Textile Production Process Optimization Method Based on Smart Terminals

Abstract

The present invention discloses an optimization method for textile production processes based on intelligent terminals, which relates to the technical field of textile production. The optimization method for textile production processes based on intelligent terminals integrates sensors through intelligent terminals to obtain process parameters and yarn surface image data in real time, and inputs them into a textile production process monitoring model to analyze the matching degree between the process parameters and the yarn surface state, and obtain a process adaptation index. According to the process adaptation index, a fuzzy control algorithm is used to dynamically adjust the yarn tension and spinning speed, thereby optimizing the production process. Based on the equipment position information and the process adaptation index, it is judged whether there is an abnormality in the textile equipment, and the inspection path is optimized through the A* algorithm to ensure the timely inspection and maintenance of the equipment. It realizes the intelligent monitoring and optimization adjustment of the textile production process, improves the production efficiency, yarn quality and equipment operation stability, and reduces the manual intervention and failure risk.

Description

Technical Field

[0001] The present invention relates to the technical field of textile production, and specifically to an optimization method for textile production processes based on intelligent terminals. Background Art

[0002] With the continuous development of global manufacturing, the textile industry, as a traditional basic industry, occupies an important position in the global economy. In recent years, with the rapid progress of technologies such as artificial intelligence, the Internet of Things, and big data, the textile industry is also transforming towards intelligence and automation, gradually promoting the upgrade of production models. Especially against the backdrop of increasingly fierce global competition, rising labor costs, and increasing environmental protection requirements, textile enterprises urgently need to improve production efficiency, reduce costs, and enhance product quality to meet the changing market demands. In this process, intelligent optimization methods for textile production processes provide new development opportunities for enterprises. By applying intelligent terminal technology and real-time data monitoring, enterprises can achieve precise control of the production process, efficient utilization of resources, and real-time management of equipment, thereby maintaining a competitive edge in the industry.

[0003] Although some textile enterprises have started to introduce intelligent technologies in production, the existing optimization methods for textile production processes still face many challenges. Traditional control methods cannot flexibly adjust core process parameters according to real-time changes, resulting in fluctuations in product quality and low production efficiency. Secondly, in a production environment where multiple devices operate in coordination, there are significant differences in the operating states of the devices. Traditional resource scheduling methods cannot effectively make dynamic adjustments according to the real-time states of the devices, resulting in low resource scheduling efficiency, uneven distribution of monitoring paths, and further affecting production efficiency and the accuracy of equipment management. In addition, due to interference from factors such as illumination and image blurring in the existing image acquisition technology during the production process, the recognition of abnormal device states is inaccurate, affecting the monitoring accuracy of the production process and the effect of anomaly detection. Therefore, the existing methods cannot fully meet the requirements of real-time, intelligence, and resource optimization, and new technical means are urgently needed to solve these problems. Summary of the Invention

[0004] Aiming at the deficiencies of the existing technology, the present invention provides an optimization method for textile production processes based on intelligent terminals. By collecting real-time data on the spinning process and image data of the yarn surface, and combining advanced intelligent algorithms such as fuzzy control and A* algorithm, it can accurately analyze the matching degree between yarn quality and production processes, realize automatic adjustment of spinning parameters, thereby improving the stability of the textile production process and the quality of the yarn, reducing the failure rate of equipment, and enhancing production efficiency. The problems in the above background art are solved.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: A method for optimizing the textile production process based on an intelligent terminal, comprising the following steps: S1. Connect the sensors integrated in the smart glasses to the interface module of the textile equipment to obtain process parameters in real time, and collect images of the surface state of the yarn to obtain yarn surface image data; S2. Input the process parameters and the yarn surface image data into the MES system, construct a textile production process monitoring model, analyze the matching degree between the yarn surface state and the process parameters, and obtain a process adaptation index; S3. Dynamically adjust the yarn tension and spinning speed according to the process adaptation index through a fuzzy control algorithm; S4. Determine the abnormal working state of the textile equipment according to the position information of the textile equipment and the process adaptation index, and optimize the inspection path by dynamically planning the inspection trajectory through the A* algorithm; the MES system has the functions of receiving information, displaying the position information of the textile equipment, and reporting the processing results; the process adaptation index is used to evaluate the matching degree between the yarn quality and the current production process parameters.

[0006] Further, the process parameters include yarn tension, spinning speed, spinning temperature, and air flow rate; the yarn surface image data includes the yarn thickness change rate, yarn color difference value, and yarn roughness.

[0007] Further, the specific process of constructing the textile production process monitoring model is as follows: Perform data cleaning, denoising, and standardization processing on the process parameters and the yarn surface image data; Extract surface quality features from the yarn surface image data, combine with the process parameters to construct a data set, and train the data set through a neural network to establish a textile production process monitoring model to analyze the relationship between the process parameters and the yarn quality.

[0008] Further, the specific process of analyzing the matching degree between the yarn surface state and the process parameters is as follows: Input the yarn surface image data and the process parameters into the established textile production process monitoring model; Extract the correlation relationship between the features of the yarn surface image data and the process parameter features, compare each feature in the process parameters and the surface image data, and calculate the matching degree between the process parameters and the yarn surface quality based on the trained correlation function in the textile production process monitoring model. Identify whether the process parameters match the yarn surface state by analyzing the matching degree index.

[0009] Further, the specific process of obtaining the process adaptation index is as follows: Analyze the relationship between the yarn surface state features and the process parameters according to the trained correlation function in the textile production process monitoring model, identify the matching degree between the process parameters and the yarn surface quality, and obtain the process adaptation index.

[0010] Furthermore, according to the process adaptation index, the specific process of dynamically adjusting the yarn tension and spinning speed through the fuzzy control algorithm is as follows: Input the process adaptation index into the fuzzy control system; conduct fuzzy inference according to the preset fuzzy rule base to analyze the relationship between the process adaptation index, yarn tension, and spinning speed; perform defuzzification processing to obtain the adjustment values of the yarn tension and spinning speed; adjust the yarn tension and spinning speed according to the defuzzification results, and monitor the adjusted yarn tension and spinning speed in real time.

[0011] Furthermore, according to the textile equipment position information and the process adaptation index, the specific process of judging the abnormal working state of the textile equipment is as follows: Obtain the position information and process adaptation index of the textile equipment; compare the process adaptation index of the equipment with the preset threshold according to the threshold range of the process adaptation index; when the process adaptation index exceeds the threshold range of the process adaptation index, it indicates that the textile equipment has an abnormality, trigger an alarm message, and mark the abnormal position of the equipment.

[0012] Furthermore, the specific process of optimizing the inspection path by dynamically planning the inspection trajectory through the A* algorithm is as follows: Determine the textile equipment that needs to be inspected according to the alarm message, and obtain the process adaptation index of the textile equipment; construct a map model of the textile equipment position and define the connection relationship between the equipment; according to the process adaptation index of the equipment, analyze the process adaptation index and path cost of the equipment through the A* algorithm, calculate the shortest path from the current equipment to the target equipment, and generate the inspection trajectory; monitor the process adaptation index in real time and dynamically adjust the inspection path.

[0013] The present invention has the following beneficial effects:

[0014] (1). This method for optimizing the textile production process based on an intelligent terminal can accurately monitor the quality change of the yarn during the textile production process by connecting the sensors integrated in the smart glasses with the interface module of the textile equipment, and real-time obtaining process parameters and collecting yarn surface images. This process can carefully capture the surface state of the yarn by obtaining the yarn surface image data, providing high-quality data support for subsequent analysis. After inputting these data into the MES system and combining with the textile production process monitoring model, the matching degree between the yarn surface state and process parameters can be comprehensively analyzed, and then the process adaptation index can be generated. This real-time data collection and analysis method not only improves the transparency of the production process but also provides a scientific basis for process optimization, helps to achieve refined management of the production process, and improves product quality and production efficiency.

[0015] (2) The textile production process optimization method based on intelligent terminals can effectively achieve precise control of textile process parameters by dynamically adjusting the yarn tension and spinning speed according to the process adaptation index through a fuzzy control algorithm. Based on the change of the process adaptation index, the fuzzy control algorithm adjusts the yarn tension and spinning speed in real time, thereby reducing the quality fluctuations in the textile process and improving the consistency and stability of the yarn. This intelligent adjustment method not only reduces the errors caused by human intervention but also improves the automation and intelligence level of the system and optimizes the production efficiency. By combining the position information of textile equipment and the process adaptation index, the inspection path is dynamically planned through the A* algorithm and optimized, which can improve the efficiency and accuracy of equipment inspection. When the process adaptation index of the equipment exceeds the preset threshold, it can be timely judged whether the equipment is in an abnormal state, and the inspection path is optimized to reduce ineffective inspections and waiting time. By optimizing the inspection path, it is ensured that equipment failures can be timely detected and processed, reducing the downtime caused by equipment failures during the production process and improving the overall production efficiency and equipment reliability.

[0016] Of course, it is not necessary for any product implementing the present invention to achieve all the above-mentioned advantages simultaneously. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a flowchart of the textile production process optimization method based on intelligent terminals of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] The embodiments of the present application solve the problems of unstable yarn quality, unmatched process parameters, and difficulty in timely detecting equipment failures in the textile production process through the textile production process optimization method based on intelligent terminals.

[0019] The general idea for the problems in the embodiments of the present application is as follows:

[0020] By connecting the sensors integrated in the smart glasses with the interface module of the textile equipment, process parameters are obtained in real time, and image acquisition of the yarn surface state is performed to obtain yarn surface image data.

[0021] The process parameters and the yarn surface image data are input into the MES system to construct a textile production process monitoring model, analyze the matching degree between the yarn surface state and the process parameters, and obtain the process adaptation index.

[0022] According to the process adaptation index, the yarn tension and spinning speed are dynamically adjusted through a fuzzy control algorithm.

[0023] According to the position information of the textile equipment and the process adaptation index, the abnormal working state of the textile equipment is judged, and the inspection path is dynamically planned through the A* algorithm and optimized.

[0024] Please refer to Figure 1 , an embodiment of the present invention provides a technical solution: an optimization method for textile production processes based on intelligent terminals, including the following steps: S1. Connect the sensors integrated in the smart glasses to the interface module of the textile equipment to obtain process parameters in real time, and collect images of the surface state of the yarn to obtain yarn surface image data; S2. Input the process parameters and yarn surface image data into the MES system, construct a textile production process monitoring model, analyze the matching degree between the yarn surface state and the process parameters, and obtain a process adaptation index; S3. Dynamically adjust the yarn tension and spinning speed according to the process adaptation index through a fuzzy control algorithm; S4. Determine the abnormal working state of the textile equipment according to the textile equipment position information and the process adaptation index, dynamically plan the inspection trajectory through the A* algorithm, and optimize the inspection path; the MES system has the functions of receiving information, displaying the textile equipment position information, and reporting the processing results; the process adaptation index is used to evaluate the matching degree between the yarn quality and the current production process parameters.

[0025] In this implementation scheme, Step S1: Smart glasses: An intelligent device equipped with sensors that can collect environmental data in real time and display feedback information. In the present invention, the smart glasses are connected to textile equipment through integrated sensors (such as temperature sensors, pressure sensors, optical sensors, etc.) to obtain real-time process parameters (such as yarn tension, rotational speed, etc.) and collect image data of the yarn surface state through a camera. The use of smart glasses can improve the work efficiency of operators and provide real-time feedback on important process data during production. Process parameters: Refer to the key parameters that need to be controlled and optimized during textile production. Yarn surface state image data: The image of the yarn surface is collected through the camera on the smart glasses, and these image data can be used for subsequent quality analysis after being processed. Step S2: MES system: The Manufacturing Execution System, which is a system for real-time management of production site operations. The MES system can integrate data from various links (such as process parameters, equipment status, production tasks, etc.), and display, analyze, and process them in real time. The role of this system is to connect production equipment and management to ensure the smooth and efficient production process. Textile production process monitoring model: This model integrates spinning process data and yarn surface image data to establish a data analysis model for monitoring each link in the production process. The main role of this model is to analyze the relationship between process parameters and yarn quality, evaluate whether the production process meets the expected goals, and provide optimization suggestions. Process adaptation index: The process adaptation index is a value calculated based on the matching degree between the yarn surface quality and the process parameters (such as tension, speed, etc.) collected during the production process. This index is used to measure the adaptability of the current process parameters to the yarn quality. The higher the process adaptation index, the better the matching degree between the process parameters and the yarn surface quality, and the more stable the yarn quality. Step S3: Fuzzy control algorithm: Fuzzy control is a control method based on fuzzy logic, suitable for dealing with uncertainty and ambiguity problems. In the present invention, the fuzzy control algorithm dynamically adjusts the yarn tension and spinning speed according to the process adaptation index. Through fuzzy control, the system can automatically adjust the parameters in the production process according to the real-time changing process adaptation index to ensure that the yarn quality is optimized during production. Step S4: Textile equipment location information: Refers to the specific location of textile equipment in the production site. This information is usually provided by a positioning system (such as GPS, RFID, or other sensors) to help monitor and manage the location changes of the equipment. A* algorithm: The A* algorithm is a heuristic search algorithm commonly used for path planning, which can find the shortest path from the starting point to the target point in a known map. In the present invention, the A* algorithm dynamically plans the inspection trajectory and optimizes the inspection path by real-time monitoring of the process adaptation index of the equipment, so that the inspection personnel can check the equipment status and perform maintenance in the shortest time.The application of the A* algorithm can improve the inspection efficiency and ensure that the equipment can be repaired in time when abnormalities occur. The MES system's function of receiving information: The MES system can receive real-time data from textile equipment, including process parameters, equipment status, image data, etc. This information provides data support for subsequent production process analysis and optimization. Displaying the location information of textile equipment and reporting the processing results: The system will display the location information of the equipment, the matching situation of process parameters, and the processing results (such as abnormal status alarms, etc.) to production management personnel in real time, facilitating decision-making and adjustment.

[0026] Specifically, the process parameters include: yarn tension, spinning speed, spinning temperature, air flow rate; the yarn surface image data includes the yarn thickness change rate, yarn color difference value, and yarn roughness.

[0027] In this implementation plan, yarn tension: Yarn tension refers to the pulling force or pressure exerted on the yarn during the spinning process. This parameter has an important impact on the shape, strength, and quality of the yarn. Excessive or too low yarn tension will cause the yarn to break or deform, thus affecting the quality of the final product. Spinning speed: Spinning speed refers to the speed at which the spinning machine rotates or the textile equipment processes the yarn during the spinning process. The spinning speed directly affects the spinning quality and production efficiency of the yarn. Excessive spinning speed may cause uneven stretching or breakage of the yarn, while too low speed may lead to a decrease in production efficiency. Spinning temperature: Spinning temperature refers to the temperature of the environment or inside the equipment during the spinning process. Spinning temperature plays an important role in the processing of fiber materials. Excessive or too low temperature may cause a decrease in the quality of the yarn. Air flow rate: Air flow rate refers to the air flow speed or air volume used to support or regulate the yarn during the spinning process. In textile equipment, air flow can be used for processes such as yarn transportation, shaping, or cooling. Yarn thickness change rate: The yarn thickness change rate refers to the degree of thickness difference of the yarn at different parts during the production process. It is usually measured through the image data on the yarn surface. This parameter is used to evaluate the consistency of the yarn. Yarns with a large thickness change usually result in unstable product quality. By monitoring this parameter in real time, the process parameters can be adjusted in time to ensure the consistency of the yarn. Yarn color difference value: The yarn color difference value refers to the color difference between different parts of the yarn or between different batches. It calculates the degree of color difference of each area on the yarn surface through image processing technology. Yarns with too large a color difference are usually regarded as unqualified in quality and may affect the appearance quality of the final fabric. Real-time monitoring of the yarn color difference value can ensure the uniform color of the product. Yarn roughness: Yarn roughness refers to the unevenness of the yarn surface, which is usually quantified by image acquisition and analysis of the yarn surface morphology. Higher roughness may cause the yarn to be not smooth, affecting the feel and appearance of the fabric. By controlling the roughness, the quality of the yarn can be improved, making its surface smoother and more uniform.

[0028] Specifically, the specific process of constructing a textile production process monitoring model is as follows: perform data cleaning, denoising, and standardization on process parameters and yarn surface image data; extract surface quality features from the yarn surface image data, combine with process parameters to construct a data set, train the data set through a neural network, establish a textile production process monitoring model, and analyze the relationship between process parameters and yarn quality.

[0029] In this implementation plan, preprocess the collected process parameters and yarn surface image data, including: Data cleaning: Remove missing or inconsistent data points to ensure data integrity. Denoising: Eliminate noise in the image data to ensure the clarity of the surface image and improve the accuracy of subsequent analysis. Standardization processing: Normalize the data so that each feature value is within the same range, eliminating the influence brought by different scales.

[0030] Extract features related to surface quality from the yarn surface image data. Common features include: Coarseness change rate: The non-uniformity of the yarn thickness. Color difference: The degree of change in the yarn color. Roughness: The smoothness or roughness of the yarn surface. Construct a data set Combine the extracted features with corresponding process parameters (such as tension, speed, temperature, etc.) to construct a complete data set as the input data for the neural network. Each row of data includes the surface features of the yarn and the corresponding process parameter values. Use the constructed data set to train through a neural network. The neural network forms a model by learning the complex relationship between process parameters and yarn surface quality. The network adjusts parameters according to the training data and gradually optimizes to accurately predict the impact of process parameters on yarn quality. Based on the trained neural network, establish a textile production process monitoring model. This model can input new process parameters and yarn image data in real time and output the evaluation results of yarn quality to help monitor the stability and quality of textile production.

[0031] Specifically, the specific process of analyzing the matching degree between the yarn surface state and process parameters is as follows: Input the yarn surface image data and process parameters into the established textile production process monitoring model; Extract the correlation relationship between the features of the yarn surface image data and the process parameter features, compare each feature in the process parameters and surface image data, and calculate the matching degree between the process parameters and the yarn surface quality based on the trained correlation function in the textile production process monitoring model. By analyzing the matching degree index, identify whether the process parameters match the yarn surface state.

[0032] In this implementation, the real-time collected yarn surface image data and process parameters are input into the established textile production process monitoring model. Based on the trained correlation function in the textile production process monitoring model, the extracted features are compared. Correlation function: A mathematical function obtained through model training, used to describe the relationship between process parameters and yarn surface quality characteristics. Calculate the matching degree between the process parameters and the yarn surface quality, and this value is usually expressed as a matching degree index. Matching degree analysis: By analyzing the matching degree index, it is judged whether the current process parameters are suitable for the surface state of the yarn. If the matching degree index is within the preset reasonable range, it means that the process parameters match the yarn surface state; otherwise, it means that the process parameters may need to be adjusted.

[0033] Specifically, the specific process of obtaining the process adaptation index is as follows: According to the trained correlation function in the textile production process monitoring model, analyze the relationship between the yarn surface state characteristics and the process parameters, identify the matching degree between the process parameters and the yarn surface quality, and obtain the process adaptation index.

[0034] In this implementation, a multi-layer non-linear correlation function is used to extract the complex non-linear relationship between process parameters and yarn surface state. The output of each layer is based on the weighted sum and activation function processing results of the previous layer. Specifically, the model can be expressed as: Where: is a vector of process parameters, including yarn tension, spinning speed, spinning temperature, and air flow rate. is a vector of yarn surface state characteristics, including yarn thickness change rate, yarn color difference value, and yarn roughness. and are the weights of the first layer, corresponding to the process parameters and surface state characteristics respectively. is the bias term of the first layer. is the activation function, used to introduce non-linearity. This formula represents the weighted sum and activation processing of the process parameters and yarn surface state characteristics in the first layer. In order to introduce more complex non-linear relationships, we can use a multi-layer structure in the neural network. Each layer takes the output of the previous layer as input to form deep feature learning: ; Where: is the output of the second layer, representing the result after the output of the first layer is processed by the activation function. and are the weights of the third layer. is the activation function of the third layer. This process can be extended to more layers to form a deeper network architecture. The weights and biases of each layer are parameters optimized by training through the backpropagation algorithm, and finally, the relationship between complex input features can be captured. Based on the trained deep neural network, the process adaptation index (WED) is calculated by the output layer of the network: ; wherein: is the matching degree output by the neural network. is the weight coefficient, which controls the contribution of each term to the final matching degree index. i represents each element in the process parameters. j represents each element in the yarn surface state characteristics. n is the number of process parameters, and m is the number of yarn surface state characteristics. and The means of the process parameters and the yarn surface state characteristics ensure that the model can perform normalization processing and reduce the influence range of different characteristics. Specifically, according to the process adaptation index, the specific process of dynamically adjusting the yarn tension and spinning speed through the fuzzy control algorithm is as follows: Input the process adaptation index into the fuzzy control system; perform fuzzy inference according to the preset fuzzy rule base to analyze the relationship between the process adaptation index and the yarn tension and spinning speed; perform defuzzification processing to obtain the adjustment values of the yarn tension and spinning speed; adjust the yarn tension and spinning speed according to the defuzzification results, and monitor the adjusted yarn tension and spinning speed in real time.

[0035] In this implementation scheme, the process adaptation index is calculated through the previously established textile production process monitoring model and is used to evaluate the matching degree between the current process parameters and the yarn quality. This index reflects the optimization space in the textile production process and helps the control system determine whether it is necessary to adjust the process parameters.

[0036] Take this exponent as an input variable and pass it into the fuzzy control system to provide a basis for subsequent control decisions. Conduct fuzzy inference according to the preset fuzzy rule base: In the fuzzy control system, the fuzzy rule base contains a set of "if-then" type rules, which define the relationship between the process adaptation exponent, yarn tension, and spinning speed. For example: If the process adaptation exponent is low, then the yarn tension and spinning speed should be increased to improve the production effect. If the process adaptation exponent is high, then the yarn tension and spinning speed should be decreased to avoid yarn damage caused by excessive tension. The fuzzy inference process infers the input process adaptation exponent according to these rules to determine the adjustment direction and degree of the yarn tension and spinning speed. Conduct defuzzification to obtain the adjustment values of the yarn tension and spinning speed: Defuzzification is a key step in the fuzzy control system. In fuzzy inference, the output variables (i.e., the adjustment values of the yarn tension and spinning speed) are usually fuzzy, and these values are inferred based on fuzzy sets (such as "high", "medium", "low"). The fuzzy output results are converted into precise adjustment numerical values through defuzzification techniques. These adjustment values will directly guide how the textile equipment adjusts the yarn tension and spinning speed. Adjust the yarn tension and spinning speed according to the defuzzification result: According to the adjustment values after defuzzification, the control system will issue adjustment instructions to change the settings of the textile equipment, thereby realizing the dynamic adjustment of the yarn tension and spinning speed. This helps to optimize the production process in real time and ensure that the quality of the yarn always meets the standards. Real-time monitor the adjusted yarn tension and spinning speed: After the adjustment, the system will continue to monitor the yarn tension and spinning speed in real time and compare them with the target values. If the actual values deviate from the target values, the system will make dynamic adjustments again. This closed-loop control ensures that the quality of the yarn in the production process can always be maintained at the best level.

[0037] Specifically, according to the textile equipment location information and the process adaptation exponent, the specific process of judging the abnormal working state of the textile equipment is as follows: Obtain the location information and process adaptation exponent of the textile equipment; According to the threshold range of the process adaptation exponent, compare the process adaptation exponent of the equipment with the preset threshold; When the process adaptation exponent exceeds the threshold range of the process adaptation exponent, it indicates that the textile equipment is abnormal and triggers an alarm message and marks the abnormal location of the equipment.

[0038] In this implementation plan, the location information of textile equipment: During the textile production process, the actual location of the equipment is very important, especially in large production lines where multiple equipment are distributed at different locations. The location information helps the system accurately identify the location of the equipment, facilitating management and monitoring. Process adaptation index: As mentioned before, the process adaptation index is used to measure the matching degree between the current production process (such as tension, speed, etc.) and the yarn quality (such as surface smoothness, roughness, etc.). This index value can indicate whether the current production state of the textile equipment meets the expected process requirements. According to the threshold range of the process adaptation index, compare the process adaptation index of the equipment with the preset threshold: The process adaptation index of each equipment has a normal range (i.e., the threshold range), which is usually preset according to historical data, process requirements, and production standards. Threshold comparison: According to the process adaptation index of the equipment, compare it with the preset threshold range. For example: If the process adaptation index is higher than the threshold, it may indicate that the equipment has excessive adjustment or production anomalies (such as too high tension or speed), resulting in product quality not meeting the standards. If the process adaptation index is lower than the threshold, it may indicate that the equipment is not operating properly (such as equipment failure, resulting in substandard yarn quality). If the process adaptation index is within the normal range, the equipment state is normal; if it exceeds the threshold range, the system will consider that the equipment has an anomaly. When the process adaptation index exceeds the threshold range of the process adaptation index, it means that the textile equipment has an anomaly and triggers an alarm message and marks the abnormal location of the equipment: Abnormal state determination: When the process adaptation index of the equipment exceeds the predetermined normal range, it indicates that the equipment may have performance failures or improper process settings. For example, there may be excessive tension, too high temperature, or unreasonable speed, resulting in problems with the surface quality of the yarn. Trigger alarm message: When the system detects an anomaly, it will automatically trigger an alarm. This usually includes sound, light alarm, SMS notification, or other alarm methods to notify the operator or maintenance personnel to handle it immediately. Mark the abnormal location of the equipment: By combining with the location information of the equipment, the system can mark the location of the equipment where the anomaly occurs, helping the staff quickly locate the problem equipment for inspection or maintenance. This mark can also be displayed on the operation interface through the system or automatically recorded in the equipment log.

[0039] Specifically, the specific process of optimizing the patrol path by dynamically programming the patrol trajectory through the A* algorithm is as follows: Determine the textile equipment that needs to be patrolled according to the alarm information, and obtain the process adaptation index of the textile equipment; Construct a map model of the location of the textile equipment and define the connection relationship between the equipment; According to the process adaptation index of the equipment, analyze the process adaptation index and path cost of the equipment through the A* algorithm, calculate the shortest path from the current equipment to the target equipment, and generate a patrol trajectory; Real-time monitor the process adaptation index and dynamically adjust the patrol path.

[0040] In this implementation, the textile equipment to be inspected is determined based on the alarm information, and the process adaptation index of the textile equipment is obtained: Through the alarm information received by the system (such as equipment anomalies, process adaptation index exceeding the threshold, etc.), the system identifies the equipment that needs to be inspected. The process adaptation index related to each piece of equipment is obtained, which represents the matching degree between the current operating state of the equipment and the optimal process parameters, and is used to determine whether the equipment needs inspection or maintenance. A map model of the textile equipment location is constructed, and the connection relationship between the equipment is defined: According to the physical location of the equipment, a map model of the equipment location is constructed. This model converts the equipment location into a network graph, where the equipment nodes represent different textile equipment, and the connection relationship between the equipment represents the path between them. The connection relationship between the equipment can be a directly connected path (such as physical distance, connection of the production line, etc.) or a connection through a preset path. Based on the process adaptation index of the equipment, the process adaptation index and path cost of the equipment are analyzed through the A* algorithm: The A* algorithm is a heuristic search algorithm used to find the shortest path in a graph. In this step, the A* algorithm not only considers the physical distance (path cost) between the equipment, but also combines the process adaptation index of each piece of equipment as an additional cost. Path cost: includes the distance between the equipment, the working state of the equipment (such as process adaptation index), etc. The higher the process adaptation index, the closer the state of the equipment is to the ideal process, and the lower the path cost may be; conversely, equipment with a low process adaptation index may require a longer inspection time or adjustment, so the path cost may be higher. Calculate the shortest path from the current equipment to the target equipment and generate an inspection trajectory: Use the A* algorithm to calculate the shortest path from the current inspected equipment to the target equipment. This path not only considers the distance, but also adjusts the weight according to the process adaptation index of each piece of equipment to ensure that the inspector inspects the equipment along the optimal path. Generate an inspection trajectory: According to the calculated shortest path, the system plans the route that the inspector should follow to ensure the optimal use of resources and time. Monitor the process adaptation index in real time and dynamically adjust the inspection path: As the inspection progresses, the system continuously monitors the process adaptation index of the equipment to ensure real-time acquisition of the equipment status update. If the process adaptation index of a certain piece of equipment changes during the inspection, the system will automatically adjust the inspection path to ensure that the actual state of the equipment matches the planned inspection path, thereby achieving dynamic optimization.

[0041] In summary, this application has at least the following effects:

[0042] The textile production process optimization method based on intelligent terminals can obtain process parameters and yarn surface states in real time, automatically adjust yarn tension and spinning speed, optimize the production process, reduce manual intervention, and improve the automation level and efficiency of the production process. By accurately analyzing the matching degree between process parameters and yarn surface states, it can ensure the best matching of the production process and yarn quality, thereby improving the stability and quality of products and reducing the generation of unqualified products. Based on the dynamic monitoring of the process adaptation index and combining the A-star algorithm to optimize the inspection path, it can detect equipment abnormalities in a timely manner and trigger alarms, ensuring that equipment problems can be discovered and repaired as early as possible, thereby reducing the failure rate and the risk of production interruption. The application of the A-star algorithm in inspection path planning enables inspectors to efficiently complete equipment inspection tasks. By combining the process adaptation index of the equipment, optimizing the inspection sequence and path, it ensures the reasonable allocation of inspection resources and improves the inspection efficiency. Through the combination of the fuzzy control algorithm and the real-time monitoring system, this application can intelligently adjust production parameters and optimize equipment management, reduce human intervention, and improve the flexibility and adaptability of the production process.

[0043] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0044] The present invention is described with reference to the flowcharts and / or block diagrams of systems, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, and the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices produce means for realizing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 the functions specified in one block or multiple blocks.

[0045] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including instruction means, and the instruction means realizes the functions in Figure 1 one process or multiple processes and / or blocks Figure 1The functions specified in one or more boxes.

[0046] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are executed on the computer or other programmable apparatus to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable apparatus provide for implementing the steps of the process Figure 1 One process or more processes and / or boxes Figure 1 The steps of the functions specified in one box or more boxes.

[0047] Although the preferred embodiments of the present invention have been described, additional changes and modifications can be made by those skilled in the art once they learn of the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications falling within the scope of the present invention.

[0048] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A textile production process optimization method based on intelligent terminals, characterized in that: The following steps are involved: S1. By connecting the sensor integrated in the smart glasses with the interface module of the textile equipment, the process parameters are obtained in real time, and the image of the yarn surface state is collected to obtain the yarn surface image data; S2. Input the process parameters and yarn surface image data into the MES system, build a textile production process monitoring model, analyze the matching degree between the yarn surface state and the process parameters, and obtain the process adaptation index; S3. dynamically adjust the yarn tension and spinning speed through fuzzy control algorithm according to the process adaptation index; S4. According to the location information of textile equipment and the process adaptation index, the abnormal working state of textile equipment is judged, and the inspection trajectory is dynamically planned through the A-star algorithm to optimize the inspection path; The MES system has the functions of receiving information, displaying textile equipment location information and reporting processing results; The process adaptation index is used to evaluate the matching degree between the yarn quality and the current production process parameters; The specific process of constructing the textile production process monitoring model is as follows: Perform data cleaning, denoising and standardization on process parameters and yarn surface image data; Extract surface quality features from yarn surface image data, combine process parameters, build a data set, train the data set through neural network, establish a textile production process monitoring model, and analyze the relationship between process parameters and yarn quality; The specific process of analyzing the matching degree between the yarn surface state and the process parameters is as follows: Input yarn surface image data and process parameters into the established textile production process monitoring model; Extract the correlation between the features of yarn surface image data and process parameter features, compare the process parameters and various features in the surface image data, calculate the matching degree between process parameters and yarn surface quality based on the trained correlation function in the textile production process monitoring model, and identify whether the process parameters match the yarn surface state by analyzing the matching index; The specific process of obtaining the process adaptation index is as follows: According to the trained correlation function in the textile production process monitoring model, the relationship between the yarn surface state characteristics and the process parameters is analyzed, the matching degree between the process parameters and the yarn surface quality is identified, and the process adaptation index is obtained; The process adaptation index formula is as follows: ;in: is the matching degree of the neural network output, is the weight coefficient, which controls the contribution of each item to the final matching index, i represents each element in the process parameters, j represents each element in the yarn surface state characteristics, n is the number of process parameters, m is the number of yarn surface state characteristics, and is the mean of process parameters and yarn surface state characteristics; The specific process of dynamically adjusting the yarn tension and spinning speed by fuzzy control algorithm according to the process adaptation index is as follows: Inputting the process adaptation index into the fuzzy control system; Fuzzy reasoning is performed based on the preset fuzzy rule base to analyze the relationship between the process adaptation index and the yarn tension and spinning speed; Perform defuzzification to obtain adjustment values ​​of yarn tension and spinning speed; Adjusting the yarn tension and spinning speed according to the defuzzification results, and monitoring the adjusted yarn tension and spinning speed in real time; The specific process of optimizing the inspection path by dynamically planning the inspection trajectory through the A-star algorithm is as follows: Determine the textile equipment that needs to be inspected based on the alarm information, and obtain the process adaptation index of the textile equipment; Build a map model of the location of textile equipment and define the connection relationship between equipment; According to the process adaptation index of the equipment, the A-star algorithm is used to analyze the process adaptation index and path cost of the equipment, calculate the shortest path from the current equipment to the target equipment, and generate the inspection trajectory; Monitor the process adaptation index in real time and dynamically adjust the inspection path.

2. The textile production process optimization method based on intelligent terminal according to claim 1 is characterized in that: The process parameters include yarn tension, spinning speed, spinning temperature, and air flow; The yarn surface image data includes yarn thickness change rate, yarn color difference value, and yarn roughness.

3. The textile production process optimization method based on intelligent terminal according to claim 2 is characterized in that: According to the location information of textile equipment and the process adaptation index, the specific process of judging the abnormal working state of textile equipment is as follows: Obtain location information and process adaptation index of textile equipment; According to the threshold range of the process fitness index, the process fitness index of the equipment is compared with a preset threshold value; When the process adaptation index exceeds the threshold range of the process adaptation index, it indicates that there is an abnormality in the textile equipment and triggers an alarm message and marks the abnormal location of the equipment.

Images