to finishing. An expert knowledge base gathers the extensive experience and practical skills accumulated by senior industry experts in the polyester fabric production process. This expert knowledge base integrates successful cases and problem-solving solutions from different companies and production scenarios, providing practical guidance for process parameter optimization. The process knowledge acquired through web crawlers is systematically integrated with the experience and skills collected from the expert knowledge base. Duplicate and invalid information is removed, and the knowledge is classified, summarized, and organized to form a comprehensive knowledge base for production process parameter optimization. This knowledge base provides a comprehensive theoretical and practical basis for subsequent process parameter optimization.

[0135] A thorough analysis of the characteristics of polyester fabric production, such as the continuous nature of the production process, the complexity of process parameters, and the multidimensional nature of quality indicators, was conducted. The objectives for process parameter optimization were clearly defined, such as improving production efficiency, reducing production costs, and enhancing product quality. Based on these characteristics and objectives, the most appropriate intelligent optimization algorithm was selected from a wide range of algorithms, such as genetic algorithms, particle swarm optimization, and neural networks. The selected intelligent optimization algorithm was then used to adaptively optimize the production process parameters. The algorithm automatically adjusted the parameter range and optimization direction based on real-time production data and the optimization objectives. Through continuous iterative calculations and parameter adjustments, the optimal combination of process parameters was found to optimize the production process.

[0136] Based on the physical and chemical principles of polyester fabric production, a mathematical model of the production process was established. This model accurately describes the quantitative relationship between various process parameters and production results and quality indicators during the production process, providing a theoretical basis for simulation. Using computer simulation software, different combinations of process parameters were input into the established mathematical model for simulation experiments. The simulation software's high-speed computing and visualization capabilities predicted production results (e.g., yield, production cycle), as well as quality indicators such as polyester fabric strength, elongation, and color fastness) under different parameter combinations. Simulation technology allows for rapid assessment of the feasibility of different parameter combinations without actual production, providing a reference for actual production.

[0137] Based on the simulation results, the optimal parameter combination was selected for actual production testing. In a real-world production environment, the production equipment was configured according to the selected parameter combination to produce polyester fabric. During the actual production process, various sensors and monitoring devices were used to monitor quality indicators and equipment operating conditions, such as temperature, pressure, speed, and tension, in real time. This data was recorded promptly to provide data support for subsequent analysis and optimization.

[0138] Compare and analyze the results of actual production tests with those of simulations. If there are discrepancies between actual production results and simulations, conduct in-depth analysis to determine the causes. These discrepancies may be due to factors such as inaccurate mathematical models, differences between the actual production environment and the simulation environment, or unstable equipment performance. Based on the results of this discrepancy analysis, promptly adjust the optimization strategy. Revise and improve the mathematical model to increase its accuracy. Consider the influencing factors of the actual production environment and further optimize the parameter combination to ensure that actual production results meet the expected goals.

[0139] Process parameters verified and optimized during actual production are transmitted in real time to the production equipment control system via a communication interface with the production equipment. This communication interface can be wired or wireless, ensuring stable and timely parameter transmission. Upon receiving the optimized parameters, the production equipment control system automatically adjusts the equipment's operating parameters to achieve precise control of production process parameters. This automated adjustment and control ensures the production process is always optimized, improving production stability and consistent product quality.

[0140] The benefits of this technical solution include: by integrating process knowledge and experience, a comprehensive knowledge base for optimizing production process parameters has been established, enabling more scientific and precise adjustments to production process parameters, thereby improving production process stability and product quality. Adaptive optimization of production process parameters through intelligent optimization algorithms automatically adjusts parameters based on the specific characteristics of polyester fabric production, reducing manual intervention and errors, thereby reducing uncertainty and volatility in the production process.

[0141] By using simulation technology to test different parameter combinations, the optimal parameter combination can be predicted before actual production, reducing the number and time of production tests, thereby significantly improving production efficiency. During the optimization process, simulation tests predict production results and quality indicators under different parameter combinations, allowing for precise adjustment of key parameters in the production process, improving product consistency and quality stability.

[0142] By optimizing and simulating production processes, we reduce waste and defective products caused by improper parameter settings, lowering the waste of raw materials and energy consumption during production, thereby effectively reducing production costs. By monitoring quality indicators and equipment operating status during production in real time and automatically transmitting optimized process parameters to the production equipment control system, we can make real-time adjustments during production, making the production process more flexible and adaptable.

[0143] Feedback from simulations and actual production trials provides management with data support, ensuring more scientific and reliable decision-making and reducing the risks associated with empirical judgment. Preliminary testing through simulations allows for the evaluation of the effects of different parameter combinations in a risk-free environment, avoiding extensive trial and error in actual production and reducing the costs associated with trial and error.

[0144] Timely adjustments to optimization strategies based on actual production feedback ensure continuous iteration and improvement of the process optimization process, enhancing its sustainability and long-term effectiveness. Real-time transmission of optimized process parameters via communication interfaces with production equipment enables automatic adjustment and control of the production process, increasing the automation level of production equipment and reducing manual intervention and operational errors.

[0145] In one embodiment of the present invention, the S5 includes:

[0146] S51. During the polyester fabric production process, a unique identification code is assigned to each batch of products; all relevant data from the production process is associated and stored with the identification code; a product information database is established, and the associated data is stored in the database;

[0147] S52. Establish a real-time quality traceability system to query the entire life cycle information of a batch of products by scanning the identification code; use data mining and machine learning technology to analyze historical quality data;

[0148] S53. Use a classification algorithm to establish a quality defect early warning model to monitor quality indicators in the production process in real time. When it is detected that the quality indicators deviate from the normal range, an early warning signal is issued, indicating the possible type of quality defects and the cause of the defects.

[0149] S54. Production management personnel take measures to make adjustments and improvements based on early warning information.

[0150] The working principle of the above technical solution is as follows: During the polyester fabric production process, each batch of products is assigned a unique identification code; the identification code can be in the form of a barcode, QR code, or radio frequency identification (RFID) tag; all relevant data in the production process, such as raw material information, process parameters, equipment operation data, quality inspection data, etc., are associated and stored with the identification code; a product information database is established, and the associated data is stored in the database;

[0151] Establish a real-time quality traceability system that can quickly query the entire life cycle information of a batch of products by scanning the identification code; use data mining and machine learning technology to analyze historical quality data;

[0152] A quality defect early warning model is established using a classification algorithm to monitor quality indicators such as fiber strength, fabric density, and dye uptake during the production process in real time. When a quality indicator deviates from the normal range, an early warning signal is issued, indicating the type of quality defect and its cause. For example, if the fiber strength during the spinning process is detected to be below a set threshold, the early warning model will sound an alarm and indicate the possible cause, such as excessive temperature or insufficient pressure.

[0153] Production managers can quickly take corrective measures based on early warning information. They can promptly adjust production process parameters, strengthen equipment maintenance, and retest raw materials to address potential quality defects. They also record and analyze quality defect incidents, draw lessons from them, and continuously improve the quality management system and production processes to prevent the escalation and recurrence of quality issues.

[0154] The benefits of this technical solution are: by assigning a unique identification code to each batch of products and associating all production-related data with the identification code, an efficient product information database is established, improving the traceability of information throughout the product lifecycle and providing greater transparency in the quality traceability, management, and maintenance of each batch of products. The real-time quality traceability system allows production managers to quickly access historical product data, promptly identify potential quality issues, and take corrective measures, reducing the risk of production interruptions and customer complaints caused by quality issues.

[0155] By combining data mining and machine learning technologies to analyze historical quality data, potential quality issues can be identified in advance. Classification algorithms are then used to establish a quality defect early warning model, enabling real-time monitoring of quality indicators and improving the accuracy of quality management. This real-time early warning system issues alerts promptly and accurately identifies the type of quality defect and its likely cause, enabling production managers to quickly implement adjustments and improvements, thereby increasing the responsiveness and flexibility of the production process.

[0156] Early warning models issue timely alerts and provide possible causes, enabling intervention and adjustments before quality issues occur. This reduces the frequency of quality defects and reduces scrap and defective product rates. Recording and analyzing quality defect incidents not only enables lessons learned but also enables continuous improvement of the quality management system and production processes, thereby enhancing the continuous improvement capabilities of the production process and gradually improving process standards.

[0157] By promptly adjusting production process parameters, strengthening equipment maintenance, and retesting raw materials, we ensure that all parameters in the production process remain within the ideal range, enhancing the controllability of the production process and reducing the impact of external factors on product quality. Early warning models enable timely identification and correction of problems, effectively reducing the number of rework and repairs, thereby saving production costs and resources wasted due to quality defects.

[0158] By establishing a transparent and efficient quality traceability system, customers can choose and use products with greater confidence, enhancing their trust and satisfaction with manufacturers and helping to improve the brand's market competitiveness. Real-time monitoring of key quality indicators and early warning during the production process helps ensure consistent and stable product quality, reducing quality fluctuations caused by human error and equipment problems.

[0159] In one embodiment of the present invention, the S6 includes:

[0160] S61. Comprehensively consider the production demand dynamic forecast results, production situation assessment reports, process parameter optimization results, and quality traceability and defect warning information, and integrate and analyze these multi-source information;

[0161] S62. Use operations research and intelligent scheduling algorithms to intelligently allocate production resources; use linear programming to optimize the supply plan of raw materials, and use genetic algorithms to optimize the scheduling plan of production equipment;

[0162] S63. Establish a production collaborative optimization mechanism to strengthen information communication and coordination between various production links; through the establishment of a production collaborative management platform, real-time sharing and transmission between various production links;

[0163] S64. Evaluate the effectiveness of intelligent allocation of production resources, establish an evaluation index system, and evaluate the actual effect of intelligent allocation of production resources by regularly collecting and analyzing relevant data; based on the evaluation results, continuously improve and optimize the production resource allocation strategy and collaborative optimization mechanism.

[0164] The working principle of the above technical solution is as follows: comprehensively consider the results of dynamic production demand forecasts, production situation assessment reports, process parameter optimization results, and quality traceability and defect warning information, integrate and analyze these multi-source information; clarify the decision-making factors for production resource allocation, such as the priority and urgency of production tasks, the supply of raw materials, the operating status of production equipment, and the skill level of human resources; and through the comprehensive evaluation of these factors, provide a scientific basis for the intelligent allocation of production resources.

[0165] Use operations research and intelligent scheduling algorithms to intelligently allocate production resources; use linear programming to optimize raw material supply plans to ensure timely supply and reasonable inventory; use genetic algorithms to optimize production equipment scheduling to improve equipment utilization and production efficiency; and, based on the characteristics of production tasks and the skill levels of human resources, rationally allocate human resources positions to achieve optimal allocation of human resources.

[0166] Establish a production collaborative optimization mechanism to strengthen information communication and coordination between various production links; through the establishment of a production collaborative management platform, real-time sharing and transmission of production plans, process parameters, quality inspection and other information between various production links;

[0167] Evaluate the effectiveness of intelligent allocation of production resources and establish an evaluation indicator system, such as production efficiency improvement rate, resource utilization improvement rate, production cost reduction rate, etc.; evaluate the actual effect of intelligent allocation of production resources by regularly collecting and analyzing relevant data; and continuously improve and optimize production resource allocation strategies and collaborative optimization mechanisms based on the evaluation results.

[0168] The above technical solution achieves the following: By comprehensively analyzing dynamic production demand forecasts, production status assessment reports, process parameter optimization results, and quality traceability and defect warning information, it ensures a more comprehensive, accurate, and scientific basis for decision-making in production resource allocation, thereby improving the rationality of resource allocation and the effectiveness of production plans. By optimizing raw material supply plans through operations research and intelligent scheduling algorithms, particularly the use of linear programming, the timely supply and reasonable inventory of raw materials are ensured, reducing the risk of production interruptions and waste caused by untimely raw material supply or inventory backlogs.

[0169] Using genetic algorithms to optimize production equipment scheduling improves equipment utilization and production efficiency, reduces equipment idle time and downtime losses during production, and ensures a smooth and efficient production process. By rationally allocating human resources to positions, combining the characteristics of production tasks with employee skill levels, we achieve optimal human resource allocation, ensuring that the skill requirements of each position match the production tasks, improving production efficiency and employee job satisfaction.

[0170] By establishing a collaborative production optimization mechanism, we strengthen information communication and coordination across all production links, avoid information silos and duplication of effort, and reduce errors and costs caused by poor communication during the production process. By establishing a collaborative production management platform, we achieve real-time sharing and transmission of information such as production plans, process parameters, and quality inspections, enabling each production link to quickly respond to changing needs and enhancing the flexibility and adaptability of production plans.

[0171] By optimizing intelligent scheduling algorithms and comprehensively considering the actual conditions of various resources, resource utilization in the production process is made more efficient, production efficiency is improved, and resource waste is significantly reduced. Through intelligent allocation and optimized management of production resources, the use of production equipment, raw materials, and human resources is more refined, reducing energy waste, equipment wear and tear, and unnecessary labor costs in the production process, thereby reducing production costs.

[0172] By establishing an evaluation mechanism for the intelligent allocation of production resources and regularly assessing key indicators such as production efficiency, resource utilization, and production costs, we ensure the continuous optimization and adjustment of production scheduling strategies and enhance the ability to continuously improve the production process. By sharing and transmitting production information in real time, production management becomes more transparent, making related decisions and operations more controllable, helping managers improve their control over the production process and their ability to proactively identify potential problems.

[0173] One embodiment of the present invention is a monitoring and management system for the entire polyester fabric production process, comprising:

[0174] one or more processors;

[0175] a memory for storing one or more programs,

[0176] When the one or more programs are executed by the one or more processors, the one or more processors implement any one of the methods described above.

[0177] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for monitoring and managing the entire polyester fabric production process, characterized in that: The method comprises: S1. Deploy various types of sensors at key nodes of the polyester fabric production line to collect various physical parameters and environmental information related to polyester fabric production in real time. At the same time, integrate the operating status monitoring system of production equipment to obtain equipment data. Initially integrate the data from different sensors and equipment monitoring systems to build a holographic perception architecture for polyester fabric production. S2. Perform deep fusion processing on multi-source heterogeneous data obtained from the polyester fabric production holographic perception architecture; construct a data association model; based on this model, conduct a comprehensive assessment of the production situation in combination with the polyester fabric production process and quality standards; and generate a production situation assessment report based on the production situation assessment. S3. Collect historical multi-dimensional data on polyester fabrics; use machine learning algorithms to train and learn the multi-dimensional data to build a dynamic production demand forecasting model; compare and analyze the dynamic production demand forecast results with the current production plan to identify potential production gaps or surpluses; S4. Based on the dynamic production demand forecast results and production situation assessment report, combined with the process knowledge of polyester fabric production, the production process parameters are adaptively optimized using intelligent optimization algorithms. During the optimization process, the quality indicators and equipment operating status of the production process are monitored in real time, and the optimization strategy is adjusted in a timely manner based on the feedback information. S5. During the polyester fabric production process, each batch of products is assigned a unique identification code, and all relevant data from the production process is associated and stored with the identification code. A real-time quality traceability system is established to query the entire life cycle information of a batch of products by scanning the identification code. At the same time, historical quality data is analyzed using data mining and machine learning techniques to establish a quality defect early warning model. S6. Comprehensively consider the dynamic prediction results of production demand, production situation assessment reports, process parameter optimization results, quality traceability and defect warning information, and use operations research and intelligent scheduling algorithms to intelligently allocate production resources.

2. The method for monitoring and managing the entire polyester fabric production process according to claim 1, wherein: Said S1 comprises: S11. Conduct surveys and analyses at key nodes of the polyester fabric production line and determine the type of sensors to be deployed based on the production characteristics and monitoring requirements of each node. S12. Install and debug the sensors according to the selected sensor types and deployment locations. At the same time, configure data acquisition equipment to convert the analog signals collected by the sensors into digital signals and perform preliminary storage and processing. S13, integrated production equipment operation status monitoring system, through equipment monitoring technology, to obtain key equipment data; using industrial Ethernet to seamlessly connect the equipment monitoring system with the data acquisition network, synchronously transmit equipment operation data and sensor collection data; S14. Conduct preliminary integration of data collected from different sensors and equipment monitoring systems, use data fusion technology to correlate and match data from multiple data sources, and eliminate data redundancy and conflict; build a holographic perception architecture for polyester fabric production, and connect various data sources into an organic whole.

3. The method for monitoring and managing the entire polyester fabric production process according to claim 2, wherein: Said S14 comprises: S141. Pre-process all types of collected raw data, apply data mining and association analysis techniques to deeply analyze the inherent connections between different data sources; establish a data association model based on the logical relationship of the production process and the collaborative working principle between equipment; S142. Use a data fusion algorithm to conduct in-depth analysis on the associated and matched data; at the same time, process conflicting data from different data sources according to preset rules and priorities; S143. Based on the processed data, a data fusion model for polyester fabric production is constructed; the data is fused and optimized; S144. With the fused data stream as the core, a holographic perception architecture for polyester fabric production is constructed; it is connected into an organic whole through data interfaces and network protocols to carry out real-time data sharing and interaction.

4. The method for monitoring and managing the entire polyester fabric production process according to claim 3, wherein: The S142 includes: Calculate various statistical indicators for the matched data and identify highly correlated data by analyzing the statistical correlation between different data sequences. Combined with the professional knowledge base in the production field, perform semantic analysis on the data to determine whether there is semantically duplicated data. For time series data, analyze its changing trends and cyclical characteristics. If multiple data series show similar changing trends and cyclical patterns within the same time interval, and this similarity exceeds a reasonable error range, it is determined to be redundant data. For redundant data that is statistically related or semantically repeated, use data aggregation methods to process it. Select aggregation functions based on the type and characteristics of the data, and use data sampling methods to eliminate redundant data in the time series. Determine the sampling interval based on the frequency and importance of the data changes. Utilize the established data association model and prediction algorithm to predict and replace redundant data; establish a prediction model by analyzing the changing patterns of historical data and current data, and use the predicted values ​​to replace some redundant data; After correlation and matching, the data is checked for consistency across different data sources. Conflicting data is identified by comparing data attributes. Conflict determination rules are developed based on the business rules and process requirements for polyester fabric production. Normal and abnormal data patterns are established using historical data. Data that does not conform to normal patterns is identified by comparing current data with historical data patterns, and is then determined to be conflicting data. Evaluate the data sources of conflicting data and prioritize the timeliness of the data; prioritize the business importance of the data based on its importance to the polyester fabric production business; use machine learning algorithms to fuse and process the conflicting data; collect a large amount of historical conflict data and the corresponding correct processing results to build a training data set; The training data set is trained through a neural network so that the model can learn the processing mode of conflicting data; when new conflicting data appears, the data is input into the trained model to obtain the fused result.

5. The method for monitoring and managing the entire polyester fabric production process according to claim 1, wherein: Said S2 comprises: S21. Deeply clean the multi-source heterogeneous data obtained from the polyester fabric production holographic perception architecture; identify and remove noise data and outliers through machine learning algorithms; S22. Use data standardization methods to unify data of different dimensions to the same scale; through data standardization, eliminate the dimensional differences between different data; S23. Use data association analysis algorithms to mine potential relationships between data, and use association rule mining to find the intrinsic connections between data in different production links; build a data association model; S24. Based on the constructed data association model, the production situation is evaluated in combination with the process flow and quality standards of polyester fabric production. Various data in the production process are monitored and analyzed in real time using preset evaluation indicators and thresholds. S25. When the data exceeds the normal range, an early warning signal is issued; based on the production situation assessment results, a production situation assessment report is generated.

6. The method for monitoring and managing the entire polyester fabric production process according to claim 1, wherein: Said S3 comprises: S31. Obtain multi-dimensional data of historical polyester fabrics, and use a machine learning algorithm to train and learn the multi-dimensional data; S32. Divide historical data into training sets and test sets, continuously adjust the parameters and structure of the model, build a dynamic production demand forecasting model, automatically adjust the forecasting parameters based on real-time input data, and forecast the production demand of polyester fabric in the future; S33. Compare and analyze the dynamic forecast results of production demand with the current production plan; calculate the difference between the forecast demand and the production plan by establishing a comparative analysis model, and adjust the production plan based on the comparative analysis results.

7. The method for monitoring and managing the entire polyester fabric production process according to claim 1, wherein: Said S4 comprises: S41. Acquire process knowledge of polyester fabric production through web crawlers, and obtain experience and skills in the production process through expert knowledge bases; integrate process knowledge, experience and skills to form a complete knowledge base for production process parameter optimization; S42. Select an intelligent optimization algorithm based on the characteristics of polyester fabric production and the goal of process parameter optimization, and perform adaptive optimization of production process parameters; S43. During the optimization process, simulation technology is used to conduct simulation tests on different parameter combinations; by establishing a mathematical model of the production process and using computer simulation software to conduct simulation, the production effects and quality indicators under different parameter combinations are predicted; S44. Based on the simulation results, select the optimal parameter combination to conduct actual production tests; during the actual production process, monitor the quality indicators and equipment operating status of the production process in real time and record relevant data; S45. Adjust the optimization strategy in a timely manner based on the feedback information from the actual production test; if there is a difference between the actual production effect and the simulation result, analyze the cause and further optimize the parameter combination; S46. Transmit the optimized process parameters to the production equipment control system to automatically adjust and control the process parameters; and send the optimized parameters to the equipment controller in real time through the communication interface with the production equipment.

8. The method for monitoring and managing the entire polyester fabric production process according to claim 1, wherein: Said S5 comprises: S51. During the polyester fabric production process, a unique identification code is assigned to each batch of products; all relevant data from the production process is associated and stored with the identification code; a product information database is established, and the associated data is stored in the database; S52. Establish a real-time quality traceability system to query the entire life cycle information of a batch of products by scanning the identification code; use data mining and machine learning technology to analyze historical quality data; S53. Use a classification algorithm to establish a quality defect early warning model to monitor quality indicators in the production process in real time. When it is detected that the quality indicators deviate from the normal range, an early warning signal is issued, indicating the possible type of quality defects and the cause of the defects. S54. Production management personnel take measures to make adjustments and improvements based on early warning information.

9. The method for monitoring and managing the entire polyester fabric production process according to claim 1, wherein: Said S6 comprises: S61. Comprehensively consider the production demand dynamic forecast results, production situation assessment reports, process parameter optimization results, and quality traceability and defect warning information, and integrate and analyze these multi-source information; S62. Use operations research and intelligent scheduling algorithms to intelligently allocate production resources; use linear programming to optimize the supply plan of raw materials, and use genetic algorithms to optimize the scheduling plan of production equipment; S63. Establish a production collaborative optimization mechanism to strengthen information communication and coordination between various production links; through the establishment of a production collaborative management platform, real-time sharing and transmission between various production links; S64. Evaluate the effectiveness of intelligent allocation of production resources, establish an evaluation index system, and evaluate the actual effect of intelligent allocation of production resources by regularly collecting and analyzing relevant data; based on the evaluation results, continuously improve and optimize the production resource allocation strategy and collaborative optimization mechanism.

10. A monitoring and management system for the entire production process of polyester fabric, comprising: one or more processors; a memory for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors are enabled to implement the method according to any one of claims 1 to 9.

Images