A new textile material intelligent manufacturing internet of things monitoring system

Abstract

The application relates to a new textile material intelligent manufacturing Internet of Things monitoring system and relates to the technical field of intelligent manufacturing of the textile industry.The system comprises a sensing layer, a network layer and a platform layer; the sensing layer comprises various sensors arranged at various links of a textile production line and is used for collecting temperature, humidity, tension, speed and quality parameters in a new textile material production process in real time; the network layer adopts an industrial Internet of Things communication protocol to realize reliable transmission of data; the platform layer comprises an edge computing node and a cloud data processing center and is used for data storage, analysis and decision-making; and the application layer provides intelligent monitoring, predictive maintenance and quality tracing functions.Through multi-source data fusion and edge-cloud collaborative computing architecture, the application realizes real-time monitoring, intelligent early warning and self-adaptive regulation and control of the whole process of new textile material production, improves production efficiency and product quality, and reduces energy consumption and equipment failure rate.

Description

Technical Field

[0001] This invention relates to the field of intelligent manufacturing technology in the textile industry, and in particular to an Internet of Things (IoT) monitoring system for intelligent manufacturing of new textile materials. Background Technology

[0002] As an important component of the high-tech industry, the production of new textile materials involves multiple complex processes such as spinning, weaving, and dyeing and finishing, requiring extremely high precision in controlling the temperature and humidity of the production environment, equipment operating status, and process parameters. Traditional textile production monitoring mainly relies on manual inspections and decentralized automated control systems, which suffer from problems such as incomplete data collection, poor real-time performance, severe information silos, and delayed decision-making responses.

[0003] With the development of intelligent manufacturing technology, the application of IoT technology in the textile industry is becoming increasingly widespread. However, most existing IoT systems for textile production only achieve simple data acquisition and remote monitoring functions, and still have significant shortcomings in terms of the real-time and depth of data processing, the flexibility and scalability of system architecture, and the accuracy and adaptability of intelligent decision-making. Especially in the production of new textile materials, due to the large variety of products, rapid process changes, and strict quality requirements, existing systems are unable to meet the needs of flexible and intelligent production.

[0004] Therefore, it is evident that the existing monitoring technologies for the production of new textile materials still have inconveniences and shortcomings in terms of methods, system architecture, data processing, and usage, and urgently need further improvement. To address the problems in intelligent manufacturing monitoring of new textile materials, relevant manufacturers have spared no effort in seeking solutions, but for a long time, no suitable design has been developed. Furthermore, general methods, manufacturing methods, processing methods, and systems lack appropriate methods, manufacturing methods, processing methods, and structures to solve the aforementioned problems. This is clearly a problem that relevant industries urgently need to solve.

[0005] In view of the shortcomings of existing monitoring technologies for the production of new textile materials, the inventor, based on years of practical experience and professional knowledge in the design and manufacture of such products, and in conjunction with theoretical application, actively researched and innovated to create a new Internet of Things (IoT) monitoring system for intelligent manufacturing of new textile materials. This system aims to improve upon existing textile production monitoring systems, making them more practical. After continuous research, design, and repeated trials and improvements, this invention, possessing genuine practical value, was finally created. Summary of the Invention

[0006] The main objective of this invention is to overcome the shortcomings of existing monitoring technologies for the production of new textile materials and to provide a new Internet of Things (IoT) monitoring system for intelligent manufacturing of new textile materials. The technical problem to be solved is to enable the IoT system to achieve comprehensive perception, reliable transmission, intelligent processing and precise service throughout the entire production process of new textile materials by constructing a four-layer architecture of perception-network-platform-application, thereby making it more practical and having industrial application value.

[0007] Another objective of this invention is to provide an IoT monitoring system for intelligent manufacturing of new textile materials. The technical problem to be solved is to enable it to achieve in-depth analysis and global optimization of large-scale data while ensuring real-time response capabilities through an edge-cloud collaborative computing architecture, thereby making it more suitable for practical use.

[0008] Another objective of this invention is to provide an Internet of Things (IoT) monitoring system for intelligent manufacturing of new textile materials. The technical problem to be solved is to enable the system to achieve predictive maintenance of equipment, intelligent quality prediction, and adaptive optimization of processes through multi-source sensor data fusion and artificial intelligence analysis, thereby making it more suitable for practical use.

[0009] Another objective of this invention is to provide an Internet of Things (IoT) monitoring system for intelligent manufacturing of new textile materials. The technical problem to be solved is to enable it to ensure the security and traceability of production data through blockchain technology, thereby meeting the management requirements for high-quality production of new textile materials and making it more suitable for practical use.

[0010] The objective of this invention and the technical problem it solves are achieved through the following technical solution. The IoT monitoring system for intelligent manufacturing of new textile materials proposed in this invention includes: a perception layer, comprising various sensor nodes deployed in each process stage of the textile production line, used to collect process parameters, equipment status parameters, and environmental parameters in real time during the production of new textile materials; a network layer, employing industrial IoT communication protocols to achieve data transmission between the perception layer and the platform layer, including edge gateways, industrial Ethernet, and wireless communication networks; a platform layer, comprising edge computing nodes deployed on the production site and a remote cloud data processing center, wherein the edge computing nodes are used for localized processing and rapid response of real-time data, and the cloud data processing center is used for large-scale data storage, in-depth analysis, and global optimization decision-making; and an application layer, based on the data analysis results of the platform layer, providing functions such as intelligent monitoring of the production process, predictive maintenance of equipment, product quality traceability, and energy consumption optimization management; wherein, the edge computing nodes and the cloud data processing center adopt a collaborative computing architecture, dynamically allocating computing tasks according to data characteristics and processing timeliness requirements.

[0011] The objectives of this invention and the technical problems it addresses can be further achieved by the following technical measures.

[0012] The aforementioned IoT monitoring system for intelligent manufacturing of new textile materials includes sensor nodes in the sensing layer, such as temperature sensors, humidity sensors, tension sensors, speed sensors, visual inspection sensors, vibration sensors, and energy consumption monitoring sensors. Each sensor node has self-diagnosis and adaptive calibration functions.

[0013] The aforementioned IoT monitoring system for intelligent manufacturing of new textile materials uses a heterogeneous network architecture that combines at least one of the following wireless communication technologies: 5G, Wi-Fi 6, LoRa, and NB-IoT, with industrial Ethernet. It also employs time-sensitive networking technology to ensure the real-time transmission of critical control data.

[0014] The objectives of this invention and the solutions to its technical problems are also achieved through the following technical solutions. According to the IoT monitoring system for intelligent manufacturing of new textile materials proposed in this invention, the edge computing node includes: a data preprocessing module for filtering, compressing, and extracting features from the collected raw data; a local decision-making module for millisecond-level response control in emergency situations; and a data caching module for temporarily storing data during network interruptions. The edge computing node and the cloud transmit data using an incremental synchronization mechanism.

[0015] The objectives of this invention and the technical problems it addresses can be further achieved by the following technical measures.

[0016] The aforementioned IoT monitoring system for intelligent manufacturing of new textile materials includes a cloud data processing center comprising: a data lake storage module for storing multi-source heterogeneous production data; a digital twin module for constructing a virtual mapping model of the textile production line; an artificial intelligence analysis engine for analyzing production data based on deep learning algorithms to achieve process parameter optimization, quality prediction, and equipment fault diagnosis; and a visualization module for presenting production status and decision-making suggestions.

[0017] The aforementioned IoT monitoring system for intelligent manufacturing of new textile materials includes the following intelligent monitoring functions for the production process at the application layer: production progress tracking based on real-time data, process deviation early warning, and multi-dimensional data visualization; and the predictive maintenance function for equipment uses machine learning algorithms to predict the remaining service life of the equipment and generate a maintenance plan based on equipment vibration data, temperature data, and operating time.

[0018] The aforementioned IoT monitoring system for intelligent manufacturing of new textile materials, wherein the product quality traceability function at the application layer assigns a unique identifier to each batch of new textile materials, links the entire process data from raw material warehousing to finished product warehousing, and enables rapid location and cause analysis of quality problems.

[0019] The aforementioned IoT monitoring system for intelligent manufacturing of new textile materials, wherein the edge-cloud collaborative computing architecture adopts a dynamic task scheduling mechanism, specifically including: tasks with real-time requirements exceeding a preset threshold are processed locally by edge computing nodes; tasks with computational complexity exceeding a preset threshold are uploaded to the cloud for processing; and the edge computing nodes and the cloud achieve collaborative updates of the algorithm model through model compression and knowledge distillation techniques.

[0020] The aforementioned IoT monitoring system for intelligent manufacturing of new textile materials also includes a security management layer, which uses blockchain-based data storage technology to ensure the immutability of production data, employs a zero-trust architecture to achieve device access authentication and data transmission encryption, and uses hierarchical permission management to control the data access scope of different roles.

[0021] The aforementioned IoT monitoring system for intelligent manufacturing of new textile materials employs an adaptive control strategy. When process parameters deviate from the preset range, the system automatically triggers a feedback control mechanism to adjust the operating status of the production equipment or sends early warning information to the operators and provides optimization suggestions.

[0022] Compared with the prior art, the present invention has significant advantages and beneficial effects. As can be seen from the above technical solution, in order to achieve the aforementioned objectives, the main technical contents of the present invention are as follows:

[0023] This invention proposes an IoT monitoring system for intelligent manufacturing of new textile materials. By constructing a five-layer architecture—a perception layer, a network layer, a platform layer, an application layer, and a security management layer—it achieves comprehensive digitalization and intelligentization of new textile material production. The perception layer uses multiple types of sensors to collect data throughout the entire production process; the network layer ensures the reliability and real-time performance of data transmission through a heterogeneous network architecture; the platform layer balances the needs of real-time response and in-depth analysis through an edge-cloud collaborative computing architecture; the application layer achieves intelligent monitoring, predictive maintenance, and quality traceability through artificial intelligence algorithms; and the security management layer ensures data security through technologies such as blockchain.

[0024] As can be seen from the above, this invention constructs a complete solution for intelligent manufacturing of new textile materials by integrating technologies such as the Internet of Things, edge computing, cloud computing, artificial intelligence, and blockchain.

[0025] By employing the above technical solution, the IoT monitoring system for intelligent manufacturing of new textile materials of the present invention has at least the following advantages:

[0026] 1. Through the edge-cloud collaborative computing architecture, it not only ensures millisecond-level real-time response for critical control tasks, but also realizes in-depth analysis and global optimization of large-scale production data, solving the problems of insufficient real-time performance of traditional centralized cloud computing architecture and limited analysis capabilities of pure edge computing architecture;

[0027] 2. By using multi-source sensor data fusion and digital twin technology, virtual mapping and real-time monitoring of the textile production line were achieved, improving the transparency and controllability of the production process;

[0028] 3. By using an artificial intelligence analysis engine, we can predict equipment failures, provide early warnings of quality risks, and optimize process parameters, shifting from passive maintenance to predictive maintenance and from experience-driven to data-driven approaches, which significantly improves production efficiency and product quality.

[0029] 4. By using blockchain technology to achieve tamper-proof storage of production data, combined with full-process quality traceability, the management requirements and market supervision needs of high-quality production of new textile materials are met.

[0030] 5. The system adopts a modular and scalable architecture design, which can be flexibly configured according to the production scale and process characteristics of different textile enterprises, and has good adaptability and promotion value.

[0031] In summary, this invention's unique IoT monitoring system for intelligent manufacturing of new textile materials achieves an intelligent upgrade in the production of these materials through innovative system architecture and technological integration. It possesses numerous advantages and practical value, and is truly innovative as no similar designs have been publicly disclosed or used in the same field. It represents a significant improvement in system architecture, data processing algorithms, and application functions, demonstrating substantial technological advancement and producing user-friendly and practical results. Compared to existing textile production monitoring systems, it offers enhanced functionality, making it more suitable for practical application and possessing broad industrial applicability. It is indeed a novel, progressive, and practical new design.

[0032] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, the preferred embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0033] The specific embodiments and system structure of the present invention are given in detail in the following examples and accompanying drawings. Attached Figure Description

[0034] Figure 1 This is a schematic diagram of the overall architecture of the intelligent manufacturing IoT monitoring system for new textile materials of the present invention. Detailed Implementation

[0035] To further illustrate the technical means and effects adopted by the present invention to achieve the intended purpose, the following detailed description, in conjunction with the accompanying drawings and preferred embodiments, describes the specific implementation, system structure, functional modules, and effects of the IoT monitoring system for intelligent manufacturing of new textile materials proposed according to the present invention.

[0036] The preferred embodiment of the intelligent manufacturing IoT monitoring system for new textile materials of the present invention has an overall architecture comprising five parts: a perception layer, a network layer, a platform layer, an application layer, and a security management layer.

[0037] The sensing layer is deployed at various stages of the textile production line, including sensor groups for the spinning, weaving, dyeing and finishing, and environmental monitoring. The spinning sensor group includes melt temperature sensors, spinning box temperature sensors, side-blowing air temperature and humidity sensors, oil concentration sensors, yarn tension sensors, and winding speed sensors, used to monitor process parameters in real time. The weaving sensor group includes warp tension sensors, weft tension sensors, loom vibration sensors, weaving speed sensors, and warp / weft breakage detection sensors. The dyeing and finishing sensor group includes dye liquor temperature sensors, pH sensors, concentration sensors, fabric running speed sensors, and color difference detection sensors. The environmental monitoring sensor group includes workshop temperature and humidity sensors, dust concentration sensors, noise sensors, and energy consumption monitoring sensors. Each sensor node has self-diagnostic capabilities, automatically detecting and reporting sensor faults, and also features adaptive calibration, automatically adjusting measurement parameters according to environmental changes to ensure data accuracy.

[0038] The network layer employs a heterogeneous network architecture, including fieldbus, industrial Ethernet, edge gateways, and a wireless network. The fieldbus connects each sensor node to the edge gateway, using Modbus, Profibus, or CAN bus protocols. The industrial Ethernet connects the edge gateway, edge computing nodes, and production control equipment, using EtherCAT or Profinet real-time Ethernet protocols. The wireless network includes 5G communication modules deployed on mobile devices, Wi-Fi 6 access points, and a LoRa / NB-IoT network for low-power sensor connectivity, enabling flexible data transmission. The network layer utilizes time-sensitive networking technology, prioritizing critical control data to ensure real-time transmission even during network congestion.

[0039] The platform layer includes edge computing nodes and a cloud data processing center. The edge computing nodes are deployed in the production workshop and include a data preprocessing module, a local decision-making module, and a data caching module. The data preprocessing module filters and denoises the collected raw data, compresses the data, and extracts features, reducing the original sampling frequency from the kHz level to the Hz level and decreasing the data transmission volume. The local decision-making module runs lightweight machine learning models to identify and respond to emergency conditions such as equipment overheating and abnormal tension in milliseconds, directly controlling the equipment to stop or adjusting the operating parameters. The data caching module adopts a circular buffer design and can cache at least 24 hours of production data during network interruptions, automatically synchronizing to the cloud after the network resumes. The cloud data processing center is deployed in the enterprise private cloud or public cloud and includes a data lake storage module, a digital twin module, an artificial intelligence analysis engine, and a visualization display module. The data lake storage module uses a distributed file system to store structured, semi-structured, and unstructured production data, supporting PB-level data storage and second-level queries. The digital twin module constructs a high-fidelity virtual production line model based on the geometric parameters, equipment parameters, and operating data of the physical production line, realizing real-time mapping and simulation prediction of the production status. The artificial intelligence analysis engine runs deep learning models such as long short-term memory networks and convolutional neural networks based on the TensorFlow / PyTorch framework to achieve process parameter optimization, quality prediction, and equipment fault diagnosis. The visualization display module constructs a three-dimensional visualization interface based on WebGL technology to display information such as production status, equipment health, and quality analysis results.

[0040] The application layer includes an intelligent monitoring module, a predictive maintenance module, a quality traceability module, and an energy consumption optimization module. The intelligent monitoring module provides functions such as a production progress dashboard, real-time process curves, and an abnormal alarm list, supporting access from the PC side and the mobile side. The predictive maintenance module predicts the remaining service life of equipment based on equipment vibration spectrum analysis, temperature trend analysis, and operation duration statistics, generating a maintenance plan 7 - 30 days in advance to avoid unplanned downtime. The quality traceability module generates a unique blockchain-based identification code for each batch of products, recording all-process data such as raw material batches, production time, process parameters, and quality inspection results, and can locate the problem link within 5 minutes when a quality problem occurs. The energy consumption optimization module analyzes the energy consumption data of each process, identifies high-energy-consuming equipment and process links, provides energy-saving transformation suggestions, and achieves a 10% - 20% reduction in energy consumption.

[0041] The security management layer includes a blockchain evidence storage module, a zero-trust security module, and an access control module. The blockchain evidence storage module uses consortium blockchain technology to store critical production data, such as process parameter modification records and quality inspection reports, on the blockchain, ensuring data immutability and traceability. The zero-trust security module employs technologies such as device certificate authentication, two-way TLS encrypted transmission, and micro-segmentation to achieve a "never trust, continuous verification" security architecture. The access control module, based on the RBAC model, assigns different data access permissions to operators, technicians, and managers, supporting fine-grained data anonymization and audit logs.

[0042] On the spinning production line, temperature and pressure sensors are deployed at the melt pipe, multiple temperature sensors are deployed at the spinning box, temperature and humidity sensors and wind speed sensors are deployed at the side blowing windows, oil concentration sensors are deployed at the oil tanker, tension and speed sensors are deployed at the guide roller, and winding tension sensors and vision inspection sensors are deployed at the winding head. All sensors are connected to the edge gateway via a fieldbus, and the sampling frequency is set to vary from 10ms to 1s depending on the parameter variation characteristics.

[0043] After being collected by the perception layer, the raw data first enters the edge computing nodes for preprocessing step S1, including data cleaning, feature extraction, and outlier detection. Then, it enters the task scheduling step S2, where data is distributed according to data type and processing requirements: emergency control data enters the local decision-making step S3, where the edge nodes directly process and output control commands; routine monitoring data enters the data caching step S4, is compressed, and then transmitted to the cloud via the network layer; complex analysis tasks enter the cloud processing step S5, where the cloud-based AI engine performs in-depth analysis. The edge nodes and the cloud maintain algorithm model consistency through a model synchronization step S6, where the cloud-trained model is compressed and then distributed to the edge nodes for updates.

[0044] The system continuously performs data acquisition step T1, followed by deviation analysis step T2 comparing real-time data with preset process standards. If the deviation is within the allowable range, it returns to normal monitoring status; if the deviation exceeds the threshold, it proceeds to risk level assessment step T3. In low-risk situations, it enters early warning step T4, sending a notification to operators and providing optimization suggestions; in medium-risk situations, it enters automatic adjustment step T5, where edge computing nodes directly control the actuators to adjust process parameters; in high-risk situations, it enters emergency shutdown step T6, immediately cutting off equipment power and locking the site, while simultaneously notifying management personnel. All abnormal events are recorded on the blockchain for evidence storage step T7, ensuring the integrity and immutability of the event records.

[0045] In this embodiment, the dynamic task scheduling mechanism for edge-cloud collaborative computing is implemented as follows: A time threshold Tth and a computational complexity threshold Cth are set. For tasks with processing time requirements less than Tth (such as emergency device shutdown control requiring a response time of <10ms), they are processed locally by the edge computing nodes. For tasks with computational complexity greater than Cth (such as training a quality prediction model based on deep learning), they are uploaded to the cloud for processing. For tasks between these two thresholds, dynamic decisions are made based on the current edge node load and network conditions. An incremental synchronization mechanism is used between the edge nodes and the cloud, transmitting only changed data rather than the entire dataset, reducing network bandwidth usage by more than 90%.

[0046] In this embodiment, the adaptive control strategy is specifically applied in the dyeing and finishing process as follows: the system monitors the dye liquor temperature, fabric running speed, and color difference value in real time. When the temperature deviation exceeds ±1℃ or the color difference ΔE exceeds 0.5, the system automatically adjusts the steam valve opening or the fabric running speed to bring the process parameters back to the standard range. If three consecutive adjustments are ineffective or the deviation continues to increase, it is determined to be an equipment failure, triggering the predictive maintenance process.

[0047] Example 1:

[0048] This embodiment provides an intelligent manufacturing IoT monitoring system for a high-performance carbon fiber textile new material production line. The system adopts a four-layer architecture design to realize intelligent monitoring of the entire process from raw material pretreatment, spinning, weaving to finishing.

[0049] In the sensing layer deployment, PT100 platinum resistance temperature sensors are installed in key locations such as the spinning box, coagulation bath, and heat treatment furnace. The measurement range covers -50℃ to 400℃ with an accuracy of ±0.1℃. The sampling frequency is set to 10Hz and has a self-diagnostic function. When the self-drift exceeds ±0.5℃, the calibration program is automatically triggered. At the same time, capacitive humidity sensors are deployed in the raw yarn storage area and weaving workshop, with a range of 0-100%RH and an accuracy of ±2%RH. The reference value can be automatically adjusted according to environmental changes. Strain gauge tension sensors are installed in the spinning drafting area and winding area to monitor the yarn tension in real time. A laser Doppler velocimeter is used to monitor the spinning and winding speeds. High-speed industrial cameras are deployed on the spinning line in conjunction with AI image processing chips to detect yarn defects. MEMS triaxial accelerometers are installed on rotating equipment to monitor vibration status with a sampling frequency of 10kHz. Smart meters are installed in the power distribution circuits of each piece of equipment to calculate the energy consumption per unit output. All sensor nodes integrate self-diagnostic modules and transmit information through a unified data encapsulation format.

[0050] The network layer adopts a heterogeneous network architecture of "5G + Industrial Ethernet + LoRa". The 5G network is used for high-bandwidth video stream transmission of visual inspection sensors and access of mobile inspection equipment, with end-to-end latency controlled within 10ms. The Industrial Ethernet uses the PROFINET protocol to connect control devices and is designed with ring network redundancy, with a switching time of less than 50ms. At the same time, TSN switches are deployed to reserve time slots for critical control data to ensure transmission latency of less than 1ms. The LoRa network is used for low-speed sensor transmission, and multi-protocol conversion is realized through industrial edge gateways, with 72-hour local caching capability.

[0051] The platform layer deploys edge computing nodes in each production workshop. Its data preprocessing module uses wavelet denoising algorithm to process vibration signals and moving average filtering to process temperature signals. It uses lossy compression based on the rotating door algorithm to achieve a 10:1 compression ratio and extracts time-domain and frequency-domain features from vibration signals to compress the data volume to 5% of the original data. The local decision module deploys a lightweight neural network model for real-time detection of yarn defects with an inference latency of less than 50ms. It is configured with emergency response logic to trigger the winding head to decelerate in milliseconds when the spinning tension exceeds a set threshold of 120%. The data caching module is configured with 1TB of storage using a circular buffer mechanism and stores various types of data according to priority. It uses an incremental synchronization mechanism with the cloud to transmit only new data added during network interruptions. The cloud data processing center is deployed on the enterprise's private cloud. The data lake storage module uses HDFS to retain 3 years of original time-series data, HBase to store structured process data, and MongoDB to store unstructured data, partitioned by production line and date. The digital twin module builds a 3D virtual model based on the Unity 3D engine and accesses on-site data in real time through OPC UA, integrating ANSYS. The Fluent simulation engine predicts tow quality and supports historical data playback. The AI ​​analysis engine, based on deep reinforcement learning, automatically optimizes process parameters to achieve minimum energy consumption and optimal quality, reducing energy consumption by 8%. It uses an LSTM neural network to predict finished product performance with 92% accuracy and provides a 4-hour early warning of quality anomalies. A convolutional neural network analyzes vibration spectra to identify fault types with 95% accuracy. The visualization module, based on Grafana, develops a monitoring dashboard supporting web and mobile access. The edge-cloud collaborative computing architecture establishes a hierarchical task processing strategy, deploying emergency control tasks at the edge to achieve a response time of less than 10ms, real-time detection tasks at the edge to achieve a response time of less than 100ms, and deep analysis tasks deployed in the cloud. Large models trained in the cloud are compressed into lightweight models using knowledge distillation and distributed to edge nodes. Edge nodes collect misclassified samples and upload them periodically for incremental training, while a federated learning mechanism protects data privacy.

[0052] The application layer's intelligent production process monitoring function displays the completion rate and estimated completion time of each process in real time based on the MES system. It establishes standard ranges for process parameters to achieve graded early warnings and provides multi-dimensional visualization through trend charts, scatter plots, and 3D production line models. The equipment predictive maintenance function collects vibration, temperature, and runtime data to build a health indicator model. It uses a random forest algorithm to predict the remaining service life of the equipment and automatically generates maintenance work orders when the remaining service life is less than 7 days, reducing unplanned downtime by 60% and maintenance costs by 25%. The product quality traceability function assigns a unique QR code to each batch of carbon fiber precursor, establishing a full-process association from raw material information, process data, testing data to environmental data, enabling the location of quality problems within 30 minutes. The energy consumption optimization management function monitors the energy consumption of each piece of equipment in real time, establishes a benchmark model, identifies high-energy-consuming equipment, and optimizes the start-up and shutdown sequence to reduce overall energy consumption by 12%.

[0053] The security management layer uses the Hyperledger Fabric consortium blockchain to store critical process data on the blockchain to ensure its immutability. It uses X.509 certificates and two-way TLS authentication to authenticate device access and uses air interface encryption, IPSec, MACsec and AES-128 to encrypt data transmission. It uses network segmentation to achieve micro-segmentation to prevent lateral movement and establishes hierarchical permission management to control the data access scope of different roles.

[0054] The system also employs an adaptive control strategy to establish a mapping relationship between process parameters and equipment control. In automatic mode, it automatically adjusts when parameters deviate from the set value by ±2%, and triggers an early warning when they deviate by ±5%, requiring manual confirmation before adjustment. Simultaneously, it constructs a fault diagnosis expert system based on a knowledge graph, which pushes early warning information and provides possible cause analysis, suggested operating steps, and historical similar cases when an anomaly is detected. Ultimately, it achieves significant results, including increasing overall equipment efficiency from 78% to 89%, improving the rate of superior products from 92% to 97%, reducing quality complaints by 70%, reducing energy consumption by 12%, reducing maintenance costs by 25%, reducing labor costs by 30%, and shortening the response time for process anomalies from hours to seconds.

[0055] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the methods and techniques disclosed above without departing from the scope of the present invention to create equivalent embodiments. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. An IoT monitoring system for intelligent manufacturing of new textile materials, characterized in that, include: The perception layer includes various sensor nodes deployed in each process stage of the textile production line, used to collect process parameters, equipment status parameters and environmental parameters in real time during the production of new textile materials. The network layer uses industrial IoT communication protocols to realize data transmission between the perception layer and the platform layer, including edge gateways, industrial Ethernet and wireless communication networks; The platform layer includes edge computing nodes deployed on the production site and a remote cloud data processing center. The edge computing nodes are used for local processing and rapid response of real-time data, while the cloud data processing center is used for large-scale data storage, in-depth analysis, and global optimization decision-making. The application layer, based on the data analysis results from the platform layer, provides functions such as intelligent monitoring of the production process, predictive maintenance of equipment, product quality traceability, and energy consumption optimization management. The edge computing nodes and the cloud data processing center adopt a collaborative computing architecture, dynamically allocating computing tasks according to data characteristics and processing timeliness requirements.

2. The IoT monitoring system for intelligent manufacturing of new textile materials according to claim 1, characterized in that, The sensor nodes of the sensing layer include: temperature sensor, humidity sensor, tension sensor, speed sensor, visual inspection sensor, vibration sensor and energy consumption monitoring sensor. Each sensor node has self-diagnosis and adaptive calibration functions.

3. The IoT monitoring system for intelligent manufacturing of new textile materials according to claim 1 or 2, characterized in that, The network layer adopts a heterogeneous network architecture that combines at least one of the wireless communication technologies, such as 5G, Wi-Fi 6, LoRa, and NB-IoT, with industrial Ethernet, and uses time-sensitive networking technology to ensure the real-time transmission of critical control data.

4. The IoT monitoring system for intelligent manufacturing of new textile materials according to claim 1, characterized in that, The edge computing node includes: a data preprocessing module for filtering, compressing, and extracting features from the collected raw data; a local decision-making module for millisecond-level response control in emergency situations; and a data caching module for temporarily storing data during network interruptions. The edge computing node transmits data to the cloud using an incremental synchronization mechanism.

5. The IoT monitoring system for intelligent manufacturing of new textile materials according to claim 1, characterized in that, The cloud-based data processing center includes: a data lake storage module for storing multi-source heterogeneous production data; a digital twin module for constructing a virtual mapping model of the textile production line; an artificial intelligence analysis engine for analyzing production data based on deep learning algorithms to achieve process parameter optimization, quality prediction, and equipment fault diagnosis; and a visualization module for presenting production status and decision-making suggestions.

6. The IoT monitoring system for intelligent manufacturing of new textile materials according to claim 1, characterized in that, The intelligent monitoring function of the production process in the application layer includes: production progress tracking based on real-time data, process deviation early warning, and multi-dimensional data visualization; the predictive maintenance function of the equipment uses machine learning algorithms to predict the remaining service life of the equipment and generate a maintenance plan based on equipment vibration data, temperature data and running time.

7. The IoT monitoring system for intelligent manufacturing of new textile materials according to claim 1 or 6, characterized in that, The product quality traceability function in the application layer assigns a unique identifier to each batch of new textile materials, linking data from raw material warehousing to finished product delivery, enabling rapid location and root cause analysis of quality problems.

8. The IoT monitoring system for intelligent manufacturing of new textile materials according to claim 1, characterized in that, The edge-cloud collaborative computing architecture adopts a dynamic task scheduling mechanism, which includes: tasks with real-time requirements higher than a preset threshold are processed locally by edge computing nodes; tasks with computational complexity higher than a preset threshold are uploaded to the cloud for processing; and the edge computing nodes and the cloud achieve collaborative updates of algorithm models through model compression and knowledge distillation techniques.

9. The IoT monitoring system for intelligent manufacturing of new textile materials according to claim 1, characterized in that, The system also includes a security management layer, which uses blockchain-based data storage technology to ensure the immutability of production data, employs a zero-trust architecture to implement device access authentication and data transmission encryption, and uses hierarchical permission management to control the data access scope of different roles.

10. The IoT monitoring system for intelligent manufacturing of new textile materials according to claim 1, characterized in that, The system adopts an adaptive control strategy. When the process parameters are detected to deviate from the preset range, the feedback control mechanism is automatically triggered to adjust the operating status of the production equipment, or to send early warning information to the operators and provide optimization suggestions.

Images