Chemical fiber whole plant equipment internet of things electrical energy-saving closed-loop monitoring system

Abstract

The present application relates to the technical field of equipment energy-saving monitoring, and particularly relates to a chemical fiber whole workshop equipment Internet of Things electrical energy-saving closed-loop monitoring system, which comprises a global perception module, a network transmission module, an edge computing energy-saving regulation and control module, a cloud management and control platform and a field execution regulation and control module. The present application synchronously collects electrical parameters, operating conditions and environmental parameters of field equipment by arranging distributed Internet of Things sensing terminals, and completes data regularization and stable transmission through a protocol adaptation gateway; the edge computing module combines an embedded energy consumption identification model and an energy-saving regulation and control algorithm to identify the low-efficiency operating state of equipment in real time and output corresponding energy-saving regulation and control instructions. The present application completes the closed-loop management and control of electrical energy consumption monitoring, analysis and regulation of a chemical fiber workshop, effectively improves the hidden energy consumption problem in the chemical fiber production process, and improves the electrical energy utilization rate.

Description

Technical Field

[0001] This invention relates to the field of equipment energy-saving monitoring technology, and in particular to an Internet of Things (IoT) closed-loop monitoring system for electrical energy saving in a chemical fiber workshop. Background Technology

[0002] Chemical fiber production is a continuous, energy-intensive industrial production model. Workshops contain a large number of electrical devices, including those for spinning, texturing, winding, air conditioning and temperature control, water circulation, ventilation, and lighting. These devices are numerous, diverse, and operate in clusters, with electrical energy consumption accounting for over 70% of the company's total energy consumption. Currently, the electrical energy consumption management in most domestic chemical fiber production workshops has many shortcomings, severely hindering companies from achieving energy conservation, cost reduction, and intelligent upgrading.

[0003] The existing patent CN118966475A discloses an energy consumption optimization system for polyester fiber production. This solution relies on the Internet of Things to collect energy consumption data in polyester production, and realizes energy consumption statistics and anomaly early warning through background data analysis, thus completing basic digital management of production energy consumption. However, this solution can only realize open-loop monitoring and post-event data statistical analysis, and can only summarize and display the generated energy consumption data, resulting in extremely poor initiative and real-time performance in energy-saving control.

[0004] Meanwhile, chemical fiber production demands high stability of process parameters. Traditional energy-saving solutions often employ fixed parameter adjustments without considering production process constraints. Blindly adjusting speed and pressure can easily lead to quality problems such as uneven spinning tension, process temperature deviations, and product defects, failing to balance energy saving and production stability. Furthermore, chemical fiber workshops are characterized by high dust levels, strong electromagnetic interference, and continuous equipment operation year-round. Conventional monitoring systems suffer from unstable data transmission, frequent disconnections, and data loss, resulting in poor on-site applicability and a lack of long-term data review and strategy optimization capabilities, hindering sustained improvement in energy-saving effects. Summary of the Invention

[0005] To address the aforementioned technical shortcomings, this invention provides an IoT-based closed-loop monitoring system for electrical energy conservation in a chemical fiber workshop. This system enables comprehensive monitoring, intelligent analysis, precise closed-loop control, and autonomous iteration of energy-saving strategies for all electrical equipment in the workshop. It reduces electrical energy consumption while ensuring stable chemical fiber production processes and qualified product quality.

[0006] This invention discloses an IoT-based closed-loop monitoring system for electrical energy conservation in a chemical fiber workshop, comprising a global sensing module, a network transmission module, an edge computing energy-saving control module, a cloud management platform, and a field execution control module. The signal output terminal of the global sensing module is connected to the signal input terminal of the network transmission module, the signal output terminal of the network transmission module is connected to the signal input terminal of the edge computing energy-saving control module, the control signal output terminal of the edge computing energy-saving control module is connected to the signal input terminal of the field execution control module, and the edge computing energy-saving control module communicates bidirectionally with the cloud management platform. The global perception module includes multiple sets of distributed industrial-grade IoT sensor terminals. Each sensor terminal is deployed one-to-one or in zones according to the workshop equipment layout, corresponding to electrical equipment such as spinning equipment, texturing equipment, winding equipment, air conditioning auxiliary equipment, circulating water pumps, ventilation fans, and workshop lighting distribution cabinets. Each IoT sensor terminal continuously collects electrical parameters such as equipment voltage, current, active power, reactive power, power consumption, operating frequency, load rate, and start / stop status. At the same time, it collects operating condition parameters such as workshop temperature and humidity, air duct pressure, spinning process temperature, and equipment operating speed, achieving full coverage collection of operating parameters of all electrical equipment in the workshop. The network transmission module includes an industrial multi-protocol adapter gateway, a wired Ethernet transmission unit, and a wireless LoRa anti-interference transmission unit. The industrial multi-protocol adapter gateway has built-in protocol parsing and data preprocessing functions, which can automatically identify and adapt to industrial heterogeneous protocols such as Modbus and Profibus of various sensor terminals, and clean, deduplicate, and unify the format of the raw collected data. The gateway has local caching and breakpoint resume functions, which can adapt to the complex working conditions of strong electromagnetic interference and high dust in chemical fiber workshops, and ensure low-latency, high-reliability bidirectional transmission of multi-source sensing data. The edge computing energy-saving control module is the core control unit of the system, integrating an energy consumption feature extraction unit, an energy consumption anomaly identification unit, a process constraint-based adaptive energy-saving algorithm unit, and an instruction output unit. The energy consumption feature extraction unit performs multi-source fusion on the received standardized electrical data and operating condition data to extract multi-dimensional features such as equipment no-load energy consumption, light-load redundant energy consumption, and process parameter mismatch energy consumption. The energy consumption anomaly identification unit pre-stores a standard energy consumption threshold library for various chemical fiber equipment and a trained machine learning identification model, and determines the type and level of equipment energy consumption anomalies based on multi-dimensional features. The process constraint-based adaptive energy-saving algorithm unit presets chemical fiber production process priority rules, and under the premise of meeting the requirements of spinning and texturing production processes and ensuring product quality, matches the optimal operating parameters of the equipment and outputs refined energy-saving control instructions such as frequency fine-tuning, voltage stabilization, no-load delayed shutdown, load dynamic adaptation, and auxiliary machine cluster linkage start-stop. The on-site execution and control module includes an intelligent frequency converter, an electrical voltage stabilization module, an equipment start-stop control terminal, and an auxiliary machine cluster linkage controller. This module receives control commands from the edge computing energy-saving control module and, based on the operating characteristics and process requirements of different equipment, performs energy-saving actions such as correcting equipment electrical parameters, switching operating modes, and controlling start-stop status. The on-site execution and control module can also transmit the regulated equipment operating parameters, energy consumption data, and operating status back to the edge computing energy-saving control module, forming a closed-loop feedback link on-site. The cloud-based management platform is equipped with a full-domain energy consumption monitoring unit, a data statistical analysis unit, a fault and energy consumption anomaly early warning unit, an energy-saving strategy iteration and optimization unit, and a human-machine interaction unit. The full-domain energy consumption monitoring unit summarizes and displays the energy consumption and operating status data of all equipment in the workshop in real time. The data statistical analysis unit automatically generates daily, weekly, and monthly energy consumption statistical reports and energy consumption trend analysis data. The fault and energy consumption anomaly early warning unit provides graded early warnings and pushes prompt information for excessive energy consumption, electrical faults, and abnormal operating conditions. The energy-saving strategy iteration and optimization unit continuously optimizes algorithm parameters and judgment thresholds based on historical operating data, control records, and energy consumption data, and updates the equipment energy consumption standard database. The human-machine interaction unit supports parameter query, strategy configuration, data export, and remote equipment management operations.

[0007] As a preferred technical solution, the IoT sensing terminal adopts an IP65 or higher dustproof and moisture-proof industrial packaging structure, which is suitable for the high dust and high humidity production environment of chemical fiber workshops. The data sampling frequency of the sensing terminal is set to 10Hz to 50Hz, supporting 24-hour continuous acquisition. The sensing terminal can simultaneously collect electrical parameters and operating parameters, which can reduce the number of sensing terminals deployed on site and reduce operation and maintenance costs.

[0008] As a preferred technical solution, the industrial multi-protocol adapter gateway supports automatic identification, parsing and bidirectional conversion of mainstream industrial protocols such as Modbus and Profibus. It has a built-in large-capacity local cache, which can cache collected data on-site when the network is abnormal and automatically resume transmission after the network is restored, avoiding the loss of energy consumption data during continuous production. The end-to-end data transmission delay does not exceed 200ms, ensuring the real-time performance and integrity of the data.

[0009] As a preferred technical solution, the energy consumption anomaly identification unit is equipped with identification logic for different devices and different scenarios. For spinning equipment, it identifies energy consumption anomalies caused by high-frequency light load and tension mismatch. For air conditioning auxiliary equipment, it identifies redundant energy consumption caused by mismatch of temperature, humidity and wind pressure parameters. For water pumps and fans, it identifies energy consumption problems caused by long-term power frequency no-load and inefficient operation. For standby equipment, it identifies continuous no-load loss, thereby realizing performance consumption fault diagnosis for different electrical devices.

[0010] As a preferred technical solution, the process-constrained adaptive energy-saving algorithm unit is equipped with priority judgment logic, which takes the compliance of production process and the stability of product quality as the primary constraints. All energy-saving control instructions are verified by process thresholds before they are generated. Energy consumption optimization is only performed under the premise that the production parameters are within the qualified range and do not affect product quality, thereby eliminating process deviations and product defects caused by energy-saving control.

[0011] As a preferred technical solution, the on-site execution control module adopts a hierarchical and time-sharing control method. It uses millisecond-level small-amplitude parameter fine-tuning for continuous frequency conversion production equipment such as spinning machines and texturing machines, second-level coordinated control for linked auxiliary machines such as air conditioners, water pumps, and fans, and an automatic shutdown control method after status delay judgment for equipment that has been idle for a long time. It is adapted to the operating characteristics and production sequence requirements of various chemical fiber equipment.

[0012] As a preferred technical solution, the system is configured with a local emergency control unit. The local emergency control unit communicates with the edge computing energy-saving control module in real time. When the cloud network is abnormal, communication is interrupted, or cloud equipment fails, the local emergency control unit automatically takes over the on-site control work and independently completes data collection, energy consumption analysis, energy-saving control and closed-loop feedback to ensure that the workshop can continue to produce 24 hours a day without interruption.

[0013] Furthermore, the fully closed-loop energy control method of this system includes the following steps: S1. The full-domain perception module collects electrical parameters and production condition parameters of all electrical equipment in the entire chemical fiber workshop in real time and completes the initial data filtering. S2, the network transmission module completes the multi-source data protocol conversion and stable transmission, and uploads the data to the edge computing energy-saving control module; S3, the edge computing energy-saving control module performs data fusion, energy consumption feature extraction and anomaly identification, and generates the optimal energy-saving control command in combination with process constraints; S4. The on-site execution and control module executes control commands to optimize the electrical parameters and operating modes of the equipment; S5. After execution, the real-time operating data of the device is sent back to the edge computing energy-saving control module to compare the energy consumption data before and after the control, verify the energy-saving effect, and simultaneously upload it to the cloud management platform. S6, the cloud management platform iteratively optimizes energy-saving strategies based on full-domain data and updates edge computing algorithm models to achieve a continuous energy-saving optimization closed loop; In step S3, the system configures the energy-saving control logic of the equipment cluster linkage. When multiple production equipment or auxiliary machines of the same type are detected to be in a light-load state at the same time, the system adjusts the number of operating equipment and the load ratio of a single equipment according to the overall load supply and demand, shuts down redundant idle equipment, balances the load of online equipment, avoids frequent equipment adjustment, and reduces the overall energy consumption and mechanical wear of the cluster.

[0014] This invention provides an IoT-based closed-loop monitoring system for electrical energy conservation in a chemical fiber workshop. This system achieves comprehensive monitoring and closed-loop control of all electrical equipment in the workshop, overcoming the shortcomings of fragmented monitoring in traditional methods. It covers all electrical loads, including main production equipment, auxiliary electromechanical equipment, and lighting distribution. It can comprehensively identify both explicit and implicit energy waste points, providing comprehensive monitoring without blind spots. Employing a cloud-edge collaborative and edge-local control architecture, combined with a process priority constraint mechanism, it can perform energy-saving actions such as idle-load shutdown, light-load parameter optimization, operating condition matching adjustment, and cluster load balancing without affecting production processes or reducing product quality. Compared to traditional fixed-parameter control methods, it offers higher energy-saving accuracy. This system features energy consumption visualization, anomaly warning, data traceability, and automatic report generation. It can provide reliable data support for enterprise energy consumption management, equipment operation and maintenance, and production optimization, reduce manual control costs, and improve the level of refined and intelligent management in the workshop. Detailed Implementation

[0015] To further illustrate the technical means and effects of the present invention in achieving the intended purpose, the following detailed description of the specific implementation methods, structure, features and effects of the present invention, in conjunction with preferred embodiments, is provided below.

[0016] Example 1:

[0017] This invention discloses an IoT-based closed-loop monitoring system for electrical energy conservation in a chemical fiber workshop. It is suitable for continuous production workshops of conventional chemical fibers such as polyester, nylon, and polypropylene. The system adopts a four-layer cloud-edge collaborative architecture encompassing sensing, transmission, edge computing, and cloud computing, along with local emergency redundancy control capabilities. This enables closed-loop intelligent management of all electrical equipment in the workshop, from data acquisition and energy consumption diagnosis to precise control and iterative optimization. This embodiment uses a conventional chemical fiber spinning and texturing workshop as the application scenario. The workshop equipment includes multi-head spinning machines, high-speed texturing machines, winding machines, constant temperature and humidity air conditioning units, circulating cooling water pumps, ventilation fans, and the workshop's power and lighting distribution system, all of which are included in the system's monitoring and energy-saving control scope.

[0018] During the specific deployment and installation phase, industrial-grade IoT sensor terminals were installed using a combination of one-to-one equipment deployment and zoned power distribution deployment, based on the workshop equipment layout. For core production machines such as spinning machines, texturing machines, and winding machines, each machine was independently configured with a power sensor terminal to collect parameters such as three-phase voltage, three-phase current, active power, reactive power, power factor, real-time power consumption, operating frequency, and load rate. For auxiliary electromechanical equipment such as air conditioning units, cooling water pumps, and ventilation fans, sensor terminals were deployed independently for each machine. For workshop lighting and public power distribution circuits, a zoned centralized deployment method was used to collect the total circuit power consumption parameters. All sensor terminals used IP65 dustproof and moisture-proof industrial housings, suitable for the harsh working conditions of high temperature, high humidity, and high fiber dust in chemical fiber workshops. A uniform 20Hz fixed sampling frequency was set to achieve 24-hour uninterrupted synchronous collection of equipment electrical parameters and production condition parameters. Specific operating condition parameters included the spinning chamber process temperature, workshop ambient temperature and humidity, air supply pressure, and equipment spindle operating speed, ensuring the continuity and integrity of the collected data.

[0019] During the data transmission phase, heterogeneous protocol data output from all sensor terminals in the workshop are uniformly connected to the industrial multi-protocol adapter gateway. The gateway automatically identifies and parses industrial protocols such as Modbus and Profibus, and performs filtering, cleaning, invalid data removal, duplicate data deduplication, and format standardization on the raw collected data. This embodiment adopts a wired Ethernet + LoRa wireless dual-link redundant transmission architecture. Under normal operating conditions, the wired Ethernet is the primary transmission link to ensure high-speed and stable data upload. When workshop equipment is under maintenance, line disturbances occur, or electromagnetic interference is strong, it automatically switches to the LoRa wireless transmission link to avoid the risk of data disconnection. The gateway has a built-in 8G local cache space, which can achieve 72h offline data caching. During network interruptions, it automatically stores all collected data and automatically resumes transmission after network recovery, with no data loss or gaps. The end-to-end data transmission latency is stably controlled within 200ms, meeting the requirements of industrial real-time control.

[0020] The edge computing energy-saving control module is the core control unit of this system. In this embodiment, it incorporates a dedicated energy consumption threshold library for solidified chemical fiber equipment and a lightweight machine learning recognition model, pre-setting differentiated energy consumption judgment standards and recognition logic for different equipment. The system performs real-time fusion processing on uploaded multi-source electrical data and operating condition data, extracting multi-dimensional energy consumption characteristics such as equipment no-load operation, light-load inefficient operation, process parameter mismatch, and cluster load imbalance. For spinning production mainframes, it focuses on identifying reactive power loss caused by high-frequency light load and speed and tension mismatch; for air conditioning units, it identifies redundant energy consumption caused by the mismatch between temperature and humidity, wind pressure setpoints and actual production needs; for water pumps and fans, it identifies energy waste from constant speed operation at industrial frequency and low-load inefficient operation; for standby equipment, it accurately determines continuous no-load power consumption. At the same time, the system strictly follows the process priority constraint mechanism, pre-stores the legal process parameter ranges for each type of chemical fiber production, and performs process threshold verification before generating all energy-saving control commands, outputting control commands only under the premise of not affecting spinning formation, not producing filament defects, and not changing the physical indicators of the product.

[0021] The on-site execution and control module implements precise energy-saving control based on differentiated instructions issued by edge computing, achieving tiered and time-based adjustments. For continuously operating core equipment such as spinning machines and texturing machines, millisecond-level micro-parameter fine-tuning is used to dynamically adjust the inverter's operating frequency and output voltage to match real-time production load, reducing reactive power loss under light loads and preventing large parameter fluctuations from affecting production stability. For linked auxiliary equipment such as air conditioners, water pumps, and fans, a second-level collaborative control mode is used to dynamically adjust operating power and start / stop status according to real-time workshop conditions, achieving precise matching between auxiliary load and production needs. For idle equipment during production breaks and roll changing standby, a delay-based judgment logic automatically shuts down the equipment after confirming there are no subsequent production tasks, preventing long-term idle power consumption. After the control action is completed, the on-site execution module transmits the latest electrical parameters, operating status, and energy consumption data of the equipment in real time. The edge computing module immediately compares the energy consumption data and operating condition data before and after the control to verify the energy-saving effect and process compliance, forming a complete on-site closed-loop feedback. If a deviation in process parameters is detected, it immediately performs reverse fine-tuning to correct it, ensuring stable production quality.

[0022] The cloud-based management platform aggregates real-time operating data, energy consumption data, and control logs from all electrical equipment in the workshop, creating a visualized energy consumption monitoring dashboard that provides an intuitive display of workshop energy distribution, equipment operating status, and abnormal operating conditions. The platform automatically calculates total power consumption, single-equipment energy consumption, unit product power consumption, and energy loss percentage on a daily, weekly, and monthly basis, automatically generating standardized energy consumption analysis reports. For issues such as excessive equipment consumption, electrical anomalies, and control failures, the system provides tiered early warnings: pop-up notifications for minor anomalies and SMS and background message alerts for serious anomalies, facilitating timely troubleshooting by maintenance personnel. Simultaneously, the platform incorporates a temporal machine learning iteration mechanism, continuously accumulating control and energy consumption data under different product specifications, production loads, and seasonal operating conditions. It autonomously optimizes energy consumption judgment thresholds, algorithm weights, and control strategies. Compared to fixed-parameter control systems, it can adapt to flexible production scenarios for various types of chemical fibers, resulting in continuously improving long-term energy-saving effects.

[0023] To meet the 24 / 7 continuous production demands of the chemical fiber workshop, the system is equipped with an independent local emergency control unit, featuring a complete offline energy consumption threshold library and energy-saving control algorithm model. During normal operation, the local unit and the edge computing module synchronize data and parameters in real time. In the event of abnormal operating conditions such as cloud network interruption or cloud server failure, the system automatically switches to local offline control mode without manual intervention, independently completing the entire process of data collection, energy consumption analysis, energy-saving control, and closed-loop feedback, without affecting normal workshop production or energy-saving control effectiveness. Once cloud communication is restored, all operating data, control records, and energy consumption data cached during the offline period are automatically and batch-uploaded, ensuring the continuity and integrity of data across the entire system and preventing control failures caused by network anomalies.

[0024] Through long-term practical operation and verification in the workshop, this system can completely solve the problems of fragmented energy consumption monitoring, lagging control, conflicts between energy saving and processes, and serious hidden energy waste in traditional chemical fiber workshops. Through full-domain closed-loop intelligent management and control, the no-load energy consumption of workshop electrical equipment is basically eliminated, the light-load ineffective energy consumption is significantly reduced, and the energy consumption of redundant auxiliary equipment operation is significantly optimized. Under the premise of fully ensuring the stability of spinning and texturing production processes and maintaining the product qualification rate, the system can also quantitatively display energy-saving benefits, equipment operating status, and energy consumption shortcomings, providing accurate data support for enterprise production optimization, equipment operation and maintenance, and energy cost reduction. It effectively improves the level of refined and intelligent management and control of electrical equipment in chemical fiber workshops and has extremely high industrial promotion value.

[0025] 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 above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simplification, 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. A closed-loop monitoring system for electrical energy saving of all equipment in a chemical fiber workshop via the Internet of Things, characterized in that: It includes a global perception module, a network transmission module, an edge computing energy-saving control module, a cloud management and control platform, and an on-site execution control module; The signal output terminal of the global perception module is connected to the signal input terminal of the network transmission module, the signal output terminal of the network transmission module is connected to the signal input terminal of the edge computing energy-saving control module, the control signal output terminal of the edge computing energy-saving control module is connected to the signal input terminal of the field execution control module, and the edge computing energy-saving control module has a bidirectional communication connection with the cloud management and control platform. The comprehensive perception module includes multiple sets of distributed industrial-grade IoT sensor terminals. The sensor terminals are deployed one-to-one or in zones according to the workshop equipment layout. The sensor terminals are connected to the electrical equipment, including spinning equipment, texturing equipment, winding equipment, air conditioning auxiliary equipment, circulating water pumps, ventilation fans, and workshop lighting distribution cabinets. The sensor terminals continuously collect the electrical parameters of the electrical equipment, including voltage, current, active power, reactive power, power consumption, operating frequency, load rate, and start / stop status. At the same time, the sensor terminals collect operating condition parameters, including workshop temperature and humidity, air duct pressure, spinning process temperature, and equipment operating speed, to achieve full coverage collection of operating parameters of all electrical equipment in the workshop. The network transmission module includes an industrial multi-protocol adapter gateway, a wired Ethernet transmission unit, and a wireless LoRa anti-interference transmission unit. The industrial multi-protocol adapter gateway has built-in protocol parsing and data preprocessing functions, which can automatically identify and adapt to the industrial heterogeneous protocols of various sensor terminals, and clean, deduplicate, and unify the format of the raw collected data. The industrial multi-protocol adapter gateway has local caching and breakpoint resume functions, which can adapt to the complex working conditions of strong electromagnetic interference and high dust in chemical fiber workshops, and ensure low-latency, high-reliability bidirectional transmission of multi-source sensing data. The edge computing energy-saving control module is the core control unit of the system. It integrates an energy consumption feature extraction unit, an energy consumption anomaly identification unit, a process constraint-based adaptive energy-saving algorithm unit, and an instruction output unit. The energy consumption feature extraction unit performs multi-source fusion on the received standardized electrical data and operating condition data to extract multi-dimensional features of the equipment. These multi-dimensional features include no-load energy consumption, light-load redundant energy consumption, and process parameter mismatch energy consumption. The energy consumption anomaly identification unit pre-stores a standard energy consumption threshold library for all equipment in the chemical fiber workshop and a trained machine learning identification model. Based on the multi-dimensional features, it determines the type and level of equipment energy consumption anomalies. The process constraint-based adaptive energy-saving algorithm unit presets chemical fiber production process priority rules. Under the premise of meeting the requirements of spinning and texturing production processes and ensuring product quality, it matches the optimal operating parameters of the equipment and outputs refined energy-saving control instructions, including frequency fine-tuning, voltage stabilization, no-load delayed shutdown, load dynamic adaptation, and auxiliary machine cluster linkage start-stop. The field execution control module includes an intelligent frequency converter, an electrical voltage stabilizing module, an equipment start-stop control terminal, and an auxiliary machine cluster linkage controller. The field execution control module receives control instructions issued by the edge computing energy-saving control module and, in combination with the operating characteristics and process requirements of different equipment, completes energy-saving execution actions, including equipment electrical parameter correction, operating mode switching, and start-stop status control. The on-site execution control module can transmit the controlled equipment operating parameters, energy consumption data and operating status back to the edge computing energy-saving control module, forming a closed-loop feedback link on-site. The cloud-based management platform is equipped with a full-domain energy consumption monitoring unit, a data statistical analysis unit, a fault and energy consumption anomaly early warning unit, an energy-saving strategy iteration and optimization unit, and a human-machine interaction unit. The full-domain energy consumption monitoring unit summarizes and displays the energy consumption and operating status data of all equipment in the workshop in real time. The data statistical analysis unit automatically generates daily, weekly, and monthly energy consumption statistical reports and energy consumption trend analysis data. The fault and energy consumption anomaly early warning unit provides graded early warnings and pushes prompt information for excessive energy consumption, electrical faults, and abnormal operating conditions. The energy-saving strategy iteration and optimization unit continuously optimizes algorithm parameters and judgment thresholds based on historical operating data, control records, and energy consumption data, and updates the equipment energy consumption standard database. The human-machine interaction unit supports parameter query, strategy configuration, data export, and remote equipment management operations.

2. The IoT-based closed-loop monitoring system for electrical energy saving in a chemical fiber workshop according to claim 1, characterized in that: The sensor terminal adopts an IP65 or higher dustproof and moisture-proof industrial packaging structure, which is suitable for the high dust and high humidity production environment of chemical fiber workshops. The data sampling frequency of the sensor terminal is set to 10Hz to 50Hz, supporting 24-hour continuous acquisition. The sensor terminal synchronously acquires electrical parameters and operating parameters.

3. The IoT-based closed-loop monitoring system for electrical energy saving in a chemical fiber workshop according to claim 1, characterized in that: The industrial multi-protocol adapter gateway supports automatic identification, parsing, and bidirectional conversion of mainstream industrial protocols such as Modbus and Profibus. It has a built-in large-capacity local cache, which caches collected data locally when the network is abnormal and automatically resumes transmission after the network is restored. The end-to-end data transmission delay does not exceed 200ms.

4. The IoT-based closed-loop monitoring system for electrical energy saving in a chemical fiber workshop according to claim 1, characterized in that: The energy consumption anomaly identification unit is set up with identification logic for different devices and different scenarios. For spinning equipment, it identifies energy consumption anomalies caused by high frequency light load and tension mismatch. For air conditioning auxiliary equipment, it identifies redundant energy consumption caused by temperature, humidity and wind pressure parameter mismatch. For water pumps and fans, it identifies energy consumption problems caused by long-term power frequency no-load and inefficient operation. For standby equipment, it identifies continuous no-load loss, so as to realize the performance consumption fault diagnosis of different electrical equipment.

5. The IoT-based closed-loop monitoring system for electrical energy saving in a chemical fiber workshop according to claim 1, characterized in that: The process-constrained adaptive energy-saving algorithm unit is set with priority judgment logic, taking production process compliance and product quality stability as the primary constraints. All energy-saving control instructions are verified by process thresholds before they are generated. Energy consumption optimization is only performed when production parameters are within the qualified range and do not affect product quality, thus preventing process deviations and product defects caused by energy-saving control.

6. The IoT-based closed-loop monitoring system for electrical energy saving in a chemical fiber workshop according to claim 1, characterized in that: The on-site execution control module adopts a hierarchical and time-sharing control method. It uses millisecond-level small parameter fine-tuning for continuous frequency conversion production equipment, second-level coordinated control for linked auxiliary machines, and automatic shutdown control after status delay judgment for long-term idle standby equipment. It is adapted to the operating characteristics and production sequence requirements of various chemical fiber equipment.

7. The IoT-based closed-loop monitoring system for electrical energy saving in a chemical fiber workshop according to claim 1, characterized in that: The energy-saving strategy iterative optimization unit adopts a time-series machine learning algorithm to accumulate control data and energy consumption data under the corresponding chemical fiber product type, production load, and equipment operating conditions. It autonomously optimizes algorithm parameters and control thresholds to adapt to diverse production scenarios and realize continuous iterative updates of energy-saving strategies without the need for repeated manual calibration.

8. The IoT-based closed-loop monitoring system for electrical energy saving in a chemical fiber workshop according to claim 1, characterized in that: The system is equipped with a local emergency control unit, which communicates with the edge computing energy-saving control module in real time. When the cloud network is abnormal, communication is interrupted, or cloud equipment fails, the local emergency control unit automatically takes over the on-site control work, independently completes data collection, energy consumption analysis, energy-saving control and closed-loop feedback, and ensures that the workshop can continue to produce 24 hours a day without interruption.

9. The IoT-based closed-loop monitoring system for electrical energy saving in a chemical fiber workshop according to claim 1, characterized in that: The fully closed-loop energy control method includes the following steps: S1. The full-domain perception module collects electrical parameters and production condition parameters of all electrical equipment in the entire chemical fiber workshop in real time and completes the initial data filtering. S2, the network transmission module completes the multi-source data protocol conversion and stable transmission, and uploads the data to the edge computing energy-saving control module; S3, the edge computing energy-saving control module performs data fusion, energy consumption feature extraction and anomaly identification, and generates the optimal energy-saving control command in combination with process constraints; S4. The on-site execution and control module executes control commands to optimize the electrical parameters and operating modes of the equipment; S5. After execution, the real-time operating data of the device is sent back to the edge computing energy-saving control module to compare the energy consumption data before and after the control, verify the energy-saving effect, and simultaneously upload it to the cloud management platform. The S6 cloud management platform iteratively optimizes energy-saving strategies based on full-domain data and updates edge computing algorithm models to achieve a continuous energy-saving optimization closed loop.

10. The IoT-based closed-loop monitoring system for electrical energy saving in a chemical fiber workshop according to claim 9, characterized in that: In step S3, the system configures the energy-saving control logic of the equipment cluster linkage. When multiple production equipment or auxiliary machines of the same type are detected to be in a light-load state at the same time, the system adjusts the number of operating equipment and the load ratio of a single equipment according to the overall load supply and demand, shuts down redundant idle equipment, balances the load of online equipment, avoids frequent equipment adjustment, and reduces the overall energy consumption and mechanical wear of the cluster.