A method and system for optimizing the performance of a gas turbine generator set

Abstract

The application discloses a kind of gas turbine generator set performance optimization method and system, it is related to power generation technical field.The method comprises the following steps: initializing population;Based on the ratio of multiple light fuels in each fuel configuration scheme and the component parameters of various light fuels, the combustion parameters of each fuel configuration scheme are predicted by a combustion parameter prediction model;A target function is established with the objective of minimizing the comprehensive cost corresponding to the fuel configuration scheme;The fitness value of each individual is calculated;Based on the heat release constraint and the fitness value of the individual, select excellent individuals from the population;The population is updated by crossover and mutation operations;When the number of iterations reaches the maximum number of iterations, the individual that meets the heat release constraint and has the lowest fitness value is selected as the optimal individual, and the final fuel configuration scheme of the gas turbine generator set is determined based on the ratio of the light fuel corresponding to the optimal individual.The application can optimize the performance of the gas turbine generator set.

Description

Technical Field

[0001] This invention belongs to the field of power generation technology, specifically relating to a method and system for optimizing the performance of a gas turbine generator set. Background Technology

[0002] As a highly efficient power generation device, the choice and configuration of fuels for gas turbine generator sets have a significant impact on power generation efficiency, cost, and environmental performance. Traditional gas turbine generator sets can use various light fuels such as natural gas, diesel, liquefied petroleum, ethanol, and biomass fuels. However, with the diversification of energy structures and the increasing environmental requirements, fuel blending configuration methods for gas turbine generator sets have become a research hotspot.

[0003] Currently, most gas turbine generator sets still use a single light fuel for power generation to achieve specific goals, such as improving fuel combustion efficiency, reducing costs, or reducing pollutant emissions. However, using a single light fuel for power generation often fails to balance cost and pollution emissions. For example, using biomass fuel can significantly reduce costs but greatly increase pollutant emissions, while using ethanol can significantly reduce pollutant emissions but greatly increase power generation costs, affecting the performance parameters of the gas turbine generator set.

[0004] Therefore, how to provide an effective solution to improve the performance parameters of gas turbine generator sets has become an urgent problem to be solved in the existing technology. Summary of the Invention

[0005] The purpose of this invention is to provide a method and system for optimizing generator set performance, in order to solve the above-mentioned problems existing in the prior art.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] In a first aspect, the present invention provides a method for optimizing the performance of a gas turbine generator set, comprising:

[0008] Initialize a population, where each individual in the population represents a fuel configuration scheme, which records the proportions of various light fuels;

[0009] Based on the proportions of various light fuels and the composition parameters of various light fuels in each fuel configuration scheme, the combustion parameters of each fuel configuration scheme are predicted by a pre-trained combustion parameter prediction model. The combustion parameters include the calorific value and pollutant concentration of the mixed fuel corresponding to the fuel configuration scheme after combustion.

[0010] An objective function is established with the goal of minimizing the overall cost corresponding to the fuel configuration scheme. The overall cost corresponding to the fuel configuration scheme is the weighted sum of the fuel cost corresponding to the fuel configuration scheme and the pollutant concentration corresponding to the fuel configuration scheme.

[0011] Calculate the fitness value of each individual in the population;

[0012] Based on the calorific value constraint corresponding to the fuel configuration scheme and the fitness value of the individual, superior individuals are selected from the population;

[0013] Crossover and mutation operations are performed on the population to update it;

[0014] When the number of iterations reaches the maximum number of iterations, the individual in the latest population that satisfies the heat generation constraint and has the lowest corresponding fitness value is taken as the optimal individual. The final fuel configuration scheme of the gas turbine generator set is determined based on the proportion of light fuel corresponding to the optimal individual, so as to reduce the fuel cost and pollutant emissions of the gas turbine generator set.

[0015] In one possible design, the objective function is: Where n represents the type of light fuel in the fuel mix, and y i c represents the proportion of the i-th type of light fuel. i Let L represent the purchase cost of the i-th type of light fuel, L represent the pollutant concentration after combustion of the mixed fuel corresponding to the fuel configuration scheme, and α and β both represent weights, with α+β=1.

[0016] In one possible design, based on the calorific value constraint corresponding to the fuel configuration scheme and the fitness value of the individual, superior individuals are selected from the population, including:

[0017] Based on the calorific value constraint corresponding to the fuel configuration scheme and the fitness value of the individuals, the top K individuals with the calorific value of the corresponding mixed fuel combustion being greater than the preset calorific value and the lowest fitness value are selected from the population as excellent individuals, where K≤Z / 2, and Z represents the total number of individuals in the population.

[0018] In one possible design, when performing crossover and mutation operations on the population, the crossover probability is 0.8 and the mutation probability is 0.1.

[0019] In one possible design, the composition parameters of light fuel are the content of the main components of light fuel, or the content of hydrocarbons, hydrogen, sulfur, aromatics, olefins and / or impurities in light fuel.

[0020] In one possible design, the pollutant concentration includes sulfur oxide concentration, nitrogen oxide concentration and / or particulate matter concentration.

[0021] In one possible design, the combustion parameter prediction model is a backpropagation neural network model.

[0022] Secondly, the present invention provides a gas turbine generator set performance optimization system, comprising:

[0023] An initialization unit is used to initialize a population, wherein each individual in the population represents a fuel configuration scheme, and the fuel configuration scheme records the proportions of various light fuels.

[0024] The prediction unit is used to predict the combustion parameters of each fuel configuration scheme based on the proportion of various light fuels and the composition parameters of various light fuels in each fuel configuration scheme, through a pre-trained combustion parameter prediction model. The combustion parameters include the calorific value and pollutant concentration of the mixed fuel corresponding to the fuel configuration scheme after combustion.

[0025] A unit is established to establish an objective function with the goal of minimizing the overall cost corresponding to the fuel configuration scheme. The overall cost corresponding to the fuel configuration scheme is the weighted sum of the fuel cost corresponding to the fuel configuration scheme and the pollutant concentration corresponding to the fuel configuration scheme.

[0026] A computing unit is used to calculate the fitness value of each individual in the population;

[0027] The selection unit is used to select superior individuals from the population based on the calorific value constraint corresponding to the fuel configuration scheme and the individual's fitness value.

[0028] The update unit is used to perform crossover and mutation operations on the population to update the population;

[0029] The unit is determined when the number of iterations reaches the maximum number of iterations. It selects the individual in the latest population that satisfies the heat generation constraint and has the lowest corresponding fitness value as the optimal individual, and determines the final fuel configuration scheme of the gas turbine generator set based on the proportion of light fuel corresponding to the optimal individual, so as to reduce the fuel cost and pollutant emissions of the gas turbine generator set.

[0030] Thirdly, the present invention provides a computer device comprising a memory, a processor, and a transceiver connected in sequence and communication, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the gas turbine generator set performance optimization method as described in the first aspect or any possible design of the first aspect.

[0031] Fourthly, the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, perform the gas turbine generator set performance optimization method described in the first aspect or any possible design of the first aspect.

[0032] Fifthly, the present invention provides a computer program product containing instructions that, when executed on a computer, cause the computer to perform the gas turbine generator set performance optimization method as described in the first aspect or any possible design of the first aspect.

[0033] Beneficial effects:

[0034] This invention initializes a population, where each individual represents a fuel configuration scheme, recording the proportions of various light fuels. Based on the proportions of these light fuels and their component parameters, a pre-trained combustion parameter prediction model predicts the combustion parameters of each fuel configuration scheme. These combustion parameters include the calorific value and pollutant concentration of the fuel mixture corresponding to each fuel configuration scheme. An objective function is established to minimize the overall cost corresponding to each fuel configuration scheme, where the overall cost is the calorific value of the fuel mixture corresponding to the chosen fuel configuration scheme. The process involves: weighting the fuel cost and the pollutant concentration corresponding to the fuel configuration scheme; calculating the fitness value of each individual in the population; selecting superior individuals from the population based on the calorific value constraint corresponding to the fuel configuration scheme and the individual's fitness value; performing crossover and mutation operations on the population to update it; when the maximum number of iterations is reached, selecting the individual with the lowest fitness value in the latest population that satisfies the calorific value constraint as the optimal individual, and determining the final fuel configuration scheme of the gas turbine generator set based on the proportion of light fuel corresponding to the optimal individual, thereby reducing the fuel cost and pollutant emissions of the gas turbine generator set. In this way, when selecting and configuring fuel for a gas turbine generator set, the fuel cost and pollutant emission concentration corresponding to the fuel configuration scheme can be comprehensively considered while ensuring calorific value, enabling the gas turbine generator set to achieve lower pollutant emissions with lower fuel costs as much as possible. Furthermore, fuel improvement optimizes the performance of the gas turbine generator set, facilitating practical application and promotion. Attached Figure Description

[0035] Figure 1 A flowchart of a gas turbine generator set performance optimization method provided in an embodiment of this application;

[0036] Figure 2 A block diagram of a gas turbine generator set performance optimization system provided in an embodiment of this application;

[0037] Figure 3 This is a block diagram of a computer device provided in an embodiment of this application. Detailed Implementation

[0038] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in conjunction with the accompanying drawings and descriptions of the embodiments or the prior art. Obviously, the following description of the structure of the accompanying drawings is 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. It should be noted that the description of these embodiments is for the purpose of helping to understand the present invention, but does not constitute a limitation of the present invention.

[0039] It should be understood that although the terms first, second, etc., may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit, without departing from the scope of the exemplary embodiments of the invention.

[0040] It should be understood that the term "and / or" that may appear in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, B exists alone, and A and B exist simultaneously. The term " / and" that may appear in this document describes another relationship between related objects, indicating that two relationships can exist. For example, A / and B can mean: A exists alone, and A and B exist alone. In addition, the character " / " that may appear in this document generally indicates that the related objects before and after it are in an "or" relationship.

[0041] It should be understood that specific details are provided in the following description to facilitate a complete understanding of the exemplary embodiments. However, those skilled in the art will understand that the exemplary embodiments can be implemented without these specific details. For example, the system may be shown in block diagrams to avoid obscuring the example with unnecessary details. In other instances, well-known processes, structures, and techniques may be shown without unnecessary details to avoid obscuring the exemplary embodiments.

[0042] To improve the performance parameters of gas turbine generator sets, this application provides a gas turbine generator set performance optimization method and system. This gas turbine generator set performance optimization method and system can enable the gas turbine generator set to achieve lower pollutant emissions with lower fuel costs, thereby improving the performance of the gas turbine generator set.

[0043] The gas turbine generator set performance optimization method provided in this application embodiment can be executed, but is not limited to, by a computer device or virtual machine with certain computing resources, such as by a personal computer, smartphone or personal digital assistant or other electronic device, or by a virtual machine.

[0044] like Figure 1 The diagram shown is a flowchart of a gas turbine generator set performance optimization method provided in the first aspect of the present application. The gas turbine generator set performance optimization method may include, but is not limited to, the following steps S101-S107.

[0045] Step S101. Initialize the population.

[0046] Each individual in the population represents a fuel configuration scheme, which records the proportions of various light fuels.

[0047] In this embodiment, two or more light fuels can be selected and mixed in a certain proportion to form a fuel configuration scheme. By adjusting the proportion of each light fuel, multiple fuel configuration schemes can be obtained, each fuel configuration scheme corresponding to an individual (particle) in a population. For example, natural gas and biomass fuel can be mixed to improve the combustion efficiency of the mixed fuel and reduce carbon dioxide emissions; natural gas and liquefied petroleum gas can be mixed to improve the combustion efficiency of the mixed fuel and reduce sulfur oxide emissions; gasoline and ethanol can be mixed to improve the combustion efficiency of the mixed fuel and reduce carbon monoxide emissions; and oilfield oil and liquefied natural gas can be mixed to improve the combustion efficiency of the mixed fuel and reduce sulfur oxide emissions, etc.

[0048] Step S102. Based on the proportion of various light fuels and the composition parameters of various light fuels in each fuel configuration scheme, the combustion parameters of each fuel configuration scheme are predicted by a pre-trained combustion parameter prediction model.

[0049] In this embodiment, a combustion parameter prediction model for predicting combustion parameters of various fuel configuration schemes can be pre-trained. This model can be trained using the proportions of multiple sample light fuels and their component parameters as inputs, and the combustion parameters of the sample fuel configuration schemes as outputs. The combustion parameter prediction model can be, but is not limited to, a back propagation (BP) neural network model, a convolutional neural network (CNN) model, etc., and is not specifically limited in this embodiment.

[0050] In the performance optimization of gas turbine generator sets, the proportions of various light fuels and their composition parameters in each fuel configuration scheme can be used as inputs to a combustion parameter prediction model, outputting the combustion parameters for each fuel configuration scheme. The composition parameters of the light fuels can be the content of their main components (e.g., the content of methane (CH4) in natural gas, the content of propane (C3H8) and butane (C4H10) in liquefied petroleum gas), or the content of hydrocarbons, hydrogen, sulfur, aromatics, olefins, and / or impurities. Combustion parameters may include, but are not limited to, the calorific value and pollutant concentration after combustion of the mixed fuels corresponding to the fuel configuration scheme. The pollutant concentration may include, but is not limited to, sulfur oxide concentration, nitrogen oxide concentration, and / or particulate matter concentration.

[0051] Step S103. Establish an objective function with the goal of minimizing the overall cost corresponding to the fuel configuration scheme.

[0052] The comprehensive cost corresponding to the fuel configuration scheme is the weighted sum of the fuel cost corresponding to the fuel configuration scheme and the pollutant concentration corresponding to the fuel configuration scheme. In this embodiment, the objective function can be expressed as: Where n represents the type of light fuel in the fuel mix, and y i c represents the proportion of the i-th type of light fuel. i Let L represent the purchase cost of the i-th type of light fuel, L represent the pollutant concentration after combustion of the mixed fuel corresponding to the fuel configuration scheme, α and β both represent weights, and α+β=1. The values ​​of α and β can be taken based on the degree of importance attached to cost and pollutant emissions.

[0053] Step S104. Calculate the fitness value of each individual in the population.

[0054] In this embodiment of the application, the comprehensive cost of the fuel configuration scheme corresponding to each individual in the population can be calculated based on the established objective function, and the comprehensive cost of the fuel configuration scheme corresponding to each individual can be used as the fitness value of the individual, and the fitness value of each individual in the population can be calculated accordingly.

[0055] Step S105. Based on the calorific value constraint corresponding to the fuel configuration scheme and the fitness value of the individual, select superior individuals from the population.

[0056] Specifically, based on the calorific value constraint corresponding to the fuel configuration scheme and the fitness value of individuals, the top K individuals with the lowest fitness values ​​after the combustion of the corresponding mixed fuel are selected from the population as superior individuals, where K ≤ Z / 2, and Z represents the total number of individuals in the population. The calorific value constraint corresponding to the fuel configuration scheme can refer to the minimum calorific value requirement of the mixed fuel corresponding to the fuel configuration scheme, which can be set based on practical experience.

[0057] It should be noted that after selecting superior individuals from the population, the number of individuals in the population will be lower than the number of individuals in the original population. Therefore, after selecting superior individuals from the population, some individuals can be randomly generated to supplement the population so that the number of individuals in the population is equal to the number of individuals in the original population.

[0058] Step S106. Perform crossover and mutation operations on the population to update the population.

[0059] In this embodiment of the application, the crossover probability and mutation probability can be set according to the actual situation. For example, the crossover probability can be 0.8 and the mutation probability can be 0.1.

[0060] Step S107. When the number of iterations reaches the maximum number of iterations, the individual in the latest population that satisfies the heat generation constraint and has the lowest corresponding fitness value is taken as the optimal individual, and the final fuel configuration scheme of the gas turbine generator set is determined based on the proportion of light fuel corresponding to the optimal individual, so as to reduce the fuel cost and pollutant emissions of the gas turbine generator set.

[0061] The gas turbine generator set performance optimization method provided by this invention initializes a population, where each individual represents a fuel configuration scheme, and the fuel configuration scheme records the proportions of various light fuels. Based on the proportions of various light fuels and the component parameters of each light fuel in each fuel configuration scheme, a pre-trained combustion parameter prediction model predicts the combustion parameters of each fuel configuration scheme. The combustion parameters include the calorific value and pollutant concentration after combustion of the mixed fuel corresponding to the fuel configuration scheme. An objective function is established with the goal of minimizing the comprehensive cost corresponding to the fuel configuration scheme, where the comprehensive cost corresponding to the fuel configuration scheme is the fuel cost. The process involves: summing the weighted values ​​of fuel cost and pollutant concentration corresponding to the fuel configuration scheme; calculating the fitness value of each individual in the population; selecting superior individuals from the population based on the calorific value constraint corresponding to the fuel configuration scheme and the individual's fitness value; performing crossover and mutation operations on the population to update it; when the maximum number of iterations is reached, selecting the individual with the lowest fitness value in the latest population that satisfies the calorific value constraint as the optimal individual; and determining the final fuel configuration scheme of the gas turbine generator set based on the proportion of light fuel corresponding to the optimal individual to reduce the fuel cost and pollutant emissions of the gas turbine generator set. In this way, when selecting and configuring fuel for gas turbine generator sets, the fuel cost and pollutant emission concentration corresponding to the fuel configuration scheme can be comprehensively considered while ensuring calorific value, thereby enabling the gas turbine generator set to achieve lower pollutant emissions with lower fuel costs. Furthermore, fuel improvement optimizes the performance of the gas turbine generator set, facilitating practical application and promotion.

[0062] Please see Figure 2 The second aspect of this application provides a gas turbine generator set performance optimization system, which includes:

[0063] An initialization unit is used to initialize a population, wherein each individual in the population represents a fuel configuration scheme, and the fuel configuration scheme records the proportions of various light fuels.

[0064] The prediction unit is used to predict the combustion parameters of each fuel configuration scheme based on the proportion of various light fuels and the composition parameters of various light fuels in each fuel configuration scheme, through a pre-trained combustion parameter prediction model. The combustion parameters include the calorific value and pollutant concentration of the mixed fuel corresponding to the fuel configuration scheme after combustion.

[0065] A unit is established to establish an objective function with the goal of minimizing the overall cost corresponding to the fuel configuration scheme. The overall cost corresponding to the fuel configuration scheme is the weighted sum of the fuel cost corresponding to the fuel configuration scheme and the pollutant concentration corresponding to the fuel configuration scheme.

[0066] A computing unit is used to calculate the fitness value of each individual in the population;

[0067] The selection unit is used to select superior individuals from the population based on the calorific value constraint corresponding to the fuel configuration scheme and the individual's fitness value.

[0068] The update unit is used to perform crossover and mutation operations on the population to update the population;

[0069] The unit is determined when the number of iterations reaches the maximum number of iterations. It selects the individual in the latest population that satisfies the heat generation constraint and has the lowest corresponding fitness value as the optimal individual, and determines the final fuel configuration scheme of the gas turbine generator set based on the proportion of light fuel corresponding to the optimal individual, so as to reduce the fuel cost and pollutant emissions of the gas turbine generator set.

[0070] The working process, working details and technical effects of the gas turbine generator set performance optimization system provided in the second aspect of this embodiment can be found in the first aspect of the embodiment, and will not be repeated here.

[0071] Please see Figure 3 The third aspect of this application provides a computer device, including a memory, a processor, and a transceiver that are sequentially and communicatively connected, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the gas turbine generator set performance optimization method as described in the first aspect of the application.

[0072] Specifically, the memory may include, but is not limited to, random access memory (RAM), read-only memory (ROM), flash memory, first-in-first-out (FIFO) memory, and / or last-in-first-out (FILO) memory, etc.; the processor may not be limited to microprocessors of the STM32F105 series, ARM (Advanced RISC Machines), x86 architecture processors, or processors with integrated NPU (neural-network processing units); the transceiver may be, but is not limited to, WiFi (Wireless Fidelity) wireless transceivers, Bluetooth wireless transceivers, General Packet Radio Service (GPRS) wireless transceivers, ZigBee (a low-power LAN protocol based on the IEEE 802.15.4 standard), 3G transceivers, 4G transceivers, and / or 5G transceivers, etc.

[0073] This fourth aspect of the embodiment provides a computer-readable storage medium storing instructions containing the gas turbine generator set performance optimization method described in the first aspect of the embodiment. Specifically, the computer-readable storage medium stores instructions that, when executed on a computer, perform the gas turbine generator set performance optimization method as described in the first aspect. The computer-readable storage medium refers to a data storage medium, which may include, but is not limited to, floppy disks, optical disks, hard disks, flash memory, USB flash drives, and / or Memory Sticks. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0074] The fifth aspect of this embodiment provides a computer program product containing instructions that, when executed on a computer, cause the computer to perform the gas turbine generator set performance optimization method as described in the first aspect of this embodiment, wherein the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.

[0075] Finally, it should be noted that the above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of 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 method for optimizing the performance of a gas turbine generator set, characterized in that, include: Initialize a population, where each individual in the population represents a fuel configuration scheme, which records the proportions of various light fuels; Based on the proportions of various light fuels and the composition parameters of various light fuels in each fuel configuration scheme, the combustion parameters of each fuel configuration scheme are predicted by a pre-trained combustion parameter prediction model. The combustion parameters include the calorific value and pollutant concentration of the mixed fuel corresponding to the fuel configuration scheme after combustion. An objective function is established with the goal of minimizing the overall cost corresponding to the fuel configuration scheme. The overall cost corresponding to the fuel configuration scheme is the weighted sum of the fuel cost corresponding to the fuel configuration scheme and the pollutant concentration corresponding to the fuel configuration scheme. The comprehensive cost of the fuel configuration scheme corresponding to each individual in the population is calculated based on the objective function, and the comprehensive cost of the fuel configuration scheme corresponding to each individual is used as the fitness value of the individual. The fitness value of each individual in the population is then calculated. Based on the calorific value constraint corresponding to the fuel configuration scheme and the fitness value of the individual, superior individuals are selected from the population; Crossover and mutation operations are performed on the population to update it; When the number of iterations reaches the maximum number of iterations, the individual in the latest population that satisfies the heat generation constraint and has the lowest corresponding fitness value is taken as the optimal individual. The final fuel configuration scheme of the gas turbine generator set is determined based on the proportion of light fuel corresponding to the optimal individual, so as to reduce the fuel cost and pollutant emissions of the gas turbine generator set.

2. The method for optimizing the performance of a gas turbine generator set according to claim 1, characterized in that, The objective function is: Where n represents the type of light fuel in the fuel mix, and y i c represents the proportion of the i-th type of light fuel. i Let L represent the purchase cost of the i-th type of light fuel, L represent the pollutant concentration after combustion of the mixed fuel corresponding to the fuel configuration scheme, and α and β both represent weights, with α+β=1.

3. The method for optimizing the performance of a gas turbine generator set according to claim 1, characterized in that, Based on the calorific value constraint corresponding to the fuel configuration scheme and the fitness value of the individual, superior individuals are selected from the population, including: Based on the calorific value constraint corresponding to the fuel configuration scheme and the fitness value of the individuals, the top K individuals with the calorific value of the corresponding mixed fuel combustion being greater than the preset calorific value and the lowest fitness value are selected from the population as excellent individuals, where K≤Z / 2, and Z represents the total number of individuals in the population.

4. The method for optimizing the performance of a gas turbine generator set according to claim 1, characterized in that, When performing crossover and mutation operations on the population, the crossover probability is 0.8 and the mutation probability is 0.

1.

5. The method for optimizing the performance of a gas turbine generator set according to claim 1, characterized in that, The composition parameters of light fuels are the content of the main components of light fuels, or the content of hydrogen, sulfur, aromatic hydrocarbons and olefins in light fuels.

6. The method for optimizing the performance of a gas turbine generator set according to claim 1, characterized in that, The pollutant concentrations include sulfur oxide concentrations, nitrogen oxide concentrations, and / or particulate matter concentrations.

7. The method for optimizing the performance of a gas turbine generator set according to claim 1, characterized in that, The combustion parameter prediction model is a backpropagation neural network model.

8. A performance optimization system for a gas turbine generator set, characterized in that, include: An initialization unit is used to initialize a population, wherein each individual in the population represents a fuel configuration scheme, and the fuel configuration scheme records the proportions of various light fuels. The prediction unit is used to predict the combustion parameters of each fuel configuration scheme based on the proportion of various light fuels and the composition parameters of various light fuels in each fuel configuration scheme, through a pre-trained combustion parameter prediction model. The combustion parameters include the calorific value and pollutant concentration of the mixed fuel corresponding to the fuel configuration scheme after combustion. A unit is established to establish an objective function with the goal of minimizing the overall cost corresponding to the fuel configuration scheme. The overall cost corresponding to the fuel configuration scheme is the weighted sum of the fuel cost corresponding to the fuel configuration scheme and the pollutant concentration corresponding to the fuel configuration scheme. The computing unit is used to calculate the comprehensive cost of the fuel configuration scheme corresponding to each individual in the population based on the objective function, and to use the comprehensive cost of the fuel configuration scheme corresponding to each individual as the fitness value of the individual, and to calculate the fitness value of each individual in the population. The selection unit is used to select superior individuals from the population based on the calorific value constraint corresponding to the fuel configuration scheme and the individual's fitness value. The update unit is used to perform crossover and mutation operations on the population to update the population; The unit is determined when the number of iterations reaches the maximum number of iterations. It selects the individual in the latest population that satisfies the heat generation constraint and has the lowest corresponding fitness value as the optimal individual, and determines the final fuel configuration scheme of the gas turbine generator set based on the proportion of light fuel corresponding to the optimal individual, so as to reduce the fuel cost and pollutant emissions of the gas turbine generator set.

Images