Operation method and system of digital twin factory

Abstract

The invention discloses an operation method and system of a digital twin factory. According to the system, the equipment state monitoring sub-module monitors and displays the equipment parameters in real time, the equipment state monitoring sub-module provides a visual equipment operation state for an operator, potential faults can be found in time, and therefore production interruption caused by the equipment faults is reduced. And secondly, the early warning function of the module can give an alarm before a fault occurs, so that a time window is provided for preventive maintenance, and the influence of fault expansion is avoided. In addition, the real-time monitoring function of the equipment state monitoring sub-module is beneficial for improving the production efficiency because the equipment state monitoring sub-module can ensure that the equipment runs in the optimal state, and the non-planned downtime is reduced. And meanwhile, the data recording and analyzing functions of the module are beneficial to improving the reliability of the equipment, and potential problems of the equipment can be identified by analyzing historical data, so that measures are taken for preventive maintenance, the service life of the equipment is prolonged, and stable operation of a factory is guaranteed.

Description

Technical Field

[0001] The present invention belongs to the technical field of digital twin factories, and specifically relates to an operation method and system of a digital twin factory. Background Art

[0002] The digital twin factory is a factory design and management method based on digital technology. It achieves real-time monitoring, predictive analysis and optimization adjustment of the factory by establishing a digital model that completely corresponds to the actual factory physical entity. The digital twin factory can improve the factory's operating efficiency, reduce operating costs, reduce the occurrence of failures, and improve product quality. The advantages of the digital twin factory are: Improve production efficiency: The digital twin factory can achieve real-time monitoring and optimization adjustment of production lines and equipment to improve production efficiency. Reduce operating costs: The digital twin factory can reduce equipment downtime, reduce maintenance costs, optimize energy use, and reduce operating costs. Reduce the occurrence of failures: The digital twin factory can predict equipment failures, take maintenance measures in advance, and reduce the occurrence of failures. Improve product quality: The digital twin factory can optimize process parameters and improve product quality. Enhance corporate competitiveness: The digital twin factory can improve production efficiency, reduce operating costs, improve product quality, and enhance corporate competitiveness. In short, the digital twin factory is a factory design and management method based on digital technology, which can achieve real-time monitoring, predictive analysis and optimization adjustment of the factory. With the development of information technology and the continuous advancement of intelligent manufacturing, digital twin factories will play an increasingly important role in corporate operations.

[0003] However, common existing monitoring technologies may not cover all key equipment and process flows, resulting in monitoring blind spots. At the same time, existing diagnostic technologies may not accurately predict faults or diagnose problems, resulting in misdiagnosis or missed diagnosis. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for operating a digital twin factory in order to solve the above-mentioned problems.

[0005] The technical solution adopted by the present invention is as follows: a digital twin factory system, the system comprising: a data acquisition and processing module, a virtual modeling module, a real-time monitoring and diagnosis module, a production optimization and decision-making module, and a safety and emergency management module;

[0006] The data collected by the data acquisition and processing module is transmitted to the virtual modeling module to update the model, and at the same time provides basic data for monitoring and analysis for the real-time monitoring and diagnosis module.

[0007] The monitoring results and fault diagnosis information of the real-time monitoring and diagnosis module are fed back to the production optimization and decision-making module to guide production adjustment and equipment maintenance.

[0008] The optimization scheme and decision instructions of the production optimization and decision-making module affect the monitoring strategy of the real-time monitoring and diagnosis module.

[0009] The safety and emergency management module receives safety alarm information from the real-time monitoring and diagnosis module and triggers emergency response when necessary. At the same time, its safety monitoring data also comes from the data acquisition and processing module;

[0010] The real-time monitoring and diagnosis module includes an equipment status monitoring submodule, a fault warning and diagnosis submodule, a production process monitoring submodule, a safety monitoring submodule, an alarm and communication submodule and a maintenance management submodule.

[0011] In a preferred embodiment, the data acquisition and processing module first collects data such as temperature, humidity, pressure, vibration, and current in real time through sensors and equipment deployed at key points in the factory. The data acquisition and processing module regularly calibrates sensors to ensure data accuracy; uses data compression technology to reduce data transmission volume; filters and standardizes data through data preprocessing algorithms; establishes a data warehouse for data storage and management; and uses a data synchronization mechanism to ensure data consistency. In addition, the module is also responsible for real-time data transmission, pushing processed data to other modules through wired or wireless networks for further analysis and application.

[0012] In a preferred embodiment, the virtual modeling module uses the collected data to build and update the digital twin model. Use 3D modeling software to create accurate models of factories and equipment; map real-time data to virtual models through data interfaces; implement dynamic simulation of models to simulate equipment operation and production processes; provide an interactive interface to allow users to operate and adjust in a virtual environment; and regularly verify and optimize the model to ensure its consistency with the actual factory.

[0013] In a preferred embodiment, the equipment status monitoring submodule ensures real-time monitoring and effective management of the factory equipment status through the following three main steps: first, establish communication connections with sensors and actuators, periodically read data, and perform preliminary data verification to ensure data accuracy and real-time performance; second, perform time synchronization, unit conversion, cleaning, and outlier detection on the collected data to optimize data quality, and cache it for real-time monitoring and historical data analysis; finally, display the processed data in real time on the monitoring interface, and through functions such as threshold monitoring, alarm triggering, user interaction, and event recording, achieve continuous monitoring and rapid response to the equipment status, and adjust the monitoring strategy based on monitoring results and user feedback to continuously improve the effectiveness of the monitoring system and the overall operational efficiency of the factory;

[0014] The fault warning and diagnosis submodule includes:

[0015] Early warning model training: Use historical fault data to train early warning models, such as using SVM, neural networks, etc.

[0016] Real-time data analysis: Real-time analysis of equipment operation data and comparison with the early warning model.

[0017] Fault diagnosis: Once an abnormality is found, fault diagnosis is performed using the fault tree analysis (FTA) method;

[0018] The early warning model: Y = f(X; θ), where Y is the early warning output, X is the input feature, and θ is the model parameter;

[0019] Fault diagnosis: D = g(A;), where D is the diagnosis result, A is the abnormal data, and is the diagnosis model parameter.

[0020] In a preferred embodiment, the production process monitoring submodule operation method includes:

[0021] Production data integration: Obtain production plans and data from MES, ERP and other systems.

[0022] Process tracking: Track the location of products on the production line through technologies such as RFID and barcode scanning.

[0023] Quality Control: Use statistical process control (SPC) methods to monitor product quality;

[0024] The calculation formula used by the production process monitoring submodule for statistical process control is:

[0025] Where Xˉ is the sample mean, S is the sample standard deviation, and n is the sample size.

[0026] In a preferred embodiment, the safety monitoring submodule uses risk assessment tools to quantify potential risks, and formulates and tests emergency response plans to ensure the safety of the factory environment. Specifically, the module first collects and records environmental parameters and safety equipment status in real time to ensure that these data can provide accurate information for subsequent risk assessments. Secondly, using risk assessment tools such as the LEC method, combined with the possibility of accidents, exposure frequency and severity of accident consequences, each risk point is quantitatively evaluated and divided into different levels so that emergency response plans can be formulated in a targeted manner. Finally, the module ensures that it can respond quickly and effectively in emergencies, minimize the impact of accidents, and ensure the safety of factories and personnel by regularly training employees, testing and rehearsing emergency response plans. Through these three steps, the safety monitoring submodule plays a vital role in the digital twin factory operation system, providing strong guarantees for the safe and stable operation of the factory;

[0027] The calculation formula of LEC method is: R = L × E × C

[0028] Where L is the probability of an accident occurring.

[0029] E is the frequency of personnel exposure to hazardous environments.

[0030] C is the possible consequences of the accident.

[0031] In a preferred embodiment, the alarm logic of the alarm and communication submodule is:

[0032] Preset condition setting: According to the factory's safety standards and operating procedures, set a series of alarm trigger conditions, such as equipment parameters exceeding safety thresholds, safety equipment status abnormalities, etc.

[0033] Logical combination: Establish a logical combination of alarm conditions to ensure that the alarm is triggered only when specific conditions are met at the same time, avoiding false alarms and missed alarms.

[0034] Real-time monitoring: Continuously monitor plant status and automatically detect and evaluate whether alarm conditions are met.

[0035] Alarm triggering: When a situation that meets the alarm conditions is detected, the alarm is triggered immediately;

[0036] The communication mechanism of the alarm and communication submodule is:

[0037] SMS notification: Send alarm information to relevant personnel via SMS service, including alarm type, occurrence time, possible impact, etc.

[0038] Email notification: Send emails to relevant personnel to provide detailed alarm information and necessary action guidelines.

[0039] Sound and light alarm: Set up sound and light alarm system inside the factory to notify on-site personnel with visual and auditory signals and remind them to take action.

[0040] Internal communication system: Use the factory's internal communication system, such as intercoms, broadcasting systems, etc., to quickly convey alarm information.

[0041] In a preferred embodiment, the maintenance management submodule first formulates a maintenance plan based on the equipment operating time and failure history, and formulates a preventive maintenance plan, including maintenance cycles, maintenance content, maintenance tools and materials, etc. Secondly, the maintenance work order generation automatically identifies the equipment maintenance needs and generates a maintenance work order, including detailed information such as maintenance tasks, maintenance personnel, and maintenance time. Finally, the maintenance record analysis evaluates the effectiveness of the maintenance activities by recording the detailed information of each maintenance activity, and optimizes the maintenance strategy according to the actual situation to improve maintenance efficiency and equipment reliability. Through these processes, the maintenance management submodule can ensure the normal operation of factory equipment and extend the life of equipment, reduce the failure rate, improve production efficiency, and further ensure the stable operation of the factory.

[0042] In a preferred embodiment, the production optimization and decision-making module uses historical data and real-time monitoring information to analyze production efficiency; uses optimization algorithms to adjust production plans and resource allocation; evaluates the effects of different decision-making plans through simulation and prediction tools; integrates expert systems to provide decision support for complex problems; implements a closed-loop feedback mechanism to continuously adjust optimization strategies based on production results;

[0043] The safety and emergency management module focuses on monitoring the safety status within the factory, including environmental safety, equipment safety and personnel safety. It receives safety data from the real-time monitoring and diagnosis module, and immediately triggers the early warning system and initiates the emergency plan once a safety hazard or accident is detected. This module ensures a quick response in an emergency, minimizes the impact of the accident, and ensures the safety of the factory and personnel.

[0044] In a preferred embodiment, the operating method comprises the following steps:

[0045] 1. Data collection and processing: First, the digital twin factory collects real-time data from sensors and actuators through industrial protocols, including equipment operation data, environmental data, etc. These data are the original information of factory operation and provide the basis for subsequent monitoring, diagnosis and optimization. The collected data needs to be time synchronized, unit converted and outlier detected to ensure the accuracy and availability of the data. This step is the basis of the entire operation method and provides key data support for subsequent modules.

[0046] 2. Virtual modeling: Based on the collected data, a three-dimensional virtual model of the factory is established, including the factory layout, production line, equipment, etc. This model is the core of the digital twin factory, and it can be updated in real time to reflect the status of the actual factory. Through virtual modeling, operators can perform simulation operations, predictive analysis, and scene reproduction without affecting actual production, providing an intuitive visualization and simulation environment for subsequent monitoring, diagnosis, and optimization.

[0047] 3. Real-time monitoring and diagnosis: The real-time monitoring and diagnosis module of the digital twin factory is responsible for continuous monitoring of the equipment status, production process and safety hazards in the factory. Through real-time data and virtual models, the module can display equipment parameters in real time, warn of potential faults, and provide fault diagnosis information. At the same time, it can also monitor the production process, track production progress, and ensure the smooth progress of production plans. This step is the key to ensuring production continuity and equipment reliability. It will feed back the monitoring results to other modules to support production optimization and safety emergency management.

[0048] 4. Production optimization and decision-making: The production optimization and decision-making module of the digital twin factory uses the data and analysis results provided by the real-time monitoring and diagnosis module to optimize production plans, analyze energy consumption, and make equipment maintenance and update decisions. It proposes improvement measures through algorithms and simulation experiments to help management make more reasonable production decisions. At the same time, it is also responsible for formulating equipment maintenance plans to extend equipment life and improve production efficiency. This step is the key to improving factory production efficiency and reducing costs, and it provides support for the continuous improvement and optimization of the digital twin factory.

[0049] 5. Safety and emergency management: The safety and emergency management module of the digital twin factory focuses on monitoring the safety conditions within the factory, including environmental safety, equipment safety, and personnel safety. It receives safety data from the real-time monitoring and diagnosis module, and immediately triggers the early warning system and initiates the emergency plan once a safety hazard or accident is detected. This module ensures a rapid response in an emergency, minimizes the impact of accidents, and ensures the safety of the factory and personnel. Through the safety and emergency management module, the digital twin factory can achieve safety monitoring and emergency management of the factory to ensure the stable and safe operation of the factory.

[0050] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0051] 1. In the present invention, the equipment status monitoring submodule provides operators with intuitive equipment operation status by real-time monitoring and displaying equipment parameters, which helps to discover potential faults in time, thereby reducing production interruptions caused by equipment failures. Secondly, the early warning function of the module can issue an alarm before a fault occurs, providing a time window for preventive maintenance and avoiding the impact of fault expansion. In addition, the real-time monitoring function of the equipment status monitoring submodule helps to improve production efficiency because it can ensure that the equipment operates in the best state and reduce unplanned downtime. At the same time, the data recording and analysis function of the module helps to improve the reliability of the equipment because by analyzing historical data, potential problems of the equipment can be identified, so that measures can be taken for preventive maintenance and extend the life of the equipment. Finally, the alarm and communication functions of the equipment status monitoring submodule are particularly important in emergency situations because it can quickly notify relevant personnel and start the emergency response process, thereby minimizing the impact of accidents. In summary, the equipment status monitoring submodule plays a key role in the operation system of the digital twin factory. It helps to improve the reliability and production efficiency of the equipment, reduce the impact of accidents, and ensure the stable operation of the factory through functions such as real-time monitoring, early warning, data recording and analysis.

[0052] 2. In the present invention, the virtual modeling module provides an intuitive visualization and simulation environment for operators by establishing a three-dimensional virtual model of the factory, which helps to better understand and analyze the operating status of the factory and provides a basis for monitoring, diagnosis and optimization. Secondly, the real-time monitoring and diagnosis module helps to improve the reliability and production efficiency of the equipment, reduce the impact of accidents, and ensure the stable operation of the factory through functions such as real-time monitoring of equipment status, early warning of potential faults, and monitoring of production processes. The production optimization and decision-making module analyzes production efficiency by analyzing historical data and real-time monitoring information, adjusts production plans and resource allocation using optimization algorithms, provides decision support for management, improves production efficiency, and reduces costs. At the same time, the simulation experiment function of this module helps to verify the effect of the optimization plan and provide a reference for actual production. The safety and emergency management module helps to improve the safety of the factory and reduce accidents through functions such as continuous monitoring of safety indicators, recording and analyzing safety incidents, designing emergency plans, and conducting emergency drills regularly. When a safety incident occurs, the module can quickly start the emergency response process, reduce the impact of the accident, and ensure the safety of the factory and personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 is the overall system block diagram of the present invention;

[0054] Figure 2 This is a system block diagram of the real-time monitoring and diagnosis module in the present invention. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0056] Reference Figure 1-2 ,

[0057] A digital twin factory system, the system comprising: a data acquisition and processing module, a virtual modeling module, a real-time monitoring and diagnosis module, a production optimization and decision-making module, and a safety and emergency management module;

[0058] The data collected by the data acquisition and processing module is transmitted to the virtual modeling module to update the model, and at the same time provides basic data for monitoring and analysis for the real-time monitoring and diagnosis module.

[0059] The monitoring results and fault diagnosis information of the real-time monitoring and diagnosis module are fed back to the production optimization and decision-making module to guide production adjustments and equipment maintenance.

[0060] The optimization scheme and decision instructions of the production optimization and decision-making module affect the monitoring strategy of the real-time monitoring and diagnosis module.

[0061] The safety and emergency management module receives the safety alarm information from the real-time monitoring and diagnosis module and triggers emergency response when necessary. At the same time, its safety monitoring data also comes from the data acquisition and processing module;

[0062] The real-time monitoring and diagnosis module includes equipment status monitoring submodule, fault warning and diagnosis submodule, production process monitoring submodule, safety monitoring submodule, alarm and communication submodule and maintenance management submodule;

[0063] The data acquisition and processing module first collects temperature, humidity, pressure, vibration, current and other data in real time through sensors and equipment deployed at key points in the factory. The data acquisition and processing module regularly calibrates sensors to ensure data accuracy; uses data compression technology to reduce data transmission volume; filters and standardizes data through data preprocessing algorithms; establishes a data warehouse for data storage and management; and uses a data synchronization mechanism to ensure data consistency. In addition, this module is also responsible for real-time data transmission, pushing processed data to other modules through wired or wireless networks for further analysis and application.

[0064] The virtual modeling module uses the collected data to build and update the digital twin model. Use 3D modeling software to create accurate models of factories and equipment; map real-time data to virtual models through data interfaces; implement dynamic simulation of models to simulate equipment operation and production processes; provide interactive interfaces that allow users to operate and adjust in a virtual environment; and regularly verify and optimize the model to ensure its consistency with the actual factory.

[0065] The equipment status monitoring submodule ensures real-time monitoring and effective management of the factory equipment status through the following three main steps: first, establish communication connections with sensors and actuators, periodically read data, and perform preliminary data verification to ensure data accuracy and real-time performance; second, perform time synchronization, unit conversion, cleaning, and outlier detection on the collected data to optimize data quality, and cache it for real-time monitoring and historical data analysis; finally, display the processed data in real time on the monitoring interface, and through functions such as threshold monitoring, alarm triggering, user interaction, and event recording, achieve continuous monitoring and rapid response to equipment status, and adjust the monitoring strategy based on monitoring results and user feedback to continuously improve the effectiveness of the monitoring system and the overall operational efficiency of the factory;

[0066] The fault warning and diagnosis submodules include:

[0067] Early warning model training: Use historical fault data to train early warning models, such as using SVM, neural networks, etc.

[0068] Real-time data analysis: Real-time analysis of equipment operation data and comparison with the early warning model.

[0069] Fault diagnosis: Once an abnormality is found, fault diagnosis is performed using the fault tree analysis (FTA) method;

[0070] The early warning model: Y = f(X; θ), where Y is the early warning output, X is the input feature, and θ is the model parameter;

[0071] Fault diagnosis: D = g(A;), where D is the diagnosis result, A is the abnormal data, and is the diagnosis model parameter.

[0072] The operation method of the production process monitoring submodule includes:

[0073] Production data integration: Obtain production plans and data from MES, ERP and other systems.

[0074] Process tracking: Track the location of products on the production line through technologies such as RFID and barcode scanning.

[0075] Quality Control: Use statistical process control (SPC) methods to monitor product quality;

[0076] The calculation formula used by the production process monitoring submodule for statistical process control is:

[0077] Where Xˉ is the sample mean, S is the sample standard deviation, and n is the sample size;

[0078] The safety monitoring submodule uses risk assessment tools to quantify potential risks and develop and test emergency response plans to ensure the safety of the factory environment. Specifically, this module first collects and records environmental parameters and safety equipment status in real time to ensure that these data can provide accurate information for subsequent risk assessments. Secondly, using risk assessment tools such as the LEC method, combined with the possibility of accidents, exposure frequency and severity of accident consequences, each risk point is quantitatively evaluated and divided into different levels so that emergency response plans can be formulated in a targeted manner. Finally, this module ensures that it can respond quickly and effectively in emergencies, minimize the impact of accidents, and ensure the safety of factories and personnel by regularly training employees, testing and rehearsing emergency response plans. Through these three steps, the safety monitoring submodule plays a vital role in the digital twin factory operation system, providing strong guarantees for the safe and stable operation of the factory;

[0079] The calculation formula of LEC method is: R = L × E × C

[0080] Where L is the probability of an accident occurring.

[0081] E is the frequency of personnel exposure to hazardous environments.

[0082] C is the possible consequences of the accident.

[0083] The alarm logic of the alarm and communication submodule is:

[0084] Preset condition setting: According to the factory's safety standards and operating procedures, set a series of alarm trigger conditions, such as equipment parameters exceeding safety thresholds, safety equipment status abnormalities, etc.

[0085] Logical combination: Establish a logical combination of alarm conditions to ensure that the alarm is triggered only when specific conditions are met at the same time, avoiding false alarms and missed alarms.

[0086] Real-time monitoring: Continuously monitor plant status and automatically detect and evaluate whether alarm conditions are met.

[0087] Alarm triggering: When a situation that meets the alarm conditions is detected, the alarm is triggered immediately;

[0088] The communication mechanism of the alarm and communication submodule is:

[0089] SMS notification: Send alarm information to relevant personnel via SMS service, including alarm type, occurrence time, possible impact, etc.

[0090] Email notification: Send emails to relevant personnel to provide detailed alarm information and necessary action guidelines.

[0091] Sound and light alarm: Set up sound and light alarm system inside the factory to notify on-site personnel with visual and auditory signals and remind them to take action.

[0092] Internal communication system: Use the factory's internal communication system, such as intercoms, broadcasting systems, etc., to quickly convey alarm information.

[0093] The maintenance management submodule first formulates a maintenance plan based on the equipment's operating time and failure history, and formulates a preventive maintenance plan, including maintenance cycles, maintenance content, maintenance tools and materials, etc. Secondly, maintenance work order generation automatically identifies equipment maintenance needs and generates maintenance work orders, including detailed information such as maintenance tasks, maintenance personnel, and maintenance time. Finally, maintenance record analysis records the details of each maintenance activity, evaluates the effectiveness of maintenance activities, and optimizes maintenance strategies based on actual conditions to improve maintenance efficiency and equipment reliability. Through these processes, the maintenance management submodule can ensure the normal operation of factory equipment and extend equipment life, reduce failure rates, improve production efficiency, and further ensure the stable operation of the factory:

[0094] The production optimization and decision-making module uses historical data and real-time monitoring information to analyze production efficiency; uses optimization algorithms to adjust production plans and resource allocation; evaluates the effects of different decision-making plans through simulation and prediction tools; integrates expert systems to provide decision support for complex problems; and implements a closed-loop feedback mechanism to continuously adjust optimization strategies based on production results.

[0095] The safety and emergency management module focuses on monitoring the safety status within the factory, including environmental safety, equipment safety and personnel safety. It receives safety data from the real-time monitoring and diagnosis module. Once a safety hazard or accident is detected, it immediately triggers the early warning system and starts the emergency plan. This module ensures a quick response in an emergency, minimizes the impact of the accident, and ensures the safety of the factory and personnel.

[0096] In the present invention, the equipment status monitoring submodule provides operators with intuitive equipment operation status by real-time monitoring and displaying equipment parameters, which helps to discover potential faults in time, thereby reducing production interruptions caused by equipment failures. Secondly, the early warning function of the module can issue an alarm before the fault occurs, providing a time window for preventive maintenance and avoiding the impact of fault expansion. In addition, the real-time monitoring function of the equipment status monitoring submodule helps to improve production efficiency because it can ensure that the equipment operates in the best state and reduce unplanned downtime. At the same time, the data recording and analysis function of the module helps to improve the reliability of the equipment because by analyzing historical data, potential problems of the equipment can be identified, so that measures can be taken for preventive maintenance and extend the life of the equipment. Finally, the alarm and communication functions of the equipment status monitoring submodule are particularly important in emergency situations because it can quickly notify relevant personnel and start the emergency response process, thereby minimizing the impact of accidents. In summary, the equipment status monitoring submodule plays a key role in the operation system of the digital twin factory. It helps to improve the reliability and production efficiency of the equipment, reduce the impact of accidents, and ensure the stable operation of the factory through functions such as real-time monitoring, early warning, data recording and analysis.

[0097] In the present invention, the virtual modeling module provides an intuitive visualization and simulation environment for operators by establishing a three-dimensional virtual model of the factory, which helps to better understand and analyze the operating status of the factory and provides a basis for monitoring, diagnosis and optimization. Secondly, the real-time monitoring and diagnosis module helps to improve the reliability and production efficiency of the equipment, reduce the impact of accidents, and ensure the stable operation of the factory through functions such as real-time monitoring of equipment status, early warning of potential faults, and monitoring of production processes. The production optimization and decision-making module analyzes production efficiency by analyzing historical data and real-time monitoring information, adjusts production plans and resource allocation using optimization algorithms, provides decision support for management, improves production efficiency, and reduces costs. At the same time, the simulation experiment function of this module helps to verify the effect of the optimization plan and provide a reference for actual production. The safety and emergency management module helps to improve the safety of the factory and reduce accidents through functions such as continuous monitoring of safety indicators, recording and analyzing safety incidents, designing emergency plans, and conducting emergency drills regularly. When a safety incident occurs, this module can quickly start the emergency response process, reduce the impact of the accident, and ensure the safety of the factory and personnel.

[0098] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprise" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0099] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A digital twin factory system, characterized by: The system includes: a data acquisition and processing module, a virtual modeling module, a real-time monitoring and diagnosis module, a production optimization and decision-making module, and a safety and emergency management module; The data collected by the data acquisition and processing module is transmitted to the virtual modeling module to update the model, and at the same time provides basic data for monitoring and analysis for the real-time monitoring and diagnosis module; The monitoring results and fault diagnosis information of the real-time monitoring and diagnosis module are fed back to the production optimization and decision-making module to guide production adjustment and equipment maintenance; The optimization scheme and decision instructions of the production optimization and decision-making module affect the monitoring strategy of the real-time monitoring and diagnosis module; The safety and emergency management module receives the safety alarm information from the real-time monitoring and diagnosis module and triggers an emergency response when necessary. At the same time, its safety monitoring data also comes from the data acquisition and processing module; The real-time monitoring and diagnosis module includes an equipment status monitoring submodule, a fault warning and diagnosis submodule, a production process monitoring submodule, a safety monitoring submodule, an alarm and communication submodule, and a maintenance management submodule.

2. A digital twin factory system as claimed in claim 1, characterized in that: The data acquisition and processing module first collects temperature, humidity, pressure, vibration, and current data in real time through sensors and equipment deployed at key points in the factory; the data acquisition and processing module regularly calibrates sensors to ensure data accuracy; uses data compression technology to reduce data transmission volume; filters and standardizes data through data preprocessing algorithms; establishes a data warehouse for data storage and management; uses a data synchronization mechanism to ensure data consistency; in addition, this module is also responsible for real-time data transmission, and pushes processed data to other modules through wired or wireless networks for further analysis and application.

3. A digital twin factory system as claimed in claim 1, characterized in that: The virtual modeling module uses the collected data to build and update the digital twin model; uses 3D modeling software to create accurate models of factories and equipment; maps real-time data to the virtual model through a data interface; realizes dynamic simulation of the model, simulates equipment operation and production process; and provides an interactive interface.

4. A digital twin factory system as claimed in claim 1, characterized in that: The equipment status monitoring submodule ensures real-time monitoring and effective management of the factory equipment status through the following three main steps: first, establish communication connections with sensors and actuators, periodically read data, and perform preliminary data verification to ensure data accuracy and real-time performance; second, perform time synchronization, unit conversion, cleaning, and outlier detection processing on the collected data to optimize data quality, and cache it for real-time monitoring and historical data analysis; finally, display the processed data in real time on the monitoring interface, and through threshold monitoring, alarm triggering, user interaction, and event recording functions, achieve continuous monitoring and rapid response to equipment status, and adjust the monitoring strategy based on monitoring results and user feedback to continuously improve the effectiveness of the monitoring system and the overall operational efficiency of the factory; The fault warning and diagnosis submodule includes: Early warning model training: Use historical fault data to train the early warning model; Real-time data analysis: Real-time analysis of equipment operation data and comparison with the early warning model; Fault diagnosis: Once an abnormality is found, fault diagnosis is performed using the fault tree analysis (FTA) method; The early warning model: Y = f(X; θ), where Y is the early warning output, X is the input feature, and θ is the model parameter; Fault diagnosis: D = g(A;), where D is the diagnosis result, A is the abnormal data, and is the diagnosis model parameter.

5. The digital twin factory system according to claim 1, characterized in that: The production process monitoring submodule operation method comprises: Production data integration: obtain production plans and data from MES and ERP systems; Process tracking: Track the location of products on the production line through RFID and barcode scanning technology; Quality Control: Use statistical process control (SPC) methods to monitor product quality; The calculation formula used by the production process monitoring submodule for statistical process control is: Where Xˉ is the sample mean, S is the sample standard deviation, and n is the sample size.

6. A digital twin factory system as claimed in claim 1, characterized in that: The safety monitoring submodule uses risk assessment tools to quantify potential risks and develop and test emergency response plans to ensure the safety of the factory environment. Specifically, the module first collects and records environmental parameters and safety equipment status in real time to ensure that these data can provide accurate information for subsequent risk assessments. Secondly, the LEC method risk assessment tool is used to quantitatively evaluate each risk point in combination with the possibility of accidents, exposure frequency and severity of accident consequences, and divide them into different levels so that emergency response plans can be formulated in a targeted manner. The calculation formula of LEC method is: R = L × E × C Where L is the probability of an accident occurring; E is the frequency of personnel exposure to hazardous environments; C is the possible consequences of the accident.

7. The digital twin factory system according to claim 1, characterized in that: The alarm logic of the alarm and communication submodule is: Preset condition setting: set a series of alarm trigger conditions according to the factory's safety standards and operating procedures; Logical combination: Establish a logical combination of alarm conditions to ensure that the alarm is triggered only when specific conditions are met at the same time, avoiding false alarms and missed alarms; Real-time monitoring: Continuously monitor the factory status and automatically detect and evaluate whether alarm conditions are met; Alarm triggering: When a situation that meets the alarm conditions is detected, the alarm is triggered immediately; The communication mechanism of the alarm and communication submodule is: SMS notification: Send alarm information to relevant personnel via SMS service, including alarm type, occurrence time, and possible impact; Email notification: Send emails to relevant personnel, providing detailed alarm information and necessary action guidelines; Sound and light alarm: Set up sound and light alarm system inside the factory to notify on-site personnel with visual and auditory signals and remind them to take action; Internal communication system: Use the factory's internal communication system, including intercoms and broadcasting systems, to quickly convey alarm information.

8. The digital twin factory system according to claim 1, characterized in that: The maintenance management submodule first formulates a maintenance plan based on the equipment operating time and failure history, and formulates a preventive maintenance plan, including maintenance cycles, maintenance content, maintenance tools and materials; secondly, maintenance work order generation automatically identifies equipment maintenance requirements and generates a maintenance work order, including maintenance tasks, maintenance personnel, and maintenance time details.

9. The digital twin factory system according to claim 1, characterized in that: The production optimization and decision-making module uses historical data and real-time monitoring information to analyze production efficiency; uses optimization algorithms to adjust production plans and resource allocation; evaluates the effects of different decision-making plans through simulation and prediction tools; integrates expert systems to provide decision support for complex problems; implements a closed-loop feedback mechanism to continuously adjust optimization strategies based on production results; The safety and emergency management module focuses on monitoring the safety status within the factory, including environmental safety, equipment safety and personnel safety.

10. The method for operating a digital twin factory according to claim 1, characterized in that: The operation method comprises the following steps: S1. Data collection and processing: First, the digital twin factory collects real-time data from sensors and actuators through industrial protocols, including equipment operation data and environmental data. These data are the original information of factory operation and provide a basis for subsequent monitoring, diagnosis and optimization. S2. Virtual modeling: Based on the collected data, a three-dimensional virtual model of the factory is built, including the factory layout, production lines, and equipment. This model is the core of the digital twin factory and can be updated in real time to reflect the status of the actual factory. S3. Real-time monitoring and diagnosis: The real-time monitoring and diagnosis module of the digital twin factory is responsible for continuous monitoring of the equipment status, production process and safety hazards in the factory; S4. Production optimization and decision-making: The production optimization and decision-making module of the digital twin factory uses the data and analysis results provided by the real-time monitoring and diagnosis module to optimize production plans, analyze energy consumption, and make equipment maintenance and update decisions; S5. Safety and emergency management: The safety and emergency management module of the digital twin factory focuses on monitoring the safety conditions within the factory, including environmental safety, equipment safety, and personnel safety; it receives safety data from the real-time monitoring and diagnosis module, and once a safety hazard or accident is detected, it immediately triggers the early warning system and initiates the emergency plan.

Images