Digital twin factory system and application method thereof in chemical production

Abstract

The invention discloses a digital twin factory system based on a strict dynamic mechanism model and an application method of the digital twin factory system in chemical production. The digital twinning factory system comprises a data acquisition layer, a data processing layer, a digital twinning model layer, a visual management layer and an application layer. According to the digital twin factory system, multi-source data are collected in real time, deep processing and analog calculation are conducted on production data through a digital twin strict dynamic mechanism model, comparative analysis is conducted on generated optimization data and actual field production data, and reasonable process optimization suggestions are accurately given. Meanwhile, the visual management layer of the digital twinning factory system can realize visual presentation of the production process, ensures that a manager can grasp the alarm state of equipment and the production dynamic state of the device in real time and make a decision in time, and improves the efficiency, safety and quality of chemical production in an omnibearing manner.

Description

Technical Field

[0001] This invention belongs to the field of smart factory technology, specifically a digital twin factory system based on a rigorous dynamic mechanism model and its application method in chemical production. Background Technology

[0002] Currently, the application of digital twin technology in the chemical industry mainly focuses on single-dimensional physical model mapping and basic data monitoring, which has the following shortcomings: the data dimension is limited, existing systems only support simple visualization of physical equipment status, and lack integrated analysis of multi-dimensional data such as production process flow, simulation data, and real-time on-site data; in terms of visualization management, most chemical plants can only achieve two-dimensional data display, and cannot intuitively present complex production scenarios and equipment operating status; the interactive capabilities are weak, and users cannot adjust the model position and perform interactive operations through multi-view interaction.

[0003] In summary, the shortcomings mentioned above indicate that current digital twin factory systems in the chemical industry lack multi-dimensional data integration and analysis, which prevents managers from obtaining accurate information in a timely manner and making informed decisions. Summary of the Invention

[0004] To address the technical challenge of lacking multi-dimensional data integration and analysis in digital twin factory systems, this application provides the following technical solution: A digital twin factory system, comprising a data acquisition layer, a data processing layer, a digital twin model layer, a visualization management layer, and an application layer.

[0005] According to an embodiment of the present invention, the data acquisition layer is used for: Collect factory production data in real time.

[0006] For example, the factory production data includes at least one of the following: production equipment operating parameters (such as temperature, pressure, vibration), production process data (such as material composition, product output), and personnel information (such as department, position).

[0007] For example, the data acquisition layer utilizes Industrial Internet of Things (IIoT) technology to collect factory production data in real time. For instance, it employs various communication protocols such as OPC, SQL, MQTT, and HTTP to achieve seamless integration between the data acquisition layer and heterogeneous data sources such as real-time production databases, ERP systems, and BW (data warehouses).

[0008] According to an embodiment of the present invention, the data processing layer is used for: The factory production data collected by the data acquisition layer is optimized to remove noisy data.

[0009] Specifically, in the chemical process flow, the data processing layer optimizes factory production data to obtain optimized data, such as through cleaning, conversion, and analysis, to accurately reflect the operating status of the production equipment. Furthermore, conversion refers to uniformly converting data of different formats collected by the data acquisition layer into a format recognizable by the system.

[0010] According to an embodiment of the present invention, the digital twin model layer is used for: Monitor the production dynamics of the production equipment to achieve visualized operation of the production equipment.

[0011] Specifically, the production dynamics include, for example, the component composition throughout the entire chemical process, the transient changes in the physical and chemical processes of materials in the process unit, and the performance and influencing factors of the production equipment.

[0012] Specifically, the production dynamics are visualized through a digital twin model layer. The digital twin model layer is an online dynamic device model established to simulate the production device. The online dynamic device model is connected to the real-time production data of the production device and is driven by the operation signals of the production device. It performs simulation calculations and simulates the operation of the production device in real time, thereby realizing the visualization of the operation of the production device.

[0013] Specifically, in chemical process flow, the digital twin model layer is a twin of the actual production unit, used to monitor the production dynamics of each link in the production unit, such as the composition of the entire process, the transient changes of the physical and chemical processes of materials in the process unit, and the performance and influencing factors of the production unit, thereby realizing the visualization of the operation of the production unit.

[0014] According to an embodiment of the present invention, the visualization management layer is used for: Real-time observation of the appearance, structure, and operation of production equipment enables visualized management.

[0015] Specifically, the visualization management layer includes a 3D visualization model of the device and an interactive interface.

[0016] Furthermore, the device's 3D visualization model achieves high-performance 3D visualization operations through 3D modeling, WebGL technology, and other methods.

[0017] Furthermore, the three-dimensional visualization model of the device refers to a three-dimensional model of the production device, including the various components of the production device and their connection methods, the operation path of the production device, and its operating status.

[0018] Furthermore, the device's three-dimensional visualization model can also access real-time factory production data, software instrument data, and business management data.

[0019] Furthermore, the interactive interface is used to view various modules in the 3D visualization model of the device, such as rotating, zooming in or out of the various devices and components in the model; at the same time, combined with real-time factory production data, soft instrument data and business management data, it provides an in-depth understanding of the various components, connection methods, operation paths and operating conditions of the production device, and to grasp information on all aspects of the production device.

[0020] Furthermore, managers can view production information of the production unit in real time through the interactive interface, achieving a visual management effect. Even further, the production information includes the operating status of the production unit, unit load rate, equilibrium temperature range, operating line, and product selectivity.

[0021] According to an embodiment of the present invention, the application layer is used for: By adjusting the thresholds or indicators of production parameters for key equipment in the digital twin model layer, the production behavior of the devices in the digital twin model layer is triggered, enabling prediction of the device operation process at a future point in time. The application layer of this invention can eliminate "one-size-fits-all" alarms, achieving real-time monitoring, timely prediction, and accurate tracking of alarms for key equipment, improving the reliability of production equipment operation, and realizing proactive monitoring of the production process. In this invention, the future point in time (T-future) refers to the time point reached after adding a preset, fixed time interval (ΔT) to the instant when production data is collected (T-collection).

[0022] The present invention also provides an application method for the above-mentioned digital twin factory system, which is used in chemical production, for example, for monitoring the production of synthetic ammonia.

[0023] According to an embodiment of the present invention, the application method includes the following steps: (1) Model establishment: Based on the thermodynamic and kinetic parameters in the chemical production process and the design data of the chemical production equipment, a digital twin model layer is constructed; (2) After the digital twin model layer is completed, the production data of the production device is collected in real time through the data acquisition layer, and the production data is optimized through the data processing layer. The optimized data is used as the input data of the digital twin model layer to simulate and calculate the key process parameters. The real-time production data, optimized data and key process parameters are transmitted to the visualization management layer. (3) By visualizing the management layer, the real-time operation of the production equipment can be viewed, and the thresholds or indicators of important equipment in the digital twin model layer can be adjusted through the application layer to predict the production status of the production equipment, trigger the production behavior of the equipment in the digital twin model layer, and realize the prediction of the equipment operation process at a certain point in the future.

[0024] Preferably, in step (1), the thermodynamic parameters include specific heat capacity, heat of reaction, etc., and the heat of reaction can be calculated using the SRK (Soave-Redlich-Kwong) equation of state.

[0025] Preferably, in step (1), the reaction kinetic parameters include parameters related to the rate and mechanism of the chemical reaction, such as at least one of the following: reaction rate constant, activation energy, reaction order, reaction mechanism, etc.

[0026] Preferably, in step (1), the design data of the chemical production device is design data known in the art, such as process flow piping and instrumentation diagram (PID), process flow diagram (PFD), equipment assembly diagram, etc.

[0027] Preferably, in step (2), the production data of the chemical production device includes measurable data, such as temperature, pressure, flow rate, liquid level, etc.

[0028] Preferably, in step (2), the key process parameters refer to the key process parameters of production devices known in the art that cannot or are difficult to obtain directly through the data acquisition layer. This invention does not specifically limit the key process parameters; depending on the chemical product, the key process parameters are not entirely the same.

[0029] For example, when the application method is used to monitor ammonia synthesis, the key process parameter in the digital twin model layer is the equilibrium temperature distance.

[0030] Preferably, in step (3), after triggering the production behavior of the device in the digital twin model layer, the operating parameters of the actual production device are adjusted according to the prediction results of the operation process of the production device, thereby improving the production efficiency, safety and quality of chemical products.

[0031] Beneficial effects In the chemical industry, traditional digital twin systems suffer from problems such as limited data dimensions, difficulty in optimizing reaction processes, silos in production information, scattered and disorganized operational knowledge, and one-size-fits-all alarm information, making it difficult to meet the industry's stringent requirements for high precision, high safety, and strong timeliness. The digital twin factory system of this invention effectively solves these problems by constructing a closed-loop system of data acquisition, model building, and visualization. This digital twin factory system collects multi-source data in real time, uses a rigorous dynamic mechanism model of digital twins to perform in-depth processing and simulation calculations on production data, and compares and analyzes the generated optimized data with actual on-site production data to provide accurate and reasonable process optimization suggestions. Simultaneously, the visualized management layer of this digital twin factory system provides an intuitive presentation of the production process, ensuring that managers can monitor equipment alarm status and plant production dynamics in real time, making timely decisions and comprehensively improving the efficiency, safety, and quality of chemical production.

[0032] The digital twin factory system of this invention constructs a digital model of the physical factory and collects multi-source data in real time during the production process, thereby achieving multi-dimensional visual management of the entire production process. Attached Figure Description

[0033] Figure 1 This is a data flow diagram of the digital twin factory system of the present invention.

[0034] Figure 2 The image shows the equilibrium temperature curves in the digital twin model of the ammonia synthesis unit. The solid red line represents the reaction equilibrium line. Other lines of different colors represent different beds: yellow represents bed 1, blue represents bed 2, white represents bed 3, and green represents bed 4. Solid lines represent real-time data, and dashed lines represent optimized data.

[0035] Figure 3 This involves comparing the predicted values ​​of a digital twin factory system with the real-time values ​​of actual production over a certain period of time. Detailed Implementation

[0036] The technical solution of the present invention will be further described in detail below with reference to specific embodiments. It should be understood that the following embodiments are merely illustrative and explanatory of the present invention, and should not be construed as limiting the scope of protection of the present invention. All technologies implemented based on the above content of the present invention are covered within the scope of protection intended by the present invention.

[0037] Unless otherwise stated, the raw materials and reagents used in the following examples are commercially available products or can be prepared by known methods.

[0038] To address the technical problem of the lack of multi-dimensional data integration and analysis in digital twin factory systems, this invention provides the following solution: A digital twin factory system, comprising a data acquisition layer, a data processing layer, a digital twin model layer, a visualization management layer, and an application layer.

[0039] In one specific implementation, the data acquisition layer is used for: Collect factory production data in real time.

[0040] For example, the factory production data includes at least one of the following: production equipment operating parameters (such as temperature, pressure, vibration), production process data (such as material composition, product output), and personnel information (such as department, position).

[0041] For example, the data acquisition layer utilizes Industrial Internet of Things (IIoT) technology to collect factory production data in real time. For instance, it employs various communication protocols such as OPC, SQL, MQTT, and HTTP to achieve seamless integration between the data acquisition layer and heterogeneous data sources such as real-time production databases, ERP systems, and BW (data warehouses).

[0042] In one specific implementation, the data processing layer is used for: The factory production data collected by the data acquisition layer is optimized to remove noisy data.

[0043] Specifically, in the chemical process flow, the data processing layer optimizes factory production data to obtain optimized data, such as through cleaning, conversion, and analysis, to accurately reflect the operating status of the production equipment. Furthermore, conversion refers to uniformly converting data of different formats collected by the data acquisition layer into a format recognizable by the system.

[0044] In one specific implementation, the digital twin model layer is used for: Monitor the production dynamics of the production equipment to achieve visualized operation of the production equipment.

[0045] Specifically, the production dynamics include, for example, the component composition throughout the entire chemical process, the transient changes in the physical and chemical processes of materials in the process unit, and the performance and influencing factors of the production equipment.

[0046] Specifically, the production dynamics are visualized through a digital twin model layer. The digital twin model layer is an online dynamic device model established to simulate the production device. The online dynamic device model is connected to the real-time production data of the production device and is driven by the operation signals of the production device. It performs simulation calculations and simulates the operation of the production device in real time, thereby realizing the visualization of the operation of the production device.

[0047] Specifically, the operating speed of the production device can be adjusted, for example, to achieve an operating speed of 0.1-5 times (such as 0.5 times, 1 times, 2 times, 4 times).

[0048] Specifically, in chemical process flow, the digital twin model layer is a twin of the actual production unit, used to monitor the production dynamics of each link in the production unit, such as the composition of the entire process, the transient changes of the physical and chemical processes of materials in the process unit, and the performance and influencing factors of the production unit, thereby realizing the visualization of the operation of the production unit.

[0049] In one specific implementation, the visualization management layer is used for: Real-time observation of the appearance, structure, and operation of production equipment enables visualized management.

[0050] Specifically, the visualization management layer includes a 3D visualization model of the device and an interactive interface.

[0051] Furthermore, the device's 3D visualization model achieves high-performance 3D visualization operations through 3D modeling, WebGL technology, and other methods.

[0052] Furthermore, the three-dimensional visualization model of the device refers to a three-dimensional model of the production device, including the various components of the production device and their connection methods, the operation path of the production device, and its operating status.

[0053] Furthermore, the device's three-dimensional visualization model can also access real-time factory production data, software instrument data, and business management data.

[0054] Furthermore, the interactive interface is used to view various modules in the 3D visualization model of the device, such as rotating, zooming in or out of the various devices and components in the model; at the same time, combined with real-time factory production data, soft instrument data and business management data, it provides an in-depth understanding of the various components, connection methods, operation paths and operating conditions of the production device, and to grasp information on all aspects of the production device.

[0055] Furthermore, managers can view production information such as the operating status of the production unit, unit load rate, equilibrium temperature distance, operating line, and product selectivity in real time through the interactive interface, achieving the effect of visual management.

[0056] In one specific implementation, the application layer is used for: By adjusting the thresholds or indicators of production parameters for key equipment in the digital twin model layer, the production behavior of the devices in the digital twin model layer is triggered, enabling prediction of the device operation process at a future point in time. The application layer of this invention can eliminate "one-size-fits-all" alarms, achieving real-time monitoring, timely prediction, and accurate tracking of alarms for key equipment, improving the reliability of production equipment operation, and realizing proactive monitoring of the production process.

[0057] Example 1 The following section further illustrates this by applying the aforementioned mathematical twin factory system to the production process of an ammonia synthesis unit.

[0058] The ammonia synthesis reaction involves a dynamic process encompassing gas-solid phase catalysis, complex chemical reaction equilibrium, and multiphase heat and mass transfer. Traditional instruments struggle to accurately measure process data such as equilibrium temperature distance and reaction rate in real time. This embodiment employs a mathematical twin factory system to monitor the ammonia synthesis production process, specifically: Using the laws of conservation of mass, energy, and momentum, a complete material and energy balance equation for the ammonia synthesis process, including the main reaction and side reactions of hydrogen and nitrogen, is established. An online dynamic model of the ammonia synthesis unit is constructed by combining this with kinetic models. Furthermore, a digital twin model layer is obtained by incorporating the physical and chemical mechanisms involved in the reaction process. The specific steps are as follows: (1) Model establishment: In the production process simulation, thermodynamic parameters, including specific heat capacity and heat of reaction, are calculated using the SRK (Soave-Redlich-Kwong) equation of state. The following is a detailed analysis of the thermodynamic and kinetic parameters of the ammonia synthesis reaction: 1) Fundamentals of Thermodynamics and the SRK Equation of State The SRK equation takes the following form:

[0059] In the formula:

[0060]

[0061]

[0062]

[0063] For ammonia synthesis reaction:

[0064] Since the reactants H2 and N2 are both elemental gases, their standard molar Gibbs free energy of formation (ΔfG°) is 0. Therefore, the change in Gibbs free energy of formation (ΔrG°) can be directly calculated from the standard molar Gibbs free energy of formation of NH3. The standard molar Gibbs free energy of formation of NH3 can be calculated using the following formula.

[0065] 2) Equilibrium constant and fugacity correction Ammonia synthesis is an exothermic and reversible reaction involving volume reduction. At equilibrium, the equilibrium constant K... p It can be represented as:

[0066] In the formula , , These are the partial pressures of NH3, N2, and H2 under equilibrium conditions.

[0067] However, under high pressure conditions, the non-ideal nature of the hydrogen-nitrogen-ammonia system is significant, necessitating the use of the fugacity of the real gas instead of the partial pressure. In this case, the equilibrium constant Kf is expressed as:

[0068] In the formula , , These represent the fugacity of NH3, N2, and H2 in the real gas at high pressure, in their pure state, and at equilibrium temperature and total pressure. The fugacity coefficients can be calculated using the SRK equation of state, thus correcting for non-ideal effects under high pressure.

[0069] 3) Relationship between Gibbs free energy and equilibrium constant According to the fundamental principles of thermodynamics, the relationship between the equilibrium constant and the standard Gibbs free energy change is as follows:

[0070] By combining the Gibbs-Helmholtz equation, the effect of temperature on the equilibrium constant can be further analyzed:

[0071] The equilibrium constants at different temperatures can be obtained by integration, providing a theoretical basis for optimizing reaction conditions.

[0072] 4) Reaction kinetic parameters The kinetics of ammonia synthesis reactions are typically described using a two-rate equation: Forward reaction (synthesis of ammonia):

[0073] Reverse reaction (ammonia decomposition):

[0074] in, A 1. A 2 is a pre-exponential factor. E 1. E 2 represents the activation energy.

[0075] Among them, the kinetic parameters of the reverse reaction ( A 2. E 2) Industry-known parameters are used; the parameters of the forward reaction are obtained through correlation calculations using equilibrium constants, and the equilibrium constant relationships are as follows:

[0076] By drawing 1 / T with ln K By plotting the relationship between 1 and 2 and performing linear regression, the pre-exponential factor of the positive response can be obtained. A 1 and activation energy E 1.

[0077] Through the process analysis in steps 1)-4) above, the ammonia synthesis reaction is accurately simulated, and a digital twin model layer of the ammonia synthesis unit is constructed, such as... Figure 1 As shown in the image.

[0078] (2) After the digital twin model layer is constructed, the real-time production data of the ammonia synthesis unit in the factory, such as temperature, pressure, flow rate, liquid level and other measurable data, are collected in real time through the data acquisition layer. The processed data is used as the input data of the digital twin model layer through the data processing layer. The model is used to calculate the key process parameters that are difficult to measure directly. Table 1 lists some key process parameters of the ammonia synthesis unit calculated through the digital twin model layer.

[0079] Table 1. Some soft instrument data (instantaneous values ​​at a certain moment) in the digital twin model layer of the ammonia synthesis unit.

[0080] The following example, using the equilibrium temperature curve, further illustrates this: Based on the initial conditions of the ammonia synthesis reaction, such as temperature, pressure, and inlet gas composition, and the equilibrium constant, the equilibrium line of the reaction can be plotted using equilibrium state data obtained from the Gibbs reactor (see [link to Gibbs reactor]). Figure 2 The difference between the outlet temperature of the reaction bed and the reaction equilibrium line (represented by the red curve in the middle) is the equilibrium temperature distance. When the synthesis gas (hydrogen and nitrogen) enters reaction bed 1, as the reaction proceeds, the concentration of ammonia in reaction bed 1 continuously increases while releasing a large amount of heat of reaction. The bed temperature in reaction bed 1 rises, and the reaction quickly reaches equilibrium. In order to improve the reaction conversion rate, the heat of reaction needs to be removed in time. After the temperature drops, the reaction can proceed to reaction bed 2 to continue the ammonia synthesis reaction, and so on.

[0081] like Figure 2 The figure shows the equilibrium temperature curve in the reaction bed during the ammonia synthesis reaction in this embodiment. The red line is the reaction equilibrium line obtained by theoretical calculation. Among the other colored lines, the solid line is the outlet temperature data of different reaction beds monitored on site, and the dashed line is the data optimized by the data processing layer of the digital twin factory system.

[0082] Managers can view the real-time operation of production units through a visual management layer, and adjust the thresholds or indicators of important equipment in the digital twin model layer through the application layer to predict the production status of the synthetic ammonia production unit, trigger the production behavior of the unit in the digital twin model layer, and realize the prediction of the actual operation process of the synthetic ammonia production unit at a future point in time, make technical decisions, and improve the efficiency, safety and quality of synthetic ammonia production.

[0083] Figure 3This is a comparison chart of the predicted values ​​from the digital twin factory system and the actual real-time production values ​​of the on-site ammonia synthesis production unit from December 18, 2025 to December 28, 2025. The blue line represents fresh gas, which is the flow rate of raw material gas during actual production. The red line represents the actual ammonia production during actual production. Both are real-time data from the on-site ammonia synthesis production unit. By importing the actual feed and process conditions of production during the same period into the digital twin model layer through a real-time production database and data acquisition layer, the calculated ammonia production value obtained through simulation is shown below. Figure 3 As shown by the white dashed line (dot); The actual feed from the production process during the same period is imported into the digital twin simulation layer through a real-time production database and data acquisition layer. After optimization by the application layer (such as reducing the reaction pressure of the ammonia synthesis tower to the predicted value), the calculated ammonia production value is obtained through simulation. Figure 3 As shown by the pink dashed line.

[0084] The difference between the white dashed line and the red line represents the degree of alignment between the digital twin factory system's twin model layer and the on-site ammonia synthesis production unit. Figure 3 As can be seen, although the actual ammonia production on site fluctuates, it matches the calculated value of the twin model layer in the digital twin factory system, indicating that the twin model layer has high accuracy.

[0085] And through Figure 3 The pink dotted line shows that by using a digital twin factory system for production simulation and optimizing it at the application layer, the reaction pressure of the ammonia synthesis tower can be reduced to the predicted value while ensuring ammonia production, thereby reducing the actual energy consumption of the ammonia synthesis unit. Managers can view the corresponding interface in the visual management layer and adjust the process conditions of the on-site ammonia synthesis unit based on the prediction results of the digital twin factory system. This includes reducing the reaction pressure of the ammonia synthesis tower to the predicted value and gradually optimizing and adjusting the reaction pressure and the anti-surge mechanism of the syngas compressor.

[0086] By simulating actual ammonia production using a digital twin factory system and optimizing the production process, the on-site ammonia production unit gradually reduced the outlet pressure of the syngas compressor from 13MPa to 10.6MPa under 90% operating load. The steam consumption per unit of liquid ammonia product decreased from 2.3 tons to 2.1 tons, reducing steam consumption by 0.17 tons per ton of product, which can increase revenue by 3.42 million yuan per year.

[0087] The exemplary embodiments of the present invention have been described above. However, the scope of protection of this application is not limited to the above embodiments. Any modifications, equivalent substitutions, improvements, etc., made by those skilled in the art within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A digital twin factory system, characterized in that, The digital twin factory system includes a data acquisition layer, a data processing layer, a digital twin model layer, a visualization management layer, and an application layer. The data acquisition layer is used for: Real-time collection of factory production data; The data processing layer is used for: Optimize the factory production data collected by the data acquisition layer and remove noisy data; The digital twin model layer is used for: Monitor the production dynamics of the production unit to achieve visualized operation of the production unit; The visualization management layer is used for: Real-time observation of the appearance, structure, and operation of production equipment enables visualized management; The application layer is used for: Adjusting the thresholds or indicators of production parameters for key equipment in the digital twin model triggers the production behavior of devices in the digital twin model layer, enabling prediction of device operation at a future point in time.

2. The digital twin factory system according to claim 1, characterized in that, The factory production data includes at least one of the following: production equipment operating parameters, production process data, and personnel information; The data acquisition layer utilizes Industrial Internet of Things (IIoT) technology to collect factory production data in real time.

3. The digital twin factory system according to claim 1, characterized in that, In the chemical process, the data processing layer obtains optimized data by optimizing the factory production data.

4. The digital twin factory system according to claim 1, characterized in that, The production dynamics include the component composition of the entire chemical process, the transient changes in the physical and chemical processes of materials in the process unit, and the performance and influencing factors of the production equipment. The production dynamics are visualized through a digital twin model layer, which is an online dynamic device model established to simulate the production device. The online dynamic device model is connected to the real-time production data of the production device and is driven by the operation signals of the production device to simulate and calculate the real-time dynamics of the production device, thereby realizing the visualization of the operation of the production device.

5. The digital twin factory system according to claim 1, characterized in that, The visualization management layer includes a 3D visualization model of the device and an interactive interface.

6. The digital twin factory system according to claim 5, characterized in that, The three-dimensional visualization model of the device refers to the three-dimensional model of the production device, including the various components of the production device and their connection methods, the operation path and operation status of the production device; The device's 3D visualization model also integrates real-time factory production data, software instrument data, and business management data.

7. The digital twin factory system according to claim 5, characterized in that, The interactive interface is used to view the various modules in the 3D visualization model of the device; at the same time, combined with real-time factory production data, soft instrument data and business management data, it allows for a deeper understanding of the various components, connection methods, operation paths and operating conditions of the production device, and to grasp information about all aspects of the production device. Managers can view the production information of the production unit in real time through the interactive interface, achieving the effect of visual management; the production information includes the operating status of the production unit, unit load rate, equilibrium temperature distance, operating line, and product selectivity.

8. The application method of the digital twin factory system according to any one of claims 1-7, characterized in that, The application method is used in chemical production.

9. The application method according to claim 8, characterized in that, The application method includes the following steps: (1) Model establishment: Based on the thermodynamic and kinetic parameters in the chemical production process and the design data of the chemical production equipment, a digital twin model layer is constructed; (2) After the digital twin model layer is completed, the production data of the production device is collected in real time through the data acquisition layer, and the production data is optimized through the data processing layer. The optimized data is used as the input data of the digital twin model layer to simulate and calculate the key process parameters. The real-time production data, optimized data and key process parameters are transmitted to the visualization management layer. (3) By visualizing the management layer, the real-time operation of the production equipment can be viewed, and the thresholds or indicators of important equipment in the digital twin model layer can be adjusted through the application layer to predict the production status of the production equipment, trigger the production behavior of the equipment in the digital twin model layer, and realize the prediction of the equipment operation process at a certain point in the future.

10. The application method according to claim 9, characterized in that, In step (3), after triggering the production behavior of the device in the digital twin model layer, the operating parameters of the actual production device are adjusted according to the prediction results of the operation process of the production device.

Images