Chemical intelligent desktop factory teaching system

Abstract

The invention belongs to the technical field of digital twinning, and discloses a chemical intelligent desktop factory teaching system. Comprises: a project creation module for creating a chemical project; the process building module is used for identifying a topological structure and building a twin process flow in combination with a chemical project; the parameter setting module is used for carrying out parameter setting on chemical equipment in the twin technological process; the dynamic operation module is used for performing dynamic operation on the twinning process flow to obtain an operation result; the reverse optimization module is used for acquiring a target operation result and performing parameter optimization on the chemical equipment in the twin process flow; according to the invention, visual teaching experience is provided, students are promoted to understand the complex chemical process, the practical ability and innovation awareness of the students can be enhanced, the problems of abstraction, potential safety hazards, single function and the like existing in traditional teaching are effectively solved, and an innovative solution is provided for teaching practice of the chemical major.

Description

Technical Field

[0001] The present invention relates to the field of digital twin technology, and more specifically, to a chemical industry smart desktop factory teaching system. Background Art

[0002] The teaching process of traditional chemical engineering colleges usually involves complex devices and various unit operations. Students who are new to professional knowledge often have low learning efficiency due to poor learning methods. The current teaching solutions for chemical engineering have the following limitations:

[0003] 1) Abstractness of 2D teaching software: The existing traditional 2D teaching software is relatively abstract in content presentation and lacks intuitive and concrete forms of expression, making it difficult for students to effectively understand complex chemical equipment and its operating procedures;

[0004] 2) Safety hazards of practical training devices and limitations of process selection: Many practical training devices have certain safety risks, and the selectable process flows are also very limited, which cannot fully meet students' needs for diversified practical learning;

[0005] 3) The teaching sandbox has a single function: the current teaching sandbox is mainly used for appearance display, lacks effective teaching functions, and cannot provide students with real operation experience and practical learning conditions;

[0006] Therefore, it is urgent to develop more advanced teaching tools and methods to improve the teaching quality of chemical engineering majors, enhance students' practical ability and innovative awareness, and adapt to the future development needs of the chemical industry.

[0007] The patent with announcement number CN105448142B discloses a simulation teaching system and a corresponding teaching method; the simulation teaching system includes: an NPO simulation server, a simulation sandbox and a teaching controller; the simulation sandbox includes: a background display screen, a power supply film and a simulation device, the teaching controller is connected to the NPO simulation server for setting a simulation scene, the NPO simulation server is connected to the simulation sandbox, and controls the simulation sandbox based on the simulation scene, the NPO simulation server provides a background image or video for the background display screen, and controls the power supply film to power the target simulation device; the simulation teaching system of this invention reduces a large amount of adhesives and chemical materials required for model making, reduces pollution, is flexible to use, and can flexibly switch between different scenes.

[0008] However, although the above-mentioned technology can realize chemical engineering professional teaching, it only uses simulation scenarios and students cannot directly operate related equipment, resulting in insufficient understanding of equipment operation and lack of realism; and the above-mentioned technology lacks a distributed control system and cannot reversely optimize the control strategy based on the calculation results, resulting in students only staying on the surface of the operation, lacking understanding of the deep-level mechanism of the chemical process, and unable to effectively combine theoretical knowledge with practical operations.

[0009] In view of this, the present invention proposes a chemical industry intelligent desktop factory teaching system to solve the above problems. Summary of the invention

[0010] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solutions: a chemical intelligent desktop factory teaching system, comprising:

[0011] Project creation module, used to create chemical projects;

[0012] The process building module is used to identify topological structures and build twin process flows in combination with chemical projects;

[0013] Parameter setting module, used to set parameters of chemical equipment in the twin process;

[0014] Dynamic calculation module, used to perform dynamic calculation on the twin process flow and obtain calculation results;

[0015] The reverse optimization module is used to obtain the target operation results and optimize the parameters of the chemical equipment in the twin process.

[0016] Furthermore, the chemical project includes project components and thermodynamic methods; the project components include chemical substances and chemical properties corresponding to the chemical substances; the thermodynamic method includes a thermodynamic model and model parameters corresponding to the thermodynamic model;

[0017] The method for identifying a topological structure comprises:

[0018] The equipment connection relationship is obtained, the corresponding adjacency matrix is ​​constructed according to the equipment connection relationship, and the topological structure is identified according to the adjacency matrix; the equipment connection relationship is obtained through the chemical desktop factory, the chemical desktop factory includes micro-factory equipment components, and the micro-factory equipment components include chemical unit equipment components, valve components and display instrument components.

[0019] Furthermore, the method of constructing a corresponding adjacency matrix according to the device connection relationship includes:

[0020] Identify all chemical equipment in the equipment connection relationship, chemical equipment includes chemical unit equipment, valves and display instruments; mark each chemical equipment as a node, set different digital labels for each node in turn, and mark them as node labels. The range of node labels is [1, m], m is the number of nodes, and the node labels correspond to chemical equipment one by one; create an initial matrix, the size of the initial matrix is ​​m×m, and the value of each element in the initial matrix is ​​0; mark the elements in the initial matrix as P(a, b), P(a, b) represents the connection relationship between the a-th node and the b-th node, the connection relationship includes connected and unconnected, a∈[1, m], b∈[1, m]; combine all nodes to obtain c node sets, each node set includes two different nodes, and each node set is different,

[0021] According to the two nodes included in each node set and the two nodes corresponding to each element in the initial matrix, the node sets are matched one by one with the elements in the initial matrix; according to the device connection relationship, the two nodes in each node set are analyzed; if the two nodes are connected, the values ​​of the elements corresponding to the corresponding node set are updated to d, where d is an integer greater than 0; if the two nodes are not connected, the values ​​of the elements corresponding to the corresponding node set are not updated; the initial matrix after the updated values ​​is used as the adjacency matrix.

[0022] Furthermore, the step of identifying the topological structure according to the adjacency matrix includes:

[0023] Step A1: Mark the elements in the adjacency matrix that are not 0 as connection elements, regard the two nodes in each connection element as adjacent nodes, and mark all nodes in the connection elements as topological nodes;

[0024] Step A2: Randomly select a topological node that is not marked as a selected node and mark it as the initial node; starting from the initial node, explore all adjacent nodes of the initial node, and randomly select one of the adjacent nodes as the successor node, and mark the successor node as the selected node;

[0025] Step A3: Explore all adjacent nodes of the successor node, and randomly select one of the adjacent nodes that is not marked as a selected node as an update node, update the successor node to the update node, and mark the update node as a selected node;

[0026] Step A4: loop step A3 until all the adjacent nodes of the successor node have been marked as visited nodes, then the loop ends and goes to step A5;

[0027] Step A5: determine whether all adjacent nodes corresponding to each selected node have been marked as selected nodes. If not, proceed to step A6. If yes, obtain a connected component and proceed to step A8.

[0028] Step A6: trace back from the successor node to the predecessor node, explore all the adjacent nodes of the predecessor node, randomly select one of the adjacent nodes that is not marked as the selected node as the update node, update the successor node to the update node, and mark the update node as the selected node; the predecessor node is the node that selects the successor node as the update node;

[0029] Step A7: looping steps A3 to A6 until all adjacent nodes corresponding to each selected node have been marked as selected nodes, obtaining a connected component, and proceeding to step A8;

[0030] Step A8: loop through steps A2 to A7 until all topological nodes are marked as selected nodes, and all connected components are combined into a topological structure.

[0031] Furthermore, the method for building a twin process flow includes:

[0032] According to the node label, each node in the topological structure is mapped to the corresponding chemical equipment; according to the preset association set, each chemical equipment is associated with the corresponding thermodynamic model in the thermodynamic method, and the association set includes chemical equipment and the thermodynamic model corresponding to the chemical equipment; according to the model parameters corresponding to each thermodynamic model, the mathematical equation corresponding to each thermodynamic model is constructed; the mathematical equation corresponding to each thermodynamic model is associated with the chemical equipment corresponding to the corresponding thermodynamic model; according to the chemical equipment in the topological structure, as well as the thermodynamic model and mathematical equation corresponding to each chemical equipment, a twin process flow is built.

[0033] Furthermore, the step of setting parameters for the chemical equipment in the twin process flow includes:

[0034] Step B1: setting equipment parameters of each chemical unit equipment in the chemical equipment;

[0035] Equipment parameters are the parameters corresponding to the operation of chemical unit equipment;

[0036] Step B2: adjusting the valve opening of each valve in the chemical equipment;

[0037] The valve opening is the degree of opening and closing of each valve;

[0038] Step B3: Bind each display instrument in the chemical equipment to the chemical unit equipment;

[0039] Bind each display instrument to a chemical unit device one by one, that is, one display instrument corresponds to one chemical unit device;

[0040] The method for obtaining the calculation results is: using the project components as input data of the twin process flow, calling the mathematical equations corresponding to each chemical equipment in the twin process flow, performing calculations through a preset back-end dynamic simulation engine, and obtaining the calculation results.

[0041] Furthermore, the step of optimizing parameters of chemical equipment in the twin process flow includes:

[0042] Step C1: construct N sets of parameter sets, set different digital labels for each set of parameter sets, and mark them as parameter labels;

[0043] Step C2: construct a population S, which includes n individuals. Each individual in the population S corresponds to a parameter label one by one. The number of iterations t corresponding to the population S is 0, 1<n<N;

[0044] Step C3: define the iteration threshold w;

[0045] Step C4: Calculate the target value set corresponding to each individual and divide it into levels;

[0046] Step C5: Calculate the sparsity corresponding to each individual;

[0047] Step C6: Filter source individuals according to the hierarchical division and the sparsity corresponding to each individual;

[0048] Step C7: Perform crossover and mutation on the source individuals in turn to generate a subpopulation S;

[0049] Step C8: Merge the population S and the subpopulation S to obtain a merged population;

[0050] Step C9: Compare the number of iterations t with the iteration threshold w. If t≥w, proceed to step C10; if t<w, set t=t+1, select n individuals from the merged population, reconstruct the population S, and return to step C4;

[0051] Step C10: Filter out the best individual from the merged population, obtain the parameter label corresponding to the best individual, and mark it as the best label; optimize the parameters of the chemical equipment in the twin process according to the parameter set corresponding to the best label.

[0052] Furthermore, in the step C1, the method for constructing N sets of parameter sets is: obtaining a parameter range, the parameter range includes an equipment parameter range and a valve opening range, the equipment parameter range includes a range of each equipment parameter corresponding to each chemical unit equipment in the chemical equipment, and the valve opening range includes a range of valve opening corresponding to each valve in the chemical equipment; randomly selecting a value from each range in the parameter range to construct a set of parameter sets, and constructing a total of N sets of parameter sets, and the N sets of parameter sets are all different;

[0053] In step C2, the expression of each individual in population S is: In the formula, is the i-th individual, P i is the random coefficient of the ith individual, P i ∈[0,1], i∈[1,n];

[0054] In step C4, the method for calculating the target value set corresponding to each individual is as follows: obtaining the parameter set corresponding to the parameter label corresponding to each individual and marking it as an optimization set; according to each optimization set, setting parameters for the chemical equipment in the twin process flow in turn, and performing dynamic calculations, obtaining the calculation results corresponding to each optimization set, and using them as the target value set of the corresponding individual, and using each value in the target value set as the target value;

[0055] The steps to perform the hierarchical division include:

[0056] Step C401: every two individuals in the population S are regarded as a group of individuals;

[0057] Step C402: according to the target value set corresponding to each individual, determine in turn whether there is an individual dominating another individual in each group of individuals, and obtain the determination result;

[0058] Step C403: according to the judgment result, count the dominated sets corresponding to each individual;

[0059] Step C404: All individuals that do not exist in the dominated set are divided into a level and marked as the current level, and the individuals in the current level are marked as the current individuals, and all current individuals in the dominated set are deleted;

[0060] Step C405: All individuals in the dominated set that only have the current individual are divided into a level and marked as an update level, the current level is updated to the update level, the current individual is updated to the individual in the update level, and the current individuals in all dominated sets are deleted;

[0061] Step C406: Loop step C405 until all individuals have completed the hierarchical division. The loop ends and digital labels are set in ascending order from the first to the last according to the order in which each level is marked as the current level. The digital labels are marked as level labels. The range of the level labels is [1, v], where v is the number of levels.

[0062] Furthermore, in step C402, the method for obtaining the judgment result includes:

[0063] Compare the target values ​​of the same type in the two target value sets corresponding to each group of individual sets;

[0064] like Then the jth individual dominates the ith individual; among them, is the i-th individual in the t-th iteration process, is the jth individual in the tth iteration process. The i-th individual and the j-th individual belong to the same individual set. is the kth target value in the target value set corresponding to the i-th individual, k∈[1,K], K is the number of target values ​​in the target value set, Indicates that for all target values ​​in the target value set, there exists It means that for the kth target value in the target value set, there exists ∩ means and, j∈[1,n], i≠j;

[0065] like Then the i-th individual and the j-th individual do not dominate each other.

[0066] Furthermore, in step C5, the expression of sparsity is: is the sparsity of the i-th individual, f k (max) is the kth target value with the largest value in all target value sets, f k (min) is the kth target value with the smallest value in the set of all target values;

[0067] In step C6, the method for screening source individuals is: preset a sorting rule, and sort each individual according to the level label and sparsity corresponding to each individual to generate an individual sorting table; according to the positive order of the individual sorting table, screen out the source individuals from all individuals. Individuals are collected and marked as source individuals; the sorting rules are as follows: individuals with smaller hierarchical labels are sorted first, and individuals with larger sparsity are sorted first;

[0068] In step C7, the method of crossing the source individuals includes:

[0069] According to the positions of all source individuals in the individual sorting table, every two adjacent source individuals are regarded as a group of crossover sets; the crossover coefficient is preset, and the two parameter labels corresponding to each crossover set are added to obtain the sum label; the two parameter labels corresponding to each crossover set are subtracted and the absolute value is taken to obtain the difference label; each sum label is multiplied by 0.5, and the difference label is added and multiplied by the crossover coefficient to obtain the crossover label corresponding to each crossover set; according to the crossover label, the corresponding crossover individual is obtained, and the crossover individual is the individual obtained after crossing the source individuals;

[0070] Methods for mutating source individuals include:

[0071] Preset the variation range, multiply the crossover label corresponding to the crossover individual by the variation range, and add the random number in the standard normal distribution to obtain the variation label corresponding to each crossover individual; according to each variation label, mutate the corresponding crossover individual to obtain the variation individual corresponding to each crossover individual;

[0072] In step C10, the method for selecting the best individual from the combined population includes:

[0073] A weight set is preset, and the weight set includes a weight coefficient corresponding to each target value in the target value set; according to the weight set, the weight coefficient corresponding to each target value in the target value set is obtained, and each target value corresponding to each individual in the merged population is multiplied by the corresponding weight coefficient to obtain the weight value; the weight values ​​corresponding to each individual in the merged population are added in sequence to obtain the total weight value; the total weight value of each individual in the merged population is compared respectively, and the individual with the largest total weight value in the merged population is marked as the best individual.

[0074] The technical effects and advantages of the chemical industry intelligent desktop factory teaching system of the present invention are as follows:

[0075] Through the integration of project creation, process construction, parameter setting, dynamic calculation and reverse optimization modules, the problems of insufficient understanding of equipment operation and safety hazards in traditional teaching have been effectively solved; by using digital twin technology to build a visual virtual process flow, students can enhance their understanding of theoretical knowledge and process mechanisms, and improve their practical skills and problem-solving abilities by independently adjusting equipment parameters, observing process operation results and performing reverse optimization; it not only provides an intuitive teaching experience and promotes students' understanding of complex chemical processes, but also enhances students' practical ability and innovative consciousness through dynamic calculation and parameter optimization functions, effectively solving the problems of abstractness, safety hazards and single functions in traditional teaching, and providing innovative solutions for chemical engineering professional teaching practice. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] Figure 1 This is a schematic diagram of a chemical industry smart desktop factory teaching system according to Example 1 of the present invention;

[0077] Figure 2 This is a flow chart of the topology structure identification method of Example 1 of the present invention. DETAILED DESCRIPTION

[0078] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0079] Example 1

[0080] See also Figure 1 As shown, the chemical intelligent desktop factory teaching system described in this embodiment includes a project creation module, a process construction module, a parameter setting module, a dynamic calculation module and a reverse optimization module; each module is connected by wired and / or wireless means to realize data transmission between modules.

[0081] Project creation module, used to create chemical projects.

[0082] Chemical projects include project components and thermodynamic methods;

[0083] Project components include chemical substances and their corresponding chemical properties; chemical substances such as water (H2O), ethanol (C2H5OH), benzene (H2O), etc.; chemical properties such as molecular weight, density, boiling point, melting point, etc.; project components are obtained by students from a pre-constructed database, which is pre-constructed by technicians in the field. The database contains more than 5,000 pure substances and more than 1,000 electrolyte ions and their corresponding chemical properties;

[0084] Thermodynamic methods include thermodynamic models and model parameters corresponding to thermodynamic models; thermodynamic models include heat conduction model, ideal gas model, phase change model, etc.; model parameters include heat flux density, thermal conductivity, temperature gradient, etc. corresponding to heat conduction model, pressure, volume, gas constant, etc. corresponding to ideal gas model, thermalization enthalpy, evaporation enthalpy, phase change temperature, etc. corresponding to phase change model; thermodynamic methods are obtained through students' own selection and setting.

[0085] The process building module is used to identify topological structures and build twin process flows in combination with chemical projects.

[0086] Methods for identifying topology include:

[0087] Obtain device connection relationships, build a corresponding adjacency matrix based on the device connection relationships, and identify the topological structure based on the adjacency matrix.

[0088] The equipment connection relationship is obtained through the chemical desktop factory. The chemical desktop factory includes freely assembled micro-factory equipment components. Students can assemble and disassemble them freely according to actual needs, thereby enhancing the experience of real construction and operation and increasing students' hands-on practice opportunities; the micro-factory equipment components are equipment components that are scaled proportionally based on the real factory. The chemical process flow can be restored on the micro-factory equipment components. Not only does it occupy a small area and have low environmental requirements, but it is also rechargeable and independently powered, which is safe and convenient; the micro-factory equipment components include chemical unit equipment components, valve components and display instrument components; chemical unit equipment such as distillation towers, centrifugal pumps, heat exchangers, etc., valves such as adjustable valves, ball valves, etc., display instruments such as pressure gauges, thermometers, flow meters, etc.; chemical unit equipment is connected by pipelines, and valves and display instruments are connected to pipelines or chemical unit equipment by magnetic suction or snaps.

[0089] Methods for constructing a corresponding adjacency matrix according to device connection relationships include:

[0090] Identify all chemical equipment in the equipment connection relationship, chemical equipment includes chemical unit equipment, valves and display instruments; mark each chemical equipment as a node, set different digital labels for each node in turn, and mark them as node labels. The range of node labels is [1, m], m is the number of nodes, and the node labels correspond to chemical equipment one by one; create an initial matrix, the size of the initial matrix is ​​m×m, and the value of each element in the initial matrix is ​​0; mark the elements in the initial matrix as P(a, b), P(a, b) represents the connection relationship between the a-th node and the b-th node, the connection relationship includes connected and unconnected, a∈[1, m], b∈[1, m]; combine all nodes to obtain c node sets, each node set includes two different nodes, and each node set is different,

[0091] According to the two nodes included in each node set and the two nodes corresponding to each element in the initial matrix, the node sets are matched one by one with the elements in the initial matrix; according to the device connection relationship, the two nodes in each node set are analyzed; if the two nodes are connected, the values ​​of the elements corresponding to the corresponding node set are updated to d, where d is an integer greater than 0; if the two nodes are not connected, the values ​​of the elements corresponding to the corresponding node set are not updated; the initial matrix after the updated values ​​is used as the adjacency matrix.

[0092] The steps to identify the topology from the adjacency matrix include:

[0093] Step A1: Mark the elements in the adjacency matrix that are not 0 as connection elements, regard the two nodes in each connection element as adjacent nodes, and mark the nodes in all connection elements as topological nodes; illustratively, a connection element includes the second node and the fourth node, then the second node is the adjacent node of the fourth node, and the fourth node is also the adjacent node of the second node;

[0094] Step A2: Randomly select a topological node that is not marked as a selected node and mark it as the initial node; starting from the initial node, explore all adjacent nodes of the initial node, and randomly select one of the adjacent nodes as the successor node, and mark the successor node as the selected node;

[0095] Step A3: Explore all adjacent nodes of the successor node, and randomly select one of the adjacent nodes that is not marked as a selected node as an update node, update the successor node to the update node, and mark the update node as a selected node;

[0096] Step A4: loop step A3 until all the adjacent nodes of the successor node have been marked as visited nodes, then the loop ends and goes to step A5;

[0097] Step A5: determine whether all adjacent nodes corresponding to each selected node have been marked as selected nodes. If not, proceed to step A6. If yes, obtain a connected component and proceed to step A8.

[0098] Step A6: trace back from the successor node to the predecessor node, explore all the adjacent nodes of the predecessor node, randomly select one of the adjacent nodes that is not marked as a selected node as the update node, update the successor node to the update node, and mark the update node as the selected node; the predecessor node is the node that selects the successor node as the update node; illustratively, when the successor node is the second node, the fourth node is selected as the update node, and the successor node is updated to the fourth node, then the second node is the predecessor node of the fourth node;

[0099] Step A7: looping steps A3 to A6 until all adjacent nodes corresponding to each selected node have been marked as selected nodes, obtaining a connected component, and proceeding to step A8;

[0100] Step A8: loop through steps A2 to A7 until all topological nodes are marked as selected nodes, and all connected components are combined into a topological structure.

[0101] It should be understood that the reason for tracing back from the successor node to the predecessor node is that, since the selection of the updated node in step 3 is random, the topological nodes that are not marked as selected nodes will be adjacent to the topological nodes marked as selected nodes, and the topological nodes that are not marked as selected nodes can only be found by tracing back to the predecessor node in sequence.

[0102] Methods for building a twin process flow include:

[0103] According to the node label, each node in the topological structure is mapped to the corresponding chemical equipment; according to the preset association set, each chemical equipment is associated with the corresponding thermodynamic model in the thermodynamic method. The association set is pre-set by technical personnel in this field according to actual conditions, and the association set includes chemical equipment and the thermodynamic model corresponding to the chemical equipment; illustratively, the distillation tower is associated with the phase change model, the centrifugal pump is associated with the fluid dynamics model, and the heat exchanger is associated with the heat conduction model; according to the model parameters corresponding to each thermodynamic model, the mathematical equation corresponding to each thermodynamic model is constructed; the mathematical equation corresponding to each thermodynamic model is associated with the chemical equipment corresponding to the corresponding thermodynamic model; according to the chemical equipment in the topological structure, as well as the thermodynamic model and mathematical equation corresponding to each chemical equipment, a twin process flow is constructed.

[0104] The parameter setting module is used to set parameters of chemical equipment in the twin process.

[0105] The steps for setting parameters for chemical equipment in the twin process flow include:

[0106] Step B1: setting equipment parameters of each chemical unit equipment in the chemical equipment;

[0107] The equipment parameters are the parameters corresponding to the operation of the chemical unit equipment; for example: flow, temperature, pressure, speed, etc.; the equipment parameters of each chemical unit equipment are manually set and obtained by students using mobile devices to scan the QR code of the corresponding chemical unit equipment.

[0108] Step B2: adjusting the valve opening of each valve in the chemical equipment;

[0109] The valve opening is the degree of opening and closing of each valve; the valve opening is manually adjusted by students, and the valve opening is obtained by a potentiometer position sensor or magnetostrictive displacement sensor installed on each valve;

[0110] Step B3: Bind each display instrument in the chemical equipment to the chemical unit equipment.

[0111] Bind each display instrument to the chemical unit equipment one by one, that is, one display instrument corresponds to one chemical unit equipment; students use mobile devices to scan the QR code corresponding to each chemical unit equipment to bind the chemical unit equipment to the display instrument.

[0112] The dynamic calculation module is used to perform dynamic calculations on the twin process flow and obtain calculation results.

[0113] The method for obtaining the calculation results is: taking the project components as the input data of the twin process flow, calling the mathematical equations corresponding to each chemical equipment in the twin process flow, and performing calculations through a preset back-end dynamic simulation engine to obtain the calculation results; calculation results such as reactant conversion rate, product yield, separation efficiency, product output, etc.; the back-end dynamic simulation engine is pre-set by technical personnel in this field according to actual conditions.

[0114] The reverse optimization module is used to obtain the target operation results and optimize the parameters of the chemical equipment in the twin process.

[0115] The target calculation results are obtained through manual input by students; it should be understood that when the obtained calculation results do not reach the ideal state, students need to master how to optimize the parameters of chemical equipment to obtain the calculation results under ideal conditions; therefore, when students input the target calculation results, the system can automatically optimize the parameters of chemical equipment in the twin process flow, thereby deepening students' understanding of the deep-level mechanisms of chemical processes and effectively combining theoretical knowledge with practical operations.

[0116] The steps for optimizing parameters of chemical equipment in twin process flow include:

[0117] Step C1: construct N sets of parameter sets, set different digital labels for each set of parameter sets, and mark them as parameter labels;

[0118] Step C2: construct a population S, which includes n individuals. Each individual in the population S corresponds to a parameter label one by one. The number of iterations t corresponding to the population S is 0, 1<n<N;

[0119] Step C3: define the iteration threshold w;

[0120] Step C4: Calculate the target value set corresponding to each individual and divide it into levels;

[0121] Step C5: Calculate the sparsity corresponding to each individual;

[0122] Step C6: Filter source individuals according to the hierarchical division and the sparsity corresponding to each individual;

[0123] Step C7: Perform crossover and mutation on the source individuals in turn to generate a subpopulation S;

[0124] Step C8: Merge the population S and the subpopulation S to obtain a merged population;

[0125] Step C9: Compare the number of iterations t with the iteration threshold w. If t≥w, proceed to step C10; if t<w, set t=t+1, select n individuals from the merged population, reconstruct the population S, and return to step C4;

[0126] Step C10: Filter out the best individual from the merged population, obtain the parameter label corresponding to the best individual, and mark it as the best label; optimize the parameters of the chemical equipment in the twin process according to the parameter set corresponding to the best label.

[0127] In the above step C1, the method for constructing N groups of parameter sets is: obtaining a parameter range, the parameter range includes an equipment parameter range and a valve opening range, the equipment parameter range includes a range of each equipment parameter corresponding to each chemical unit equipment in the chemical equipment, and the valve opening range includes a range of valve opening corresponding to each valve in the chemical equipment; the equipment parameter range is obtained by technicians in this field according to the technical parameters of the chemical unit equipment, and the valve opening range is obtained by technicians in this field according to the technical parameters of the valve; a value is randomly selected from each range in the parameter range to construct a group of parameter sets, and a total of N groups of parameter sets are constructed, and the N groups of parameter sets are all different.

[0128] In the above step C2, the expression of each individual in population S is: In the formula, is the i-th individual, P i is the random coefficient of the ith individual, P i ∈[0,1], i∈[1,n].

[0129] In the above step C3, the iteration threshold w is predefined by those skilled in the art according to actual conditions.

[0130] In the above step C4, the method for calculating the target value set corresponding to each individual is: obtain the parameter set corresponding to the parameter label of each individual, and mark it as the optimization set; according to each optimization set, set the parameters of the chemical equipment in the twin process flow in turn, and perform dynamic calculations to obtain the calculation results corresponding to each optimization set, and use them as the target value set of the corresponding individual, and use each value in the target value set as the target value.

[0131] The steps to perform the hierarchical division include:

[0132] Step C401: every two individuals in the population S are regarded as a group of individuals;

[0133] Step C402: according to the target value set corresponding to each individual, determine in turn whether there is an individual dominating another individual in each group of individuals, and obtain the determination result;

[0134] Step C403: according to the judgment result, count the dominated sets corresponding to each individual;

[0135] Step C404: All individuals that do not exist in the dominated set are divided into a level and marked as the current level, and the individuals in the current level are marked as the current individuals, and all current individuals in the dominated set are deleted;

[0136] Step C405: All individuals in the dominated set that only have the current individual are divided into a level and marked as an update level, the current level is updated to the update level, the current individual is updated to the individual in the update level, and the current individuals in all dominated sets are deleted;

[0137] Step C406: Loop step C405 until all individuals have completed the hierarchical division. The loop ends and digital labels are set in ascending order from the first to the last according to the order in which each level is marked as the current level. The digital labels are marked as level labels. The range of the level labels is [1, v], where v is the number of levels.

[0138] In the above step C402, the method for obtaining the judgment result includes:

[0139] Compare the target values ​​of the same type in the two target value sets corresponding to each group of individual sets;

[0140] like Then the jth individual dominates the ith individual; among them, is the i-th individual in the t-th iteration process, is the jth individual in the tth iteration process. The i-th individual and the j-th individual belong to the same individual set. is the kth target value in the target value set corresponding to the i-th individual, k∈[1,K], K is the number of target values ​​in the target value set, Indicates that for all target values ​​in the target value set, there exists It means that for the kth target value in the target value set, there exists ∩ means and, j∈[1,n], i≠j;

[0141] like Then the i-th individual and the j-th individual do not dominate each other.

[0142] In the above step C5, the expression of sparsity is: is the sparsity of the i-th individual, f k(max) is the kth target value with the largest value in all target value sets, f k (min) is the kth target value with the smallest value in the set of all target values.

[0143] In the above step C6, the method for screening source individuals is: preset sorting rules, and sort each individual according to the level label and sparsity corresponding to each individual, and generate an individual sorting table; according to the positive order of the individual sorting table, screen out the source individuals from all individuals. Individuals are collected and marked as source individuals; the sorting rule is: individuals with smaller hierarchical labels are sorted first, and individuals with larger sparsity are sorted first.

[0144] In the above step C7, the method of crossing the source individuals includes:

[0145] According to the positions of all source individuals in the individual sorting table, every two adjacent source individuals are taken as a group of crossover sets; a crossover coefficient is preset, and the crossover coefficient is preset by those skilled in the art according to actual conditions; two parameter labels corresponding to each group of crossover sets are added to obtain a sum label; two parameter labels corresponding to each group of crossover sets are subtracted and the absolute value is taken to obtain a difference label; each sum label is multiplied by 0.5, and the difference label is multiplied by the crossover coefficient to obtain a crossover label corresponding to each group of crossover sets; according to the crossover label, the corresponding crossover individual is obtained, and the crossover individual is the individual obtained after crossing the source individuals;

[0146] Methods for mutating source individuals include:

[0147] The variation range is preset, and the variation range is preset by technical personnel in this field according to actual conditions; the crossover label corresponding to the crossover individual is multiplied by the variation range, and then added with a random number in the standard normal distribution to obtain the variation label corresponding to each crossover individual; according to each variation label, the corresponding crossover individual is mutated to obtain the variation individual corresponding to each crossover individual.

[0148] In the above step C10, the method for selecting the best individual from the combined population includes:

[0149] A preset weight set, the weight set includes a weight coefficient corresponding to each target value in the target value set, and the weight set is pre-set by technical personnel in this field according to actual conditions; according to the weight set, the weight coefficient corresponding to each target value in the target value set is obtained, and each target value corresponding to each individual in the merged population is multiplied by the corresponding weight coefficient to obtain the weight value; the weight values ​​corresponding to each individual in the merged population are added in turn to obtain the total weight value; the total weight value of each individual in the merged population is compared respectively, and the individual with the largest total weight value in the merged population is marked as the best individual.

[0150] This embodiment effectively solves the problems of insufficient understanding of equipment operation and potential safety hazards in traditional teaching through the integration of project creation, process construction, parameter setting, dynamic calculation and reverse optimization modules. By using digital twin technology to build a visual virtual process flow, students can enhance their understanding of theoretical knowledge and process mechanisms, and improve their practical skills and problem-solving abilities by independently adjusting equipment parameters, observing process operation results and performing reverse optimization. This not only provides an intuitive teaching experience and promotes students' understanding of complex chemical processes, but also enhances students' practical ability and innovative consciousness through dynamic calculation and parameter optimization functions, effectively solving the problems of abstractness, potential safety hazards and single functions in traditional teaching, and providing innovative solutions for chemical engineering professional teaching practice.

[0151] Example 2

[0152] The present application also provides an electronic device. The electronic device may include one or more processors and one or more memories. The memories store computer-readable codes, and when the computer-readable codes are run by the one or more processors, they may execute a chemical intelligent desktop factory teaching system as described above.

[0153] The method or system according to the implementation mode of the present application can also be implemented with the help of the architecture of the electronic device shown in the present application. The electronic device may include a bus, one or more CPUs, ROM, RAM, a communication port connected to a network, input / output, a hard disk, etc. A storage device in the electronic device, such as a ROM or a hard disk, can store a chemical intelligent desktop factory teaching system provided by the present application. Furthermore, the electronic device may also include a user interface. Of course, the architecture shown in the present application is only exemplary. When implementing different devices, one or more components in the electronic device shown in the present application may be omitted according to actual needs.

[0154] Example 3

[0155] One embodiment of the present application discloses a computer-readable storage medium. Computer-readable instructions are stored on the computer-readable storage medium. When the computer-readable instructions are executed by the processor, a chemical intelligent desktop factory teaching system according to the embodiment of the present application described with reference to the above figures can be executed. The storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0156] In addition, according to the implementation of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the present application provides a non-transitory machine-readable storage medium, which stores machine-readable instructions, and the machine-readable instructions can be executed by a processor to execute instructions corresponding to the method steps provided in the present application, for example: a chemical intelligent desktop factory teaching system. When the computer program is executed by a central processing unit (CPU), the above functions defined in the method of the present application are executed.

[0157] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0158] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A chemical industry intelligent desktop factory teaching system, characterized in that: include: Project creation module, used to create chemical projects; The process building module is used to identify topological structures and build twin process flows in combination with chemical projects; Parameter setting module, used to set parameters of chemical equipment in the twin process; Dynamic calculation module, used to perform dynamic calculation on the twin process flow and obtain calculation results; The reverse optimization module is used to obtain the target operation results and optimize the parameters of the chemical equipment in the twin process.

2. A chemical industry intelligent desktop factory teaching system according to claim 1, characterized in that: The chemical project includes project components and thermodynamic methods; the project components include chemical substances and chemical properties corresponding to the chemical substances; the thermodynamic method includes a thermodynamic model and model parameters corresponding to the thermodynamic model; The method for identifying a topological structure comprises: The device connection relationship is obtained, the corresponding adjacency matrix is ​​constructed according to the device connection relationship, and the topological structure is identified according to the adjacency matrix; the device connection relationship is obtained through the chemical desktop factory, the chemical desktop factory includes micro-factory equipment components, and the micro-factory equipment components include chemical unit equipment components, valve components and display instrument components.

3. A chemical industry intelligent desktop factory teaching system according to claim 2, characterized in that: The method for constructing a corresponding adjacency matrix according to the device connection relationship includes: Identify all chemical equipment in the equipment connection relationship, chemical equipment includes chemical unit equipment, valves and display instruments; mark each chemical equipment as a node, set different digital labels for each node in turn, and mark them as node labels. The range of node labels is [1, m], m is the number of nodes, and the node labels correspond to chemical equipment one by one; create an initial matrix, the size of the initial matrix is ​​m×m, and the value of each element in the initial matrix is ​​0; mark the elements in the initial matrix as P(a, b), P(a, b) represents the connection relationship between the a-th node and the b-th node, the connection relationship includes connected and unconnected, a∈[1, m], b∈[1, m]; combine all nodes to obtain c node sets, each node set includes two different nodes, and each node set is different, According to the two nodes included in each node set and the two nodes corresponding to each element in the initial matrix, the node sets are matched one by one with the elements in the initial matrix; according to the device connection relationship, the two nodes in each node set are analyzed; if the two nodes are connected, the values ​​of the elements corresponding to the corresponding node set are updated to d, where d is an integer greater than 0; if the two nodes are not connected, the values ​​of the elements corresponding to the corresponding node set are not updated; the initial matrix after the updated values ​​is used as the adjacency matrix.

4. A chemical intelligent desktop factory teaching system according to claim 3, characterized in that: The step of identifying the topological structure according to the adjacency matrix comprises: Step A1: Mark the elements in the adjacency matrix that are not 0 as connection elements, regard the two nodes in each connection element as adjacent nodes, and mark the nodes in all connection elements as topological nodes; Step A2: randomly select a topological node that is not marked as a selected node and mark it as the initial node; starting from the initial node, explore all adjacent nodes of the initial node, and randomly select one of the adjacent nodes as the successor node, and mark the successor node as the selected node; Step A3: Explore all adjacent nodes of the successor node, and randomly select one of the adjacent nodes that is not marked as a selected node as an update node, update the successor node to the update node, and mark the update node as a selected node; Step A4: loop step A3 until all the adjacent nodes of the successor node have been marked as visited nodes, then the loop ends and goes to step A5; Step A5: determine whether all adjacent nodes corresponding to each selected node have been marked as selected nodes. If not, proceed to step A6. If yes, obtain a connected component and proceed to step A8. Step A6: trace back from the successor node to the predecessor node, explore all the adjacent nodes of the predecessor node, randomly select one of the adjacent nodes that is not marked as the selected node as the update node, update the successor node to the update node, and mark the update node as the selected node; the predecessor node is the node that selects the successor node as the update node; Step A7: looping steps A3 to A6 until all adjacent nodes corresponding to each selected node have been marked as selected nodes, obtaining a connected component, and proceeding to step A8; Step A8: loop through steps A2 to A7 until all topological nodes are marked as selected nodes, and all connected components are combined into a topological structure.

5. A chemical industry intelligent desktop factory teaching system according to claim 4, characterized in that: The method for building a twin process flow includes: According to the node label, each node in the topological structure is mapped to the corresponding chemical equipment; according to the preset association set, each chemical equipment is associated with the corresponding thermodynamic model in the thermodynamic method, and the association set includes chemical equipment and the thermodynamic model corresponding to the chemical equipment; according to the model parameters corresponding to each thermodynamic model, the mathematical equation corresponding to each thermodynamic model is constructed; the mathematical equation corresponding to each thermodynamic model is associated with the chemical equipment corresponding to the corresponding thermodynamic model; according to the chemical equipment in the topological structure, as well as the thermodynamic model and mathematical equation corresponding to each chemical equipment, a twin process flow is built.

6. A chemical industry intelligent desktop factory teaching system according to claim 5, characterized in that: The step of setting parameters for the chemical equipment in the twin process flow comprises: Step B1: setting equipment parameters of each chemical unit equipment in the chemical equipment; Equipment parameters are the parameters corresponding to the operation of chemical unit equipment; Step B2: adjusting the valve opening of each valve in the chemical equipment; The valve opening is the degree of opening and closing of each valve; Step B3: Bind each display instrument in the chemical equipment to the chemical unit equipment; Bind each display instrument to a chemical unit device one by one, that is, one display instrument corresponds to one chemical unit device; The method for obtaining the calculation results is: using the project components as input data of the twin process flow, calling the mathematical equations corresponding to each chemical equipment in the twin process flow, performing calculations through a preset back-end dynamic simulation engine, and obtaining the calculation results.

7. A chemical industry intelligent desktop factory teaching system according to claim 6, characterized in that: The step of optimizing parameters of chemical equipment in the twin process flow comprises: Step C1: construct N sets of parameter sets, set different digital labels for each set of parameter sets, and mark them as parameter labels; Step C2: construct a population S, which includes n individuals. Each individual in the population S corresponds to a parameter label one by one. The number of iterations t corresponding to the population S is 0, 1<n<N; Step C3: define the iteration threshold w; Step C4: Calculate the target value set corresponding to each individual and divide it into levels; Step C5: Calculate the sparsity corresponding to each individual; Step C6: Filter source individuals according to the hierarchical division and the sparsity corresponding to each individual; Step C7: Perform crossover and mutation on the source individuals in turn to generate a subpopulation S; Step C8: Merge the population S and the subpopulation S to obtain a merged population; Step C9: Compare the number of iterations t with the iteration threshold w. If t≥w, proceed to step C10; if t<w, set t=t+1, select n individuals from the merged population, reconstruct the population S, and return to step C4; Step C10: Filter out the best individual from the merged population, obtain the parameter label corresponding to the best individual, and mark it as the best label; optimize the parameters of the chemical equipment in the twin process according to the parameter set corresponding to the best label.

8. The chemical industry intelligent desktop factory teaching system according to claim 7 is characterized in that: In the step C1, the method for constructing N sets of parameter sets is: obtaining a parameter range, the parameter range includes an equipment parameter range and a valve opening range, the equipment parameter range includes a range of each equipment parameter corresponding to each chemical unit equipment in the chemical equipment, and the valve opening range includes a range of valve opening corresponding to each valve in the chemical equipment; randomly selecting a value from each range in the parameter range to construct a set of parameter sets, and constructing a total of N sets of parameter sets, and the N sets of parameter sets are all different; In step C2, the expression of each individual in population S is: In the formula, is the i-th individual, P i is the random coefficient of the ith individual, P i ∈[0,1], i∈[1,n]; In step C4, the method for calculating the target value set corresponding to each individual is as follows: obtaining the parameter set corresponding to the parameter label corresponding to each individual and marking it as an optimization set; according to each optimization set, setting parameters for the chemical equipment in the twin process flow in turn, and performing dynamic calculations, obtaining the calculation results corresponding to each optimization set, and using them as the target value set of the corresponding individual, and using each value in the target value set as the target value; The steps to perform the hierarchical division include: Step C401: every two individuals in the population S are regarded as a group of individuals; Step C402: according to the target value set corresponding to each individual, determine in turn whether there is an individual dominating another individual in each group of individuals, and obtain the determination result; Step C403: according to the judgment result, count the dominated sets corresponding to each individual; Step C404: All individuals that do not exist in the dominated set are divided into a level and marked as the current level, and the individuals in the current level are marked as the current individuals, and all current individuals in the dominated set are deleted; Step C405: All individuals in the dominated set that only have the current individual are divided into a level and marked as an update level, the current level is updated to the update level, the current individual is updated to the individual in the update level, and the current individuals in all dominated sets are deleted; Step C406: Loop step C405 until all individuals have completed the hierarchical division. The loop ends and digital labels are set in ascending order from the first to the last according to the order in which each level is marked as the current level. The digital labels are marked as level labels. The range of the level labels is [1, v], where v is the number of levels.

9. A chemical industry intelligent desktop factory teaching system according to claim 8, characterized in that: In step C402, the method for obtaining the judgment result includes: Compare the target values ​​of the same type in the two target value sets corresponding to each group of individual sets; like Then the jth individual dominates the ith individual; among them, is the i-th individual in the t-th iteration process, is the jth individual in the tth iteration process. The i-th individual and the j-th individual belong to the same individual set. is the kth target value in the target value set corresponding to the i-th individual, k∈[1,K], K is the number of target values ​​in the target value set, Indicates that for all target values ​​in the target value set, there exists It means that for the kth target value in the target value set, there exists ∩ means and, j∈[1,n], i≠j; like Then the i-th individual and the j-th individual do not dominate each other.

10. A chemical intelligent desktop factory teaching system according to claim 9, characterized in that: In step C5, the expression of sparsity is: is the sparsity of the i-th individual, f k (max) is the kth target value with the largest value in all target value sets, f k (min) is the kth target value with the smallest value in the set of all target values; In step C6, the method for screening source individuals is: presetting a sorting rule, and combining the level label and sparsity corresponding to each individual, sorting each individual to generate an individual sorting table; According to the positive order of the individual sorting table, filter out from all individuals Individuals are collected and marked as source individuals; the sorting rules are as follows: individuals with smaller hierarchical labels are sorted first, and individuals with larger sparsity are sorted first; In step C7, the method of crossing the source individuals includes: According to the positions of all source individuals in the individual sorting table, every two adjacent source individuals are regarded as a group of crossover sets; the crossover coefficient is preset, and the two parameter labels corresponding to each crossover set are added to obtain the sum label; the two parameter labels corresponding to each crossover set are subtracted and the absolute value is taken to obtain the difference label; each sum label is multiplied by 0.5, and the difference label is added and multiplied by the crossover coefficient to obtain the crossover label corresponding to each crossover set; according to the crossover label, the corresponding crossover individual is obtained, and the crossover individual is the individual obtained after crossing the source individuals; Methods for mutating source individuals include: Preset the variation range, multiply the crossover label corresponding to the crossover individual by the variation range, and add the random number in the standard normal distribution to obtain the variation label corresponding to each crossover individual; according to each variation label, mutate the corresponding crossover individual to obtain the variation individual corresponding to each crossover individual; In step C10, the method for selecting the best individual from the combined population includes: A weight set is preset, and the weight set includes a weight coefficient corresponding to each target value in the target value set; according to the weight set, the weight coefficient corresponding to each target value in the target value set is obtained, and each target value corresponding to each individual in the merged population is multiplied by the corresponding weight coefficient to obtain the weight value; the weight values ​​corresponding to each individual in the merged population are added in sequence to obtain the total weight value; the total weight value of each individual in the merged population is compared respectively, and the individual with the largest total weight value in the merged population is marked as the best individual.

Images