Engineering rapid calculation system for comprehensive performance of Brayton cycle
By using the Brayton cycle module and neural network method, the problems of high experimental difficulty and insufficient quantitative calculation in the engineering application of Brayton cycle are solved, realizing fast and accurate system performance evaluation and parameter optimization, improving system efficiency and reducing operation and maintenance costs.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHINA THREE GORGES CORPORATION
- Filing Date
- 2025-12-09
- Publication Date
- 2026-04-14
AI Technical Summary
In existing engineering applications of Brayton cycles, experiments are difficult and costly, and there is a lack of systematic parameter sensitivity analysis. Existing studies are mostly qualitative analyses and lack quantitative calculations, which cannot meet the needs of rapid optimization.
The system employs a Brayton cycle module to calculate multiple operating parameters, combines a neural network method to rank the parameters by importance, and performs comprehensive performance analysis through quantitative calculation modules for efficiency, output power, and heat supply, thereby achieving fast and accurate engineering calculations.
It enables rapid evaluation of Brayton cycle system performance, improves calculation accuracy and work efficiency, reduces operation and maintenance costs, and supports on-site parameter optimization.
Smart Images
Figure CN121859698A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of dynamic cycle calculation, and in particular to an engineered fast calculation system for the comprehensive performance of Brayton cycles. Background Technology
[0002] The power cycle is the core component that converts thermal energy into mechanical or electrical energy. In the field of solar thermal power generation, the Brayton cycle is hailed as a representative of third-generation technology due to its high efficiency potential and is becoming a hot topic in power cycle research.
[0003] Currently, as an emerging power generation technology, the engineering application and optimization of the Brayton cycle suffers from the following shortcomings: First, the high difficulty and cost of testing result in limited experimental data available for analysis. This leads to insufficient research on the impact mechanisms of system operating parameters, such as pressure and temperature, on cycle performance indicators, and a lack of systematic ranking and screening of the sensitivity of different parameters. Second, existing research largely focuses on qualitative analysis of single parameters or relies on complex one-dimensional simulation models. For engineers, the process of remodeling and calculating is cumbersome and cannot meet the needs of on-site operation and maintenance and rapid parameter optimization. Engineering practice urgently needs a method that can directly and quickly evaluate the overall system performance. Third, existing system performance evaluation methods, such as qualitative analysis based on hierarchical models, while capable of systematic evaluation, often lack specific quantitative calculation formulas, making it difficult to achieve accurate and rapid prediction and evaluation of Brayton cycle performance. Summary of the Invention
[0004] The main objective of this invention is to provide an engineering-based rapid calculation system for the comprehensive performance of the Brayton cycle, which solves the problems of insufficient experimental data and analysis, complex modeling and cumbersome calculation, and insufficient accuracy in the prior art.
[0005] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is: an engineering-based fast calculation system for Brayton cycle synthesis performance, comprising: The Brayton cycle module is used to calculate the Brayton cycle efficiency under multiple operating parameters, including turbine inlet temperature, compressor inlet temperature, maximum operating pressure, pressure ratio, compressor efficiency, turbine efficiency, and heat exchanger efficiency. The neural network method module is used to sort the importance of multiple operating parameters based on the collected Brayton cycle efficiency using the control variable method, and to filter out multiple important parameters, including turbine inlet temperature and pressure ratio. The comprehensive performance calculation module includes an efficiency quantitative calculation module, an output work quantitative calculation module, and a heat supply quantitative calculation module. It is used to perform quantitative analysis of the corresponding performance of the Brayton cycle based on the multiple important parameters, and derive the corresponding performance engineering rapid calculation formula.
[0006] In a preferred embodiment, the Brayton cycle module includes: The heater submodule is used to use the supplied heat to raise the temperature of the working medium at the turbine inlet. The turbine submodule is used to convert the enthalpy difference between the turbine inlet and outlet into shaft work. The compressor submodule is used to allocate a portion of the shaft power to increase the temperature and entropy of the working medium at the compressor outlet; The precooler submodule is used to further cool the temperature of the working medium to meet the parameter requirements at the compressor inlet. The heat exchanger submodule uses a counter-current heat exchanger to exchange heat between the two working media, thereby increasing the temperature at the heater inlet and decreasing the temperature at the turbine outlet.
[0007] In the preferred embodiment, the key configuration parameters of the neural network method module include the neuron submodule, the multiple feedforward connection submodule, the training method submodule, the training function submodule, the learning rate submodule, the momentum coefficient submodule, and the iteration step size submodule. The neuron submodule acts as multiple computation nodes in the process of multiple inputs and single outputs. The number of neuron layers is set to 2 to ensure computational accuracy. The multi-feedforward connection submodule is responsible for determining the output based on the weights, biases, and input parameters. The training method submodule is responsible for calculating the weight gradient and adjusting the weights using the gradient. It is set to batch backpropagation to achieve faster convergence speed and better prediction performance. The training function submodule is responsible for training the neural network, which learns the input data and outputs the object's output parameters; The learning rate submodule is used to control the frequency of parameter updates during the learning process; The momentum coefficient submodule controls the intensity of weight updates based on the directional characteristics of the current gradient and the previous gradient.
[0008] In the preferred embodiment, the efficiency quantitative calculation module utilizes several selected key parameters and employs the high-precision prediction characteristics of neural networks to quantitatively analyze the Brayton cycle efficiency, deriving a rapid engineering calculation formula, including: The formula for calculating efficiency in the Brayton cycle model is: ; In the formula, For the efficiency of the Brayton cycle; This is the enthalpy value at the turbine outlet; This is the enthalpy value at the turbine inlet; This is the enthalpy value at the compressor outlet; This is the enthalpy value at the compressor inlet; This is the enthalpy value at the heater outlet; This is the enthalpy value at the heater inlet; The general quantitative equation for the Brayton cycle efficiency output by the neural network is: ; In the formula, For the predicted value of efficiency; to These are the parameter values for the quantitative analysis equation; and These are the turbine inlet temperature and pressure ratio, respectively.
[0009] In the preferred embodiment, the output work quantitative calculation module utilizes several selected important parameters and employs a neural network method to obtain the output work quantitative analysis equation of the Brayton cycle, including: The formula for calculating the output work in the Brayton cycle model is: ; In the formula, This represents the output work of the Brayton cycle; This is the enthalpy value at the turbine outlet; This is the enthalpy value at the turbine inlet; The general quantitative analysis equation for the work output by the Brayton cycle from the neural network is: ; In the formula, This is the predicted value of the output work; to These are the parameter values for the quantitative analysis equation; and These are the turbine inlet temperature and pressure ratio, respectively.
[0010] In the preferred embodiment, the heat supply quantitative calculation module obtains the heat supply quantitative analysis equation for the Brayton cycle based on several selected important parameters using a neural network method, including: The formula for calculating the heat supply of a Brayton cycle is: ; In the formula, For the heat supply of the Brayton cycle, This is the enthalpy value at the heater outlet; This is the enthalpy value at the heater inlet; The general quantitative analysis equation for the Brayton cycle heat supply output by the neural network is as follows: ; In the formula, This is the predicted value for heat supply; to These are the parameter values for the quantitative analysis equation; and These are the turbine inlet temperature and pressure ratio, respectively.
[0011] In the preferred embodiment, the neural network method module uses the control variable method and employs... The indicators are used to determine the importance of multiple operating parameters. Taking efficiency as an example, The formula for calculating the coefficient of determination is: ; In the formula, The coefficient of determination; This represents the average of the actual efficiency values. This represents the average of the predicted efficiency values.
[0012] In the preferred embodiment, the efficiency calculation formula for the turbine submodule is as follows: ; In the formula, This represents the efficiency value of the turbine submodule. This is the enthalpy value at the inlet of the turbine submodule; This refers to the enthalpy value at the outlet of the turbine submodule; This is the isentropic enthalpy value at the outlet of the turbine submodule.
[0013] In the preferred embodiment, the efficiency calculation formula for the compressor submodule is as follows: ; In the formula, This refers to the efficiency value of the compressor submodule. This is the isentropic enthalpy value at the outlet of the compressor submodule; This is the enthalpy value at the inlet of the compressor submodule; This is the enthalpy value at the outlet of the compressor submodule.
[0014] In the preferred embodiment, the efficiency calculation formula for the heat exchanger submodule is as follows: ; In the formula, This refers to the efficiency value of the heat exchanger submodule. This is the enthalpy value at the cold fluid outlet of the heat exchanger submodule; This refers to the enthalpy value at the cold fluid inlet of the heat exchanger submodule; This refers to the enthalpy value at the hot fluid inlet of the heat exchanger submodule; This refers to the temperature at the cold fluid inlet of the heat exchanger submodule. This refers to the pressure at the hot fluid outlet of the heat exchanger submodule.
[0015] This invention provides an engineering-based rapid calculation system for the comprehensive performance of the Brayton cycle. The Brayton cycle module calculates the efficiency of the Brayton cycle under multiple operating parameters. The neural network method module sorts the collected Brayton cycle efficiencies using a controlled variable method, ranking the importance of multiple operating parameters and selecting two key parameters. The engineering calculation module, based on these key parameters, quantitatively analyzes the comprehensive performance indicators of the Brayton cycle, such as efficiency, output work, and heat supply, and derives engineering-based rapid calculation formulas. This system automates the process from parameter selection to quantitative performance calculation, allowing for rapid result acquisition by substituting key parameters without complex modeling, thus improving calculation accuracy and work efficiency. It also enables rapid evaluation of the system's comprehensive performance under different operating conditions, allowing for timely parameter adjustments to improve system efficiency and reduce maintenance costs. Attached Figure Description
[0016] The present invention will be further described below with reference to the accompanying drawings and embodiments: Figure 1 This is a schematic diagram of the overall system flow of the fast calculation method of the present invention; Figure 2 This is a schematic diagram of the Brayton loop module program of the fast calculation method of the present invention; Figure 3 This is a schematic diagram of the neural network module program used in this invention; Figure 4 This is a schematic diagram of the efficiency quantitative calculation module program of the present invention; Figure 5 This is a schematic diagram of the net work quantity calculation module program of the present invention; Figure 6 This is a schematic diagram of the heat supply quantitative calculation module program of the present invention; Figure 7 This is a schematic diagram of the neural network structure of the present invention. Detailed Implementation
[0017] Example 1 like Figure 1-7 As shown, an engineering-grade fast calculation system for Brayton cycle synthesis performance includes the following steps: The Brayton cycle module is used to calculate the Brayton cycle efficiency under multiple operating parameters, including turbine inlet temperature, compressor inlet temperature, maximum operating pressure, pressure ratio, compressor efficiency, turbine efficiency, and heat exchanger efficiency.
[0018] The neural network method module is used to sort the importance of multiple operating parameters based on the collected Brayton cycle efficiency using the control variable method, and to filter out multiple important parameters, including turbine inlet temperature and pressure ratio.
[0019] The comprehensive performance calculation module includes an efficiency quantitative calculation module, an output work quantitative calculation module, and a heat supply quantitative calculation module. It is used to perform quantitative analysis of the corresponding performance of the Brayton cycle based on the multiple important parameters, and derive the corresponding performance engineering rapid calculation formula.
[0020] In this embodiment, the Brayton cycle module is responsible for calculating the Brayton cycle efficiency under multiple operating parameters. The neural network method module sorts the importance of multiple operating parameters using the controlled variable method based on the collected Brayton cycle efficiency and selects two important parameters. Based on the two important parameters, the engineering calculation module performs quantitative analysis on the comprehensive performance indicators of the Brayton cycle, such as efficiency, output work, and heat supply, and derives a rapid engineering calculation formula. This realizes an automated process from parameter selection to quantitative performance calculation, allowing for rapid results by substituting key parameters without complex modeling, thus improving calculation accuracy and work efficiency. It also enables rapid evaluation of the system's comprehensive performance under different operating conditions, thereby allowing for timely parameter adjustments to improve system efficiency and reduce operation and maintenance costs.
[0021] In this embodiment, seven operating parameters are used, including: 1. The main pressure and temperature boundary conditions and component performance parameters that constitute the Brayton cycle design point, as shown in Table 1; 2. The remaining operating parameters refer to the intermediate parameters generated during the calculation process, as shown in Table 2.
[0022] Table 1. Temperature Boundary Conditions and Component Performance Parameters
[0023] Table 2 Intermediate Parameter Data Table
[0024] In this embodiment, two parameters with the greatest influence are selected from the above-mentioned parameters using neural networks and the controlled variable method. Based on thermodynamic principles and engineering practice, as well as the form of quantitative analysis equations in the patent document, this embodiment uses two important parameters: pressure ratio and turbine inlet temperature.
[0025] The selection of the number and types of multiple important parameters in this embodiment can be adapted to different system design goals, working fluids and operating conditions. Important parameters can be modified adaptively among multiple operating parameters according to specific circumstances. It also includes: compressor inlet temperature, compressor inlet pressure, or regenerator efficiency or component isentropic efficiency, etc.
[0026] In the preferred solution, such as Figure 7As shown, the key configuration parameters of the neural network method module include the neuron submodule, the multiple feedforward connection submodule, the training method submodule, the training function submodule, the learning rate submodule, the momentum coefficient submodule, and the iteration step size submodule. The neuron submodule acts as multiple computation nodes in the process of multiple inputs and single outputs. The number of neuron layers is set to 2 to ensure computational accuracy.
[0027] The multi-feedforward connection submodule is responsible for determining the output based on the weights, biases, and input parameters.
[0028] The training method submodule is responsible for calculating the weight gradient and adjusting the weights using the gradient. It is set to batch backpropagation to achieve faster convergence and better prediction performance.
[0029] The training function submodule is responsible for training the neural network, which learns the input data and outputs the object's output parameters; The learning rate submodule is used to control the frequency of parameter updates during the learning process.
[0030] The momentum coefficient submodule controls the intensity of weight updates based on the directional characteristics of the current gradient and the previous gradient.
[0031] In the preferred embodiment, the neural network method module uses the control variable method and employs... The indicators are used to determine the importance of multiple operating parameters. Taking efficiency as an example, The formula for calculating the coefficient of determination is: ; In the formula, The coefficient of determination; This represents the average of the actual efficiency values. This represents the average of the predicted efficiency values.
[0032] Based on several key parameters selected, this embodiment utilizes the powerful nonlinear fitting capability of neural networks to derive quantitative formulas for calculating the thermal efficiency, output work, and heat supply of a Brayton cycle. The process is simple and fast, eliminating the need to reconstruct complex physical models and perform iterative calculations. By simply substituting the key parameters, the predicted values of core performance indicators can be obtained quickly and accurately, resulting in high-precision, fast engineering calculation formulas that greatly improve computational efficiency and engineering practicality.
[0033] In the preferred scheme, the efficiency quantitative calculation module utilizes two key parameters—the turbine inlet temperature and pressure ratio—and employs the high-precision prediction capabilities of neural networks to quantitatively analyze the Brayton cycle efficiency, deriving a rapid engineering calculation formula, including: The formula for calculating efficiency in the Brayton cycle model is: ; In the formula, For the efficiency of the Brayton cycle; This is the enthalpy value at the turbine outlet; This is the enthalpy value at the turbine inlet; This is the enthalpy value at the compressor outlet; This is the enthalpy value at the compressor inlet; This is the enthalpy value at the heater outlet; This is the enthalpy value at the heater inlet.
[0034] The general quantitative equation for the efficiency of the Brayton cycle is: ; In the formula, For the predicted value of efficiency; to These are the parameter values for the quantitative analysis equation; and These are two important operating parameters, namely the turbine inlet temperature and pressure ratio.
[0035] In this embodiment, the relevant parameters in the quantitative formula output by the neural network are: to The values are 0.581858, 0.798717, -0.034924, -3.129586, 0.884225, -0.085913, 0.260804, -0.609661, and 0.044601.
[0036] In the preferred scheme, the output work quantitative calculation module uses two key parameters—the turbine inlet temperature and pressure ratio—selected from the selection process, and employs a neural network method to obtain the quantitative analysis equation for the output work of the Brayton cycle, including: The formula for calculating the work output of a Brayton cycle is: ; In the formula, This represents the output work of the Brayton cycle; This is the enthalpy value at the turbine outlet; This is the enthalpy value at the turbine inlet.
[0037] The general quantitative analysis equation for the work output by the Brayton cycle from the neural network is: ; In the formula, This is the predicted value of the output work; to These are the parameter values for the quantitative analysis equation; and These are the turbine inlet temperature and pressure ratio, respectively.
[0038] In this embodiment, to The values are -5442.46686, 2530.691129, 1397.126598, -392.110836, 33.457864, 20.245347, 1.509248, -505.81314, 48.83986, and -7.939281.
[0039] In the preferred scheme, the heat supply quantitative calculation module utilizes two key parameters—the turbine inlet temperature and pressure ratio—selected from the selection process, and employs a neural network method to obtain the heat supply quantitative analysis equation for the Brayton cycle, including: The formula for calculating the heat supply of a Brayton cycle is: ; In the formula, For the heat supply of the Brayton cycle, This is the enthalpy value at the heater outlet; This is the enthalpy value at the heater inlet.
[0040] The general quantitative analysis equation for the Brayton cycle heat supply output by the neural network is as follows: ; In the formula, This is the predicted value for heat supply; to These are the parameter values for the quantitative analysis equation; and These are the turbine inlet temperature and pressure ratio, respectively.
[0041] In this embodiment, to The values are 5237.896963, 0.26753, -1.369932e-5, -7.602740e-10, -8321.224852, 4758.954509, -1169.210892, 111.105707, and -1.522392.
[0042] In the three embodiments described above, the analytical parameters such as efficiency, output power, and heat supply are shown in Table 3: Table 3. Parameters related to the general quantitative analysis equation
[0043] In the preferred embodiment, the Brayton cycle module includes: The heater submodule is used to use the supplied heat to raise the temperature of the working medium at the turbine inlet. The turbine submodule is used to convert the enthalpy difference between the turbine inlet and outlet into shaft work. The compressor submodule is used to allocate a portion of the shaft power to increase the temperature and entropy of the working medium at the compressor outlet; The precooler submodule is used to further cool the temperature of the working medium to meet the parameter requirements at the compressor inlet. The heat exchanger submodule uses a counter-current heat exchanger to exchange heat between the two working media, thereby increasing the temperature at the heater inlet and decreasing the temperature at the turbine outlet.
[0044] In the preferred scheme, the efficiency calculation formula for the turbine submodule is as follows: ; In the formula, This represents the efficiency value of the turbine submodule. This is the enthalpy value at the inlet of the turbine submodule; This refers to the enthalpy value at the outlet of the turbine submodule; This is the isentropic enthalpy value at the outlet of the turbine submodule.
[0045] In this embodiment, under design state , , The values of the parameters are 525, 363.2, and 351 kJ / kg, and the calculated values are... The parameter value is 93%, and the values of the above four parameters will change as the iteration step size increases.
[0046] In the preferred embodiment, the efficiency calculation formula for the compressor submodule is as follows: ; In the formula, This refers to the efficiency value of the compressor submodule. This is the isentropic enthalpy value at the outlet of the compressor submodule; This is the enthalpy value at the inlet of the compressor submodule; This is the enthalpy value at the outlet of the compressor submodule.
[0047] In this embodiment, under design state , , The values of the parameters are -83.84, -123.4, and -78.39 kJ / kg, and the calculated values are... The parameter value is 89%, and the values of the above four parameters will change as the iteration step size increases.
[0048] In the preferred embodiment, the efficiency calculation formula for the heat exchanger submodule is as follows: ; In the formula, This refers to the efficiency value of the heat exchanger submodule. This is the enthalpy value at the cold fluid outlet of the heat exchanger submodule; This refers to the enthalpy value at the cold fluid inlet of the heat exchanger submodule; This refers to the enthalpy value at the hot fluid inlet of the heat exchanger submodule; This refers to the temperature at the cold fluid inlet of the heat exchanger submodule. This refers to the pressure at the hot fluid outlet of the heat exchanger submodule.
[0049] In this embodiment, under design state , , , , The values of these parameters are 236.3 kJ / kg, -78.39 kJ / kg, 363.2 kJ / kg, and 111.1 kJ / kg. o C, 7.353 MPa, the calculated The parameter value is 95%, and the values of the above six parameters will change as the iteration step size increases.
[0050] In this embodiment, a high-precision Brayton cycle physical model provides a reliable data foundation for neural network training and the generation of fast calculation formulas.
[0051] This embodiment enables engineers to bypass specialized simulation software and quickly and accurately perform performance evaluation and parameter optimization on-site or during the design phase, thereby improving efficiency and reducing costs.
[0052] The above embodiments are merely preferred technical solutions of the present invention and should not be considered as limitations on the present invention. The scope of protection of the present invention should be limited to the technical solutions described in the claims, including equivalent substitutions of the technical features described in the claims. That is, equivalent substitutions and improvements within this scope are also within the scope of protection of the present invention.
Claims
1. An engineered fast calculation system for the comprehensive performance of Brayton cycles, characterized in that, include: The Brayton cycle module is used to calculate the Brayton cycle efficiency under multiple operating parameters, including turbine inlet temperature, compressor inlet temperature, maximum operating pressure, pressure ratio, compressor efficiency, turbine efficiency, and heat exchanger efficiency. The neural network method module is used to sort the importance of multiple operating parameters based on the collected Brayton cycle efficiency using the control variable method, and to filter out multiple important parameters, including turbine inlet temperature and pressure ratio. The comprehensive performance calculation module includes an efficiency quantitative calculation module, an output work quantitative calculation module, and a heat supply quantitative calculation module. It is used to perform quantitative analysis of the corresponding performance of the Brayton cycle based on the multiple important parameters, and derive the corresponding performance engineering rapid calculation formula.
2. The engineered fast calculation system for the comprehensive performance of the Brayton cycle according to claim 1, characterized in that, The Brayton cycle module includes: The heater submodule is used to use the supplied heat to raise the temperature of the working medium at the turbine inlet. The turbine submodule is used to convert the enthalpy difference between the turbine inlet and outlet into shaft work. The compressor submodule is used to allocate a portion of the shaft power to increase the temperature and entropy of the working medium at the compressor outlet; The precooler submodule is used to further cool the temperature of the working medium to meet the parameter requirements at the compressor inlet. The heat exchanger submodule uses a counter-current heat exchanger to exchange heat between the two working media, thereby increasing the temperature at the heater inlet and decreasing the temperature at the turbine outlet.
3. The engineered fast calculation system for the comprehensive performance of the Brayton cycle according to claim 1, characterized in that, The key configuration parameters of the neural network method module include the neuron submodule, the multiple feedforward connection submodule, the training method submodule, the training function submodule, the learning rate submodule, the momentum coefficient submodule, and the iteration step size submodule. The neuron submodule acts as multiple computation nodes in the process of multiple inputs and single outputs. The number of neuron layers is set to 2 to ensure computational accuracy. The multi-feedforward connection submodule is responsible for determining the output based on the weights, biases, and input parameters. The training method submodule is responsible for calculating the weight gradient and adjusting the weights using the gradient. It is set to batch backpropagation to achieve faster convergence speed and better prediction performance. The training function submodule is responsible for training the neural network, which learns the input data and outputs the object's output parameters; The learning rate submodule is used to control the frequency of parameter updates during the learning process; The momentum coefficient submodule controls the intensity of weight updates based on the directional characteristics of the current gradient and the previous gradient.
4. The engineered fast calculation system for the comprehensive performance of the Brayton cycle according to claim 1, characterized in that, The efficiency quantitative calculation module utilizes several selected key parameters and employs the high-precision prediction characteristics of neural networks to quantitatively analyze the Brayton cycle efficiency, deriving a rapid engineering calculation formula, including: The formula for calculating efficiency in the Brayton cycle model is: ； In the formula, For the efficiency of the Brayton cycle; This is the enthalpy value at the turbine outlet; This is the enthalpy value at the turbine inlet; This is the enthalpy value at the compressor outlet; This is the enthalpy value at the compressor inlet; This is the enthalpy value at the heater outlet; This is the enthalpy value at the heater inlet; The general quantitative equation for the Brayton cycle efficiency output by the neural network is: ； In the formula, For the predicted value of efficiency; to These are the parameter values for the quantitative analysis equation; and These are the turbine inlet temperature and pressure ratio, respectively.
5. The engineered fast calculation system for the comprehensive performance of the Brayton cycle according to claim 1, characterized in that, In the output work quantitative calculation module, using several selected important parameters, a neural network method is employed to obtain the output work quantitative analysis equation of the Brayton cycle, including: The formula for calculating the output work in the Brayton cycle model is: ； In the formula, This represents the output work of the Brayton cycle; This is the enthalpy value at the turbine outlet; This is the enthalpy value at the turbine inlet; The general quantitative analysis equation for the work output by the Brayton cycle from the neural network is: ； In the formula, This is the predicted value of the output work; to These are the parameter values for the quantitative analysis equation; and These are the turbine inlet temperature and pressure ratio, respectively.
6. The engineered fast calculation system for the comprehensive performance of the Brayton cycle according to claim 1, characterized in that, In the heat supply quantitative calculation module, based on several selected important parameters, a neural network method is used to obtain the heat supply quantitative analysis equation for the Brayton cycle, including: The formula for calculating the heat supply of a Brayton cycle is: ； In the formula, For the heat supply of the Brayton cycle, This is the enthalpy value at the heater outlet; This is the enthalpy value at the heater inlet; The general quantitative analysis equation for the Brayton cycle heat supply output by the neural network is as follows: ； In the formula, This is the predicted value for heat supply; to These are the parameter values for the quantitative analysis equation; and These are the turbine inlet temperature and pressure ratio, respectively.
7. The engineered fast calculation system for the comprehensive performance of the Brayton cycle according to claim 1, characterized in that, The neural network method module uses the control variable method and employs... The indicators are used to determine the importance of multiple operating parameters. Taking efficiency as an example, The formula for calculating the coefficient of determination is: ； In the formula, The coefficient of determination; This represents the average of the actual efficiency values. This represents the average of the predicted efficiency values.
8. The engineered fast calculation system for the comprehensive performance of the Brayton cycle according to claim 2, characterized in that, The efficiency calculation formula for the turbine submodule is as follows: ； In the formula, This represents the efficiency value of the turbine submodule. This is the enthalpy value at the inlet of the turbine submodule; This refers to the enthalpy value at the outlet of the turbine submodule; This is the isentropic enthalpy value at the outlet of the turbine submodule.
9. The engineered fast calculation system for the comprehensive performance of the Brayton cycle according to claim 2, characterized in that, The efficiency calculation formula for the compressor submodule is as follows: ； In the formula, This refers to the efficiency value of the compressor submodule. This is the isentropic enthalpy value at the outlet of the compressor submodule; This is the enthalpy value at the inlet of the compressor submodule; This is the enthalpy value at the outlet of the compressor submodule.
10. The engineered fast calculation system for the comprehensive performance of the Brayton cycle according to claim 2, characterized in that, The efficiency calculation formula for the heat exchanger submodule is as follows: ； In the formula, This refers to the efficiency value of the heat exchanger submodule. This is the enthalpy value at the cold fluid outlet of the heat exchanger submodule; This refers to the enthalpy value at the cold fluid inlet of the heat exchanger submodule; This refers to the enthalpy value at the hot fluid inlet of the heat exchanger submodule; This refers to the temperature at the cold fluid inlet of the heat exchanger submodule. This refers to the pressure at the hot fluid outlet of the heat exchanger submodule.