A Multi-Objective Cooperative Optimization Method for Supercritical CO2 Cycle Systems

Abstract

The present application relates to supercritical carbon dioxide cycle power generation technology field, especially provide a kind of supercritical CO2 circulation system multi-objective collaborative optimization method.The method includes generating equipment geometric parameter combination and performance index dataset based on system boundary parameter;Multi-objective optimization is carried out based on performance index dataset and optimal solution is solved, and mapping model is constructed;According to the mapping model, optimal performance is predicted, and design parameters are output, and the method realizes the global optimization design of unit efficient, flexible and safe.

Description

Technical Field

[0001] This invention relates to the field of supercritical carbon dioxide cycle power generation technology, and in particular to a multi-objective collaborative optimization method for a supercritical CO2 cycle system. Background Technology

[0002] Supercritical carbon dioxide Brayton cycle power generation technology, with its high efficiency, compactness, and flexibility, has become a key technological path supporting the construction of new power systems. However, traditional research and development focuses on optimizing thermodynamic efficiency under rated operating conditions, lacking a systematic consideration of dynamic response capabilities under variable load scenarios. The significant increase in new energy grid connection in new power systems requires units to have rapid load adjustment capabilities. To meet flexibility requirements, secondary modifications are needed after the project is put into operation to achieve dynamic performance standards. This fragmented research and development model, separating the design phase from dynamic modification, leads to an extended investment payback period. Summary of the Invention

[0003] In view of this, the present invention provides a multi-objective collaborative optimization method for supercritical CO2 cycle systems to achieve efficient, flexible and safe global optimization design of the unit.

[0004] In a first aspect, the present invention provides a multi-objective collaborative optimization method for a supercritical CO2 cycle system, the method comprising: Step 1: Based on the system boundary parameters, generate a dataset of equipment geometric parameter combinations and performance indicators; Step 2: Perform multi-objective optimization and solve for the optimal solution based on the performance index dataset, and construct a mapping model; Step 3: Predict the optimal performance based on the mapping model and output the design parameters.

[0005] Optionally, the system boundary parameters in step 1 include: circulating working fluid flow rate, turbine inlet pressure, turbine inlet temperature, compressor inlet pressure, compressor inlet temperature, turbine isentropic efficiency, temperature difference between the hot and cold sides of the heat exchanger, and power grid load command fluctuation range; the system boundary parameters serve as input conditions to determine the operating boundaries of the system's process nodes.

[0006] Optionally, generating the equipment geometric parameter combination in step 1 includes: generating multiple sets of equipment geometric parameter combinations based on the value range of the system boundary parameters and in conjunction with the equipment design specifications; Each combination includes parameter values ​​for the heat exchanger, turbine, compressor, and buffer tank. The heat exchanger parameters include flow channel diameter D, flow channel length L, core height H, core width W, flow pattern coefficient f, and arrangement coefficient p. The turbine parameters include stage specific speed n. s The compressor's parameters include impeller diameter D, blade height b, installation angle α, and reaction degree Ω. c Number of leaves Nc Inlet angle β, stage pressure ratio π c The parameters of the buffer tank include its volume V. b Inlet diameter D b Aspect ratio γ b ; When analyzing each combination of equipment geometric parameters, the constraints on the geometric parameters of a single piece of equipment are as follows: I. Heat exchanger parameter constraints, D min ≤ D ≤ D max This is to prevent D from being too small and causing blockage, or too large and reducing the heat transfer coefficient; L min ≤ L ≤ L max This is used to avoid insufficient heat transfer due to an excessively short L and increased flow losses due to an excessively long L; H min ≤ H ≤ H max This is to avoid insufficient flow due to an excessively small H value, or excessively large H value, which would increase the size of the equipment. Based on heat transfer characteristics and structural design, f∈{forward flow, counter-flow, cross flow}; Based on the flow channel processing technology, p∈{ordered, staggered}; II. Turbine parameter constraints, n smin ≤ n s ≤n smax , used to prevent n s Too small a stage results in low efficiency, while too large a stage easily leads to surge; b smin ≤ b s ≤b smax To prevent b s Too small a flow rate results in insufficient flow, while too large a flow rate leads to excessive centrifugal stress; α min ≤α≤α max If the value is too small, the airflow impact loss is large; if it is too large, the blade load is too high. min ≤Ω≤Ω max If the impulse stage is too small, its characteristics are significant, and its efficiency is sensitive to changing operating conditions; if the reaction stage is too large, its characteristics are significant, and its structure is complex. III. Compressor parameter constraints, D cmin ≤D c ≤D cmax If the pressure is too small, the boost capacity will be insufficient; if it is too large, the moment of inertia will increase, which is used to reduce the peak-shaving response speed; N cmin ≤N c ≤N cmax Too little β results in large airflow disturbances and low efficiency; too much increases manufacturing difficulty and cost. min ≤β≤β max If the value is too small, the airflow will impact the leading edge of the blade, resulting in significant losses; if it is too large, the blade load will be too high, making it prone to fatigue fracture. cmin ≤π c ≤π cmaxIf the value is too small, multiple compression stages are required, increasing system complexity; if it is too large, the efficiency of a single stage drops sharply. IV. Buffer tank parameter constraints, V bmin ≤V b ≤V bmax If the pressure is too small, the pressure stabilization capability will be insufficient, and pressure fluctuations will exceed the standard; if it is too large, the equipment size and cost will increase, and the response will be delayed; D bmin ≤D b ≤D bmax If the inlet velocity is too small, the inlet flow velocity will exceed 15 m / s, resulting in a significant increase in resistance loss; if it is too large, it will be incompatible with the pipeline connection, increasing installation difficulty; bmin ≤γ b ≤γ bmax If the value is too small, the flow field inside the tank will be turbulent and the pressure stabilization effect will be poor; if the value is too large, the axial space requirement will be large and dead zones in the flow will be easily generated. Latin hypercube sampling is used to cover the parameter space, ensuring the diversity and representativeness of the combinations. The sample size is determined according to the parameter dimension.

[0007] Optionally, generating the performance metric dataset in step 1 includes: Based on the effective combination of equipment geometric parameters, performance simulation and quantitative analysis are performed on the effective combination of equipment geometric parameters to calculate system-level performance indicators: Dynamic indicators include peak shaving speed, peak shaving depth, instantaneous temperature change rate, and instantaneous pressure fluctuation. Static indicators: average efficiency under all operating conditions and cost per kilowatt-hour; By systematically integrating all effective parameter combinations and their corresponding performance results, a mapping dataset of system boundary parameters, equipment geometric parameter combinations, and performance indicators is formed.

[0008] Optionally, the multi-objective optimization in step 2 includes: optimization of system boundary parameters. For a given set of system boundary parameters, samples of all device geometric parameters-performance indices under the boundary conditions are extracted from the dataset to construct a multi-objective optimization model. ; An improved non-dominated sorting genetic algorithm NSGA-III is used to solve the Pareto optimal solution set. The weights are determined by the analytic hierarchy process (AHP), and the combination of comprehensive optimal performance indicators is selected. The corresponding combination of equipment geometric parameters is the optimal design parameter under the boundary conditions.

[0009] Optionally, this includes constructing an optimal solution mapping model across boundary parameters to cope with different system boundary parameters and predict the optimal solution under arbitrary boundary parameters; collecting multiple sets of optimal performance indices and equipment geometric parameters corresponding to different system boundary parameters, and constructing a mapping model using Gaussian process regression (GPR). Input system boundary parameters; output optimal performance indicators and corresponding equipment geometric parameters; optimize model parameters through cross-validation to ensure prediction accuracy; finally, the established GPR mapping model is used to support the system in generating optimal design parameters and recommend equipment geometric configurations that match the optimal performance for different boundary parameters.

[0010] Optionally, step 3 includes: For predictions under new boundary parameters, for any new set of system boundary parameters, input them into the trained mapping model, and directly output: the predicted value of the optimal system performance index; and the corresponding design value of the equipment geometric parameters.

[0011] Optionally, this includes: model iterative updates, repeating steps 1 to 2 to retrain the mapping model when actual operating data or new samples accumulate to a threshold scale, in order to improve the adaptability to complex boundary conditions; when new system boundary parameters are input, the optimized mapping model is used to predict the corresponding optimal static / dynamic performance indicators and equipment geometric parameters.

[0012] In a second aspect, embodiments of the present invention provide a computer-readable storage medium comprising a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to perform a multi-objective cooperative optimization method for a supercritical CO2 cycle system as described in the first aspect or any possible implementation thereof.

[0013] Thirdly, embodiments of the present invention provide an electronic device, including: one or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions that, when executed by the device, cause the device to perform a multi-objective cooperative optimization method for a supercritical CO2 cycle system in the first aspect or any possible implementation of the first aspect.

[0014] The technical solution provided by this invention includes generating a combination of equipment geometric parameters and a performance index dataset based on system boundary parameters; performing multi-objective optimization and solving for the optimal solution based on the performance index dataset to construct a mapping model; predicting the optimal performance based on the mapping model and outputting design parameters. This method realizes efficient, flexible and safe global optimization design of the unit. Attached Figure Description

[0015] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 A flowchart of a multi-objective collaborative optimization method for a supercritical CO2 cycle system provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] It should be understood that the described embodiments are merely some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0019] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” used in the embodiments of this invention are also intended to include the plural forms unless the context clearly indicates otherwise.

[0020] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0021] Depending on the context, the word "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0022] Figure 1 The flowchart of the multi-objective cooperative optimization method for a supercritical CO2 cycle system provided in the embodiments of the present invention is as follows: Figure 1 As shown, the method includes: Step 1: Generate a dataset of equipment geometric parameter combinations and performance indicators based on system boundary parameters.

[0023] In this embodiment of the invention, the system boundary parameters (process node parameters) in step 1 include: circulating working fluid flow rate, turbine inlet pressure, turbine inlet temperature, compressor inlet pressure, compressor inlet temperature, turbine isentropic efficiency, temperature difference between the hot and cold sides of the heat exchanger, and power grid load command fluctuation range; the system boundary parameters serve as input conditions to determine the operating boundaries of the system's process nodes.

[0024] In this embodiment of the invention, step 1 of generating equipment geometric parameter combinations includes: generating multiple sets of equipment geometric parameter combinations based on the value range of system boundary parameters and in conjunction with equipment design specifications (such as the heat exchanger flow channel size needing to match the flow rate and the turbine blade height needing to match the pressure ratio). Each combination includes parameter values ​​for the heat exchanger, turbine, compressor, and buffer tank. The heat exchanger parameters include flow channel diameter D, flow channel length L, core height H, core width W, flow pattern coefficient f, and arrangement coefficient p. The turbine parameters include stage specific speed n. s The compressor's parameters include impeller diameter D, blade height b, installation angle α, and reaction degree Ω. c Number of leaves N c Inlet angle β, stage pressure ratio π c The parameters of the buffer tank include its volume V. b Inlet diameter D b Aspect ratio γ b ; When analyzing each combination of equipment geometric parameters, it is crucial to consider the individual equipment parameter constraints established in step 1. These constraints are based on the physical characteristics, operating limits, and safety regulations of each piece of equipment. The individual equipment geometric parameter constraints are as follows: I. Heat exchanger parameter constraints, D min ≤ D ≤ D max This is to prevent D from being too small and causing blockage, or too large and reducing the heat transfer coefficient; L min ≤ L ≤ L max This is used to avoid insufficient heat transfer due to an excessively short L and increased flow losses due to an excessively long L; H min ≤ H ≤ H max This is to avoid insufficient flow due to an excessively small H value, or excessively large H value, which would increase the size of the equipment. Based on heat transfer characteristics and structural design, f∈{forward flow, counter-flow, cross flow}; Based on the flow channel processing technology, p∈{ordered, staggered}; II. Turbine parameter constraints, n smin ≤ n s ≤n smax , used to prevent n s Too small a stage results in low efficiency, while too large a stage easily leads to surge; b smin ≤ bs ≤b smax To prevent b s Too small a flow rate results in insufficient flow, while too large a flow rate leads to excessive centrifugal stress; α min ≤α≤α max If the value is too small, the airflow impact loss is large; if it is too large, the blade load is too high. min ≤Ω≤Ω max If the impulse stage is too small, its characteristics are significant, and its efficiency is sensitive to changing operating conditions; if the reaction stage is too large, its characteristics are significant, and its structure is complex. III. Compressor parameter constraints, D cmin ≤D c ≤D cmax If the pressure is too small, the boost capacity will be insufficient; if it is too large, the moment of inertia will increase, which is used to reduce the peak-shaving response speed; N cmin ≤N c ≤N cmax Too little β results in large airflow disturbances and low efficiency; too much increases manufacturing difficulty and cost. min ≤β≤β max If the value is too small, the airflow will impact the leading edge of the blade, resulting in significant losses; if it is too large, the blade load will be too high, making it prone to fatigue fracture. cmin ≤π c ≤π cmax If the value is too small, multiple compression stages are required, increasing system complexity; if it is too large, the efficiency of a single stage drops sharply. IV. Buffer tank parameter constraints, V bmin ≤V b ≤V bmax If the pressure is too small, the pressure stabilization capability will be insufficient, and pressure fluctuations will exceed the standard; if it is too large, the equipment size and cost will increase, and the response will be delayed; D bmin ≤D b ≤D bmax If the inlet velocity is too small, the inlet flow velocity will exceed 15 m / s, resulting in a significant increase in resistance loss; if it is too large, it will be incompatible with the pipeline connection, increasing installation difficulty; bmin ≤γ b ≤γ bmax If the value is too small, the flow field inside the tank will be turbulent and the pressure stabilization effect will be poor; if the value is too large, the axial space requirement will be large and dead zones in the flow will be easily generated. Latin hypercube sampling is used to cover the parameter space, ensuring the diversity and representativeness of the combinations. The sample size is determined according to the parameter dimension (e.g., an 8-parameter system generates at least 500 combinations).

[0025] In this embodiment of the invention, step 1, generating the performance metric dataset, includes: Based on the effective combination of equipment geometric parameters, performance simulation and quantitative analysis are performed on the effective combination of equipment geometric parameters to calculate system-level performance indicators: Dynamic indicators include peak shaving speed, peak shaving depth, instantaneous temperature change rate, and instantaneous pressure fluctuation. Static indicators: average efficiency under all operating conditions and cost per kilowatt-hour; By systematically integrating all effective parameter combinations and their corresponding performance results, a mapping dataset of system boundary parameters, equipment geometric parameter combinations, and performance indicators is formed, providing a reliable data foundation for subsequent system optimization, scheme comparison, and operation strategy formulation.

[0026] Step 2: Perform multi-objective optimization and solve for the optimal solution based on the performance index dataset, and construct a mapping model.

[0027] In this embodiment of the invention, step 2, multi-objective optimization, includes: optimizing system boundary parameters. For a given set of system boundary parameters, samples of all device geometric parameter sets—performance indices—under the boundary conditions are extracted from the dataset to construct a multi-objective optimization model. ; An improved non-dominated sorting genetic algorithm NSGA-III is used to solve the Pareto optimal solution set. The weights are determined by the analytic hierarchy process (AHP) (e.g., peak speed weight is 0.2, efficiency weight is 0.3, and cost weight is 0.2). The combination of the best performance indicators is selected, and the corresponding combination of equipment geometric parameters is the optimal design parameters under the boundary conditions.

[0028] In this embodiment of the invention, in order to cope with different system boundary parameters and predict the optimal solution under arbitrary boundary parameters, an optimal solution mapping model across boundary parameters is constructed; multiple sets of optimal performance indicators and equipment geometric parameters corresponding to different system boundary parameters are collected, and Gaussian process regression (GPR) is used to construct the mapping model. Input system boundary parameters; output optimal performance indicators and corresponding equipment geometric parameters; optimize model parameters (such as kernel function type and regularization coefficient) through cross-validation to ensure prediction accuracy; finally, the established GPR mapping model is used to support the system in generating optimal design parameters and recommend equipment geometric configurations that match the optimal performance for different boundary parameters.

[0029] Step 3: Predict the optimal performance based on the mapping model and output the design parameters.

[0030] In this embodiment of the invention, step 3 includes: For predictions under new boundary parameters, for any new set of system boundary parameters, input them into the trained mapping model, and directly output: the predicted value of the optimal system performance index; and the corresponding design value of the equipment geometric parameters.

[0031] In this embodiment of the invention, the following steps are included: model iterative update: when actual operating data or new samples (such as design schemes under extreme boundary parameters) accumulate to a threshold scale, steps 1 to 2 are repeated to retrain the mapping model in order to improve its adaptability to complex boundary conditions; when new system boundary parameters are input, the optimized mapping model is used to predict the corresponding optimal static / dynamic performance indicators and equipment geometric parameters.

[0032] This invention achieves an upgrade from single boundary parameter optimization to rapid prediction of cross-boundary parameters by mapping system boundary parameters, equipment geometric parameters, and performance indicators, and by leveraging multi-objective optimization and machine learning models. This avoids the inefficiency of repetitive simulation calculations. Ultimately, it forms a closed-loop tool that inputs boundary parameters and outputs optimal performance indicators and equipment design parameters, providing quantitative basis for the early design of supercritical carbon dioxide cycle systems. This tool can meet the dynamic requirements of new power systems without the need for later modifications.

[0033] The technical solution provided by this invention includes generating a combination of equipment geometric parameters and a performance index dataset based on system boundary parameters; performing multi-objective optimization and solving for the optimal solution based on the performance index dataset to construct a mapping model; predicting the optimal performance based on the mapping model and outputting design parameters. This method realizes efficient, flexible and safe global optimization design of the unit.

[0034] The various steps in the embodiments of the present invention can be performed by an electronic device. This electronic device includes, but is not limited to, tablet computers, portable PCs, and desktop computers.

[0035] This invention provides a computer-readable storage medium including a stored program, wherein, when the program is running, it controls the electronic device containing the computer-readable storage medium to execute the aforementioned multi-objective cooperative optimization method for a supercritical CO2 cycle system.

[0036] Figure 2 A schematic diagram of an electronic device provided in an embodiment of the present invention, such as... Figure 2 As shown, the electronic device 21 includes a processor 211, a memory 212, and a computer program 213 stored in the memory 212 and executable on the processor 211. When the computer program 213 is executed by the processor 211, it implements the multi-objective cooperative optimization method of the supercritical CO2 cycle system in the embodiment. To avoid repetition, it will not be described in detail here.

[0037] Electronic device 21 includes, but is not limited to, processor 211 and memory 212. Those skilled in the art will understand that... Figure 2This is merely an example of electronic device 21 and does not constitute a limitation on electronic device 21. It may include more or fewer components than shown, or combine certain components, or different components. For example, electronic device may also include input / output devices, network access devices, buses, etc.

[0038] The processor 211 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0039] The memory 212 can be an internal storage unit of the electronic device 21, such as a hard disk or RAM of the electronic device 21. The memory 212 can also be an external storage device of the electronic device 21, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, or FlashCard equipped on the electronic device 21. Furthermore, the memory 212 can include both internal and external storage units of the electronic device 21. The memory 212 is used to store computer programs and other programs and data required by network devices. The memory 212 can also be used to temporarily store data that has been output or will be output.

[0040] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0041] 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 within the scope of protection of the present invention.

Claims

1. A multi-objective collaborative optimization method for a supercritical CO2 cycle system, characterized in that, The method includes: Step 1: Based on the system boundary parameters, generate a dataset of equipment geometric parameter combinations and performance indicators; Step 2: Perform multi-objective optimization and solve for the optimal solution based on the performance index dataset, and construct a mapping model; Step 3: Predict the optimal performance based on the mapping model and output the design parameters.

2. The method according to claim 1, characterized in that, The system boundary parameters in step 1 include: circulating working fluid flow rate, turbine inlet pressure, turbine inlet temperature, compressor inlet pressure, compressor inlet temperature, turbine isentropic efficiency, temperature difference between the hot and cold sides of the heat exchanger, and power grid load command fluctuation range. The system boundary parameters serve as input conditions to determine the operating boundaries of the system's process nodes.

3. The method according to claim 2, characterized in that, The step 1 of generating equipment geometric parameter combinations includes: generating multiple sets of equipment geometric parameter combinations based on the value range of system boundary parameters and in conjunction with equipment design specifications; Each combination includes parameter values ​​for the heat exchanger, turbine, compressor, and buffer tank. The heat exchanger parameters include flow channel diameter D, flow channel length L, core height H, core width W, flow pattern coefficient f, and arrangement coefficient p. The turbine parameters include stage specific speed n. s The compressor's parameters include impeller diameter D, blade height b, installation angle α, and reaction degree Ω. c Number of leaves N c Inlet angle β, stage pressure ratio π c The parameters of the buffer tank include its volume V. b Inlet diameter D b Aspect ratio γ b ; When analyzing each combination of equipment geometric parameters, the constraints on the geometric parameters of a single piece of equipment are as follows: I. Heat exchanger parameter constraints, D min ≤ D ≤ D max This is to prevent D from being too small and causing blockage, or too large and reducing the heat transfer coefficient; L min ≤ L ≤ L max This is used to avoid insufficient heat transfer due to an excessively short L and increased flow losses due to an excessively long L; H min ≤ H ≤ H max This is to avoid insufficient flow due to an excessively small H value, or excessively large H value, which would increase the size of the equipment. Based on heat transfer characteristics and structural design, f∈{forward flow, counter-flow, cross flow}; Based on the flow channel processing technology, p∈{ordered, staggered}; II. Turbine parameter constraints, n smin ≤ n s ≤n smax , used to prevent n s Too small a stage results in low efficiency, while too large a stage easily leads to surge; b smin ≤ b s ≤b smax To prevent b s Too small a flow rate results in insufficient flow, while too large a flow rate leads to excessive centrifugal stress; α min ≤α≤α max If the value is too small, the airflow impact loss is large; if it is too large, the blade load is too high. min ≤Ω≤Ω max If the impulse stage is too small, its characteristics are significant, and its efficiency is sensitive to changing operating conditions; if the reaction stage is too large, its characteristics are significant, and its structure is complex. III. Compressor parameter constraints, D cmin ≤D c ≤D cmax If the pressure is too small, the boost capacity will be insufficient; if it is too large, the moment of inertia will increase, which is used to reduce the peak-shaving response speed; N cmin ≤N c ≤N cmax Too little β results in large airflow disturbances and low efficiency; too much increases manufacturing difficulty and cost. min ≤β≤β max If the value is too small, the airflow will impact the leading edge of the blade, resulting in significant losses; if it is too large, the blade load will be too high, making it prone to fatigue fracture. cmin ≤π c ≤π cmax If the value is too small, multiple compression stages are required, increasing system complexity; if it is too large, the efficiency of a single stage drops sharply. IV. Buffer tank parameter constraints, V bmin ≤V b ≤V bmax If the pressure is too small, the pressure stabilization capability will be insufficient, and pressure fluctuations will exceed the standard; if it is too large, the equipment size and cost will increase, and the response will be delayed; D bmin ≤D b ≤D bmax If the inlet velocity is too small, the inlet flow velocity will exceed 15 m / s, resulting in a significant increase in resistance loss; if it is too large, it will be incompatible with the pipeline connection, increasing installation difficulty; bmin ≤γ b ≤γ bmax If the value is too small, the flow field inside the tank will be turbulent and the pressure stabilization effect will be poor; if the value is too large, the axial space requirement will be large and dead zones in the flow will be easily generated. Latin hypercube sampling is used to cover the parameter space, ensuring the diversity and representativeness of the combinations. The sample size is determined according to the parameter dimension.

4. The method according to claim 3, characterized in that, The performance metric dataset generated in step 1 includes: Based on the effective combination of equipment geometric parameters, performance simulation and quantitative analysis are performed on the effective combination of equipment geometric parameters to calculate system-level performance indicators: Dynamic indicators include peak shaving speed, peak shaving depth, instantaneous temperature change rate, and instantaneous pressure fluctuation. Static indicators: average efficiency under all operating conditions and cost per kilowatt-hour; By systematically integrating all effective parameter combinations and their corresponding performance results, a mapping dataset of system boundary parameters, equipment geometric parameter combinations, and performance indicators is formed.

5. The method according to claim 4, characterized in that, Step 2, the multi-objective optimization, includes: optimization of system boundary parameters. For a given set of system boundary parameters, samples of all device geometric parameters—performance indices—under the boundary conditions are extracted from the dataset to construct a multi-objective optimization model. ； An improved non-dominated sorting genetic algorithm NSGA-III is used to solve the Pareto optimal solution set. The weights are determined by the analytic hierarchy process (AHP), and the combination of comprehensive optimal performance indicators is selected. The corresponding combination of equipment geometric parameters is the optimal design parameter under the boundary conditions.

6. The method according to claim 5, characterized in that, This includes constructing an optimal solution mapping model across boundary parameters to cope with different system boundary parameters and predict the optimal solution under arbitrary boundary parameters; collecting multiple sets of optimal performance indices and equipment geometric parameters corresponding to different system boundary parameters, and using Gaussian process regression (GPR) to construct the mapping model. Input system boundary parameters; output optimal performance indicators and corresponding equipment geometric parameters; optimize model parameters through cross-validation to ensure prediction accuracy; finally, the established GPR mapping model is used to support the system in generating optimal design parameters and recommend equipment geometric configurations that match the optimal performance for different boundary parameters.

7. The method according to claim 6, characterized in that, Step 3 includes: For predictions under new boundary parameters, for any new set of system boundary parameters, input them into the trained mapping model, and directly output: the predicted value of the optimal system performance index; and the corresponding design value of the equipment geometric parameters.

8. The method according to claim 7, characterized in that, include: The model is iteratively updated. When the actual running data or new samples accumulate to a threshold scale, steps 1 to 2 are repeated to retrain the mapping model in order to improve its adaptability to complex boundary conditions. When new system boundary parameters are input, the optimized mapping model is used to predict the corresponding optimal static / dynamic performance indicators and equipment geometric parameters.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the multi-objective collaborative optimization method for the supercritical CO2 cycle system as described in any one of claims 1 to 8.

10. An electronic device, characterized in that, include: One or more processors; Memory; And one or more computer programs, wherein the one or more computer programs are stored in the memory, the one or more computer programs including instructions that, when executed by the device, cause the device to perform the multi-objective cooperative optimization method for the supercritical CO2 cycle system according to any one of claims 1 to 8.

Images