A system for constructing an intelligent simulation factory for practical teaching based on internet of things devices

Abstract

A system for constructing an intelligent simulation factory for practical teaching based on Internet of Things devices, comprising a factory operation simulation mechanism, a factory control simulation mechanism, a simulation teaching integration mechanism and a data tag generation mechanism, the factory operation simulation mechanism is used for simulating factory production operation and obtaining factory production operation data; the factory control simulation mechanism controls the production operation of the factory operation simulation mechanism to realize the automation of the factory operation simulation mechanism; the simulation teaching integration mechanism realizes simulation teaching according to a training scheme; the data tag generation mechanism marks the practical teaching training process data and the data generated by the simulation teaching integration mechanism in the student practical teaching training process, thereby distinguishing the data of different students in the simulation practice process, and enabling the factory operation simulation mechanism, the factory control simulation mechanism and the simulation teaching integration mechanism to quickly extract target data when using data.

Description

Technical Field

[0001] This invention relates to the field of engineering education technology, and more specifically, to a system for constructing an intelligent simulation factory for practical teaching based on Internet of Things (IoT) devices. Background Technology

[0002] With the continuous development and application of technology, the Internet of Things (IoT) has gradually become an important foundation for modern industrial development. IoT technology combines various sensors, controllers, communication devices, and the internet to achieve real-time communication and data sharing between devices and systems. The application of this technology can improve the efficiency, quality, and safety of industrial production, while reducing enterprise costs and resource consumption.

[0003] In the field of engineering education, the application of intelligent simulation equipment will gradually become a mainstream practical teaching method in order to cultivate students' professional skills and practical abilities.

[0004] Currently, there are numerous examples of IoT-based intelligent simulation factories for practical teaching both domestically and internationally. Examples include the FANUC Smart Manufacturing Institute in Japan, the Smart Manufacturing Lab in Singapore, and the Smart Manufacturing Lab at Miami-Witt University of Technology in the United States. These labs utilize IoT technology to build highly realistic and real-time intelligent manufacturing systems, cultivating a large number of outstanding talents for the field of industrial automation through practical teaching and innovative research.

[0005] However, the relevant research and application in China is still relatively weak. Apart from a few universities and research institutions, most educational institutions have not yet begun to get involved in this field and lack the corresponding teaching staff and equipment.

[0006] Existing intelligent simulation factory systems are typically closed systems developed by a single supplier or manufacturer, making it difficult to meet the diverse needs of different schools and enterprises, and they suffer from the following problems:

[0007] (1) Lack of real production operation environment: Most of the existing intelligent simulation factories are biased towards discrete manufacturing industries and cannot provide a realistic production operation environment to support practical training and teaching. They cannot build intelligent production scenarios and practical teaching activity scenarios based on production operation. The atmosphere of digitalization and intelligent production in practical training and teaching is insufficient. IoT devices can monitor factory processes and systems in real time and collect relevant data.

[0008] (2) High reuse cost: Virtual simulation and practical operation are costly and cannot quickly and repeatedly consolidate practice. Existing or pre-built simulation devices cannot provide convenient operations such as "one-click reset" or "one-click recovery". For the teaching needs of repeated practice or consolidation in practical teaching, a lot of teaching resource management costs are required to support students (trainees) to carry out real practical operations. At the same time, the existing simulation devices can only localize offline practical operations and cannot achieve "co-construction and sharing".

[0009] (3) Lack of comprehensive teaching support and evaluation analysis: At present, domestic facilities only provide hardware and software construction for simulation devices. However, they cannot conduct statistical analysis and evaluation of practical teaching data and student practical operation data, so as to help teachers provide reasonable teaching guidance and personalized student (trainee) assessment for practical teaching activities and provide strong practical basis.

[0010] Therefore, developing a general method for constructing a smart simulation factory for practical teaching based on Internet of Things (IoT) devices has significant theoretical and practical value. Summary of the Invention

[0011] (I) Purpose of the invention: In order to solve the problems existing in the prior art, the purpose of this invention is to provide a system and method for constructing a smart simulation factory for practical teaching of Internet of Things devices in process industry-related engineering education, so as to meet the practical teaching needs of the ever-evolving, modern and intelligent engineering education field.

[0012] (II) Technical Solution: To address the aforementioned technical problems, this technical solution provides a system for constructing a smart simulation factory for practical teaching based on Internet of Things (IoT) devices, including a factory operation simulation mechanism, a factory control simulation mechanism, a simulation teaching integration mechanism, and a data tag generation mechanism.

[0013] The factory operation simulation mechanism is used to simulate factory production operations and acquire factory production operation data;

[0014] The factory control simulation mechanism controls the production operation of the factory operation simulation mechanism, thereby automating the factory operation simulation mechanism.

[0015] The simulation teaching integration institution implements simulation teaching according to the training program;

[0016] The data tagging mechanism marks the data generated during the practical teaching and training process and the data generated by the simulation teaching integration mechanism during the students' practical teaching and training process, thereby distinguishing the data of different students in the simulation practice process, and enabling the factory operation simulation mechanism, factory control simulation mechanism, and simulation teaching integration mechanism to quickly extract target data when using the data.

[0017] The system for constructing a practical teaching intelligent simulation factory based on Internet of Things (IoT) devices includes a simulation device, IoT devices, and intelligent robots.

[0018] The factory control simulation mechanism includes a production control layer and a production execution layer. The production control layer is used for production operation control of the factory operation simulation mechanism, and the production execution layer is used for execution management of production operation of the factory operation simulation mechanism.

[0019] The simulation teaching integration mechanism includes a teaching task management unit, an artificial intelligence reasoning unit, a factory digital twin unit, and a capability assessment and diagnosis unit.

[0020] The system for constructing a smart simulation factory for practical teaching based on Internet of Things (IoT) devices, wherein the practical teaching training process data and the data generated by the simulation teaching integration mechanism during the students' practical teaching training are collectively referred to as process data; the data tag generation mechanism includes a data pool, a tag comparison generation unit, a tag generation unit, and a data extraction unit.

[0021] The data pool is used to store different process data generated in simulated teaching, including practical data and analysis data; the label comparison generation unit is used to generate labels corresponding to different tasks, different students and / or different times, and the label comparison generation unit stores the generated labels corresponding to the tasks, students and / or times; the label generation unit labels the process data in the data pool to obtain label data; the data extraction unit extracts data from the data pool according to the data extraction command to obtain target data.

[0022] The system for constructing a smart simulation factory for practical teaching based on Internet of Things devices, wherein the data in the data pool is tagged data, including a data body and a tag body, wherein the data body is the original data content, and the tag body is used to mark the corresponding task, student and / or time;

[0023] The tag comparison generation unit includes a tag comparison table, which records tags corresponding to different tasks, different trainees, and different times. The tag comparison table includes a header column, a member column, and a tag column. The header column provides a detailed description of the tag classification for tasks, trainees, or times corresponding to the member column and the tag column. The specific tag classification in the header column is a header to be selected. The member column is a member classification column that compares different task names, trainee names, and time points in the task, trainee, and / or time. The tag column contains tags corresponding to specific tasks, trainees, and / or times. The tags corresponding to different tasks, different trainees, and / or different times in the tag comparison generation unit are generated by a first rule preset by the tag comparison generation unit, or specified tags input by the input mechanism.

[0024] The system for constructing a practical teaching intelligent simulation factory based on IoT devices includes the following steps: When the data tag generation mechanism needs to tag new data, the tag generation unit searches the data pool for the new data. If there is no data source identical to the new data in the data pool, the new data is data to be tagged. The tag generation unit then selects the corresponding task, student, and / or time tag from the tag lookup table and combines it with the new data to obtain tagged data. If there is a corresponding data source in the data pool, the tag generation unit retrieves data from the data pool that is identical to the new data to obtain data to be tagged. In this case, the data from the data pool that is identical to the new data is data to be tagged. The tag generation unit then selects the corresponding task, student, and / or time tag from the tag lookup table and combines it with the data to be tagged to obtain tagged data.

[0025] In the system for constructing a practical teaching intelligent simulation factory based on Internet of Things devices, when new label data is obtained by combining new data with corresponding labels, the label generation unit directly puts the new label data into the data pool.

[0026] When new label data is obtained by combining the data in the data pool that is the same as the new data with the corresponding label, the label generation unit deletes the initial data in the data pool that is the same as the new data and puts the new label data directly into the data pool, that is, the new label data replaces the label data in the data pool that is the same as the new data.

[0027] The system for constructing a smart simulation factory for practical teaching based on Internet of Things (IoT) devices includes an extraction command that includes target members to be selected corresponding to target data. The data extraction unit obtains the target data in the following manner.

[0028] The data extraction unit reads the target members to be selected from the extraction command;

[0029] The data extraction unit searches for the target member to be selected in the label lookup table and reads the corresponding label in the label column of the target member to be selected, thereby obtaining the target label;

[0030] The data extraction unit searches the data pool and reads the tag data of the tag data in the data pool, including the tag data of the target tag, to obtain the target tag data;

[0031] The data extraction unit separates the data body and the tag body of the target tag data, and then organizes all the data body parts of the target tag data to obtain the target data.

[0032] The system for constructing a smart simulation factory for practical teaching based on Internet of Things (IoT) devices includes an extraction command that includes a tag corresponding to the target data. The data extraction unit obtains the target data in the following manner.

[0033] The data extraction unit reads the tags corresponding to the target data in the extraction command, i.e., the target tags;

[0034] The data extraction unit searches the data pool and reads the tag data of the tag data in the data pool, including the tag data of the target tag, to obtain the target tag data;

[0035] The data extraction unit separates the data body and the tag body of the target tag data, and then organizes all the data body parts of the target tag data to obtain the target data.

[0036] The system for constructing a practical teaching intelligent simulation factory based on Internet of Things devices includes a data pool comprising multiple data sub-pools. The tag data in each data sub-pool is stored in the same data sub-pool according to the different header columns in the header column. The data extraction unit searches in the corresponding data sub-pool according to the header column corresponding to the tag of the target member or target data in the extraction command.

[0037] The system for constructing a practical teaching intelligent simulation factory based on IoT devices includes a data pool comprising multiple data sub-pools. Tag data in each data sub-pool is stored according to different task names, different student names, and / or different time points in the member column. Tag data with the same task name, the same student name, and / or the same time point are stored in the same data sub-pool. The data extraction unit searches in the corresponding data sub-pool according to the member column corresponding to the target member or target data tag in the extraction command.

[0038] (III) Beneficial Effects: This invention provides a system for constructing a smart simulation factory for practical teaching based on Internet of Things (IoT) devices. It adopts a brand-new Internet application model to connect the physical world and the digital world, realize the Internet of Everything, and thus enable practical teaching based on IoT technology. This achieves a more efficient and intelligent teaching method, thereby improving students' practical and innovative abilities.

[0039] It provides a safe, low-cost, and efficient intelligent interactive teaching environment for production, offering better teaching resources for practical teaching. Students can conduct real-world practical operations and learn about the application of IoT devices and intelligent control technologies, thereby improving their practical and innovative abilities.

[0040] It provides a teaching method that closely resembles real production data and allows for real-time updates of process data based on actual factory operations, thus ensuring the accuracy and authenticity of practical teaching (training).

[0041] This invention provides a teaching system that satisfies the requirements of low storage space usage and multi-process data storage. Furthermore, it adopts a classified data pool approach during data reading, which improves the reading speed of process data and enhances the user experience of the teaching system. Attached Figure Description

[0042] Figure 1 This is a schematic diagram illustrating the process of data tagging by a data tag generation mechanism in a system for constructing a practical teaching intelligent simulation factory based on Internet of Things (IoT) devices, according to the present invention. Detailed Implementation

[0043] The present invention will be further described in detail below with reference to preferred embodiments. More details are set forth in the following description in order to provide a full understanding of the present invention. However, the present invention can obviously be implemented in many other ways different from those described herein. Those skilled in the art can make similar extensions and derivations based on actual application situations without departing from the spirit of the present invention. Therefore, the scope of protection of the present invention should not be limited by the content of this specific embodiment.

[0044] The accompanying drawings are schematic diagrams of embodiments of the present invention. It should be noted that these drawings are for illustrative purposes only and are not drawn to scale, and should not be construed as limiting the actual scope of protection of the present invention.

[0045] Traditional practical teaching methods based on simulated factories have many limitations in the field of engineering education, such as lack of real production operation data, high reuse costs, high cost of virtual simulation and practical operation, inability to quickly and repeatedly consolidate exercises, and lack of comprehensive teaching aids and evaluation analysis.

[0046] For example:

[0047] Existing technology one utilizes computer simulation technology to construct virtual simulation software, simulating production indicators and processes for students to practice. Students can conduct practical operations and optimization experiments in a virtual environment, using virtual simulation software to simulate and optimize production processes. However, virtual simulation software has drawbacks in practical teaching, including: a disconnect between practice and production (virtual simulation software cannot reproduce the real factory environment and equipment; production data and operating parameters in virtual simulation software differ from actual conditions, serving only a cognitive and simple operational teaching purpose); and a lack of real data (data in virtual simulation software is often generated based on models and algorithms; the quality of models and algorithms from various manufacturers varies, resulting in students lacking the ability to process and analyze real data during practical operations and optimization experiments, and failing to truly understand and apply data acquisition and analysis techniques in actual production processes).

[0048] Existing technology two utilizes a simulated factory in conjunction with supporting virtual simulation software to simulate a factory environment. Students (trainees) engage in practical operations and exercises using on-site simulated factory devices, communicate the status of key equipment through the supporting virtual simulation software, and simulate relevant production processes and indicators, thereby facilitating practical teaching. The problem with this approach is that it only digitizes the simulation device and initially simulates the production process, thus only supporting cognitive and practical skills training in traditional engineering education.

[0049] Traditional practical teaching methods are being used in engineering education related to process industries, resulting in a growing disconnect between the demand for intelligent process industry talent and the actual needs of the industry.

[0050] In recent years, the development of Internet of Things (IoT) technology has provided new opportunities for practical teaching in engineering education related to process industries. Therefore, this invention combines IoT devices and intelligent technologies to construct an intelligent simulation factory based on simulation devices, providing a safer, more flexible, and scalable practical environment: a system for constructing an intelligent simulation factory for practical teaching based on IoT devices.

[0051] A system for constructing a smart simulation factory for practical teaching based on Internet of Things (IoT) devices is applied to assist engineering education in various industries.

[0052] A system for constructing a smart simulation factory for practical teaching based on Internet of Things (IoT) devices includes a factory operation simulation mechanism, a factory control simulation mechanism, and a simulation teaching integration mechanism. The factory operation simulation mechanism is connected to both the factory control simulation mechanism and the simulation teaching integration mechanism. The factory operation simulation mechanism simulates factory production operations and acquires factory production operation data. The factory control simulation mechanism controls the production operation of the factory operation simulation mechanism, automating its operation. The simulation teaching integration mechanism implements simulation teaching according to the curriculum plan.

[0053] The factory operation simulation mechanism includes simulation devices, Internet of Things (IoT) equipment, and intelligent robots.

[0054] The simulation device is a newly built intelligent simulation factory or a modified simulation factory. The simulation device can simulate different production conditions and changes; specifically, it can be a virtual production environment that simulates real-world production processes and equipment, or it can learn the production processes and equipment of a target factory construction project.

[0055] The simulation device includes the following functions:

[0056] 1. Reaction process simulation: Simulates the dynamic behavior of chemical reaction processes, including reaction rate, material flow, temperature and pressure changes, etc.

[0057] 2. Process simulation: Simulate processes such as mass transfer, heat transfer, and momentum transfer to understand the distribution, transfer, and transformation of materials in the equipment.

[0058] 3. Control strategy simulation: Simulate different control strategies and evaluate their impact on process performance.

[0059] 4. Unit operation simulation: Simulate various unit operations, such as distillation, extraction, and adsorption, to understand their effects on the separation and purification of fluid components.

[0060] 5. Safety assessment and risk analysis: Through simulation and analysis, assess the safety, stability and risks of chemical processes, identify potential hazards and risks, and take corresponding measures to ensure the safety of personnel and equipment.

[0061] The simulation device includes modified equipment for data acquisition and transmission, which includes smart meters, triggers, industrial inspection terminals, industrial control terminals, and cameras.

[0062] The intelligent instruments are installed on the main and auxiliary process pipelines of typical process production equipment required for teaching purposes within the simulation device, and are used to monitor and control key process variables of critical equipment in real time. The intelligent instruments include control valves, solenoid valves, motors, etc., and the control valves can be regulating valves or shut-off valves.

[0063] The trigger is installed in the PLC control cabinet of the simulation device and is used to simulate the independent signals required by the intelligent instrument, the OTS process simulation production operation model, to complete the triggering and control of abnormal events and states, and to control the intelligent instrument to perform segmentation, activation and reset.

[0064] The industrial inspection terminal is a portable device used for sending and receiving equipment inspection and maintenance tasks in industrial environments. The application of the industrial inspection terminal can improve inspection efficiency, reduce inspection costs, and enhance equipment reliability, enabling staff to perform equipment inspection and maintenance more conveniently and accurately, promptly identify and resolve problems, and ensure the normal operation of equipment and the safety of production.

[0065] The industrial inspection terminal has the following features and functions: durability and adaptability, possessing excellent shock resistance, dustproof, and waterproof characteristics, adapting to harsh environmental conditions in industrial sites; real-time monitoring and display, receiving and displaying monitoring signals from various sensors or devices, such as temperature, pressure, and current; data recording and analysis, with data recording and storage functions, recording various data during the inspection process, including monitoring data, inspection time, and operation records; image and video acquisition, with image and video acquisition functions, capturing and recording the status of equipment through a camera; remote communication and cloud platform connection, connecting to a cloud platform or remote server via wireless communication to achieve remote monitoring, data uploading, and remote operation functions; and inspection task management, equipped with task management functions to plan, allocate, and record inspection tasks, generating inspection reports and statistical data.

[0066] The industrial control terminal is used to display key production parameters, reaction mechanisms, and other production process indicators of different devices in the simulation device, to display and operate the interactive task activities of the current device, and to send the interactive activity process to the factory control simulation organization and / or simulation teaching integration organization.

[0067] The camera is used to collect and monitor behavioral data in the area where the simulation device is located. The collected behavioral data is transmitted to the factory control simulation organization and / or simulation teaching integration organization via the RTSP transmission protocol.

[0068] The IoT devices include IoT sensors such as M5 and GPS tags. These IoT devices are used to achieve interconnection, data sharing, and real-time monitoring and control of equipment in the factory operation simulation mechanism, factory control simulation mechanism, and simulation teaching integration mechanism. Specifically, this includes data acquisition of key equipment, presentation of simulated abnormal situation data, positioning of the simulation device area inspection map and interaction in practical teaching activities, and data acquisition of inspection points, inspection digital signals, trend signals, and sensor signals required for inspection tasks, in conjunction with intelligent inspection machines.

[0069] The IoT devices can be installed on relevant equipment used for real-time monitoring and control, including both moving and stationary equipment. These IoT devices collect real data, present simulated abnormal situation data, locate areas on simulated factory inspection maps, and facilitate interaction during practical teaching activities. The IoT devices can be installed on the centrifugal pump in the feed line of a typical unit to simulate preventative maintenance scenarios for industrial centrifugal pumps. The IoT devices can also be installed on the valves in the feed or discharge lines of a typical unit to simulate abnormal phenomena and sounds such as leaks, spills, drips, and other abnormalities.

[0070] The related equipment and the key equipment can be the same equipment or different equipment.

[0071] The IoT device collects data via the standard OPC protocol. For example, it collects digital signals, trend signals, and sensor signals from key equipment in the factory operation simulation mechanism, as well as OTS simulation process data and interactive information from the entire simulation device. Combined with intelligent robot technology and 5G communication technology, it constructs the equipment layer—the factory operation simulation mechanism—that conforms to the international manufacturing industry standard SA-95. Incorporating the unique interactive attributes of the M5 IoT device, it supports specific interactive operations of key equipment, completing the practical teaching tasks of the factory control simulation mechanism equipment.

[0072] Digital signals are discrete digital sequences converted from analog signals through sampling, quantization, and encoding, with a limited number of possible values. In digital signals, signal values ​​are represented using binary numbers. Digital signals can be processed, transmitted, and stored using digital technologies such as computers, offering advantages such as strong anti-interference capabilities and long transmission distances. In process industries, digital signals are widely used for production process control and monitoring. Sensors collect signals from the production process, converting them into digital signals for processing and analysis, enabling real-time monitoring and adjustment of the production process. Digital signals effectively address the limitations of traditional analog signal technology in terms of transmission distance, interference immunity, and signal quality, improving production efficiency and product quality. Digital signals can also be combined with other digital technologies, such as digital image processing, digital signal processing, and machine learning, to achieve higher-level functions and solutions. In chemical enterprises, digital signals can help achieve intelligent manufacturing, improving production efficiency and competitiveness.

[0073] A trend signal is a signal that expresses the evolution trend of a system's state, derived from the statistical analysis of monitoring data within a certain time range. It reflects the system's operating status and changing trends over a period of time. In process industries, trend signals are often used to monitor and evaluate the stability and reliability of production processes. By monitoring and recording key parameters in the production process in real time, a large amount of data can be obtained. Analyzing this data reveals the changing trends of the system state, such as the rising or falling trends of parameters like temperature, pressure, and flow rate. Trend signals can help chemical companies promptly identify potential problems or anomalies and take corresponding measures for adjustment and improvement to ensure the stability of the production process and product quality. Furthermore, trend signals can also be used for prediction and optimization. By analyzing historical data trends, future system states and trend changes can be predicted, allowing for timely adjustments and decisions. The application of trend signals in process industries can be combined with other data analysis and control technologies, such as artificial intelligence and machine learning, to achieve more accurate and intelligent analysis and decision-making. Through the monitoring and analysis of trend signals, chemical companies can improve production efficiency, reduce production costs, and enhance their competitiveness.

[0074] Sensor signals are signals that are converted from physical quantities measured by sensors into electrical or digital signals for transmission and processing. Sensors are devices that convert one or more physical quantities into electrical signals, such as temperature sensors, pressure sensors, and light sensors. Sensor signals can provide information about the measured physical quantities, such as temperature, pressure, and light intensity. In process industries, sensor signals are a crucial source of information for real-time monitoring and control of production processes. By measuring signals from sensors, parameters such as temperature, pressure, and flow rate in the production process can be understood, helping to achieve real-time monitoring and adjustment. Sensor signals can also be used for prediction and optimization. By analyzing historical data, future system states and trends can be predicted, allowing for proactive adjustments and decisions. The application of sensor signals can be combined with other data analysis and control technologies, such as the Internet of Things (IoT), artificial intelligence (AI), and big data, to achieve higher levels of functionality and solutions. Through the monitoring and analysis of sensor signals, chemical companies can improve production efficiency, reduce production costs, and enhance their competitiveness.

[0075] The intelligent robot guides the inspection route within the area of ​​the simulation device and provides practical teaching content and knowledge expansion for key inspection positions. Through recognizing and practicing inspection job skills, and through repetitive practice and hands-on experience, it consolidates and enhances key inspection skills. Teachers (administrators) issue inspection practice tasks through the teaching task management unit of the simulation teaching integration institution. Upon receiving the inspection task, the intelligent robot, based on the inspection route selected by the student (trainee), guides the student (trainee) to the safe inspection area of ​​the simulation device. It explains the inspection task objectives, essential knowledge, reinforces and expands understanding, and outlines safety regulations and other inspection precautions. The robot then guides the student (trainee) through the explanation, interaction, and reporting of inspection points. The intelligent robot can be an industrial inspection robot or an industrial inspection drone, etc.

[0076] The factory control simulation mechanism includes a production control layer and a production execution layer. The production control layer is used for production operation control of the factory operation simulation mechanism, and the production execution layer is used for execution management of production operation of the factory operation simulation mechanism.

[0077] The production control layer collects, distributes, and / or stores relevant data from the factory operation simulation mechanism. Based on the collected data, it enables safety early warning management of the factory control simulation mechanism, intelligent control and optimization of the steady-state production of the factory operation simulation mechanism, safety control of the factory operation simulation mechanism, and simulation of the complete production process and control system of the factory operation simulation mechanism.

[0078] The production control layer includes a data integration module, an early warning management module, a production control module, a safety control module, and a simulation optimization module. The data integration module collects, distributes, and / or stores relevant data from the factory operation simulation mechanism to obtain simulated production data. The early warning management module generates safety early warning data based on the simulated production data, enabling safety early warning management of the factory control simulation mechanism. The production control module, based on the simulated production data, achieves intelligent control and production optimization of the factory operation simulation mechanism's steady-state production. The safety control module, based on the safety early warning data from the early warning management module, implements safety control of the factory operation simulation mechanism. The simulation optimization module, based on the simulated production data, simulates the complete production process and control system of the factory operation simulation mechanism, achieving real-time simulation operation.

[0079] The data integration module collects, distributes, and / or stores relevant data from the factory operation simulation mechanism. This relevant data includes production operation data, inspection data, OTTS process simulation models, behavioral data, personnel positioning data, environmental data, attendance data, etc.

[0080] The early warning and control management module monitors personnel behavior and production operations within the factory operation simulation mechanism based on collected data. This enables early warning and management of unsafe behaviors, including both unsafe personnel actions and unsafe production operations. Specifically, by monitoring collected inspection data, production operation data, behavioral data, personnel location datasets, and attendance data from the factory operation simulation mechanism, the module monitors the production operation status, typical equipment operation status, and safety status of personnel participating in practical teaching activities within the simulation area in real time. This allows for early warning and management of unsafe behaviors, thereby ensuring the normal production operation and simulated abnormal faults in the intelligent simulation factory.

[0081] For the management and early warning of unsafe personnel behavior, a specific approach can be based on 5G + monitoring + AI behavior analysis technology. The training monitoring center of the factory control simulation mechanism can monitor various sudden emergency warning behaviors in the training room, including the practical training area and surrounding areas. This data collection provides teachers with early warnings and management of student behavior during the teaching process, enabling timely correction and assistance for unsafe student actions, ensuring student safety, and providing teaching safety guarantees in the practical training area and surrounding areas. From the very beginning of practical training, it constantly enhances safety awareness. The collected sudden emergency warning behaviors include student actions and their operational behaviors on the factory control simulation mechanism.

[0082] For the management and early warning of unsafe production operations, comprehensive and timely data collection and analysis of the industrial production process through factory control simulation mechanisms provide accurate information support for production decisions, enabling the monitoring and early warning of safe production. The management and early warning of unsafe production operations includes multiple functional modules such as monitoring of all production elements, monitoring of key process parameters, equipment monitoring, monitoring of intelligent advanced control systems, monitoring of intelligent safety instrumented systems, AI intelligent safety monitoring, 3D digital twin factory display, 3D pipeline flow display, and monitoring of key equipment operation.

[0083] The production control module can adopt advanced process control (APC), also known as advanced process control. An advanced process control system includes everything from data acquisition and processing, mathematical model establishment, advanced control strategies to engineering implementation.

[0084] Advanced process control systems (APS) utilize modern mathematical modeling, optimization calculations, and control algorithms to perform multivariate control and optimization of typical reaction units in factory operation simulation mechanisms. Primarily applied in chemical plant production processes, APS aims to improve production efficiency and product quality. It enables online monitoring and control of process systems, automatically adjusting production parameters to achieve these goals. APS can monitor the real-time operating status, key parameters, and critical point values ​​of typical reaction units, displaying energy consumption, component status, and operational status, providing operators with a comprehensive understanding of the production situation. Employing a large data model matrix and an intuitive visualization interface, APS displays real-time trends and data on key process variables such as temperature and composition, providing operators with decision-making support for optimizing production operations and maximizing production performance. Compared to traditional PID control systems, APS offers higher control precision and greater adaptability, effectively responding to various changes and anomalies in the process system, thereby improving production efficiency and product quality while reducing production costs. Students (trainees) learn about real-time monitoring and operation of actual production processes through the APS operator station, cultivating their abilities in practical operating environments. The engineering workstation for advanced process control systems provides students (trainees) with more in-depth learning opportunities, allowing them to learn and understand the principles and methods of system configuration, parameter adjustment and optimization strategies, and improve their practical skills.

[0085] The safety control module can be a Safety Instrumented System (SIS), also known as a Safety Interlocking System. It primarily serves as the alarm and interlocking component of a factory control system, implementing alarm actions, adjustments, or shutdown controls based on the detection results within the control system. It is a crucial part of the automatic control system in factories and enterprises.

[0086] Safety Instrumented Systems (SIS) monitor key process variables in real time within a plant operation simulation mechanism to ensure that process operations are conducted within safe limits, monitor and handle potential hazards, and guarantee safe process operation. SIS collects and analyzes parameters such as pressure, temperature, and liquid level, comparing them with preset safety limits. If a parameter exceeds a safety limit, the SIS immediately triggers alarms and emergency shutdown functions to prevent potential hazards. When an abnormality occurs in the SIS, it activates safety protection measures, such as automatically closing valves or shutting down the system, to ensure process safety.

[0087] The simulation optimization module can employ a virtual simulation system, or DCS for short. A virtual simulation system is a computer-based system that simulates real-world control processes. It can simulate complete production processes and control systems, and can perform real-time simulations. It can be used in industrial production, R&D experiments, training and education, etc., to optimize processes, improve product quality, and reduce production costs.

[0088] The execution management of production operations in the factory simulation mechanism by the production execution layer can be achieved through a production control system (EMS). An EMS is used to monitor, manage, and optimize the manufacturing process, improving production efficiency and quality while reducing production costs. In the factory simulation mechanism, the EMS is used for production planning and scheduling, production order management, material tracking, quality control, production data acquisition, and data analysis. The EMS helps enterprises achieve digitalization, intelligentization, networking, and standardization of their production processes, improving production efficiency and quality, reducing production costs, strengthening enterprise control and management of the production process, and enhancing competitiveness and market share. Simultaneously, the EMS can also help enterprises achieve real-time monitoring and data analysis of the production process, promptly grasp production status, and provide a scientific basis for enterprise decision-making.

[0089] Production control systems can facilitate practical teaching and training by simulating scenarios, providing more realistic process industry production simulations and authentic typical job practice foundations, deepening students' understanding and mastery of the production process; they can simulate the production environment on a computer, allowing students to understand the operation of the production line, master production processes and equipment operation, and improve their understanding and mastery of the production process, preparing them for future career development; they can practice controlling the production process, such as adjusting process parameters and optimizing the production line, helping to improve students' practical skills and deepen their understanding of production control; and they can collect and store large amounts of production data, such as equipment operating status and product quality, providing analysis... This system analyzes production data application scenarios, helping students (trainees) utilize this data to understand problems in the production process, propose improvement solutions, and increase production efficiency. It can optimize production operation processes, allowing students (trainees) to use the production control system to optimize processes, such as adjusting process parameters, improving equipment operation, and enhancing product quality. This helps improve students' (trainees') innovation capabilities and prepares them for future career development. It can also leverage existing practical teaching resources for collaborative sharing and external service training for employees, providing training for students about to enter the workforce. For example, pre-employment trainees can understand the production line operation process and master equipment operation through simulations. The production control system enables the formulation and implementation of production plans, the manipulation of intelligent manufacturing systems and equipment for chemical production control, the management of production process quality, and the analysis and mining of data to find optimal process indicators and achieve high-quality, low-consumption production.

[0090] The production control system specifically includes production planning management, production scheduling management, QHSE management, equipment management, supply chain and related management. It enables the collection, organization, processing, analysis, and integration of data related to chemical production, such as plan execution, production scheduling, product quality, model management, equipment management, preventative maintenance management, material management, and personnel information management. This provides students (trainees) and teachers (managers) with the ability to execute and track plans, as well as obtain the current status information of all resources. Obtaining the current status information of all resources includes the current status information of personnel, equipment, materials, and other resources.

[0091] The production planning management includes inspection and maintenance plans, production plans, and procurement plans. Each plan includes a plan name, start time, end time, plan type, planned quantity, actual quantity, execution progress, and plan priority. The production planning management supports administrators in scheduling or creating custom planned tasks, enabling the management of these tasks.

[0092] The production scheduling management includes information such as scheduling name, type, execution content, execution status, and associated plan number. It supports schedulers in setting up various production plans, allowing students to learn related operations and skills: students can learn how to formulate reasonable production plans and schedules, flexibly respond to environmental changes, understand and master new technologies, methods, and tools, and apply them to production scheduling to improve efficiency and quality. They can also learn how to collaborate as a team to better achieve production goals. Ultimately, through simulating various problems and difficulties in a production environment, students learn how to solve, communicate, and handle these issues, improving their adaptability and teamwork skills.

[0093] QHSE management is used to ensure that enterprises achieve optimal levels of management in health, safety, and the environment. Based on the concept of comprehensive risk management, it identifies, assesses, and controls potential risks, and takes preventative measures to ensure that the enterprise's QHSE performance meets expectations. QHSE management focuses on environmental management and product quality management, emphasizing production quality and environmental protection to achieve controllable environmental hazards and superior product efficiency. QHSE management monitors the quality indicators of various raw materials and products, including the name of the sample, testing items, testing standards, submission time (selectable), testing status (selectable), submitter, test results (selectable), description of quality phenomena, and the person responsible for testing, thus forming a product quality management system.

[0094] The QHSE management system allows students to simulate product manufacturing processes in a simulation environment, gaining a deeper understanding of key technologies and processes in product manufacturing and improving their practical skills. It also enables them to learn how to effectively control product quality and handle unexpected problems under different production environments, thereby enhancing their problem-solving abilities. Furthermore, it fosters comprehensive qualities such as teamwork and communication skills, developing students' collaborative and communication abilities through practical experience. This provides multi-level, comprehensive, and three-dimensional teaching resources, broadens the content of experimental teaching, increases the technological content of experimental teaching, and allows students to better apply the knowledge taught.

[0095] The equipment management system includes equipment ledgers, equipment inspection and maintenance records, and equipment anomaly reporting and handling records. This allows students to learn the relevant operations and skills for handling equipment anomaly reports in a virtual environment, learning how to process such reports and understanding the appropriate responses to different equipment anomalies. The equipment anomaly reporting and handling record function also allows students to learn and master new technologies, methods, and tools, and how to apply them to equipment anomaly handling to improve efficiency and quality. Furthermore, it teaches them how to collaborate effectively in teams to better achieve production goals. Ultimately, by simulating the equipment anomaly reporting and handling process, students learn how to troubleshoot and handle equipment anomalies, and how to perform preventative maintenance to extend equipment lifespan and reduce production costs.

[0096] Supply chain and related management, encompassing the coordination and control of suppliers, manufacturers, logistics service providers, and distributors, is a crucial aspect of modern enterprise operations. It enables businesses to effectively transfer raw materials, components, and finished products from suppliers to end consumers, ensuring efficiency and cost control throughout the process, and primarily involves typical material management and personnel information management. This training allows students to understand the basic principles and management methods of product storage, learn about modern logistics management technologies, and grasp the importance of warehouse management, such as product inbound and outbound processes, quality control, and inventory management. Through practical exercises, students enhance their understanding and mastery of warehouse management, developing teamwork and problem-solving skills. In simulated learning sessions, students collaborate with others to complete tasks, identify and solve problems, thereby improving their overall competence.

[0097] The integrated simulation teaching mechanism includes a teaching task management unit, an artificial intelligence reasoning unit, a factory digital twin unit, and a competency assessment and diagnosis unit. The teaching task management unit is responsible for distributing teaching tasks, coordinating the factory operation simulation mechanism, collecting task completion progress and performance data, and generating practice reports for each student. The artificial intelligence reasoning unit assesses student (trainee) competency using a knowledge graph based on data from the practical teaching training process. The factory digital twin unit synchronously runs the simulated production based on real-time data from the factory operation simulation mechanism, creating a precise digital copy to enable real-time monitoring, prediction, and optimization of simulated production in a digital environment. The competency assessment and diagnosis unit summarizes the overall course achievement based on individual student (trainee) competency during practical teaching, thereby supporting the improvement of the teaching team's teaching capabilities.

[0098] The practical teaching and training process data includes the process data corresponding to the factory operation simulation mechanism and the factory control simulation mechanism during practical operation by students (trainees).

[0099] The teaching task management unit dynamically distributes practical teaching tasks and recreates and simulates the corresponding working conditions of the factory operation simulation mechanism through the linkage between the distribution of teaching tasks and the simulation of the factory operation simulation mechanism. The management of practical teaching tasks and the simulation of typical practical teaching environments of the factory operation simulation mechanism are completed simultaneously. The teaching task management unit supports the distribution, progress, and grade collection and control of practical teaching tasks, and generates practical teaching training process data for students based on teaching tasks, completion progress, and grades.

[0100] The AI ​​reasoning unit uses the data from the practical teaching and training process, based on the operational nodes of the practical process, to reason, analyze, and summarize the antecedents, consequences, and influencing relationships through bidirectional reasoning of knowledge graphs. It then conducts personalized and job-specific competency assessments of students (trainees), enabling analysis and guidance of individual trainees' abilities and providing them with suggestions and directions for consolidation and improvement.

[0101] The factory digital twin unit, based on the factory operation simulation mechanism, is deployed in the cloud and synchronizes with the valves and instruments of the on-site factory operation simulation mechanism. Utilizing cloud service and IoT technologies, it extends the on-site practical teaching and training application scenarios to the internet, achieving the co-construction and sharing of practical teaching resources. The factory digital twin unit can not only link with the on-site factory operation simulation mechanism's production operation but also supports independent cloud operation. Furthermore, by employing the OTS process simulation model of the factory operation simulation mechanism, the production process, production indicators, and energy consumption data in the twin's practical teaching and training application scenarios are completely consistent with the factory operation simulation mechanism, thereby achieving the goal of serving society and the region. Due to the consistency of the practical effects between the factory digital twin unit and the factory operation simulation mechanism, practical teaching and training activities can be carried out through the cloud-based operation of the factory digital twin unit. The teaching task management unit can be used to distribute tasks, collect task completion progress data, and collect task results, completing remote control practical teaching and training scenarios.

[0102] The competency assessment and diagnostic unit, combined with the practical teaching and training curriculum system, presents the operational capabilities of the practical process through big data visualization. Based on the summary of the overall course practical teaching situation and the course achievement, it forms a common understanding of practical teaching and training mastery, thereby helping to improve the teaching ability of the teaching team.

[0103] A system for constructing a smart simulation factory for practical teaching based on Internet of Things (IoT) devices also includes a data tag generation mechanism. The data tag generation mechanism tags the data of the practical teaching training process and the data generated by the simulation teaching integration mechanism during the practical teaching training of students, thereby distinguishing the data of different students (trainees) in the simulation practice process, and enabling the factory operation simulation mechanism, factory control simulation mechanism, and simulation teaching integration mechanism to quickly extract target data when using the data.

[0104] The data generated during the practical teaching and training process, as well as the data generated by the simulation teaching integration institution during the practical teaching and training of students, are collectively referred to as process data.

[0105] The data tag generation mechanism includes a data pool, a tag comparison generation unit, a tag generation unit, and a data extraction unit. The data pool stores different process data generated during simulation teaching, including practical data and analytical data. The tag comparison generation unit generates tags corresponding to different tasks, students, and / or times, and stores the generated tags in comparison with the corresponding tasks, students, and / or times. The tag generation unit tags the process data (process data) generated by the factory operation simulation mechanism, the factory control simulation mechanism, and the simulation teaching integration mechanism in the data pool to obtain tag data. The data extraction unit extracts data from the data pool according to a data extraction command to obtain the target data.

[0106] The data in the data pool is tagged data, including a data core and a tag core. The data core is the original data content, and the tag core is used to tag corresponding tasks, students, and / or times, etc. Only one data core is included in the data pool, and each data core's tag core can correspond to multiple tasks, students, and / or times, etc. When new data is generated, the data tag generation mechanism searches the data pool. If no identical data core is found in the data pool, the new data is considered untagged data and is placed into the data pool after tagging. When identical data cores are found in the data pool, the data tag generation mechanism retrieves data in the data pool whose data cores match the new data to obtain untagged data. At this point, the data in the data pool whose data cores match the new data is considered untagged data.

[0107] The tag comparison generation unit includes a tag comparison table, which records tags corresponding to different tasks, students, and times. The tag comparison table includes a header column, a member column, and a tag column. The header column can be input by the administrator via an input mechanism. The header column provides a detailed explanation of whether the tag classification in the member column and tag column corresponds to a task, student, or time. Specific tag classifications in the header column are selected headers. The member column is a member classification column that compares different task names, student names, and time points within a task, student, and / or time. The tag column contains tags corresponding to specific tasks, students, and / or times. Tags in the tag column can be binary data, images, or other forms of data; no specific restrictions are placed here.

[0108] Here is an example structure of a label lookup table, as shown in the table below:

[0109]

[0110]

[0111] The tags corresponding to different tasks, different trainees, and / or different times in the tag bar can be generated by the first rule preset by the tag comparison generation unit, or they can be specified tags input by the input mechanism.

[0112] When the data tag generation organization needs to tag new data (newly generated data), the specific steps are as follows:

[0113] The tag generation unit retrieves the new data from the data pool;

[0114] When there is no data unit in the data pool that is the same as the new data, the new data is data to be labeled. The label generation unit refers to the label lookup table to select the label of the current new data corresponding to the task, student and / or time and combines it with the new data (data to be labeled) to obtain labeled data.

[0115] When there are identical data units in the data pool, the tag generation unit retrieves the data units in the data pool that are identical to the new data to obtain the data to be tagged. At this time, the data units in the data pool that are identical to the new data are the data to be tagged. The tag generation unit refers to the tag lookup table and selects the tags corresponding to the current new data for the task, student and / or time, and combines them with the data to be tagged to obtain the tag data.

[0116] The tag data includes the current new data and indicates which task, student, and / or time the current new data was generated.

[0117] The tag generation unit selects the tag corresponding to the task, student, and / or time of the current new data by referring to the tag lookup table. Specifically, this can be done in the following ways.

[0118] The tag generation unit selects the corresponding header to be selected in the header column according to the task, student and / or time corresponding to the current new data.

[0119] The marker generation unit selects the corresponding task name, student name and / or time point in the member column corresponding to the selected candidate header, i.e., the candidate member;

[0120] The tag generation unit reads the corresponding tag in the tag column of the member to be selected.

[0121] The tag generation unit refers to the tag lookup table to select the tag corresponding to the current new data for the task, student, and / or time, and combines it with the data to be tagged. Specifically, this can be done in the following ways.

[0122] The tag generation unit appends the tags corresponding to the task, student, and / or time of the new data to the end of the data to be tagged, obtaining new tag data. When the new tag data is obtained by combining new data with the corresponding tag, the tag generation unit directly puts the new tag data into the data pool. When the new tag data is obtained by combining data in the data pool that is identical to the new data with the corresponding tag, the tag generation unit deletes the initial data in the data pool that is identical to the new data and directly puts the new tag data into the data pool, that is, the new tag data replaces the tag data in the data pool that is identical to the new data.

[0123] The data extraction command can be a data extraction command generated by the factory operation simulation mechanism, the factory control simulation mechanism, or the simulation teaching integration mechanism when using data, or it can be a data extraction command entered by the administrator through the input mechanism. No specific restrictions are imposed here.

[0124] The extraction command includes at least the target members to be selected corresponding to the target data, that is, the task name, student name and / or time point corresponding to the target data, and may also include the tags corresponding to the target data.

[0125] When the extraction command includes a target member to be selected corresponding to the target data, the data extraction unit can obtain the target data in the following manner.

[0126] The data extraction unit reads the target members to be selected from the extraction command, namely the target task name, student name and / or time point;

[0127] The data extraction unit searches for the target member to be selected in the label lookup table and reads the corresponding label in the label column of the target member to be selected, thereby obtaining the target label;

[0128] The data extraction unit searches the data pool and reads the tag data of the tag data in the data pool, including the tag data of the target tag, to obtain the target tag data;

[0129] The data extraction unit separates the data body and the tag body of the target tag data, and then organizes all the data body parts of the target tag data to obtain the target data.

[0130] When the extraction command includes a tag corresponding to the target data, the data extraction unit can obtain the target data in the following manner.

[0131] The data extraction unit reads the tags corresponding to the target data in the extraction command, i.e., the target tags;

[0132] The data extraction unit searches the data pool and reads the tag data of the tag data in the data pool, including the tag data of the target tag, to obtain the target tag data;

[0133] The data extraction unit separates the data body and the tag body of the target tag data, and then organizes all the data body parts of the target tag data to obtain the target data.

[0134] The data pool includes multiple data sub-pools. The tag data in each data sub-pool can be stored in the same data sub-pool according to the different headers in the header column. The data extraction unit searches in the corresponding data sub-pool according to the header column corresponding to the tag of the target member or target data in the extraction command, thereby speeding up the extraction process.

[0135] Tag data in each data pool can be stored according to different task names, different student names, and / or different time points in the member column. Tag data with the same task name, the same student name, and / or the same time point are stored in the same data pool. The data extraction unit searches in the corresponding data pool according to the member column corresponding to the target member or target data tag in the extraction command, thereby speeding up the extraction process.

[0136] A system for constructing a smart simulation factory for practical teaching based on Internet of Things (IoT) devices guides the development of simulation devices or factories in educational institutions and builds upon OTTS (Optical Time System) production algorithms. It constructs a physical smart factory for practical teaching, using simulated physical objects as the foundation and virtual systems as the guide, creating an intelligent digital factory that integrates the real and the virtual. By combining the teaching task management unit, artificial intelligence reasoning unit, factory digital twin unit, and capability assessment and diagnosis unit of the simulation teaching integration institution with supporting hardware equipment, it simulates real industrial production scenarios, realistic production data, and realistic production indicators, comprehensively simulating the smart factory environment. This allows users to understand the development trends of modern and intelligent industries through practice, and uses an intelligent production environment to support the cultivation of intelligent manufacturing talents, thereby meeting the needs of practical teaching (training).

[0137] A system for constructing a smart simulation factory for practical teaching based on Internet of Things (IoT) devices is proposed. The system uses IoT devices to collect simulated process production data of key equipment, constructs unified and standardized production parameters and indicators, processes and analyzes the simulated process production data, and uses the production data indicators to carry out job skills practice and process data optimization required for intelligent production.

[0138] A system for constructing an intelligent simulation factory for practical teaching based on Internet of Things (IoT) devices is proposed. This system closely approximates real production data, meets the requirements of actual factory operations, and can obtain dynamic updates of process data, ensuring the accuracy and authenticity of practical teaching (training).

[0139] A system for constructing a smart simulation factory for practical teaching based on Internet of Things (IoT) devices reduces memory usage in process data storage while ensuring fast data retrieval, thus improving the overall usability of the system.

[0140] The above description illustrates preferred embodiments of the present invention and helps those skilled in the art to more fully understand the technical solution of the present invention. However, these embodiments are merely illustrative and should not be construed as limiting the specific implementation of the present invention to these embodiments. For those skilled in the art, several simple deductions and modifications can be made without departing from the inventive concept, and all such modifications should be considered within the protection scope of the present invention.

Claims

1. A system for constructing an intelligent simulation factory for practical teaching based on Internet of Things (IoT) devices, characterized in that, include: Factory operation simulation mechanisms are used to simulate factory production operations and acquire factory production operation data; The factory control simulation mechanism controls the production operation of the factory operation simulation mechanism, thereby automating the factory operation simulation mechanism; The simulation teaching integration institution implements simulation teaching based on the training program; Data tagging organizations label the data generated during students' practical teaching and training processes and the data generated during students' practical teaching and training by the integrated simulation teaching organization. This allows them to distinguish the data of different students in the simulation practice process and quickly extract the target data when using the data. The data label generation mechanism includes a data pool, a label comparison generation unit, a label generation unit, and a data extraction unit. The data pool stores different process data generated during simulation teaching, including practical data and analytical data. The data in the data pool is label data, consisting of a data body and a label body. The data body contains the original data content, while the label body is used to label corresponding tasks, students, or times. The label comparison generation unit generates labels corresponding to different tasks, students, or times and stores them for comparison. The label generation unit labels the process data in the data pool to obtain label data. The data extraction unit extracts data from the data pool according to data extraction commands to obtain the target data. When the data tagging organization needs to tag new data, the tagging generation unit searches the data pool for the new data: if there is no data unit in the data pool that is the same as the new data, the new data is the data to be tagged. The tagging generation unit refers to the tag lookup table and selects the tag corresponding to the task, student, or time of the current new data and combines it with the new data to obtain the tagged data; if there is a data unit in the data pool that is the same as the new data, the tagging generation unit retrieves the data in the data pool that is the same as the new data to obtain the data to be tagged. At this time, the data in the data pool that is the same as the new data is the data to be tagged; the tagging generation unit refers to the tag lookup table and selects the tag corresponding to the task, student, or time of the current new data and combines it with the data to be tagged to obtain the tagged data. When new label data is obtained by combining new data with corresponding labels, the label generation unit directly puts the new label data into the data pool. When new label data is obtained by combining the data in the data pool that is the same as the new data with the corresponding label, the label generation unit deletes the initial data in the data pool that is the same as the new data and puts the new label data directly into the data pool. In other words, the new label data replaces the label data in the data pool that is the same as the new data.

2. The system for constructing a practical teaching intelligent simulation factory based on Internet of Things (IoT) devices according to claim 1, characterized in that, The factory operation simulation mechanism includes simulation devices, Internet of Things (IoT) equipment, and intelligent robots; The factory control simulation mechanism includes a production control layer and a production execution layer. The production control layer is used for production operation control of the factory operation simulation mechanism, and the production execution layer is used for the execution management of production operation of the factory operation simulation mechanism. The simulation-based teaching integration unit includes a teaching task management unit, an artificial intelligence reasoning unit, a factory digital twin unit, and a capability assessment and diagnosis unit.

3. The system for constructing a practical teaching intelligent simulation factory based on Internet of Things (IoT) devices according to claim 1, characterized in that, The tag comparison generation unit includes a tag comparison table, which records the tags corresponding to different tasks, different trainees, and different times. The tag comparison table includes a header column, a member column, and a tag column. The header column provides a detailed description of the tag classification for tasks, trainees, or times corresponding to the member column and the tag column. The specific tag classification in the header column is the header to be selected. The member column is a column for classifying members based on different task names, trainee names, and time points in the comparison task, trainee, or time. The tag column contains the tags corresponding to specific tasks, trainees, or times. The tags corresponding to different tasks, trainees, or times in the tag comparison generation unit are generated by the first preset rule or specified tags input by the input organization.

4. The system for constructing a practical teaching intelligent simulation factory based on Internet of Things (IoT) devices according to claim 1, characterized in that, The extraction command includes the target members to be selected corresponding to the target data. The data extraction unit obtains the target data in the following way: The data extraction unit reads the target members to be selected from the extraction command; The data extraction unit searches for the target member to be selected in the label lookup table and reads the corresponding label in the label column of the target member to obtain the target label; The data extraction unit searches the data pool and reads the tag data of the tag data in the data pool, including the tag of the target tag, to obtain the target tag data; The data extraction unit separates the data body and the label body of the target label data, and then organizes all the data body in the target label data to obtain the target data.

5. The system for constructing a practical teaching intelligent simulation factory based on Internet of Things (IoT) devices according to claim 1, characterized in that, The extraction command includes the tags corresponding to the target data. The data extraction unit obtains the target data in the following way: The data extraction unit reads the tags corresponding to the target data in the extraction command, i.e., the target tags; The data extraction unit searches the data pool and reads the tag data of the tag data in the data pool, including the tag of the target tag, to obtain the target tag data; The data extraction unit separates the data body and the label body of the target label data, and then organizes all the data body in the target label data to obtain the target data.

6. The system for constructing a practical teaching intelligent simulation factory based on Internet of Things (IoT) devices according to claim 4 or 5, characterized in that, The data pool consists of multiple data sub-pools. The tag data in each data sub-pool is stored in the same data sub-pool according to the different header columns in the header column. The data extraction unit searches in the corresponding data sub-pool according to the header column corresponding to the tag of the target member or target data in the extraction command.

7. A system for constructing a practical teaching intelligent simulation factory based on Internet of Things (IoT) devices according to claim 4 or 5, characterized in that, The data pool consists of multiple data sub-pools. Tag data in each data sub-pool is stored according to different task names, different student names, or different time points in the member column. Tag data with the same task name, the same student name, or the same time point are stored in the same data sub-pool. The data extraction unit searches in the corresponding data sub-pool according to the target member to be selected or the tag corresponding to the target data in the extraction command.

Images