A method and apparatus for optimizing the production of light hydrocarbon components of hydrocarbons

Abstract

The application discloses a kind of production and processing optimization method and device of hydrocarbon light hydrocarbon component, the optimization method includes: obtaining the data of all light hydrocarbon components of hydrocarbon, based on the molecular mapping model constructed in advance, the key component corresponding to each light hydrocarbon component is analyzed, and the kind and content of each key component are determined;Matched unit process is extracted from the database constructed in advance, and the connection relationship of each unit process is determined, to obtain the superstructure diagram;Product data is obtained using the product prediction model trained in advance, to construct unit process model;Combining the unit process model and superstructure diagram corresponding to each unit process, to obtain the superstructure network model;Based on the target benefit function and the constraint condition set containing relaxation variable constructed in advance, combined with the superstructure network model, to obtain the optimal solution that satisfies the constraint condition and makes the target benefit function reach maximum value.Formulate the optimal production scheme, improve production efficiency, reduce production cost.

Description

Technical Field

[0001] This invention relates to the field of petrochemical technology, and in particular to an optimized method and apparatus for the production and processing of light hydrocarbon components of hydrocarbons. Background Technology

[0002] Hydrocarbons, such as C4 to C8 compounds, are extremely important chemical substances in the field of chemistry. They play an irreplaceable role in many aspects of industrial production, energy supply, and daily life. The intermediate and final products obtained from their refined transformation and separation processes have extremely wide applications. These intermediate products can serve as high-quality raw materials for other chemical reactions, further synthesizing more compounds with special properties; while the final products are widely used in many industries such as fuels, solvents, plastics, and rubber, providing a solid material foundation for the development of modern industry and the improvement of people's quality of life.

[0003] However, the current situation regarding the production and processing of various light hydrocarbon components in hydrocarbons is far from optimistic. The processes are not only numerous but also extremely complex, requiring precise control at every stage. Even slight errors can lead to decreased product quality or reduced production efficiency. Furthermore, the complexity of the processes significantly increases the difficulty of resource allocation, necessitating substantial investment of human, material, and financial resources to ensure the smooth operation of each stage. Therefore, how to quickly and accurately formulate production plans that maximize efficiency has become a critical challenge for the industry, impacting the survival and development of enterprises and the progress of the entire sector. Summary of the Invention

[0004] In order to develop a production plan that can achieve the greatest benefits, thereby improving production efficiency, reducing production costs and improving product quality, this invention provides a method and apparatus for optimizing the production and processing of light hydrocarbon components.

[0005] In a first aspect, embodiments of the present invention provide an optimized method for the production and processing of light hydrocarbon components, comprising:

[0006] Data on all light hydrocarbon components of hydrocarbons are obtained, and the key components corresponding to each light hydrocarbon component are analyzed based on a pre-constructed molecular mapping model, and the types and contents of each key component are determined.

[0007] Based on the type and content of each key component, matching unit processes are extracted from a pre-built database, and the connection relationship of each unit process is determined to obtain a superstructure diagram.

[0008] For each of the aforementioned unit processes, the corresponding raw material data is extracted from the database, and the product data is obtained using a pre-trained product prediction model to construct a unit process model.

[0009] By combining the unit process models corresponding to each unit process and the superstructure diagram, a superstructure network model is obtained;

[0010] Based on the pre-constructed objective benefit function and the set of constraints including slack variables, the solution is obtained by combining the superstructure network model to obtain the optimal solution that satisfies the constraints and maximizes the objective benefit function.

[0011] Optionally, the step of extracting matching unit processes from a pre-built database based on the type and content of each key component, and determining the connection relationships of each unit process to obtain a superstructure diagram, includes:

[0012] For each of the key components, matching unit processes are extracted from a pre-built database based on the type and content of the key components, and the connection relationship between each of the unit processes is determined to obtain the generation and processing flow chart corresponding to the key component.

[0013] By integrating the process flow diagrams corresponding to all the key components, a superstructure diagram is obtained.

[0014] Optionally, the step of solving the problem based on a pre-constructed objective benefit function and a set of constraints including slack variables, combined with the superstructure network model, to obtain the optimal solution that satisfies the constraints and maximizes the objective benefit function includes:

[0015] Based on the investment parameters and the raw material and product data of each unit process, the target benefit function is obtained;

[0016] Based on the relaxation variable parameters and the key component parameters, reaction parameters, raw material data and product data of each unit process, a set of constraints is obtained.

[0017] The objective benefit function, the set of constraints, and the superstructure network model are solved using a mixed-integer nonlinear algorithm to obtain the optimal solution that satisfies the constraints and maximizes the objective benefit function.

[0018] Optionally, the unit process includes a product flow and a feed flow;

[0019] The type of unit process includes at least one: process flow, mixer and splitter;

[0020] The raw material data corresponding to the process includes at least the total amount of feed stream, the unit cost of feed stream, and the unit utility cost of feed stream;

[0021] The product data corresponding to the process includes at least the total quantity of the product stream and the unit price of the product stream;

[0022] The product data corresponding to the diverter includes at least the total quantity and unit price of the product stream;

[0023] The investment parameters include at least the annualized rate of return on investment;

[0024] The objective benefit function, derived based on investment parameters and raw material and product data for each unit process, includes:

[0025] Based on the annualized rate of investment, the total volume and unit price of the product stream in each of the aforementioned processes, the total volume and unit cost of the feed stream in each of the aforementioned processes, the unit utility cost of the feed stream in each of the aforementioned processes, and the total volume and unit price of the product stream in each of the aforementioned distributors, the following objective benefit function is obtained:

[0026]

[0027] Where Z represents the return on investment per unit, i represents the feed flow, j represents the product flow, p represents the process flow, s represents the distributor, and m represents the mixer; W j,p P represents the total product flow from the p-th process step; j,p W represents the unit price of the product flow from the p-th process step; j,s P represents the total product flow from the s-th splitter; j,s W represents the unit price of the product stream from the s-th splitter; i,p P represents the total feed flow of the p-th process; i,p UC represents the unit cost of the feed flow in the p-th process; p The ACCR represents the unit utility cost of the feed flow in the p-th process; CC represents the annualized rate of return on investment; p This represents the unit investment cost of the p-th process.

[0028] Optionally, the product data corresponding to the process may also include the flow rate and separation and recovery rate of each component in the product stream;

[0029] The corresponding raw material data for the process also includes the flow rates of each component in the feed stream and the flow rates of key components.

[0030] The reaction parameters should include at least the molecular weight of each component during the reaction, the molecular weight of the key component during the reaction, and the conversion rate.

[0031] The key component parameters include at least the reaction selectivity coefficient and the reaction stoichiometry coefficient of the key component;

[0032] The relaxation variable parameters include at least a first relaxation variable and a second relaxation variable;

[0033] The constraint set, based on the relaxation variable parameters and the key component parameters, reaction parameters, raw material data, and product data of each unit process, is obtained, including:

[0034] For each of the aforementioned process flows, based on the flow rates and separation / recovery rates of each component in the product stream, the flow rates of each component in the feed stream and the flow rates of key components, the molecular weights of each component during the reaction, the molecular weights and conversion rates of key components during the reaction, and the reaction selectivity and stoichiometric coefficients of key components, combined with the first relaxation variable and the second relaxation variable, a set of constraints containing at least the following first constraint conditions is obtained:

[0035]

[0036] Among them, W j,k,p R represents the flow rate of the k-th component in the product stream of the p-th process; j,k,p W represents the separation and recovery rate of the k-th component in the product stream of the p-th process; i,k,p M represents the flow rate of the k-th component in the feed stream of the p-th process; k,p,r M represents the molecular weight of the k-th component during the p-th process reaction; kB,p,r X represents the molecular weight of the key component in the p-th process reaction; kB,p S represents the conversion rate of the key component kB in the p-th process reaction; kB,p,r V represents the reaction selectivity coefficient of the key component kB in the p-th process; kB,p,r W represents the stoichiometric coefficient of the critical component kB in the p-th process; i,kB,p S represents the flow rate of the key component kB in the feed stream of the p-th process; 1p and S 2p Let represent the first slack variable and the second slack variable, respectively.

[0037] Optionally, the relaxation variable parameters also include a preset upper limit value for the relaxation variables and a binary variable corresponding to each of the process steps;

[0038] After obtaining a set of constraints that includes at least the first constraint, the following is also included:

[0039] Based on the upper limit of the relaxation variables and the binary variables corresponding to each process step, a set of constraints is obtained that includes at least the following second constraint:

[0040] S 1p +S 2p ≤M×(1-b p )

[0041] Where M represents the upper limit of the sum of slack variables, and b is the upper limit of the slack variables. p Let represent the binary variable corresponding to the p-th process.

[0042] Optionally, the investment parameters may also include the variable investment coefficient and fixed investment cost coefficient for each of the aforementioned processes;

[0043] The raw material data corresponding to the process also includes the feed flow rate;

[0044] After obtaining a set of constraints that includes at least the first constraint, the following is also included:

[0045] Based on the unit investment cost and feed throughput of each process, and the fixed investment cost, a set of constraints including the following third constraint is obtained:

[0046]

[0047] Among them, C 1p α represents the variable investment coefficient for the p-th process; p W represents the fixed investment coefficient for the p-th process; i,p n represents the flow rate of feed i in the p-th process; n represents W. i,p The number of index relationships for investment.

[0048] Optionally, the step of solving the objective benefit function, the constraint set, and the superstructure network model using a mixed-integer nonlinear algorithm to obtain the optimal solution that satisfies the constraints and maximizes the objective benefit function includes:

[0049] By combining the objective benefit function, the set of constraints, and the superstructure network model, a mathematical model is obtained.

[0050] The initial values ​​of the preset variables in the mathematical model are set to zero to obtain a feasible solution, and the conditions for the feasible solution are determined.

[0051] The conditions for feasible solutions are divided into mixed integer linear problems and mixed integer nonlinear problems, and the corresponding first optimization algorithm and second optimization algorithm are determined respectively.

[0052] The mathematical model is iteratively calculated by combining the first optimization algorithm and the second optimization algorithm to obtain the optimal solution that satisfies the constraints and maximizes the objective benefit function.

[0053] Secondly, embodiments of the present invention provide an optimized apparatus for the production and processing of light hydrocarbon components, comprising:

[0054] The data acquisition module is used to acquire data on all light hydrocarbon components of hydrocarbons, analyze the key components corresponding to each light hydrocarbon component based on a pre-built molecular mapping model, and determine the type and content of each key component.

[0055] The mapping module is used to extract matching unit processes from a pre-built database based on the type and content of each key component, and to determine the connection relationship of each unit process to obtain a superstructure diagram.

[0056] The first model building module is used to extract the corresponding raw material data from the database for each unit process, obtain the product data using a pre-trained product prediction model, and build a unit process model.

[0057] The second model construction module is used to combine the unit process model corresponding to each unit process and the superstructure diagram to obtain the superstructure network model;

[0058] The calculation module is used to solve the superstructure network model based on a pre-constructed objective benefit function and a set of constraints including slack variables, to obtain the optimal solution that satisfies the constraints and maximizes the objective benefit function.

[0059] Thirdly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the optimized production and processing method for light hydrocarbon components of hydrocarbons as described in the first aspect.

[0060] Fourthly, embodiments of the present invention provide an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0061] Memory, used to store computer programs;

[0062] The processor, when executing a program stored in memory, implements the optimized method for the production and processing of light hydrocarbon components as described in the first aspect.

[0063] Fifthly, embodiments of the present invention provide a computer program product containing instructions that, when run on a computer device, cause the computer device to execute the production and processing optimization method for light hydrocarbon components as described in the first aspect.

[0064] The beneficial effects of the above-mentioned technical solutions provided in the embodiments of the present invention include at least the following:

[0065] This invention provides a method for producing and processing light hydrocarbon components. A superstructure network model is constructed to represent all the technological processes involved in producing light hydrocarbon components. The superstructure network model, objective benefit function, and constraint set are solved, and relaxation variables are introduced to quickly obtain the optimal solution. This optimal solution provides the best technological process, operating parameters, and resource allocation scheme for the production and processing of light hydrocarbon components, aiming to formulate a production plan that maximizes benefits. This helps to improve production efficiency, reduce production costs, and enhance product quality.

[0066] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings.

[0067] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0068] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0069] Figure 1 A schematic flowchart illustrating an optimized production and processing method for light hydrocarbon components of hydrocarbons provided in an embodiment of the present invention;

[0070] Figure 2 A schematic diagram of a C4 superstructure network model provided in an embodiment of the present invention;

[0071] Figure 3 A schematic diagram of a production and processing optimization device for light hydrocarbon components of hydrocarbons provided in an embodiment of the present invention;

[0072] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0073] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0074] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," "outer," "far," "near," "front," and "rear," etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the accompanying drawings and are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0075] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0076] The inventors discovered that hydrocarbons (such as C4-C8) are very important chemical substances, and the intermediate and final products obtained during their conversion and separation have a wide range of applications. However, the current production and processing of various light hydrocarbon components in hydrocarbons involves numerous and complex processes, making resource allocation difficult. Therefore, how to quickly formulate a production plan that maximizes efficiency has become an urgent problem to be solved.

[0077] To address the aforementioned issues, the inventors developed a method and apparatus for optimizing the production and processing of light hydrocarbon components. By constructing a superstructure network model, objective benefit function, and constraint set that can represent all the process flows of light hydrocarbon components, and by introducing slack variables into the constraint set, the optimal solution can be obtained quickly, thereby formulating a production plan that can achieve the maximum benefit.

[0078] First, some nouns or terms that appear in the description of the embodiments of this application shall be interpreted as follows:

[0079] Hydrocarbons, also known as hydrocarbons, can be classified according to the number of carbon atoms. The hydrocarbons in this embodiment include at least one of the following: C4 compounds, C5 compounds, C6 compounds, C7 compounds, and C8 compounds.

[0080] Example 1

[0081] See Figure 1This embodiment proposes an optimized method for the production and processing of light hydrocarbon components, which may specifically include the following steps:

[0082] Step S1: Obtain data on all light hydrocarbon components of hydrocarbons, analyze the key components corresponding to each light hydrocarbon component based on the pre-constructed molecular mapping model, and determine the type and content of each key component.

[0083] Step S2: Based on the type and content of each key component, extract matching unit processes from the pre-constructed database, determine the connection relationship of each unit process, and obtain the superstructure diagram.

[0084] Step S3: For each unit process, extract the corresponding raw material data from the database, obtain the product data using the pre-trained product prediction model, and construct the unit process model.

[0085] Step S4: Combine the unit process model and superstructure diagram corresponding to each unit process to obtain the superstructure network model;

[0086] Step S5: Based on the pre-constructed objective benefit function and the set of constraints including slack variables, the solution is obtained by combining the superstructure network model to obtain the optimal solution that satisfies the constraints and maximizes the objective benefit function.

[0087] To provide a clearer explanation of the optimized production and processing methods for the aforementioned light hydrocarbon components, each step will be described in detail below.

[0088] In step S1 above, the molecular mapping model includes a key component composition library and a mapping relationship model between light hydrocarbon components and key components. The key component composition library includes conventional real molecules and virtual lumped molecules of light hydrocarbon components. Conventional real molecules are specific molecules actually present in the light hydrocarbon components, while virtual lumped molecules are obtained by aggregating molecules with similar properties to simplify calculations and analysis. Both conventional real molecules and virtual lumped molecules are represented using existing structure-guided lumped methods to accurately describe the structural features and chemical properties of the molecules. The key component composition library constructed using the structure-guided lumped method forms a standardized characterization system, effectively improving the development efficiency of process conversion and separation models.

[0089] Because light hydrocarbon components contain numerous molecular components—for example, C4 olefins generally include 1-butene, cis-2-butene, trans-2-butene, and isobutene, while C5 and C6 olefins contain even more—it is extremely difficult to completely distinguish each molecule in actual processing due to the large variety and similar properties of the molecules. Therefore, direct analysis of all molecules is extremely challenging. Thus, we must statistically analyze the key components within light hydrocarbon components, establish a key component library, and develop process conversion and separation models for these key components. Using a pre-constructed molecular mapping model, the types and contents of key components are calculated based on the mapping relationship model using light hydrocarbon component data. For example, butadiene can be mapped to three key components: cis-2-butene, trans-2-butene, and isobutene, and the content of each key component is determined. By decomposing light hydrocarbon components into key components through the molecular mapping model, complex systems can be simplified to a small number of representative components, significantly reducing analytical complexity.

[0090] In step S2 above, the specific process of extracting matching unit processes from a pre-built database based on the type and content of each key component, and determining the connection relationship of each unit process to obtain the superstructure diagram may include the following steps:

[0091] Step S201: For each key component, based on the type and content of the key component, extract the matching unit process from the pre-built database, determine the connection relationship between each unit process, and obtain the generation process flow chart corresponding to the key component.

[0092] In step S201 above, the matching logic can employ category matching, that is, filtering unit processes from the database that match the molecular formula or functional group (such as double bond, branched structure) of the key component. A unit process includes a product stream and a feed stream, and the type of unit process includes at least one: process flow, mixer, and splitter. Adjacent unit processes are matched based on the feed and product streams of the unit processes. For example, the C5 fraction, a byproduct of the MTBE unit, can be connected to the C5 isomerization unit. Generating a processing flow chart mainly refers to the conversion and separation processes of light hydrocarbon components, including mature industrialized processes and publicly available, non-industrialized technologies. The production processing flow chart is the process from feed to intermediate products according to the process flow.

[0093] In another embodiment, the database described above also pre-stores the physicochemical properties and market information corresponding to each light hydrocarbon component in the hydrocarbon compound.

[0094] Specifically, the first step is to establish a complete database of hydrocarbon molecules within a specific category that already have application value and market demand. For example, this could include a complete database of alkanes, cycloalkanes, alkenes, alkynes, and their oxygen-, nitrogen-, and halogen-containing derivatives within the C4 range; a complete database of n- / isopentanes, pentenes, cyclopentanes, and their C5 alcohols, aldehydes, and ethers within the C5 range; a complete database of n- / isohexanes, hexenes, cyclohexanes, cyclohexenes, benzenes, and their C6 alcohols, aldehydes, and ethers within the C6 range; a complete database of C7 alkanes, cycloalkanes, alkenes, aromatics, and their alcohols, aldehydes, and ethers within the C7 range; and a complete database of C8 alkanes, cycloalkanes, alkenes, aromatics, and their alcohols, aldehydes, and ethers within the C8 range. The database should include the corresponding physicochemical properties of the hydrocarbon molecules, market information, and conversion and separation production processes, including both industrialized mature processes and non-industrialized technologies.

[0095] It should be noted that the acquisition, storage and application of the physicochemical properties of hydrocarbon molecules, market information and conversion and separation production processes involved in the technical solution of this invention all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0096] Step S202: Integrate the generated process flow diagrams corresponding to all key components to obtain a superstructure diagram.

[0097] In step S202 above, the production and processing flowcharts corresponding to all key components are integrated together, common unit processes are merged, and logistics are merged to form a superstructure diagram with cross-carbon number composition.

[0098] In this embodiment, process flow diagrams for the generation and processing of key components of each type of hydrocarbon are obtained. For example, process flow diagrams for the conversion and separation of key components in the C4 range (such as alkanes, cycloalkanes, alkenes, alkynes and their oxygen-, nitrogen-, halogen-containing derivatives) are obtained; process flow diagrams for the conversion and separation of key components in the C5 range (such as n / isopentane, pentene, cyclopentane, and C5 alcohols, aldehydes, ethers and other derivatives) are obtained; process flow diagrams for the conversion and separation of key components in the C6 range (such as n / isohexane, hexene, cyclohexane, cyclohexene, benzene and C6 alcohols, aldehydes, ethers and other derivatives) are obtained; process flow diagrams for the conversion and separation of key components in the C7 range (such as C7 alkanes, cycloalkanes, alkenes, aromatics and their alcohols, aldehydes, ethers and other derivatives) are obtained; and process flow diagrams for the conversion and separation of key components in the C8 range (such as C8 alkanes, cycloalkanes, alkenes, aromatics and their alcohols, aldehydes, ethers and other derivatives) are obtained. Then, based on the conversion and separation processes of each key component, a superstructure diagram was constructed that represents the overall process options for the conversion and separation of all C4 / C5 / C6 / C7 / C8 light hydrocarbons. The superstructure diagram illustrates the process from feed to intermediate and final products according to the process flow. The superstructure diagram visually demonstrates the interactions and flow sequence between each unit process, providing a clear framework for subsequent process optimization and overall process design.

[0099] In step S3 above, the raw material data includes the molecular composition and processing quantity of the raw materials. For each unit process, the corresponding raw material data is extracted from the database. Based on the molecular composition of the raw materials, a pre-trained product prediction model is used to predict multiple products obtained under preset reaction conditions, and the molecular composition and yield of each product are determined as product data to construct a unit process model. Here, the pre-trained product prediction model includes a set of reaction rules and a reaction rate algorithm. The set of reaction rules includes conversion rules between multiple molecular compositions, and the reaction rate algorithm is a method for calculating the conversion rate of raw material molecules based on molecular composition conversion rules. The conversion rate calculation method includes the basic conversion rate and the molecular composition structure influence factor. Here, the training method of the product prediction model can refer to existing technologies. For example, a physical guided neural network (integrating reaction kinetic equations) can be constructed and trained based on the acquired raw material data, process parameters, and product data. A portion of experimental data is used as the final test set to verify the trained physical guided neural network. The unit process model details the input (raw materials), output (products), and key parameters and operating conditions of the unit process, providing accurate unit model support for the subsequent construction of superstructure network models.

[0100] In step S4 above, a superstructure network model is obtained by combining the unit process models and superstructure diagrams corresponding to each unit process. The superstructure network model integrates the various unit process models according to the connection relationships in the superstructure diagram, forming a complete and interconnected production and processing network model. This superstructure network model not only contains detailed information about each unit process but also reflects the flow paths of materials and energy throughout the entire production and processing process, providing a comprehensive model foundation for subsequent optimization solutions.

[0101] Specifically, the process of constructing a superstructure network model can include the following steps: First, based on the process flow of the conversion and separation of each key component, establish corresponding production and processing flow diagrams. Based on mathematical programming theory and the quantitative correlation between material balance, energy balance, product yield and properties and raw material properties and operating conditions related to each process mechanism, establish unit process models to explore and verify the nonlinear correlation between conversion rate, recovery rate, product quality and investment and energy consumption in each production process. Then, based on the upstream and downstream connection relationships from initial raw materials to intermediate products and final products, establish a superstructure network model that reflects the overall process options for all light hydrocarbon conversion and separation. The specific content includes exploring raw materials, process equipment and utilities that may compete, share or complement each other in different molecular production processes, and reflecting them through network flow, thereby realizing a network structure that includes all possible process paths, and establishing a reliable foundation for selecting the best process path.

[0102] For example, see Figure 2 The superstructure network model for a C4 light hydrocarbon component includes 23 process options and 91 flow lines, where flow lines indicate material flow. The superstructure network model for a C5 light hydrocarbon component includes 43 process options and 141 flow lines. The superstructure for the conversion and separation of C6 light hydrocarbon components is more complex and can be constructed separately for alkanes, cycloalkanes, and alkenes. For example, the superstructure network model for C6 alkane components includes 31 process options and 70 flow lines; the superstructure network model for C6 cycloalkanes includes 28 process options and 62 flow lines; and the superstructure network model for C6 olefins includes 48 process options and 131 flow lines. The superstructure network model for a C7 light hydrocarbon component includes 29 process options, 6 mixer units, 9 splitter units, and 86 flow lines. A superstructure network model of C8 light hydrocarbon components includes 20 process options, 6 mixer units, 9 splitter units, and 63 flow lines.

[0103] In step S5 above, the objective benefit function can be to maximize the production benefit of the superstructure system. The constraints can be determined based on the material and energy balance, dynamic / thermodynamic mechanisms and physical / equipment constraints in the production process. Furthermore, slack variables are introduced into the constraints to facilitate the solution.

[0104] The raw material data corresponding to the process flow should at least include the total amount of feed stream, the unit cost of feed stream, the unit utility cost of feed stream, the flow rate of each component in the feed stream, the flow rate of the key component, and the feed flow rate. The product data corresponding to the process flow should at least include the total amount of product stream, the unit price of product stream, the flow rate of each component in the product stream, and the separation and recovery rate. The product data corresponding to the splitter should at least include the total amount of product stream and the unit price of product stream. Investment parameters should at least include the annualized rate of return on investment, the variable investment coefficient for each process flow, and the fixed investment cost coefficient. Reaction parameters should at least include the molecular weight of each component during the reaction, the molecular weight of the key component during the reaction, and its conversion rate. Key component parameters should at least include the reaction selectivity coefficient and the reaction stoichiometric coefficient of the key component. Relaxation variable parameters should at least include the first relaxation variable, the second relaxation variable, the preset upper limit value of the relaxation variable, and the binary variable corresponding to each process flow.

[0105] The specific process of obtaining the optimal solution that satisfies the constraints and maximizes the objective benefit function based on a pre-constructed objective benefit function and a set of constraints including slack variables, combined with a hyperstructure network model, can include the following steps:

[0106] Step S501: Based on the investment parameters and the raw material and product data of each unit process, obtain the target benefit function.

[0107] In step S501 above, the objective benefit function is the unit return on investment of the integrated production and processing system. The unit return on investment is determined based on total product revenue, total raw material costs, total process utility costs, and total investment costs. The objective benefit function is the ratio of total product revenue minus total raw material costs, then minus total process utility costs, and then minus total investment costs to the total investment cost. The larger the value of the objective benefit function, the greater the system's production efficiency. Specifically, the process of constructing the objective benefit function may include the following steps:

[0108] Based on the annualized rate of investment, the total volume and unit price of the product flow in each process, the total volume and unit cost of the feed flow in each process, the unit utility cost of the feed flow in each process, and the total volume and unit price of the product flow in the distributor, the target benefit function shown in equation (1) is obtained:

[0109]

[0110] In equation (1) above, Z represents the unit return on investment, i represents the feed flow, j represents the product flow, p represents the process flow, s represents the distributor, and m represents the mixer; W j,p P represents the total product flow from the p-th process step; j,p W represents the unit price of the product flow from the p-th process step; j,s P represents the total product flow from the s-th splitter; j,s W represents the unit price of the product stream from the s-th splitter; i,p P represents the total feed flow of the p-th process; i,p UC represents the unit cost of the feed flow in the p-th process; p The ACCR represents the unit utility cost of the feed flow in the p-th process; CC represents the annualized rate of return on investment; p This represents the unit investment cost of the p-th process.

[0111] Step S502: Based on the relaxation variable parameters and the key component parameters, reaction parameters, raw material data and product data of each unit process, obtain the constraint condition set;

[0112] In step S502 above, the set of constraints includes at least: the constraint relationship between the separation and recovery rate of each component in each product stream and the feed stream and slack variables (first constraint); the constraint condition of the slack variables (second constraint); and the constraint relationship between the unit investment cost of each process and the feed throughput and fixed investment cost (third constraint).

[0113] The specific process of constructing the above first constraint may include the following steps:

[0114] For each process flow, based on the flow rate and separation recovery rate of each component in the product stream, the flow rate of each component in the feed stream and the flow rate of the key component, the molecular weight of each component during the reaction, the molecular weight and conversion rate of the key component during the reaction, the reaction selectivity coefficient and reaction stoichiometry coefficient of the key component, combined with the first relaxation variable and the second relaxation variable, the first constraint condition shown in the following equation (2) is obtained:

[0115]

[0116] In equation (2) above, W j,k,p R represents the flow rate of the k-th component in the product stream of the p-th process; j,k,p W represents the separation and recovery rate of the k-th component in the product stream of the p-th process; i,k,p M represents the flow rate of the k-th component in the feed stream of the p-th process; k,p,r M represents the molecular weight of the k-th component during the p-th process reaction; kB,p,rX represents the molecular weight of the key component in the p-th process reaction; kB,p S represents the conversion rate of the key component kB in the p-th process reaction; kB,p,r V represents the reaction selectivity coefficient of the key component kB in the p-th process; kB,p,r W represents the stoichiometric coefficient of the critical component kB in the p-th process; i,kB,p S represents the flow rate of the key component kB in the feed stream of the p-th process; 1p and S 2p Let represent the first slack variable and the second slack variable, respectively.

[0117] The specific process of constructing the above second constraint may include the following steps:

[0118] Based on the upper limit of the slack variables and the binary variables corresponding to each process, the second constraint condition shown in equation (3) is obtained:

[0119] S 1p +S 2p ≤M×(1-b p (3)

[0120] In equation (3) above, M represents the upper limit of the sum of slack variables, and b is the upper limit value of the slack variables. p Let represent the binary variable corresponding to the p-th process.

[0121] The specific process of constructing the aforementioned third constraint may include the following steps:

[0122] Based on the unit investment cost and feed throughput of each process, and the fixed investment cost, a set of constraints including the following third constraint is obtained:

[0123]

[0124] In equation (4) above, C 1p α represents the variable investment coefficient for the p-th process; p W represents the fixed investment coefficient for the p-th process; i,p n represents the flow rate of feed i in the p-th process; n represents W. i,p The number of index relationships for investment.

[0125] Of course, the constraint set can also include: the constraint relationship between the total feed flow and the feed rate of each component in each unit process; the constraint relationship between the total product flow and the product flow of each component in each unit process; the constraint relationship between the feed flow and product flow of each mixer; the constraint relationship between the feed flow and product flow of each distributor; the constraint conditions for the feed rate of each process; the constraint conditions for the flow rate of each component in the feed flow and product flow; and the constraint conditions for the purity of each component in the product flow. Specifically:

[0126] The constraint relationship between the total feed flow of each unit process and the feed rate of each component is shown in the following formulas (5)-(7):

[0127]

[0128] Equation (5) above indicates that the total feed flow of the p-th process is equal to the sum of the feed flow rates of each component in the p-th process;

[0129]

[0130] In equation (6) above, W i,s W represents the total feed flow of the s-th distributor; i,k,s Let represent the flow rate of the k-th component in the feed flow of the s-th splitter. Equation (6) above indicates that the total feed flow of the s-th splitter is equal to the sum of the flow rates of the feed flows of each component in the s-th splitter;

[0131]

[0132] In equation (7) above, W i,m W represents the total feed flow of the m-th mixer; i,k,m Let represent the flow rate of the k-th component in the feed stream of the m-th mixer. Equation (7) above indicates that the total feed stream of the m-th mixer is equal to the sum of the flow rates of the feed streams of each component in the m-th mixer.

[0133] The constraint relationship between the total product flow of each unit process and the product flow of each component is shown in formulas (8)-(10):

[0134]

[0135] Equation (8) above indicates that the total product flow of the p-th process is equal to the sum of the flow rates of each component product flow in the p-th process;

[0136]

[0137] In equation (9) above, W j,k,sLet represent the flow rate of the k-th component in the product flow of the s-th splitter. Equation (9) above indicates that the total product flow of the s-th splitter is equal to the sum of the flow rates of all components of the product flow of the s-th splitter;

[0138]

[0139] In equation (10) above, W j,m W represents the total amount of product flow from the m-th mixer; j,k,m Let represent the flow rate of the k-th component in the product flow from the m-th mixer; Equation (10) above indicates that the total product flow from the m-th mixer is equal to the sum of the flow rates of each component product flow from the m-th mixer.

[0140] The constraint relationships between the feed flow and product flow of each mixer, and between the feed flow and product flow of each splitter are shown in equations (11)-(15):

[0141]

[0142] In equation (11) above, x i,k,s This represents the feed flow proportion weight of the k-th component in the feed flow of the s-th splitter. Equation (11) above indicates that the flow rate of the k-th component in the feed flow of the s-th splitter is equal to the product of the total feed flow of the s-th splitter and the corresponding feed flow proportion weight of the k-th component;

[0143]

[0144] In equation (12) above, x j,k,s This represents the feed flow proportion weight of the k-th component in the product flow of the s-th splitter. Equation (12) above indicates that the flow rate of the k-th component in the product flow of the s-th splitter is equal to the product of the total product flow of the s-th splitter and the corresponding product flow proportion weight of the k-th component;

[0145]

[0146] Equation (13) above indicates that the flow rate of the kth component in the feed stream of the m-th mixer is equal to the flow rate of the kth component in the product stream of the m-th mixer;

[0147]

[0148] Equation (14) above indicates that the flow rate of the kth component in the feed flow of the s-th splitter is equal to the flow rate of the kth component in the product flow of the s-th splitter;

[0149]

[0150] Equation (15) above indicates that the feed flow ratio weight of the k-th component of the s-th splitter is equal to the product flow ratio weight of the k-th component of the s-th splitter.

[0151] The constraint set can also include constraints on the feed amount for each process, as shown in equation (16) below:

[0152] W i,p L ×b p ≤W i,p ≤W i,p U ×b p (16)

[0153] In equation (16) above, W i,p L W represents the lower limit of the feed flow for the p-th process; i,p U This represents the upper limit of the feed flow for the p-th process.

[0154] The constraints on the flow rates of each component in the feed flow and product flow are shown in equations (17) and (18) below:

[0155] W i,k,p L ×b p ≤W i,k,p ≤W i,k,p U ×b p (17)

[0156] In equation (17) above, W i,k,p L W represents the lower limit of the flow rate of the k-th component in the feed stream of the p-th process; i,k,p U This represents the upper limit of the flow rate of the k-th component in the feed stream of the p-th process;

[0157] W j,k,p L ×b p ≤W j,k,p ≤W j,k,p U ×b p (18)

[0158] In equation (18) above, W j,k,p L W represents the lower limit of the flow rate of the k-th component in the product stream exiting the p-th process; j,k,p U This represents the upper limit of the flow rate of the k-th component in the product stream flowing out of the p-th process.

[0159] In equations (16) to (18), the upper and lower limits are set according to the feasible capabilities of the on-site hardware equipment or the feasible market sales volume.

[0160] The constraints on the purity of each component in the product flow are shown in equation (19) below:

[0161] W j,k,p ≥α j,k,p W j,p ×b p (19)

[0162] In equation (19) above, α j,k,p This represents the concentration of the k-th component in the product stream flowing out from the p-th process.

[0163] Step S503: Solve the objective benefit function, constraint set and superstructure network model based on the mixed integer nonlinear algorithm to obtain the optimal solution that satisfies the constraints and maximizes the objective benefit function.

[0164] In step S503 above, since equations (4), (11), and (12) contain nonlinear elements, they exhibit strong mixed-integer non-convex nonlinear characteristics when optimizing the constraint set, and the problem scale is large. Therefore, embodiments of the present invention specifically establish a combination algorithm and initialization method of mixed-integer linear algorithm and nonlinear algorithm to effectively solve the difficulties in convergence and calculation speed caused by integer variables and nonlinear variables in the optimization iterative solution process. The specific process of obtaining the optimal solution that satisfies the constraint conditions and maximizes the objective benefit function may include the following steps:

[0165] Step S5031: Combine the objective benefit function, constraint set, and superstructure network model to obtain the mathematical model;

[0166] Step S5032: Set the initial value of the preset variables in the mathematical model to zero, obtain a feasible solution, and determine the conditions for the feasible solution; here, the preset variables are the optimization variables.

[0167] Step S5033: Divide the conditions of feasible solutions into mixed integer linear problems and mixed integer nonlinear problems, and determine the corresponding first optimization algorithm and second optimization algorithm respectively;

[0168] Step S5034: Combine the first optimization algorithm and the second optimization algorithm to perform iterative calculations on the mathematical model to obtain the optimal solution that satisfies the constraints and maximizes the objective benefit function.

[0169] Specifically, the first step is to initialize the problem by setting the initial values ​​of some key variables to zero, thereby transforming the optimization problem into a simulation problem. Then, a feasible solution is obtained by solving the equations simultaneously, which satisfies the condition for obtaining a feasible solution required by the optimization algorithm.

[0170] The problem is then decomposed into a combination of mixed-integer linear problems and nonlinear problems, and each is optimized using its own optimization algorithm (such as the CPLEX algorithm for solving mixed-integer linear problems and the CONOPT algorithm for solving nonlinear problems).

[0171] Then, iterative calculations are performed between the two algorithms using a global optimization algorithm strategy to finally obtain the optimal calculation result, which is the optimal solution that satisfies the constraints and maximizes the objective benefit function.

[0172] The method for producing and processing light hydrocarbon components of hydrocarbons provided in this invention involves extracting matching unit processes from a pre-built database based on the determined types and contents of key components corresponding to each light hydrocarbon component in the hydrocarbon, and determining the connection relationships of each unit process to obtain a hyperstructure diagram. A unit process model is constructed for each unit process. A hyperstructure network model is obtained by combining the unit process model and the hyperstructure diagram. Various data are used to solve the hyperstructure network model, the pre-built objective benefit function, and the constraint set, wherein slack variables are introduced into the constraint set. During the solution process, a mixed-integer nonlinear algorithm is used to obtain the optimal solution that satisfies the constraints and maximizes the objective benefit function, i.e., optimized production information, used to control the production and processing of light hydrocarbon components of hydrocarbons. The embodiments of the present invention construct a superstructure network model, objective benefit function, and constraint set that can represent all the process flows of light hydrocarbon components of hydrocarbons, and introduce slack variables to achieve rapid optimization. This optimization solution provides the optimal process flow, operating parameters, and resource allocation scheme for the production and processing of light hydrocarbon components of hydrocarbons, so as to formulate a production plan that can obtain the maximum benefit, which helps to improve production efficiency, reduce production costs, and improve product quality.

[0173] It should be noted that the biggest difference between this invention and the prior art is that the prior art focuses on the role and characteristics of a single process, while this invention, from the perspective of system integration, utilizes the developed superstructure network model and its objective benefit function and constraint set to integrate and optimize multiple processing technologies in a holistic manner, thereby leveraging the synergistic effect of these technologies in terms of resources and energy to maximize overall economic benefits.

[0174] Example 2

[0175] Based on the same inventive concept, see [reference] Figure 3 This application also proposes an optimized production and processing apparatus for light hydrocarbon components, comprising:

[0176] Data acquisition module 1 is used to acquire data on all light hydrocarbon components of hydrocarbons, analyze the key components corresponding to each light hydrocarbon component based on a pre-built molecular mapping model, and determine the type and content of each key component.

[0177] The mapping module 2 is used to extract matching unit processes from a pre-built database based on the type and content of each key component, and to determine the connection relationship of each unit process to obtain a superstructure diagram.

[0178] The first model building module 3 is used to extract the corresponding raw material data from the database for each unit process, obtain the product data using the pre-trained product prediction model, and build the unit process model.

[0179] The second model construction module 4 is used to combine the unit process model and the superstructure diagram corresponding to each unit process to obtain the superstructure network model;

[0180] Calculation module 5 is used to solve the problem based on a pre-constructed objective benefit function and a set of constraints including slack variables, combined with a superstructure network model, to obtain the optimal solution that satisfies the constraints and maximizes the objective benefit function.

[0181] The production and processing optimization device for light hydrocarbon components of hydrocarbons provided in this embodiment of the invention has a similar implementation principle and technical effect to that of Embodiment 1, and will not be repeated here.

[0182] Example 3

[0183] Based on the same inventive concept, this application also proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the optimized production and processing method for light hydrocarbon components as described in Example 1.

[0184] The computer-readable storage medium may be included in the device / apparatus described in the above embodiments; or it may exist independently and not assembled into the device / apparatus. The computer-readable storage medium carries one or more programs, which, when executed, implement the method according to Embodiment 1 of the present invention.

[0185] According to embodiments of the present invention, the computer-readable storage medium may be a non-volatile computer-readable storage medium, such as including, but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In the present invention, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0186] Example 4

[0187] Based on the same inventive concept, see [reference] Figure 4 This application also proposes an electronic device, including a processor 111, a communication interface 112, a memory 113 and a communication bus 114, wherein the processor 111, the communication interface 112 and the memory 113 communicate with each other through the communication bus 114.

[0188] Memory 113 is used to store computer programs;

[0189] In one embodiment of the present invention, when the processor 111 executes the program stored in the memory 113, it implements the steps of the production and processing method of light hydrocarbon components of hydrocarbons provided in any of the foregoing method embodiments.

[0190] The electronic device provided in this embodiment of the invention has a similar implementation principle and technical effect to the above embodiments, and will not be described again here.

[0191] The aforementioned memory 113 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. Memory 113 has storage space for program code used to perform any of the method steps described above. For example, the storage space for program code may include individual program codes for implementing the various steps in the methods described above. This program code can be read from or written to one or more computer program products. These computer program products include program code carriers such as hard disks, optical discs (CDs), memory cards, or floppy disks. Such computer program products are typically portable or fixed storage units. The storage unit may have storage segments or storage spaces arranged similarly to memory 113 in the aforementioned electronic device. The program code may be compressed, for example, in a suitable form. Typically, the storage unit includes programs for performing the method steps according to embodiments of the invention, i.e., code that can be read by a processor such as 111, which, when run by the electronic device, causes the electronic device to perform the various steps in the methods described above.

[0192] Example 5

[0193] Based on the same inventive concept, this application proposes a computer program product containing instructions that, when run on a computer device, cause the computer device to execute the production and processing optimization method for light hydrocarbon components of hydrocarbons in Embodiment 1.

[0194] The principles by which the above-mentioned devices, clients, media, and related equipment in this embodiment of the invention solve the problem are similar to those of the aforementioned methods. Therefore, their implementation can refer to the implementation of the aforementioned methods, and repeated details will not be repeated.

[0195] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0196] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0197] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0198] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0199] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0200] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

[0201] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. This disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims. Thus, if these modifications and variations of the invention fall within the scope of the claims of the invention and their equivalents, the invention is also intended to include these modifications and variations.

Claims

1. An optimized method for the production and processing of light hydrocarbon components, characterized in that, include: Data on all light hydrocarbon components of hydrocarbons are obtained, and the key components corresponding to each light hydrocarbon component are analyzed based on a pre-constructed molecular mapping model, and the types and contents of each key component are determined. Based on the type and content of each key component, matching unit processes are extracted from a pre-built database, and the connection relationship of each unit process is determined to obtain a superstructure diagram. For each of the aforementioned unit processes, the corresponding raw material data is extracted from the database, and the product data is obtained using a pre-trained product prediction model to construct a unit process model. By combining the unit process models corresponding to each unit process and the superstructure diagram, a superstructure network model is obtained; Based on the pre-constructed objective benefit function and the set of constraints including slack variables, the solution is obtained by combining the superstructure network model to obtain the optimal solution that satisfies the constraints and maximizes the objective benefit function.

2. The optimized production and processing method for light hydrocarbon components according to claim 1, characterized in that, The process of extracting matching unit processes from a pre-built database based on the type and content of each key component, and determining the connection relationships of each unit process to obtain a superstructure diagram includes: For each of the key components, matching unit processes are extracted from a pre-built database based on the type and content of the key components, and the connection relationship between each of the unit processes is determined to obtain the generation and processing flow chart corresponding to the key component. By integrating the process flow diagrams corresponding to all the key components, a superstructure diagram is obtained.

3. The optimized production and processing method for light hydrocarbon components according to claim 1, characterized in that, The optimal solution, which satisfies the constraints and maximizes the objective benefit function based on a pre-constructed objective benefit function and a set of constraints including slack variables, is obtained by combining the superstructure network model with the solution. This includes: Based on the investment parameters and the raw material and product data of each unit process, the target benefit function is obtained; Based on the relaxation variable parameters and the key component parameters, reaction parameters, raw material data and product data of each unit process, a set of constraints is obtained. The objective benefit function, the set of constraints, and the superstructure network model are solved using a mixed-integer nonlinear algorithm to obtain the optimal solution that satisfies the constraints and maximizes the objective benefit function.

4. The optimized production and processing method for light hydrocarbon components according to claim 3, characterized in that, The unit process includes a product flow and a feed flow; The type of unit process includes at least one: process flow, mixer and splitter; The raw material data corresponding to the process includes at least the total amount of feed stream, the unit cost of feed stream, and the unit utility cost of feed stream; The product data corresponding to the process includes at least the total quantity of the product stream and the unit price of the product stream; The product data corresponding to the diverter includes at least the total quantity and unit price of the product stream; The investment parameters include at least the annualized rate of return on investment; The objective benefit function, derived based on investment parameters and raw material and product data for each unit process, includes: Based on the annualized rate of investment, the total volume and unit price of the product stream in each of the aforementioned processes, the total volume and unit cost of the feed stream in each of the aforementioned processes, the unit utility cost of the feed stream in each of the aforementioned processes, and the total volume and unit price of the product stream in each of the aforementioned distributors, the following objective benefit function is obtained: Where Z represents the return on investment per unit, i represents the feed flow, j represents the product flow, p represents the process flow, s represents the distributor, and m represents the mixer; W j,p P represents the total product flow from the p-th process step; j,p W represents the unit price of the product flow from the p-th process step; j,s P represents the total product flow from the s-th splitter; j,s W represents the unit price of the product stream from the s-th splitter; i,p P represents the total feed flow of the p-th process; i,p UC represents the unit cost of the feed flow in the p-th process; p The ACCR represents the unit utility cost of the feed flow in the p-th process; CC represents the annualized rate of return on investment; p This represents the unit investment cost of the p-th process.

5. The optimized production and processing method for light hydrocarbon components according to claim 4, characterized in that, The corresponding product data for the process also includes the flow rate and separation and recovery rate of each component in the product stream; The corresponding raw material data for the process also includes the flow rates of each component in the feed stream and the flow rates of key components. The reaction parameters should include at least the molecular weight of each component during the reaction, the molecular weight of the key component during the reaction, and the conversion rate. The key component parameters include at least the reaction selectivity coefficient and the reaction stoichiometry coefficient of the key component; The relaxation variable parameters include at least a first relaxation variable and a second relaxation variable; The constraint set, based on the relaxation variable parameters and the key component parameters, reaction parameters, raw material data, and product data of each unit process, is obtained, including: For each of the aforementioned process flows, based on the flow rates and separation / recovery rates of each component in the product stream, the flow rates of each component in the feed stream and the flow rates of key components, the molecular weights of each component during the reaction, the molecular weights and conversion rates of key components during the reaction, and the reaction selectivity and stoichiometric coefficients of key components, combined with the first relaxation variable and the second relaxation variable, a set of constraints containing at least the following first constraint conditions is obtained: Among them, W j,k,p R represents the flow rate of the k-th component in the product stream of the p-th process; j,k,p W represents the separation and recovery rate of the k-th component in the product stream of the p-th process; i,k,p M represents the flow rate of the k-th component in the feed stream of the p-th process; k,p,r M represents the molecular weight of the k-th component during the p-th process reaction; kB,p,r X represents the molecular weight of the key component in the p-th process reaction; kB,p S represents the conversion rate of the key component kB in the p-th process reaction; kB,p,r V represents the reaction selectivity coefficient of the key component kB in the p-th process; kB,p,r W represents the stoichiometric coefficient of the critical component kB in the p-th process; i,kB,p S represents the flow rate of the key component kB in the feed stream of the p-th process; 1p and S 2p Let represent the first slack variable and the second slack variable, respectively.

6. The optimized production and processing method for light hydrocarbon components according to claim 5, characterized in that, The relaxation variable parameters also include a preset upper limit value for the relaxation variable and a binary variable corresponding to each of the process steps; After obtaining a set of constraints that includes at least the first constraint, the following is also included: Based on the upper limit of the relaxation variables and the binary variables corresponding to each process step, a set of constraints is obtained that includes at least the following second constraint: S 1p +S 2p ≤M×(1-b p ) Where M represents the upper limit of the sum of slack variables, and b is the upper limit of the slack variables. p Let represent the binary variable corresponding to the p-th process step.

7. The optimized production and processing method for light hydrocarbon components according to claim 5, characterized in that, The investment parameters also include the variable investment coefficient and fixed investment cost coefficient for each of the aforementioned processes; The raw material data corresponding to the process also includes the feed flow rate; After obtaining a set of constraints that includes at least the first constraint, the following is also included: Based on the unit investment cost and feed throughput of each process, and the fixed investment cost, a set of constraints including the following third constraint is obtained: Among them, C 1p α represents the variable investment coefficient for the p-th process; p W represents the fixed investment coefficient for the p-th process; i,p n represents the flow rate of feed i in the p-th process; n represents W. i,p The number of index relationships for investment.

8. The optimized method for the production and processing of light hydrocarbon components according to any one of claims 3-7, characterized in that, The method of solving the objective benefit function, the constraint set, and the superstructure network model using a mixed-integer nonlinear algorithm to obtain the optimal solution that satisfies the constraints and maximizes the objective benefit function includes: By combining the objective benefit function, the set of constraints, and the superstructure network model, a mathematical model is obtained. The initial values ​​of the preset variables in the mathematical model are set to zero to obtain a feasible solution, and the conditions for the feasible solution are determined. The conditions for feasible solutions are divided into mixed integer linear problems and mixed integer nonlinear problems, and the corresponding first optimization algorithm and second optimization algorithm are determined respectively. The mathematical model is iteratively calculated by combining the first optimization algorithm and the second optimization algorithm to obtain the optimal solution that satisfies the constraints and maximizes the objective benefit function.

9. An optimized production and processing apparatus for light hydrocarbon components, characterized in that, include: The data acquisition module is used to acquire data on all light hydrocarbon components of hydrocarbons, analyze the key components corresponding to each light hydrocarbon component based on a pre-built molecular mapping model, and determine the type and content of each key component. The mapping module is used to extract matching unit processes from a pre-built database based on the type and content of each key component, and to determine the connection relationship of each unit process to obtain a superstructure diagram. The first model building module is used to extract the corresponding raw material data from the database for each unit process, obtain the product data using a pre-trained product prediction model, and build a unit process model. The second model construction module is used to combine the unit process model corresponding to each unit process and the superstructure diagram to obtain the superstructure network model; The calculation module is used to solve the superstructure network model based on a pre-constructed objective benefit function and a set of constraints including slack variables, to obtain the optimal solution that satisfies the constraints and maximizes the objective benefit function.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the optimized production and processing method for light hydrocarbon components of hydrocarbons as described in any one of claims 1-8.

11. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; The processor, when executing a program stored in memory, implements the optimized method for the production and processing of light hydrocarbon components according to any one of claims 1-8.

12. A computer program product containing instructions, which, when run on a computer device, causes the computer device to perform the optimized method for the production and processing of light hydrocarbon components as described in any one of claims 1-8.

Images