MES-based chemical process intelligent change management method and system

Abstract

The invention provides an MES-based chemical process intelligent change management method and system, and relates to the field of MES intelligent management. A change management program is embedded into an MES system, a three-dimensional digital twinborn model covering equipment, a technological process and a specific area is constructed, a change application form and related information are obtained through the change management program, static data of the equipment and dynamic production data in the MES are extracted, multi-physics field simulation is conducted on change content, and the change content is obtained. A personnel positioning system and a mobile terminal are integrated, qualification and position information of operators is verified in real time, and actual operation data after change and a simulation prediction result are compared and analyzed, so that closed-loop change management is realized, management efficiency is improved, risk identification accuracy and pre-judgment capability are improved, process management and control and operation compliance are enhanced, and safety and reliability are improved. Closed-loop management and continuous optimization are realized, and the accuracy of future prediction is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of MES intelligent management, and in particular to a chemical process intelligent change management method and system based on MES. BACKGROUND

[0002] The manufacturing execution system (MES) is designed for the workshop of manufacturing enterprises, and is a production information management system. The MES can collect and process production data in real time, and quickly feedback production information. The system can be customized and developed and the function can be adjusted according to the specific needs and business processes of the enterprise, so as to realize the seamless connection of production planning, process management and quality control, thereby effectively optimizing the production process.

[0003] In the prior art, the chemical process change management mainly relies on traditional manual and paper-based operation mode, and has the following significant problems: 1. Low process efficiency, relying on manual operation: The change management process generally adopts paper form filling, offline manual transmission and step-by-step approval mode, which is cumbersome and long in cycle, and is easy to cause information omission or transmission delay due to human factors. 2. Strong subjectivity of risk judgment, lack of intelligent assistance: The risk assessment highly depends on the personal experience of the management personnel, lacks intelligent analysis support of massive historical data and accident cases, and is difficult to systematically and comprehensively identify potential risks, resulting in insufficient judgment accuracy and easy to miss. 3. Lack of process monitoring, difficult to guarantee operation compliance: There is a lack of effective real-time monitoring means in the implementation stage of the change scheme, which cannot automatically verify and record the qualification of the operator, the actual operation position and the step compliance, there is a supervision blind area, and illegal operation is difficult to discover and stop in time. 4. Late impact prediction, lack of pre-event simulation verification: The existing method is not deeply integrated with advanced simulation technologies such as digital twinning, and cannot simulate and predict the changes of key parameters such as equipment stress, corrosion rate and downstream process load with high precision before the implementation of the change, and it is difficult to foresee the chain effect, and the decision lacks data support. SUMMARY

[0004] The main purpose of the present application is to provide a chemical process intelligent change management method based on MES, which solves the technical problems of low change management efficiency, inaccurate risk prediction, process monitoring disconnection and lack, and prediction lag in the prior art.

[0005] To solve the above technical problems, the technical solution adopted by the present application is: a chemical process intelligent change management method based on MES, comprising the following steps: S1: embedding the change management program into the MES system to realize online management of the whole process of change application, risk assessment, hierarchical approval, implementation monitoring and acceptance archiving; S2: Construct a three-dimensional digital twin model covering equipment, process flow, and specific areas, and obtain a change application form through a change management program, upload the change plan, process drawing technical documents, and on-site photos, input the three-dimensional digital twin model, and extract the static data of the equipment and the dynamic production data in the MES; S3: Analyze the change description text through natural language processing technology, correlate the historical accident case library, and generate a preliminary risk report; S4: The three-dimensional digital twin model performs multi-physics field simulation on the change content, predicts the impact of the change on the equipment and process flow, dynamically corrects the risk level, and generates a three-dimensional visual operation plan; S5: Integrate a personnel positioning system and a mobile terminal to verify the qualification and location information of the operating personnel in real time and monitor the operation compliance; S6: Collect actual running data after the change, compare and analyze with the simulation prediction results, calculate the deviation rate, complete the effect verification and model parameter calibration, and realize change closed-loop management.

[0006] In the preferred scheme, in S1, the change management program meets the requirements of the "Guidelines for the Safety Management of Chemical Processes" and supports automatic allocation of approval processes based on risk levels, including different approval paths for general changes, larger risk changes, and major changes.

[0007] In the preferred scheme, in S2, the three-dimensional digital twin model is a three-dimensional digital twin model covering equipment, process flow, and specific areas, integrating static data of equipment material and major hazard source coordinates with dynamic production data of production temperature, pressure, and environmental monitoring in the MES system, predicting the impact of changes through ANSYS or COMSOL multi-physics field simulation, and generating a three-dimensional visual implementation plan containing isolation area labeling and optimal operation path.

[0008] In the preferred scheme, in S4, the three-dimensional digital twin model predicts equipment stress, corrosion rate, and downstream load changes through multi-physics field coupling simulation, and triggers a model self-calibration mechanism when the simulation deviation rate exceeds a set threshold.

[0009] In the preferred scheme, in S3, the natural language processing technology is used to extract keywords from the change description, match similar scenarios in the historical accident case library, and build a risk prediction model based on random forest or neural network algorithms, outputting risk levels and corresponding control measures.

[0010] In the preferred scheme, in S5, the mobile terminal supports change form filling, on-site photo uploading, electronic signature, three-dimensional path navigation, and emergency response operations, can receive and display task work orders, operation guidelines, and welding process videos issued by the MES, and realizes real-time verification of personnel location and qualification through RFID or GPS positioning technology.

[0011] In a preferred embodiment, in S6, the deviation rate calculation formula is: Deviation rate = (Actual value - Predicted value) / Predicted value ; And generate an effect verification report according to the deviation rate result, and update the three-dimensional digital twin model parameters to improve the subsequent prediction accuracy.

[0012] In a preferred embodiment, in S3, the historical accident case library contains typical chemical cases, typical equipment corrosion and leakage data. When generating the preliminary risk report, the keywords in the change description are matched with the case library to identify similar risk scenarios and provide corresponding prevention measures.

[0013] In a preferred embodiment, in S6, the effect verification and model parameter calibration are completed to realize change closed-loop management, including: The effect verification report includes operation records, actual running data, simulation prediction data, deviation rate calculation results and change effect conclusion. The report needs to be archived in the enterprise safety management system to meet the closed-loop management requirements of the "Hazardous Chemicals Enterprise Safety Standardization Review".

[0014] In a second aspect, the present application provides a MES-based intelligent change management system for chemical processes, characterized in that it comprises the following steps: The MES change management module is used to embed the change management program into the MES system to realize online management of the whole process of change application, risk assessment, hierarchical approval, implementation monitoring and acceptance filing; The digital twin engine module is used to build a three-dimensional digital twin model covering equipment, process flow and specific areas, and obtain the change application form through the change management program, upload the change scheme, process drawing technical documents and on-site photos, input the three-dimensional digital twin model and extract the equipment static data and dynamic production data in the MES; The AI analysis module is used to analyze the change description text through natural language processing technology, associate with the historical accident case library, and generate a preliminary risk report; The twin model prediction module is used for the three-dimensional digital twin model to perform multi-physical field simulation on the change content, predict the influence of the change on the equipment and process flow, dynamically correct the risk level, and generate a three-dimensional visual operation scheme; The mobile terminal and personnel positioning module is used to integrate the personnel positioning system and mobile terminal to verify the qualification and location information of the operators in real time and monitor the operation compliance; The verification and calibration module is used to collect the actual running data after the change, compare and analyze with the simulation prediction results, calculate the deviation rate, complete the effect verification and model parameter calibration, and realize the change closed-loop management. This invention provides an intelligent change management method and system for chemical processes based on MES (Manufacturing Execution System). By embedding a change management program into the MES system, a three-dimensional digital twin model covering equipment, process flow, and specific areas is constructed. The change management program obtains change request forms and related information, extracts static equipment data and dynamic production data from the MES, performs multiphysics simulation on the changed content, integrates a personnel positioning system and mobile terminals, verifies the operator's qualifications and location information in real time, and compares and analyzes the actual operating data after the change with the simulation prediction results. This achieves closed-loop change management, improves management efficiency, enhances the accuracy and predictive ability of risk identification, strengthens process control and operational compliance, realizes closed-loop management and continuous optimization, and improves the accuracy of future predictions. Attached Figure Description

[0015] The present invention will be further described below with reference to the accompanying drawings and embodiments: Figure 1 This is a flowchart of the change management method of the present invention; Figure 2 This is a system architecture diagram of the present invention; Figure 3 This is a flowchart of the change management process for this invention; Figure 4 This is the mobile operating interface of the present invention; Figure 5 This is the digital twin simulation interface of the present invention. Detailed Implementation

[0016] Example 1 like Figures 1-5 As shown, an intelligent change management method for chemical processes based on MES includes the following steps: S1: Embed the change procedures stipulated in the "Guidelines for Safety Management of Chemical Processes" into the MES system, and build an MES change management module that includes a process model library and approval rules. This enables online management of the entire process, including change application, risk assessment, hierarchical approval, implementation monitoring, and acceptance archiving. The MES change management module also integrates a 3D model library of process equipment, which can be linked to the process equipment parameters and historical maintenance records involved in the change. S2: Construct a 3D digital twin model covering equipment, process flow and specific areas, obtain a change request form through the change management program, upload change plan, process drawings, technical documents and on-site photos, input the 3D digital twin model and extract static equipment data and dynamic production data from MES; S3: Parse the change description text using natural language processing technology, link it to the historical accident case database, and generate a preliminary risk report; S4: The 3D digital twin model performs multiphysics simulation on the changes, predicts the impact of the changes on equipment and processes, dynamically corrects the risk level, and generates a 3D visualized operation plan. S5: Integrates personnel positioning system with mobile terminal to verify operator qualifications and location information in real time and monitor operational compliance; S6: Collect actual operating data after changes, compare and analyze it with simulation prediction results, calculate the deviation rate, complete effect verification and model parameter calibration, and realize closed-loop management of changes.

[0017] like Figure 1 As shown in this embodiment, by embedding the change management program into the MES system, a three-dimensional digital twin model covering equipment, process flow, and specific areas is constructed. The change management program obtains change application forms and related information, extracts static equipment data and dynamic production data from the MES, performs multi-physics simulation on the changed content, integrates a personnel positioning system and mobile terminals, verifies the operator's qualifications and location information in real time, and compares and analyzes the actual operating data after the change with the simulation prediction results. This achieves closed-loop change management, improves management efficiency, enhances the accuracy and predictive ability of risk identification, strengthens process control and operational compliance, realizes closed-loop management and continuous optimization, and improves the accuracy of future predictions.

[0018] In this embodiment, all operations, approvals, monitoring, and verification data throughout the entire process are automatically recorded and archived in the MES system, forming a complete and tamper-proof electronic archive, which fully meets the strict requirements of regulations such as the "Guidelines for Safety Management of Chemical Processes" for the traceability of change procedures.

[0019] In steps S1-S2 of this embodiment, a change application and digital twin mapping are performed: the user fills out a change application form on the mobile device, and the system automatically associates the digital twin model and extracts the device parameters.

[0020] In the preferred embodiment, in step S1, the change management procedure complies with the requirements of the "Guidelines for Safety Management of Chemical Processes" and supports automatic allocation of approval processes based on risk level, including different approval paths for general changes, major risk changes and significant changes.

[0021] This embodiment achieves online and automated operation by fully embedding the change process into the MES system, and combines it with mobile collaborative office, which greatly shortens the cycle of change application, approval and execution, and improves management efficiency.

[0022] In the preferred embodiment, in step S2, the three-dimensional digital twin model is a three-dimensional digital twin model covering equipment, process flow and specific areas. It integrates static equipment data such as equipment material and coordinates of major hazard sources with dynamic production data such as production temperature, pressure and environmental monitoring in the MES system. It uses ANSYS or COMSOL multiphysics simulation to predict the impact of changes and generates a three-dimensional visualization implementation plan that includes isolation area markings and optimal operation paths.

[0023] In this embodiment, steps S3-S4 involve simulation pre-running and dynamic grading.

[0024] In the preferred embodiment, in step S3, natural language processing technology is used to extract keywords from the change description: parsing the change request content, calling the risk knowledge base to generate a preliminary risk report, including existing risks, risk levels, and corresponding preventive measures, conducting a preliminary review of the risks of the change content, matching similar scenarios in the historical accident case library, and constructing a risk prediction model based on random forest or neural network algorithms to output the risk level and corresponding control measures. The digital twin engine simulates the potential impacts of the change, such as process disturbances and equipment material stress changes; it combines simulation data to correct the risk level, and combines optimization suggestions to generate emergency drill animations and visualized operational restricted areas, which are then pushed to mobile devices to guide on-site operations.

[0025] In the preferred embodiment, in step S3, the historical accident case library contains typical chemical cases, typical equipment corrosion and leakage data. When generating a preliminary risk report, keywords in the change description are extracted and matched with the case library to identify similar risk scenarios and provide corresponding preventive measures suggestions.

[0026] In the preferred embodiment, in step S4, the three-dimensional digital twin model predicts equipment stress, corrosion rate and downstream load changes through multiphysics coupling simulation, and triggers a model self-calibration mechanism when the simulation deviation rate exceeds a set threshold.

[0027] In this embodiment, Natural Language Processing (NLP) technology is used to intelligently analyze the changed content and match it with a historical case database. Combined with a risk prediction model based on machine learning algorithms such as random forests and digital twin multiphysics simulation, accurate and quantitative risk analysis and early warning are achieved. AI early warning and digital twin simulation shift risk assessment from experience-driven to data-driven, effectively avoiding potential accidents and improving safety.

[0028] In step S5 of this embodiment, the 3D solution is generated and the task is issued: the MES change management module automatically assigns approval nodes according to the risk level. For example, general changes are approved by the workshop director, larger risks are approved by the safety and environmental protection department and the equipment department, and major changes trigger expert review. After approval, the MES generates a task work order containing operation instructions and risk warnings, and pushes it to the mobile devices of relevant personnel.

[0029] In this embodiment, steps S5-S6 involve monitoring and effect verification: operators receive tasks via mobile devices, the personnel positioning system verifies the operator's location and qualifications, and the mobile devices record on-site equipment, process debugging parameters, operation logs, and other operation data, which are then transmitted back to the MES in real time. After the change is completed, the AI ​​module analyzes production data such as equipment efficiency and process safety indicators, compares the simulation data with the actual operating parameters using a digital twin, calculates the prediction deviation rate, and generates an effect verification report, thus achieving effect verification and closed-loop management.

[0030] Furthermore, the effectiveness verification report includes operation records, actual operating data, simulation prediction data, deviation rate calculation results, and conclusions on the effectiveness of the change. The report must be archived in the enterprise's safety management system and meet the traceability requirements of the change procedure as required by the "Guidelines for Safety Management of Chemical Processes". The dynamic effectiveness verification meets the closed-loop management requirements of the "Safety Standardization Review of Hazardous Chemical Enterprises".

[0031] In the preferred embodiment, in step S5, the mobile terminal supports filling out change forms, uploading on-site photos, electronic signatures, three-dimensional path navigation, and emergency response operations. It can receive and display task orders, operation instructions, and welding process videos issued by the MES, and realize real-time verification of personnel location and qualifications through RFID or GPS positioning technology.

[0032] This embodiment integrates personnel positioning (RFID / GPS) with mobile applications, enabling automatic verification and full recording of operator qualifications, real-time location, and operation steps. This ensures that change plans are strictly and compliantly implemented, reduces safety risks caused by human error, and strengthens process control and operational compliance.

[0033] In the preferred embodiment, the formula for calculating the deviation rate in step S6 is: Deviation rate = .

[0034] A performance verification report is generated based on the deviation rate results, and the parameters of the 3D digital twin model are updated to improve the accuracy of subsequent predictions.

[0035] This embodiment achieves closed-loop management of change projects, meets the requirements of safety standardization review, and uses deviation data to calibrate the parameters of the digital twin model, continuously improving the accuracy of future predictions.

[0036] In this embodiment, all operations, approvals, monitoring, and verification data throughout the entire process of steps S1-S6 are automatically recorded and archived in the MES system, forming a complete and tamper-proof electronic archive, which fully meets the strict requirements of regulations such as the "Guidelines for Safety Management of Chemical Processes" for the traceability of change procedures.

[0037] The following explanation uses a chemical plant as an example.

[0038] A chemical plant needs to replace the lining material of its reactor (R-101) from 304 stainless steel to Hastelloy C-276 to cope with the high-temperature chloride corrosion environment. Traditional change management processes suffer from problems such as delayed risk assessment and insufficient operational supervision. An example-based approach is adopted to achieve intelligent management of the entire process.

[0039] Step 1: Change Request and Digital Twin Mapping 1.1. The engineer opens the mobile app and fills out the change request form.

[0040] 1.2. Fill in the form page: Change type: Select "Equipment material change" from the drop-down menu; Change description: Enter "The lining material of reactor R-101 has been changed to Hastelloy C-276"; Associate a digital twin object: Click the "Select Device" button, select "R-101" from the list, such as... Figure 4 As shown.

[0041] 1.3. Upload attachments and on-site photos: such as Figure 4 Click the "Attachments" button to upload technical documents such as the revised plan and reactor process drawings (PDF format). Click the "Take Photo" button to photograph the current corrosion status of the reactor; the system will automatically add a timestamp and GPS location watermark.

[0042] System response, including: a) MES automatically calls the R-101 digital twin model, such as Figure 5 The three-dimensional model shown on the left synchronizes its static data (original material properties, design pressure) and dynamic data (real-time temperature 200℃, Cl⁻ concentration 15%).

[0043] b) Map interface, such as Figure 4 Middle section: Shows the location of R-101 and nearby hazards (such as chlorine storage tank V-201, 15 meters away).

[0044] Step 2: Simulation and Dynamic Risk Classification Data processing flow 1. AI Analysis Module Preliminary Review. The model's natural language processing module parses the change description text, extracts keywords such as "reactor," "material change," and "chloride environment," and analyzes the change content by linking it to historical cases in the knowledge base. The AI ​​preliminary review risk is "high."

[0045] 2. Digital Twin Engine ( Figure 2The processing layer synchronously receives dynamic and static change parameters from the MES database and mobile terminal, and initiates physical simulation and process simulation to simulate the corrosion behavior of Hastelloy in a Cl⁻-containing environment at 200℃ and predict the load of the downstream process condenser.

[0046] Simulation output: 1. For example Figure 5 As shown in the middle, the physical simulation output is as follows: The digital twin engine, combined with changes in welding material properties, process parameters, and geometric structure, predicts local stress concentration in the welding heat-affected zone through machine learning models and multiphysics simulation algorithms. The peak stress is 280 MPa, and the yield strength exceeds 80%. The annual corrosion rate of the reactor is 0.015 mm / year, which is better than that of the original material.

[0047] 2. For example Figure 5 As shown in the middle section, the process simulation output is as follows: The digital twin engine uses parameters such as temperature, pressure, and flow rate of upstream equipment, as well as parameters such as condenser heat exchange area, pipe diameter, material, and cooling water inlet temperature / flow rate design to establish a condenser thermodynamic model using Aspen Plus or COMSOL. The simulation predicts that material changes will not affect the operation of the downstream process condenser.

[0048] 3. Simulation results are transmitted to the AI ​​analysis module via an API interface, such as... Figure 2 The processing layer is shown. The AI ​​module, combining simulation data, analyzed the maximum stress in the welding area, finding it to be 280 MPa, exceeding the material's allowable stress of 250 MPa, and thus determining the result as "exceeding the limit." Exceeding the limit stress may cause cracking in the weld or base material, and long-term exceeding the limit stress may accelerate equipment lifespan degradation. Therefore, the risk level of the change was revised from "relatively high" to "high risk." Figure 5 As shown on the left.

[0049] 4. The AI ​​analysis module, combining simulation results and algorithms, suggests optimizing the welding process: adjusting welding parameters (such as reducing current and preheating the base material) to reduce residual stress; and increasing the frequency of non-destructive testing (such as ultrasonic testing) to monitor potential defects, such as... Figure 5 As shown on the left.

[0050] Step 3: Change Approval and Task Assignment Approval process triggered: MES automatically assigns tasks to the "Expert Review" node based on risk level, and the system pushes notifications to external experts, such as... Figure 3 The approval branch is shown. Experts view the 3D process model and locate the reactor position using the MES mobile terminal interface. Based on the AI ​​risk report, a supplementary requirement is added: "Monitor the corrosion rate quarterly after the change," with details displayed within the work order.

[0051] Task push: 1. After approval, if Figure 5As shown, the maintenance team leader receives the task order on their mobile device. The MES generates the task instructions: "Remove old liner → Weld Hastelloy → Pressure test → Thickness inspection".

[0052] 2. The task is pushed to the mobile device of the maintenance team leader. The maintenance team clicks the "Navigation" button, and the map displays a green path and restricted area warnings, such as... Figure 4 The work order interface shown.

[0053] 3. The system pushes operation instructions via the APP: Welding process videos are pushed to mobile devices, requiring users to watch them before operation. Figure 4 The work order interface shown.

[0054] Step 4: Change Implementation and Real-time Monitoring 1. Personnel Qualification and Location Verification: Maintenance personnel wear RFID name tags when entering the workshop, such as... Figure 2 The data acquisition layer shown in the diagram has a personnel positioning unit that verifies the personnel's qualifications (special equipment welding certificate).

[0055] 2. On-site operation record: such as Figure 2 As shown in the data acquisition layer, maintenance personnel use mobile devices to record videos of the welding process and upload them to the MES database; the system automatically associates these videos with operation logs (time, personnel ID, and location coordinates).

[0056] Step 5: Effect Verification and Model Calibration 1. Data collection and comparison: such as Figure 2 The data acquisition layer shown uses MES database data collected over three months after the changes. Temperature fluctuation range: 195-205℃; corrosion rate: 0.01548 mm / year. Figure 2 As shown in the application layer, the dynamic verification module calls the AI ​​analysis module to compare the simulation prediction data with the actual data.

[0057] 2. Calibration feedback, deviation rate calculation, deviation between actual corrosion rate and simulation prediction: Deviation rate = (0.01548 - 0.015) / 0.015 * 100% = 3.2%. AI output conclusion: Deviation rate < 5%, "Material change is effective, corrosion rate reduced by 80%".

[0058] 3. Report Generation and Archiving: The MES automatically generates acceptance reports (including operation records, effect data, and AI suggestions) and archives them to the enterprise security management system. The digital twin engine automatically adjusts the Hastelloy material parameter library to improve subsequent prediction accuracy and update the model.

[0059] This embodiment shortens the change approval cycle from the traditional 14 days to 7 days, greatly improving work efficiency. AI provides early warning of material corrosion risks, avoiding potential leakage accidents and significantly strengthening risk control. All process data, including application forms, operation logs, and acceptance reports, are archived in the MES system, ensuring full-process data traceability in compliance with the "Guidelines for Safety Management of Chemical Processes," thus achieving intelligent management of the entire change lifecycle.

[0060] Example 2 To further illustrate with reference to Example 1, an intelligent change management system for chemical processes based on MES includes the following steps: The MES change management module has a built-in process model library that complies with the "Guidelines for Safety Management of Chemical Processes" and corresponding user management systems, supporting the entire process of change application, risk assessment, hierarchical approval, implementation, and acceptance online. It also integrates a 3D model library of process equipment, linking the process equipment parameters and historical maintenance records involved in the change. The digital twin engine module is used to build 3D digital twin models covering equipment, processes, and specific areas, integrating static data such as equipment materials, process flow, and coordinates of major hazard sources. It also integrates dynamic data from the MES system, including production temperature, pressure, personnel location, and environmental monitoring, in real time. For changes, it automatically identifies affected equipment or areas in the digital twin model, predicts the impact of changes through multiphysics simulations (such as ANSYS and COMSOL), dynamically adjusts the risk level based on simulation results, and generates a 3D visualized implementation plan, including annotations of isolated areas and optimal operation paths. The AI ​​analysis module is used to parse change description text based on natural language processing (NLP) and match it with a historical accident case database, such as typical chemical cases, typical equipment corrosion, and leakage data. It employs machine learning algorithms such as random forests and neural networks to predict risk levels and recommend control measures. The 3D visualization platform is connected to the digital twin engine module, which is used to perform multiphysics simulation of the changes on the 3D digital twin model, predict the impact of the changes on equipment and processes, dynamically correct the risk level, and generate a 3D visualization operation plan. The mobile terminal and personnel positioning module, along with the mobile app, support features such as form completion, on-site photo upload, electronic signatures, emergency response, and notification push notifications. It integrates an RFID / GPS dual-mode positioning system for real-time monitoring of operator location and qualification information. The verification and calibration module is used to collect actual operating data after changes, compare and analyze it with simulation prediction results, calculate the deviation rate, complete effect verification and model parameter calibration, and realize closed-loop management of changes.

[0061] like Figure 2The diagram shows the system architecture integrating the method of this embodiment, the hierarchical relationship of each module in the system and the data interaction logic, clarifying the complete link of "data acquisition-processing-application". The data acquisition layer synchronizes production, personnel and on-site data to the processing layer in real time. The processing layer generates risk levels and correction suggestions through simulation and AI analysis and feeds them back to the application layer. At the same time, the application layer's operation instructions (such as task work orders) are transmitted to the mobile terminal, forming a closed-loop data flow.

[0062] This embodiment provides a working process, working details, and technical effects of an intelligent change management method for chemical processes based on MES. Please refer to Embodiment 1 for details, which will not be repeated here. The above embodiments are merely preferred technical solutions of the present invention and should not be considered as limitations on the present invention. The scope of protection of the present invention should be limited to the technical solutions described in the claims, including equivalent substitutions of the technical features described in the claims. That is, equivalent substitutions and improvements within this scope are also within the scope of protection of the present invention.

Claims

1. A method for intelligent change management of a chemical process based on MES, characterized in that, Comprise the following steps: S1: embed the change management program into the MES system to realize the online management of the whole process of change application, risk assessment, hierarchical approval, implementation monitoring and acceptance archiving; S2: build a three-dimensional digital twin model covering equipment, process flow and specific areas, and obtain the change application form through the change management program, upload the change scheme, process drawing technical document and on-site photos, input the three-dimensional digital twin model and extract the static data of the equipment and the dynamic production data in the MES; S3: analyze the change description text through natural language processing technology, correlate the historical accident case library, and generate a preliminary risk report; S4: The three-dimensional digital twin model simulates the change content in multiple physical fields, predicts the impact of the change on equipment and process flow, dynamically corrects the risk level, and generates a three-dimensional visual operation scheme; S5: Integrate personnel positioning system and mobile terminal to verify the qualification and location information of the operator in real time and monitor the operation compliance; S6: Collect actual running data after the change, compare and analyze with the simulation prediction results, calculate the deviation rate, complete the effect verification and model parameter calibration, and realize the change closed-loop management. 2.The MES-based intelligent change management method for chemical processes according to claim 1, characterized in that, In S1, the change management program meets the requirements of "Guidelines for the Safety Management of Chemical Processes" and supports automatic allocation of approval processes according to risk levels, including different approval paths for general changes, larger risk changes and major changes. 3.The MES-based intelligent change management method for chemical processes according to claim 1, characterized in that, In S2, the three-dimensional digital twin model is a three-dimensional digital twin model covering equipment, process flow and specific areas, which integrates the static data of equipment material and major hazard source coordinates with the dynamic production data of production temperature, pressure and environmental monitoring in the MES system. Through ANSYS or COMSOL multi-physical field simulation, the change impact is predicted, and a three-dimensional visual implementation scheme including isolation area labeling and optimal operation path is generated. 4.The MES-based intelligent change management method for chemical processes according to claim 3, characterized in that, In S4, the three-dimensional digital twin model predicts the stress, corrosion rate and downstream load changes through multi-physical field coupling simulation, and triggers the model self-calibration mechanism when the simulation deviation rate exceeds the set threshold. 5.The MES-based intelligent change management method for chemical processes according to claim 1, characterized in that, In S3, the natural language processing technology is used to extract keywords in the change description, match similar scenarios in the historical accident case library, and build a risk prediction model based on random forest or neural network algorithm, output risk level and corresponding control measures. 6.The MES-based intelligent change management method for chemical processes according to claim 1, characterized in that, In S5, the mobile terminal supports change form filling, on-site photo uploading, electronic signature, three-dimensional path navigation and emergency response operation, can receive and display task work orders, operation instructions and welding process videos issued by the MES, and realize real-time verification of personnel location and qualification through RFID or GPS positioning technology. 7.The MES-based intelligent change management method for chemical processes according to claim 1, characterized in that, In S6, the deviation rate calculation formula is: Bias rate = 1 - P ; And according to the deviation rate result, an effect verification report is generated, and the three-dimensional digital twin model parameters are updated to improve the prediction accuracy of subsequent predictions. 8.The MES-based intelligent change management method for chemical processes according to claim 1, characterized in that, In S3, the historical accident case library contains typical chemical cases, typical equipment corrosion and leakage data. When generating the preliminary risk report, the keywords in the change description are matched with the case library to identify similar risk scenarios and provide corresponding prevention measures. 9.The MES-based intelligent change management method for chemical processes according to claim 1, characterized in that, In the S6, the effect verification and model parameter calibration are completed, and the change closed-loop management is realized, including: The effect verification report includes operation records, actual running data, simulation prediction data, deviation rate calculation results and change effect conclusion. The report needs to be archived in the enterprise safety management system to meet the closed-loop management requirements of the "Hazardous Chemicals Enterprise Safety Standardization Review".

10. An MES-based intelligent change management system for a chemical process, characterized in that, The method comprises the following steps: The MES change management module is used to embed the change management program into the MES system to realize online management of the whole process of change application, risk assessment, hierarchical approval, implementation monitoring and acceptance archiving; The digital twin engine module is used to build a three-dimensional digital twin model covering equipment, process flow and specific areas, and obtain the change application table through the change management program, upload the change scheme, process drawing technical document and on-site photos, input the three-dimensional digital twin model and extract the equipment static data and dynamic production data in the MES; The AI analysis module is used to analyze the change description text through natural language processing technology, associate with the historical accident case library, and generate a preliminary risk report; The twin model prediction module is used to perform multi-physical field simulation on the change content by the three-dimensional digital twin model, predict the influence of the change on the equipment and process flow, dynamically correct the risk level, and generate a three-dimensional visual operation scheme; The mobile terminal and personnel positioning module is used to integrate the personnel positioning system and the mobile terminal to verify the qualification and location information of the operators in real time and monitor the operation compliance; The verification and calibration module is used to collect the actual running data after the change, compare and analyze the simulation prediction results, calculate the deviation rate, complete the effect verification and model parameter calibration, and realize the change closed-loop management.

Images