Method for analog simulation running of octafluorocyclobutane purification equipment and medium

Abstract

The application provides a simulation running method and medium for octafluorocyclobutane purification equipment, relates to the technical field of simulation and analog, and the method comprises the following steps: obtaining structure design information, generating a three-dimensional model of the purification equipment; carrying out node disassembly on the octafluorocyclobutane purification process to obtain N purification process nodes; constructing a purification equipment running data space, obtaining N node purification equipment running data sets through classification identification; creating N node running simulation mechanisms; mapping to the three-dimensional model of the purification equipment for simulation and analog fusion, determining a digital simulation model of the purification equipment, and performing simulation running control. The application solves the technical problem that the purification efficiency of the octafluorocyclobutane purification equipment is affected due to low process parameter optimization efficiency caused by the lack of simulation and analog in the prior art, realizes the full-process optimization of the octafluorocyclobutane purification process through simulation and analog, and improves the purification efficiency of the octafluorocyclobutane purification equipment.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of simulation and modeling, in particular to a simulation and modeling running method and medium for octafluorocyclobutane purification equipment. BACKGROUND

[0002] The octafluorocyclobutane purification equipment is a device used to separate impurities from octafluorocyclobutane to meet high purity requirements. The working principle of the octafluorocyclobutane purification equipment is to gradually remove impurities in octafluorocyclobutane through a series of precisely controlled units and processes, and finally obtain high-purity octafluorocyclobutane. The current octafluorocyclobutane purification equipment relies on manual experience and simple control rules to adjust process parameters, which is difficult to fully consider the dynamic changes and complex process interactions in equipment operation, and cannot respond to changes in real time. Due to the lack of simulation and modeling, the control strategy of the equipment is often fixed and rigid, which is difficult to respond to sudden changes in the production process in real time, resulting in low efficiency and low precision in the adjustment process, thereby affecting the improvement of purification efficiency.

[0003] In summary, the prior art has the technical problem of low process parameter optimization efficiency due to the lack of simulation and modeling, which affects the purification efficiency of the octafluorocyclobutane purification equipment. SUMMARY

[0004] The purpose of the present application is to provide a simulation and modeling running method and medium for octafluorocyclobutane purification equipment to solve the technical problem of low process parameter optimization efficiency due to the lack of simulation and modeling in the prior art, which affects the purification efficiency of the octafluorocyclobutane purification equipment.

[0005] In view of the above problems, the present application provides a simulation and modeling running method and medium for octafluorocyclobutane purification equipment.

[0006] In a first aspect, the present application provides a simulation and modeling running method for octafluorocyclobutane purification equipment, wherein the simulation and modeling running method for octafluorocyclobutane purification equipment comprises: obtaining structure design information of the octafluorocyclobutane purification equipment, performing three-dimensional modeling based on the structure design information, and generating a purification equipment three-dimensional model; node disassembling the octafluorocyclobutane purification process to obtain N purification process nodes; based on the octafluorocyclobutane purification equipment, performing historical data mining to construct a purification equipment running data space, classifying and identifying the purification equipment running data space using the N purification process nodes to obtain N node purification equipment running data sets; performing control logic analysis and running simulation prediction on the N node purification equipment running data sets to create N node running simulation mechanisms; mapping the N node running simulation mechanisms to the purification equipment three-dimensional model for simulation and modeling fusion to determine a purification equipment digital simulation model, and performing simulation and modeling control based on the purification equipment digital simulation model.

[0007] Optionally, part parameter extraction is performed on the structural design information to obtain a purification equipment part parameter set, the purification equipment part parameter set including specification size, material property, and assembly requirement; three-dimensional modeling of parts is performed based on the purification equipment part parameter set to obtain a purification equipment part three-dimensional model set; the purification equipment part three-dimensional model set is assembled and connected according to a part space connection relationship to obtain a purification equipment assembly model; dimension reduction optimization is performed on the purification equipment assembly model based on a model precision requirement to generate the purification equipment three-dimensional model.

[0008] Optionally, key node extraction is performed on the octafluorocyclobutane purification process according to process function characteristics to obtain M key process nodes; associated process extraction is performed on the octafluorocyclobutane purification process based on the M key process nodes to obtain M associated sub-node sets; process node quantity N is set according to a purification equipment simulation requirement, where N≤M; the M associated sub-node sets are re-planned based on the process node quantity N to determine N purification process nodes.

[0009] Optionally, a node index evaluation system is established, importance evaluation of the M key process nodes is performed according to the node index evaluation system to obtain M node importance factors; M node quantity distribution ratios are determined according to the M node importance factors; the process node quantity N is distributed according to the M node quantity distribution ratios to determine M node associated process quantities; node re-planning is performed on the M associated sub-node sets based on the M node associated process quantities to obtain the N purification process nodes.

[0010] Optionally, control logic analysis is sequentially performed on the N node purification equipment running data sets to obtain N node equipment control logics; N node equipment running prediction tasks are constructed according to the N purification process nodes; running simulation prediction is performed on the N node purification equipment running data sets based on the N node equipment running prediction tasks and the N node equipment control logics to obtain N node running simulation mechanisms.

[0011] Optionally, running variable extraction is sequentially performed on the N node purification equipment running data sets to obtain N node input variable sets and N node output variable sets; N node associated variable sets are obtained by associating and mapping each node output variable in the N node output variable sets with the N node input variable sets; N node variable fitting relationship sets are obtained by fitting relationship analysis of the N node associated variable sets, and the N node variable fitting relationship sets are taken as N node equipment control logics.

[0012] Optionally, the N node devices are run to perform a prediction task and are associated with the N node purification device operation data set for correlation analysis to determine an N node task operation data set; the N node task operation data set is simulated and predicted based on the N node device control logic to obtain the N node operation simulation mechanism.

[0013] Optionally, the N node operation simulation mechanism logic is mapped to the purification device three-dimensional model for simulation and analog fusion to obtain a basic device digital simulation model; the basic device digital simulation model is optimized for full process simulation to determine the purification device digital simulation model.

[0014] Optionally, based on the purification device digital simulation model, the preset purification device control parameters are simulated and run for process simulation and product performance evaluation to obtain octafluorocyclobutane purification performance parameters; the octafluorocyclobutane purification performance parameters are used to iteratively simulate and optimize the preset purification device control parameters and control the purification device.

[0015] In a second aspect, a computer readable storage medium stores a computer program, which, when executed, implements the steps of the simulation and simulation running method for the octafluorocyclobutane purification device of any one of the first aspect.

[0016] One or more technical solutions provided in the present application have at least the following beneficial effects:

[0017] By obtaining the structural design information of the octafluorocyclobutane purification device, generating a purification device three-dimensional model based on the structural design information, obtaining N purification process nodes by decomposing the octafluorocyclobutane purification process, performing historical data mining based on the octafluorocyclobutane purification device to construct a purification device operation data space, classifying and identifying the purification device operation data space using the N purification process nodes to obtain N node purification device operation data sets, performing control logic analysis and operation simulation prediction on the N node purification device operation data sets to create N node operation simulation mechanisms, mapping the N node operation simulation mechanisms to the purification device three-dimensional model for simulation and analog fusion to determine a purification device digital simulation model, and performing simulation running control based on the purification device digital simulation model, that is, according to the structure of the octafluorocyclobutane purification device, a purification device three-dimensional model is constructed, the octafluorocyclobutane purification process is decomposed into multiple nodes, historical operation data of the octafluorocyclobutane purification device is obtained, N node operation simulation mechanisms are constructed, are mapped to the purification device three-dimensional model for simulation and analog fusion, a purification device digital simulation model is determined, simulation running control is performed, full process optimization in the octafluorocyclobutane purification process is achieved, and the purification efficiency of the octafluorocyclobutane purification device is improved.

[0018] The above description is only a summary of the technical solutions of the present application. In order to enable the technical means of the present application to be more clearly understood, and to be implemented according to the content of the description, and in order to enable the above and other purposes, characteristics and advantages of the present application to be more apparent and easy to understand, the following specific embodiments of the present application are described. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only exemplary, and for those skilled in the art, other drawings can be obtained without creative labor on the basis of the provided drawings.

[0020] Figure 1 Flowchart for the simulation running method for the octafluorocyclobutane purification equipment of the present application;

[0021] Figure 2 Flowchart for obtaining node equipment control logic in the simulation running method for the octafluorocyclobutane purification equipment of the present application. DETAILED DESCRIPTION

[0022] The present application provides a simulation running method for octafluorocyclobutane purification equipment and a medium, which solves the technical problem in the prior art that the process parameter optimization efficiency is low due to the lack of simulation, thereby affecting the purification efficiency of the octafluorocyclobutane purification equipment. According to the structure of the octafluorocyclobutane purification equipment, a three-dimensional model of the purification equipment is constructed, the octafluorocyclobutane purification process is disassembled into multiple nodes, historical running data of the octafluorocyclobutane purification equipment is obtained, an N-node running simulation mechanism is constructed, is mapped to the three-dimensional model of the purification equipment for simulation and fusion, a digital simulation model of the purification equipment is determined, simulation running control is performed, and full-process optimization in the octafluorocyclobutane purification process is realized, thereby improving the purification efficiency of the octafluorocyclobutane purification equipment.

[0023] The technical solutions in the present application will be described clearly and completely below with reference to the drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited by the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application. In addition, it should be noted that only parts related to the present application are shown in the drawings, not all.

[0024] Embodiment one, please refer to the attached Figure 1 The application provides a simulation running method for an octafluorocyclobutane purification device, which specifically comprises the following steps:

[0025] S100: Obtain the structural design information of the octafluorocyclobutane purification device, perform three-dimensional modeling based on the structural design information, and generate a purification device three-dimensional model.

[0026] Further, the S100 of the application comprises:

[0027] S110: Extract part parameters from the structural design information to obtain a purification device part parameter set, wherein the purification device part parameter set comprises specification size, material properties and assembly requirements; S120: Perform three-dimensional modeling of parts based on the purification device part parameter set to obtain a purification device part three-dimensional model set; S130: Assemble and connect the purification device part three-dimensional model set according to the spatial connection relationship of the parts to obtain a purification device assembly model; S140: Perform dimensionality reduction optimization on the purification device assembly model based on model accuracy requirements to generate the purification device three-dimensional model.

[0028] Specifically, the structural design information of the octafluorocyclobutane purification device is collected and obtained from design drawings and technical documents, including the specific size, shape, assembly method, etc. of each component (such as a rectifying tower, a condenser, a reboiler, etc.). Key parameters of each part of the octafluorocyclobutane purification device are extracted from the structural design information, including specification size (such as the length, width and height of the part), material properties (such as the type of material used and its physical properties: steel, aluminum, copper, etc.), and assembly requirements (such as the fit tolerance between parts, installation method, connection method, etc.). The purification device part parameter set includes the technical parameters (such as specification size, material properties and assembly requirements) of each part of the octafluorocyclobutane purification device, which helps to understand how the parts work with other components.

[0029] According to the purification device part parameter set, three-dimensional modeling of each part is performed respectively by using computer-aided design software to generate a part three-dimensional model set. In the computer-aided design software, the extracted part parameters are used to gradually build the three-dimensional model of each part by drawing the geometric shape of the part, adding material properties and size annotations. After the three-dimensional modeling of each part (such as a condenser, a rectifying tower, a valve, etc.) is completed, it will be saved as an independent three-dimensional model file, which together constitutes the part three-dimensional model set. After the three-dimensional modeling of the parts is completed, it must be inspected and calibrated to ensure that the model meets the design requirements and actual manufacturing requirements, including checking whether the fit between the parts is accurate, whether the size meets the tolerance requirements, and whether the material selection is reasonable, etc.

[0030] The connection relationship between the parts is determined according to the requirements in the design drawing or assembly process, and the spatial connection relationship of the parts is obtained. The purified equipment part three-dimensional model set is assembled and connected according to the spatial connection relationship of the parts, the position, direction and cooperation relationship of each part are ensured to be correct, and the purified equipment assembly model is obtained. The spatial connection relationship of the parts is the relative position relationship and connection mode of the parts in the three-dimensional space, including how to combine different parts together through a certain way (such as bolt, welding, buckle, etc.). Generally, the three-dimensional model of each part in the purified equipment part three-dimensional model set is loaded in the computer-aided design software. According to the connection mode between the parts, appropriate cooperation constraints such as alignment, fixation, rotation, etc. are applied in the computer-aided design software, and the position of the parts is adjusted through dragging, rotating, etc. to make it meet the actual spatial layout and design requirements.

[0031] For example, the rectifying tower has a first feed port, a second feed port, a first discharge port, a second discharge port and an impurity discharge port; the condenser has an inlet, a first outlet and a second outlet, and the inlet of the condenser is communicated with the first discharge port of the rectifying tower through an exhaust pipeline; the first outlet of the condenser is communicated with the second feed port of the rectifying tower through a reflux pipeline.

[0032] In the assembly process, in addition to assembling the parts together, it is checked whether the parts will cause physical interference or cannot be normally connected during the assembly process, and if problems are found, the size, position or connection mode of the parts needs to be adjusted to ensure smooth assembly. According to the simulation and actual use requirements, the model precision requirement is obtained, that is, the precision requirement of the equipment three-dimensional model, including the accuracy of the size, the details of the shape and the physical properties of the material, etc. According to the model precision requirement, the dimensionality reduction optimization of the purified equipment assembly model is performed, that is, the three-dimensional model is simplified to reduce the resource consumption required for calculation and simulation.

[0033] The complete three-dimensional model may contain too many details and unnecessary complexities, which will increase the calculation amount, simulation time and system load. The dimensionality reduction optimization maintains the necessary precision and reduces unnecessary calculation burden by reducing the number of model surfaces and simplifying complex geometric shapes. The dimensionality reduction optimization includes simplifying geometric shapes, reducing the number of model surfaces, and merging small parts. Simplifying geometric shapes removes redundant details and simplifies complex geometric structures, such as simplifying parts with too many details (such as small holes, tiny notches, etc.) to basic geometric shapes. Reducing the number of model surfaces reduces the number of surfaces of parts with more surfaces to reduce the calculation burden. Merging small parts combines multiple small parts into a single part to reduce the number of components in the model, thereby reducing the calculation complexity.

[0034] The three-dimensional model optimized by dimension reduction will become the final digital representation of the purification equipment, i.e., the three-dimensional model of the purification equipment. Through accurate three-dimensional modeling and assembly simulation, the accuracy of equipment design and manufacturing is improved, assembly errors are reduced, and the operating efficiency of each component is optimized.

[0035] S200: Node decomposition is performed on the octafluorocyclobutane purification process to obtain N purification process nodes.

[0036] Further, the S200 of the present application comprises:

[0037] S210: Key nodes are extracted from the octafluorocyclobutane purification process according to process function characteristics, obtaining M key process nodes; S220: Correlation process extraction is performed on the M key process nodes to obtain M sets of correlation sub-nodes; S230: The number of process nodes N is set according to the simulation requirements of the purification equipment, wherein N≤M; S240: The M sets of correlation sub-nodes are re-planned based on the number of process nodes N to determine N purification process nodes.

[0038] Further, the present application further comprises the following steps:

[0039] S241: A node index evaluation system is established, and the importance of the M key process nodes is evaluated according to the node index evaluation system to obtain M node importance factors; S242: The M node quantity distribution ratios are determined according to the M node importance factors; S243: The M node correlation process quantities are determined by distributing the number of process nodes N according to the M node quantity distribution ratios; S244: The M sets of correlation sub-nodes are re-planned based on the M node correlation process quantities to obtain the N purification process nodes.

[0040] Specifically, the entire octafluorocyclobutane purification process is decomposed into a series of key process nodes to obtain multiple purification process nodes. Each node represents an important operation link or decision point, such as the feeding of the rectification tower, the cooling of the condenser, etc. Process function characteristics are the basic operation principles, objectives, and effects of each step in the octafluorocyclobutane purification process, including the basic functions, parameter controls (such as temperature, pressure, flow rate), etc. of process steps such as rectification, condensation, and vacuum. According to the process function characteristics of the octafluorocyclobutane purification process, the target effect of each process node in the entire purification process is analyzed, and M key process nodes are extracted, which are the most important operation steps in the entire purification process, and each node will directly affect the purity of the final product and the process efficiency. For example, assuming that in the octafluorocyclobutane purification process, the rectification process and the condensation process are key nodes because they directly affect the product quality.

[0041] According to the M key process nodes, the octafluorocyclobutane purification process is associated with process extraction, that is, the other steps or operation links related to the key node operation are found, and M associated sub-node sets are obtained. These sub-nodes are not all independently executed, but they are closely related to the execution of the key nodes, ensuring the smoothness and efficiency of the entire process flow. For example, the associated process sub-nodes of the rectification process include feed control, discharge control, impurity discharge control, etc.; the associated sub-nodes of the condensation process include cooling liquid flow control, condenser temperature monitoring, condenser pressure control, etc. The M associated sub-node sets include all the process nodes associated with the M key process nodes.

[0042] The purification equipment simulation requirements are obtained, that is, the requirements when simulating the octafluorocyclobutane purification equipment, including the characteristics and goals of the octafluorocyclobutane purification equipment operation. The number of process nodes N is determined from the purification equipment simulation requirements, that is, the number of selected process nodes. N must be less than or equal to the number of all key process nodes M, that is, N≤M. According to the number of process nodes N, the M associated sub-node sets are re-planned, that is, the M associated sub-nodes are reorganized, so that under the limitation of N nodes, the entire process can be described as completely as possible.

[0043] According to the influence of each process node on the quality of the final product, the contribution of the node to the efficiency of the equipment, the complexity of the node and its dependence on the entire process flow, etc., a node index evaluation system is established to measure and evaluate the role and importance of each process node in the purification equipment. The node index evaluation system can include the influence of the node on the purity of the product, the influence of the node on the stability and efficiency of the equipment, the dependence of the node on other process nodes, etc.

[0044] The importance of the M key process nodes is evaluated using the node index evaluation system, and the importance factor of each node is obtained. The importance factor is usually a numerical value that reflects the degree of influence of the node on the entire process flow. According to the M node importance factors, the resource allocation of each node in the simulation is determined, that is, the number allocation ratio of the M nodes is determined. That is, according to the M node importance factors, the number allocation ratio of the M key process nodes in the overall simulation model is determined. The higher the importance of the node, the higher the number ratio allocated.

[0045] According to the M node number allocation ratio, the process node number N is allocated to determine the number of M node associated processes. That is, for each of the M nodes, the number of associated processes that each node needs to handle is determined through the number and ratio allocated to it. Some nodes may involve multiple sub-process steps (such as multiple control parameters such as temperature and pressure for the rectification process), while other nodes may only be associated with a few sub-processes.

[0046] According to the number of associated processes of M nodes, the M associated sub-node sets are re-planned, the specific steps involved in each node are adjusted according to the number of associated processes of the node, so that each node can efficiently run in the simulation process, and the calculation redundancy is avoided. The final N purification process nodes represent the most critical process steps in the entire octafluorocyclobutane purification process, and after optimization, they can accurately and quickly simulate and optimize in the simulation process.

[0047] For example, the importance of the M key process nodes is evaluated through the node index evaluation system, including the influence of the node on the overall process, the node complexity, the operation stability of the node, the resource consumption of the node, etc. Some scores obtained are shown in Table 1:

[0048] Table 1 Key process node score table

[0049] Node Impact score Complexity score Stability score Resource consumption score Total score Rectification 9 8 7 7 31 Condensation 6 7 7 5 25 Purging 5 3 6 2 16

[0050] According to the total score, the importance factor of each node is calculated, that is, the node number is allocated proportionally: rectification is 31 / (31+25+16)=0.43, condensation is 25 / (31+25+16)=0.35, and purging is 16 / (31+25+16)=0.22. Assuming that the process node number N is 10, then according to the node number allocation proportion, the process node number is allocated as follows: the number of rectification nodes is 0.43*10=4 nodes; the node number allocation proportion of condensation nodes is 0.35*10=4 nodes; and the node number allocation proportion of purging nodes is 0.22*10=2 nodes. According to the number of associated processes of the node, the M associated sub-node sets are re-planned to obtain the final purification process nodes. Through reasonable node number and allocation method, the most important part in simulation and actual operation can be optimized, unnecessary process nodes and sub-nodes are reduced, and the burden of calculation and analysis is reduced.

[0051] S300: Based on the octafluorocyclobutane purification equipment, historical data mining is performed to construct a purification equipment operation data space, the N purification process nodes are used to classify and identify the purification equipment operation data space, and N node purification equipment operation data sets are obtained.

[0052] Specifically, historical data mining is performed on the octafluorocyclobutane purification equipment. Historical data is extracted from previous equipment operation data, including equipment operating status, process parameters, sensor data, such as temperature, pressure, flow rate, material concentration, and running time. The purpose of historical data mining is to discover patterns and trends in equipment operation and identify key factors affecting purification efficiency. The collected historical data is cleaned, denoised and formatted. For example, invalid data (such as duplicates, missing or abnormal values) is removed, data interpolation is filled, etc. to ensure data accuracy and consistency. Data from different data sources is standardized to ensure uniform data units for subsequent analysis.

[0053] The processed data is organized into a unified space. The dimensions of the data space usually include time, process parameters (such as temperature, pressure, flow rate, etc.), equipment status, etc. Each data point represents the operating status of the equipment under specific time and process conditions. The purification equipment operation data space refers to a collection of all equipment operation related data, including temperature, pressure, flow rate, concentration, and other process parameters and equipment status information.

[0054] According to N purification process nodes, the purification equipment operation data space is classified and identified, that is, the data of the purification equipment operation data space is classified according to N purification process nodes. For example, each data set is labeled with the corresponding process step (such as condensation, adsorption, etc.) through data labeling, and each process step is assigned a specific set of data. Map the historical data of each node to the corresponding process operation, so that the data is more targeted and structured. The N node purification equipment operation data set is the historical operation data set corresponding to each node obtained by the above classification and identification, and each node's operation data set contains the historical data of the node under different working conditions, such as parameter fluctuations, equipment performance, etc.

[0055] By constructing a structured purification equipment operation data space and dividing it into N data sets related to process nodes, detailed data analysis and parameter adjustment for each process node can be performed to achieve the best purification effect.

[0056] S400: Control logic analysis and operation simulation prediction are performed on the N node purification equipment operation data set to create an N node operation simulation mechanism.

[0057] Further, the S400 of the present application comprises:

[0058] S410: sequentially control logic parsing on the N node purification equipment operation data set to obtain N node device control logic; S420: constructing N node device operation prediction tasks according to the N purification process nodes; S430: performing operation simulation prediction on the N node purification equipment operation data set based on the N node device control logic according to the N node device operation prediction tasks to obtain N node operation simulation mechanism.

[0059] Further, as shown in the accompanying drawings, Figure 2 The present application further comprises the following steps:

[0060] S411: sequentially extracting operation variables from the N node purification equipment operation data set to obtain N node input variable set and N node output variable set; S412: respectively associating and mapping each node output variable in the N node output variable set with the N node input variable set to obtain N node associated variable set; S413: respectively performing fitting relationship analysis on the N node associated variable set to obtain N node variable fitting relationship set, and taking the N node variable fitting relationship set as N node device control logic.

[0061] Further, the present application further comprises the following steps:

[0062] S431: performing associated analysis on the N node device operation prediction task and the N node purification equipment operation data set to determine N node task operation data set; S432: performing operation simulation prediction on the N node task operation data set based on the N node device control logic to obtain the N node operation simulation mechanism.

[0063] Specifically, sequentially extracting operation variables from the N node purification equipment operation data set, i.e. extracting various parameters or indexes affecting the performance of the equipment such as temperature, pressure, flow, purity, etc. to obtain input and output parameters in the operation process of the equipment, i.e. N node input variable set and N node output variable set. Node input variables are usually adjustable parameters affecting the operation of the equipment, such as temperature, flow, pressure, etc.; node output variables are responses of the equipment, such as product purity, yield, etc.

[0064] Respectively associating and mapping each node output variable in the N node output variable set with the N node input variable set, i.e. clarifying the relationship between the input variables and the output variables of each node, understanding how each variable interacts with each other and affects the final output. The N node associated variable set includes all the pairs of input variables and output variables of the nodes.

[0065] For each node's input-output relationship, select a suitable fitting method for modeling, such as linear regression, nonlinear regression, etc. Through fitting analysis, the mathematical model of each node is obtained. For example, the input of a node is temperature and flow, and the output is purity, then the mathematical model after fitting may be as follows: purity = 0.2 * temperature + 0.1 * flow + 70. Fitting relationship analysis refers to mathematical modeling of the relationship between input and output variables of each node through statistical methods, forming a mathematical formula or model to describe the relationship between these variables. In other words, the data in the N-node associated variable set is fitted into a straight line, and the N-node variable fitting relationship set is determined accordingly.

[0066] The N-node variable fitting relationship set is used as the N-node device control logic for real-time adjustment of device operation. By real-time acquisition of input variables, the fitting formula is substituted, the output variable is predicted, and the device settings are adjusted accordingly to achieve the effect of optimal control.

[0067] According to the N purification process nodes, N node device operation prediction tasks are constructed. The goal of the node device operation prediction task is usually to predict how the device operates under different operating conditions and to predict its output results. For example, for a temperature control node, the goal of the prediction task can be to predict the change in reaction rate or purity under a given flow and temperature condition.

[0068] The node device operation prediction task is based on the input and output data of each purification process node, and uses data mining, machine learning, etc. to predict the future state or output of the device under that node. For example, to predict the output purity, flow, etc. of the device under a certain node. According to the N node device operation prediction task, the N node device control logic is used to simulate and predict the N node purification device operation data set. Each node has a set of control logic to guide how to adjust the input variables to affect the output. For example, the control logic of a temperature control node may include adjusting the power of the heater to achieve a predetermined temperature. Use the historical data set of each node (containing input and output data) for simulation calculation. Use the control logic and data set input to simulate through mathematical models (such as regression models, machine learning algorithms, etc.) to predict the performance of the device under given conditions.

[0069] Through correlation analysis, the device prediction task of each node is connected with the corresponding operation data set to ensure that the output data of each task can be verified and optimized through actual operation data. The operation data set of each node contains input and output variables. Through correlation analysis, the relationship between the input variables (such as temperature, flow, etc.) and the output variables (such as purity, efficiency, etc.) of the task is determined. For example, through correlation analysis, the relationship between flow and yield is determined.

[0070] The N node task running data set is run through the N node device control logic to obtain an N node running simulation mechanism. That is, the task running data set of each node is input into the simulation model to simulate the response of the device under different input conditions. According to the device control logic, the running state of each node is simulated, such as how the temperature is adjusted and how the purity changes under different input flow. The simulation results will show the control response of each node, forming the running simulation mechanism of the node, reflecting the control behavior of each node under different conditions. The specific training process of the node running simulation mechanism is as follows: the target of the prediction task is determined, such as device output, device state, production efficiency, etc. At the same time, the historical running data of each process node is obtained, including temperature, flow, pressure, purity and other related variables. The historical running data is divided into training set and test set, usually 80% training set and 20% validation set. Select a suitable machine learning algorithm for training, such as support vector machine. The training set is used to train the model, learn the relationship between input and output, and adjust the model parameters to improve the prediction accuracy. The test set is used to evaluate the trained model, for example, the accuracy of the model is evaluated by cross-validation method, such as prediction error (such as mean square error MSE), accuracy, etc. The trained model is optimized by grid search to find the best hyperparameters.

[0071] The prediction tasks of each node are integrated. Through the simulation results, each link in the entire purification process can be simulated to predict the performance of the device under future running state. Using the control logic of each node and the prediction results, multiple simulations are performed. Each simulation will give the running output of the device at this node, helping to optimize the device control strategy. By continuously adjusting the input variables (such as flow, temperature, etc.), the optimal running state of the device can be found. For example, when the prediction result of a certain node shows that the purity decreases, the simulation can automatically adjust the settings of other nodes to ensure that the device can achieve the best running effect. The simulation mechanisms of each node are integrated to form an N node running simulation mechanism, simulating each step in the entire octafluorocyclobutane purification process and predicting the running state of the device.

[0072] By establishing the node device running prediction task and control logic, the running performance of the device under different operating conditions can be accurately predicted, helping to optimize the device control strategy. Through simulation prediction, the control decision of each node can be optimized to ensure that the device can achieve the best running state in actual operation, avoiding excessive adjustment or invalid operation.

[0073] S500: mapping the N node running simulation mechanism to the purification device three-dimensional model for simulation simulation fusion, determining a purification device digital simulation model, and performing simulation running control based on the purification device digital simulation model.

[0074] Further, the S500 of the present application comprises:

[0075] S510: Map the N node running simulation mechanism logic to the purification equipment three-dimensional model for simulation simulation fusion, obtain the basic equipment digital simulation model; S520: Optimize the whole process simulation of the basic equipment digital simulation model, determine the purification equipment digital simulation model.

[0076] Specifically, the N node running simulation mechanism is mapped to the purification equipment three-dimensional model, that is, the running simulation mechanism of each node is combined with the three-dimensional geometric model of the equipment to form a complete digital simulation model, so that the running state of the equipment can be fully simulated in a virtual environment. That is, the control logic and simulation mechanism of each node are associated with the corresponding components in the three-dimensional model of the equipment. The basic equipment digital simulation model is a digital model obtained by combining the running simulation mechanism of the N nodes with the three-dimensional model of the purification equipment, which can simulate the overall operation process of the equipment and evaluate the performance of the equipment under different conditions.

[0077] Optimize the whole process simulation of the basic equipment digital simulation model, include all process steps (including temperature control, flow regulation, reactant concentration control, etc.) into the optimization process, evaluate their performance under different operating conditions. Comprehensive process simulation optimization of the basic equipment digital simulation model, including adjusting the parameters of the model, optimizing the process flow, verifying the accuracy of the model, etc. The goal of optimization is to ensure that the simulation model can accurately reflect the actual operation of the equipment and can predict the performance under different process parameters. Through this optimization, a purification equipment digital simulation model is finally determined for further simulation analysis and process optimization.

[0078] In the simulation model, there are multiple parameters that can affect the output and performance of the model, including the physical characteristics of the equipment (such as size, material properties), process conditions (such as temperature, pressure, flow rate), and operating parameters (such as feed rate, stirring speed, etc.). The purpose of adjusting the model parameters is to make the model closer to the actual operation of the equipment. Optimizing the process flow involves redesigning and arranging the process steps to improve the overall purification efficiency, including changing the order of process steps, adjusting operating conditions, introducing new process technologies, etc. The goal of optimization is to find the best process flow to achieve the highest purification effect and the lowest cost.

[0079] After the model is adjusted and optimized, the accuracy of the model needs to be verified, the predicted results of the model are compared with the actual experimental data or field operation data to complete. If the predicted results of the model are consistent with the actual data, the model can be considered accurate. If there is a significant difference, the parameters or structure of the model may need to be further adjusted. Through whole process simulation optimization, a purification equipment digital simulation model is finally determined for further simulation analysis and process optimization.

[0080] By constructing a comprehensive purification equipment digital simulation model, simulating all process nodes of the equipment in actual operation, evaluating different process parameters and equipment configurations without actual experiments, trial and error costs are reduced and production efficiency is improved.

[0081] Further, the present application further comprises the following steps:

[0082] S530: Based on the purification equipment digital simulation model, process simulation running and product performance evaluation are performed on the preset purification equipment control parameters to obtain octafluorocyclobutane purification performance parameters; S540: The octafluorocyclobutane purification performance parameters are used to iteratively simulate and optimize the preset purification equipment control parameters and control the purification equipment.

[0083] Specifically, before simulation, preset purification equipment control parameters such as reactor temperature, pressure, flow rate, etc. represent the initial operating conditions of the equipment under different working conditions. For example, assume that the preset reactor temperature is 150°C, the flow rate is 10 m 3 / h, and the pressure is 2 MPa. The preset control parameters are input into the digital simulation model for simulation running to simulate the actual performance of the equipment under these conditions, including purification effect, energy consumption, production efficiency, etc. The simulation results will provide the operating state of the equipment and predict the working efficiency of the equipment under the current conditions.

[0084] After process simulation running, the purification performance of the product is evaluated to obtain octafluorocyclobutane purification performance parameters such as octafluorocyclobutane purity, yield, energy efficiency, etc. to feedback the rationality of the control parameter setting. According to the octafluorocyclobutane purification performance parameters, the preset purification equipment control parameters are iteratively simulated and optimized to gradually improve the operating efficiency of the equipment and achieve better purification effect. In each iteration, the simulation running is performed again according to the new control parameters, and the new purification performance parameters are calculated. The control parameters are continuously adjusted until the optimal process conditions are obtained. For example, assume that after several iterations, the equipment has a purity of 99% at a temperature of 170°C, a flow rate of 13 m 3 / h, and a pressure of 2.5 MPa, an energy consumption of 4 kWh / kg, and a production rate of 220 kg / h. The optimization goal is to improve product purity, reduce energy consumption, and improve production rate, or to find the best balance point among these goals.

[0085] After iterative optimization, the optimal parameter combination is selected, and the final device control strategy is determined accordingly, so as to realize the current highest purification efficiency. According to the optimal parameter combination, the working parameters (such as temperature, flow rate, etc.) of the octafluorocyclobutane purification device are adjusted to achieve the optimal purification effect. By optimizing the control parameters of the purification device, the purification efficiency of octafluorocyclobutane is improved, the performance of the device is predicted and improved before the actual operation of the device, thereby reducing the trial and error cost and improving the production efficiency.

[0086] In summary, the simulation running method for the octafluorocyclobutane purification device provided by the present application has the following beneficial effects:

[0087] By obtaining the structure design information of the octafluorocyclobutane purification device, a three-dimensional model of the purification device is generated based on the structure design information. The octafluorocyclobutane purification process is node disassembled to obtain N purification process nodes. The historical data of the octafluorocyclobutane purification device is mined to construct a purification device running data space. The N purification process nodes are used to classify and identify the purification device running data space to obtain N node purification device running data sets. The N node purification device running data sets are analyzed and simulated to create N node running simulation mechanisms. The N node running simulation mechanisms are mapped to the purification device three-dimensional model for simulation and simulation fusion to determine a purification device digital simulation model, and the simulation running control is performed based on the purification device digital simulation model. That is, according to the structure of the octafluorocyclobutane purification device, a three-dimensional model of the purification device is constructed, the octafluorocyclobutane purification process is disassembled into multiple nodes, the historical running data of the octafluorocyclobutane purification device is obtained, N node running simulation mechanisms are constructed, and are mapped to the purification device three-dimensional model for simulation and simulation fusion to determine a purification device digital simulation model, and the simulation running control is performed, realizing the full-process optimization of the octafluorocyclobutane purification process and improving the purification efficiency of the octafluorocyclobutane purification device.

[0088] In the second embodiment, based on the same inventive concept as the simulation running method for the octafluorocyclobutane purification device in the first embodiment, the present application also provides a computer readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the simulation running method for the octafluorocyclobutane purification device in any one of the first embodiment when executed.

[0089] The above description of disclosed embodiments enables one of ordinary skill in the art to make or use the application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein can be applied to other embodiments without departing from the spirit or scope of the application. Therefore, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0090] Obviously, many modifications and changes can be made to the application without departing from the spirit and scope of the application. It is understood that the application is not to be limited to the particular embodiments disclosed, but it is intended to cover all modifications which are within the scope of the application as defined by the language of the claims.

Claims

1. A method for analog simulation operation of an octafluorocyclobutane purification plant, characterized in that, Comprise: Obtain the structure design information of the octafluorocyclobutane purification equipment, based on the structure design information, three-dimensional modeling is carried out, and the purification equipment three-dimensional model is generated; The octafluorocyclobutane purification process is node disassembled, N purification process nodes are obtained, each purification process node represents an operation link or decision point; Based on the octafluorocyclobutane purification equipment, historical data mining is carried out, the purification equipment operation data space is constructed, the N purification process nodes are used for classifying and identifying the purification equipment operation data space, and N node purification equipment operation data set is obtained, the purification equipment operation data space refers to a set containing all equipment operation related data; Control logic analysis and operation simulation prediction are carried out on the N node purification equipment operation data set, and N node operation simulation mechanism is created; The N node operation simulation mechanism is mapped to the purification equipment three-dimensional model for simulation simulation fusion, the purification equipment digital simulation model is determined, and the simulation operation control is carried out based on the purification equipment digital simulation model.

2. The simulation running method for the octafluorocyclobutane purification apparatus according to claim 1, wherein The generation of the purification equipment three-dimensional model comprises: The structure design information is subjected to part parameter extraction, and the purification equipment part parameter set is obtained, the purification equipment part parameter set includes specification size, material property and assembly requirement; Based on the purification equipment part parameter set, part three-dimensional modeling is carried out respectively, and the purification equipment part three-dimensional model set is obtained; The purification equipment part three-dimensional model set is assembled and connected according to the part space connection relationship, and the purification equipment assembly model is obtained; Based on the model precision requirement, the purification equipment assembly model is reduced and optimized, and the purification equipment three-dimensional model is generated.

3. The simulation running method for the octafluorocyclobutane purification apparatus according to claim 1, wherein The N purification process nodes are obtained, comprising: According to the process function characteristics, the key nodes of the octafluorocyclobutane purification process are extracted, and M key process nodes are obtained; Based on the M key process nodes, the associated process of the octafluorocyclobutane purification process is extracted, and M associated sub node set is obtained; According to the simulation requirement of purification equipment, the number of process nodes N is set, wherein N≤M; Based on the number of process nodes N, the M associated sub node set is reprogrammed, and N purification process nodes are determined.

4. The simulation running method for the octafluorocyclobutane purification apparatus according to claim 3, wherein The determination of N purification process nodes comprises: Establish a node index evaluation system, evaluate the importance of the M key process nodes according to the node index evaluation system, and obtain M node importance factors; According to the M node importance factors, the M node number allocation ratio is determined; According to the M node number allocation ratio, the number of process nodes N is allocated, and the number of M node associated process is determined; Based on the number of M node associated process, the M associated sub node set is reprogrammed, and the N purification process nodes are obtained.

5. The simulation running method for the octafluorocyclobutane purification apparatus according to claim 1, wherein The creation of N node operation simulation mechanism comprises: Control logic analysis is carried out on the N node purification equipment operation data set in turn, and N node equipment control logic is obtained; According to the N purification process nodes, N node equipment operation prediction task is constructed; According to the N node device running prediction task, the N node device control logic performs running simulation prediction on the N node purification device running data set, and obtains an N node running simulation mechanism.

6. The simulation running method for the octafluorocyclobutane purification apparatus according to claim 5, wherein The N node device control logic comprises: The N node purification device running data set is sequentially subjected to running variable extraction, and an N node input variable set and an N node output variable set are obtained. Each node output variable in the N node output variable set is respectively associated with the N node input variable set to obtain an N node associated variable set. The N node associated variable set is respectively subjected to fitting relationship analysis to obtain an N node variable fitting relationship set, and the N node variable fitting relationship set is taken as the N node device control logic.

7. The simulation running method for the octafluorocyclobutane purification apparatus according to claim 5, wherein The N node running simulation mechanism comprises: According to the N node device running prediction task, the N node purification device running data set is subjected to associated analysis to determine an N node task running data set. Based on the N node device control logic, the N node task running data set is subjected to running simulation prediction to obtain the N node running simulation mechanism.

8. The simulation running method for the octafluorocyclobutane purification apparatus according to claim 1, wherein The purification device digital simulation model comprises: The N node running simulation mechanism logic is mapped to the purification device three-dimensional model for simulation simulation fusion to obtain a basic device digital simulation model. The basic device digital simulation model is subjected to full process simulation optimization to determine the purification device digital simulation model.

9. The simulation running method for the octafluorocyclobutane purification apparatus according to claim 1, wherein Based on the purification device digital simulation model, the simulation running control comprises: Based on the purification device digital simulation model, the preset purification device control parameters are subjected to process simulation running and product performance evaluation to obtain octafluorocyclobutane purification performance parameters. The octafluorocyclobutane purification performance parameters are used to iteratively simulate and optimize the preset purification device control parameters and control the purification device.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program realizes the steps of the simulation and simulation running method for the octafluorocyclobutane purification device according to any one of claims 1 to 9 when executed.

Images