Calculation method and system suitable for gas path flow distribution of gas turbine

Abstract

The invention discloses a calculation method and system suitable for gas path flow distribution of a gas turbine, and relates to the technical field of gas turbines.The calculation method comprises the steps that a gas turbine model is established, and numerical calculation is conducted on the gas turbine model; constructing a database according to the numerical calculation data, and training the database through a machine learning algorithm to obtain a gas turbine prediction model; and according to the gas turbine prediction model, obtaining gas turbine gas path flow distribution data under the atypical working condition. According to the method, the research and development cost is reduced by adopting a numerical calculation method, modeling and inlet and outlet flow monitoring are carried out on parts which are difficult to actually measure, the obtained air flow of each part is not limited by external conditions, and the flexibility is high; the prediction model is established through a machine learning algorithm, only CFD numerical calculation needs to be carried out on typical working conditions in the whole operation process of the gas turbine, calculation resource consumption is reduced, and the method has guiding significance on design and optimization of the gas turbine.

Description

Technical Field

[0001] The present invention relates to the technical field of gas turbines, and in particular to a calculation method and system suitable for gas turbine gas path flow distribution. Background Art

[0002] As an efficient and clean energy conversion device, gas turbines are widely used in the fields of electricity, shipping, aviation, etc. The improvement of their performance and efficiency has always been the focus of researchers. The flow distribution characteristics of the gas turbine gas path significantly affect the working state of the gas turbine. After entering the compressor inlet, the air is heated and pressurized to achieve appropriate parameters for combustion in the combustor and cooling of the rotor and turbine. Good flow matching can improve the working performance and service life of the gas turbine.

[0003] Currently, the flow distribution characteristics of gas turbine air paths are mostly derived from experimental tests, which are costly. In addition, the flow rate of the air flow paths in individual components cannot be accurately measured due to limitations of unfavorable factors such as measurement equipment and measurement space. However, with the rapid development of computational fluid dynamics (CFD), more and more problems involving fluid flow characteristics can be solved by CFD, such as the flow characteristics of gas turbine hot end components and the flow field distribution characteristics of aircraft. However, traditional CFD consumes a lot of computing resources when solving complex models, which is costly, especially when involving different operating conditions.

[0004] With the development and integration of machine learning algorithms, they have been widely used in the field of driving CFD accelerated computing. Therefore, the present invention proposes a calculation method and system suitable for gas turbine air flow distribution. By combining numerical calculation with machine learning, each air flow path of the gas turbine to be tested is monitored in real time to obtain the gas turbine air flow distribution characteristics, which has guiding significance for gas turbine design and optimization. Summary of the Invention

[0005] In view of the above-mentioned problems, the present invention is proposed.

[0006] Therefore, the technical problem solved by the present invention is that the existing gas turbine air flow distribution calculation method has the problems of large amount of calculation, long time consumption, inability to accurately measure the flow of the air flow path in individual components, and how to meet the engineering application requirements.

[0007] To solve the above technical problems, the present invention provides the following technical solutions: a calculation method suitable for gas turbine gas path flow distribution, comprising establishing a gas turbine model and performing numerical calculations on the gas turbine model; constructing a database based on the numerical calculation data, training the database through a machine learning algorithm to obtain a gas turbine prediction model; and obtaining gas turbine gas path flow distribution data under atypical operating conditions based on the gas turbine prediction model.

[0008] As a preferred embodiment of the calculation method for gas turbine air flow distribution according to the present invention, the establishment of the gas turbine model includes three-dimensional full-scale modeling of the air circulation part of the gas turbine; the air circulation part includes the air circulation parts on the compressor side, the combustion chamber side, the turbine side, and the rotor side.

[0009] As a preferred embodiment of the calculation method for gas turbine gas path flow distribution described in the present invention, the numerical calculation includes meshing the gas turbine model and importing it into CFD software for numerical calculation; the boundary conditions of the parameters in the numerical calculation are calculated by one-dimensional heat balance simulation software; during the numerical calculation, the flow, pressure and temperature data at the inlet and outlet of the air circulation channel are monitored in real time; when the monitored data converges or no longer changes significantly with the number of iteration steps, the calculation is terminated and numerical calculations under other operating conditions are performed to obtain gas turbine gas path flow data under typical operating conditions; the typical operating conditions include gas turbine ignition conditions, gas turbine speed-up conditions, gas turbine grid-connected conditions, gas turbine load-increasing conditions, gas turbine load-reducing conditions, and gas turbine shutdown conditions.

[0010] As a preferred solution of the calculation method for gas turbine gas path flow distribution described in the present invention, the database construction includes organizing and constructing the gas turbine data under typical operating conditions of numerical calculation input and output into a database.

[0011] As a preferred embodiment of the calculation method for gas turbine gas path flow distribution described in the present invention, the method comprises: obtaining a gas turbine prediction model includes classifying data in a database, using compressor intake flow, temperature and pressure data, turbine outlet temperature and pressure data, and fuel flow, temperature and pressure data as inputs of a machine learning algorithm; using combustion chamber inlet data, combustion chamber fuel nozzle inlet and outlet data, combustion chamber cooling hole inlet and outlet data, combustion chamber outlet data, turbine inlet data, and inlet and outlet data of turbine various stages of moving and stationary blade cooling channels as outputs; dividing the input and output data of the machine learning algorithm into a training set, a test set, and a validation set according to a ratio of 8:1:1; training the training set using a machine learning algorithm, and evaluating the performance of the model using the test set and validation set; and completing the training and obtaining the prediction model when the loss functions and prediction results of the test set and validation set meet the requirements.

[0012] As a preferred embodiment of the calculation method for gas turbine gas path flow distribution described in the present invention, obtaining a gas turbine prediction model further comprises constructing a relationship model between gas turbine gas path flow data under typical operating conditions and actual gas turbine operation data through a regression analysis method; using the actual gas turbine operation data as input to the relationship model, and outputting actual data missing from the gas turbine; constructing a database using the actual gas turbine operation data and the actual data missing from the gas turbine, and training the database through a machine learning algorithm to obtain a prediction model; the actual data missing from the gas turbine comprises outlet data of exhaust pipes at various stages of the gas turbine compressor, combustion chamber inlet data, combustion chamber fuel nozzle inlet and outlet data, and combustion chamber cooling hole inlet and outlet data.

[0013] As a preferred embodiment of the calculation method for gas turbine gas path flow distribution according to the present invention, obtaining the gas turbine gas path flow distribution result under atypical operating conditions includes calculating the gas turbine boundary conditions under the atypical operating conditions using one-dimensional heat balance simulation software; and inputting the gas turbine boundary conditions under the atypical operating conditions into a prediction model to obtain gas turbine gas path flow distribution data under the atypical operating conditions.

[0014] Another object of the present invention is to provide a calculation system suitable for gas turbine air flow distribution, which can combine numerical calculation with machine learning to solve the problems of current gas turbine air flow distribution calculation methods, such as large amount of calculation, long time consumption, and inability to accurately measure the flow of air in individual components.

[0015] As a preferred solution of the calculation system suitable for gas turbine gas path flow distribution described in the present invention, it includes: a numerical calculation module, a model training module, and a data prediction module; the numerical calculation module is used to establish a gas turbine model and perform numerical calculations on the gas turbine model; the model training module is used to construct a database based on the numerical calculation data, train the database through a machine learning algorithm, and obtain a gas turbine prediction model; the data prediction module is used to obtain gas turbine gas path flow distribution data under non-typical operating conditions based on the gas turbine prediction model.

[0016] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of a calculation method applicable to gas path flow distribution of a gas turbine.

[0017] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a calculation method applicable to gas path flow distribution of a gas turbine.

[0018] Beneficial effects of the present invention: The calculation method for gas flow distribution of a gas turbine provided by the present invention adopts a numerical calculation method without the need for expensive experiments. Compared with traditional methods, it not only reduces R&D costs, but is also not limited by factors such as measuring equipment. It can model components that are difficult to measure in practice, monitor inlet and outlet flows, and obtain the air flow of each component. It is not restricted by external conditions and has high flexibility. A prediction model is established by a machine learning algorithm. Not only does it only require CFD numerical calculations for typical operating conditions during the entire operation process of the gas turbine, reducing computing resource consumption, but it can also obtain the gas flow distribution results for all operating conditions during the actual operation of the gas turbine through a machine learning model, thereby realizing state monitoring and diagnosis of the gas turbine and improving the reliability and safety of the gas turbine. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 The first embodiment of the present invention provides an overall flow chart of a calculation method for gas flow distribution in a gas turbine.

[0021] Figure 2 A schematic diagram of core components of a gas turbine body, provided in accordance with a first embodiment of the present invention, and applicable to a method for calculating gas flow distribution in a gas turbine gas path.

[0022] In the figure: 1 is the compressor; 2 is the combustion chamber; 3 is the turbine; 4 is the rotor.

[0023] Figure 3 A schematic diagram of a specific flow chart of gas turbine gas path flow distribution calculation, which is a calculation method for gas turbine gas path flow distribution provided in the first embodiment of the present invention.

[0024] Figure 4 A schematic diagram of a specific flow chart of gas path flow distribution calculation during actual operation of a gas turbine, provided as a first embodiment of the present invention, and applicable to a calculation method for gas path flow distribution of a gas turbine.

[0025] Figure 5 The third embodiment of the present invention provides an overall flow chart of a calculation system suitable for gas flow distribution in a gas turbine. DETAILED DESCRIPTION

[0026] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0027] Example 1, reference Figures 1-4 , which is an embodiment of the present invention, provides a calculation method for gas flow distribution in a gas turbine, comprising:

[0028] S1: Establish a gas turbine model and perform numerical calculations on the gas turbine model.

[0029] Furthermore, establishing the gas turbine model includes three-dimensional full-scale modeling of the air circulation part of the gas turbine; the air circulation part includes the air circulation parts on the compressor 1 side, the combustion chamber 2 side, the turbine 3 side, and the rotor 4 side.

[0030] It should be noted that the numerical calculation includes meshing the gas turbine model and importing it into the CFD software for numerical calculation; the boundary conditions of the parameters in the numerical calculation are calculated by one-dimensional heat balance simulation software; during the numerical calculation, the flow, pressure and temperature data at the inlet and outlet of the air circulation channel are monitored in real time; when the monitoring data converges or no longer changes significantly with the number of iteration steps, the calculation is terminated and the numerical calculation is repeated to obtain the gas turbine air path flow data under typical operating conditions; typical operating conditions include gas turbine ignition conditions, gas turbine speed-up conditions, gas turbine grid-connected conditions, gas turbine load-increase conditions, gas turbine load-reduction conditions, and gas turbine shutdown conditions.

[0031] It should also be noted that by performing three-dimensional full-scale modeling of the air circulation part of the gas turbine, the complex geometric shape and flow phenomena of the gas turbine can be accurately simulated, and the performance of the gas turbine can be predicted more accurately; by using CFD software to perform numerical calculations on the three-dimensional full-scale model of the gas turbine, not only can the complex flow and heat transfer phenomena inside the gas turbine be simulated with high precision, but also visual images of the flow and heat transfer inside the gas turbine can be generated, and the flow conditions inside the gas turbine can be observed intuitively, which is helpful for analyzing the working principle and performance problems of the gas turbine.

[0032] S2: Build a database based on numerical calculation data, train the database through machine learning algorithms, and obtain a gas turbine prediction model.

[0033] Furthermore, building the database includes organizing the gas turbine data under typical operating conditions of the numerical calculation input and output into a database.

[0034] It should be noted that obtaining the gas turbine prediction model includes classifying the data in the database, taking the compressor 1 intake flow, temperature and pressure data, turbine 3 outlet temperature and pressure data, and fuel flow, temperature and pressure data as inputs of the machine learning algorithm; taking the combustion chamber 2 inlet data, combustion chamber 2 cooling hole inlet and outlet data, combustion chamber 2 outlet data, turbine 3 inlet data, turbine 3 various stages of moving and static blade cooling channel inlet and outlet data, and rotor 4 inlet and outlet data as outputs; dividing the input and output data of the machine learning algorithm into training set, test set, and validation set according to the ratio of 8:1:1; using the machine learning algorithm to train the training set, and using the test set and validation set to evaluate the performance of the model; when the loss function and prediction results of the test set and validation set meet the requirements, the training is completed and the prediction model is obtained.

[0035] It should also be noted that obtaining the gas turbine prediction model also includes constructing a relationship model between the gas turbine gas path flow data under typical operating conditions and the actual operation data of the gas turbine through a regression analysis method; using the actual operation data of the gas turbine as the input of the relationship model, and outputting the actual data missing from the gas turbine; constructing a database with the actual operation data of the gas turbine and the actual data missing from the gas turbine, and training the database through a machine learning algorithm to obtain a prediction model; the actual data missing from the gas turbine include the outlet data of the exhaust pipes of each stage of the gas turbine compressor 1, the inlet and outlet data of the combustion chamber 2, the inlet and outlet data of the cooling holes of the combustion chamber 2, the inlet and outlet data of the cooling channels of the moving and stationary blades of each stage of the turbine 3, and the inlet and outlet data of the rotor 4.

[0036] It should also be noted that by constructing a database of numerical calculation output and input data of CFD software for machine learning algorithm training, it is possible to not only achieve data integration, standardization and expansion of gas turbine numerical simulation, improve data utilization and quality, but also provide rich training data for machine learning models, which helps the model learn the relationship between input parameters and gas turbine performance, and use performance prediction to facilitate model verification and optimization, ensuring the effectiveness and reliability of the prediction model; by learning the database through machine learning algorithms, it is possible to efficiently process and analyze large amounts of gas turbine data, identify complex patterns, and obtain the full-condition gas path flow distribution results under the actual operation of the gas turbine, which has guiding significance for gas turbine operating status monitoring and diagnosis, and combustion adjustment.

[0037] S3: Based on the gas turbine prediction model, obtain the gas turbine gas path flow distribution data under atypical operating conditions.

[0038] Furthermore, the gas turbine gas path flow distribution results under atypical operating conditions are obtained by calculating the gas turbine boundary conditions under atypical operating conditions through one-dimensional heat balance simulation software; the gas turbine boundary conditions under atypical operating conditions are input into the prediction model to obtain the gas turbine gas path flow distribution data under atypical operating conditions.

[0039] It should be noted that obtaining the gas flow distribution data of the gas turbine under atypical operating conditions through the predictive model can not only provide an in-depth understanding of the performance of the gas turbine under extreme or abnormal working conditions, thereby optimizing the design to improve the reliability and adaptability of the gas turbine, but also help to identify potential failure modes in advance when the gas turbine encounters unexpected operating conditions to ensure safe operation; the gas flow distribution data of the gas turbine under atypical operating conditions can be used to improve the control system to better cope with non-standard operating conditions and improve the overall operating efficiency and maintenance strategy.

[0040] Example 2 is an embodiment of the present invention, which provides a calculation method suitable for gas flow distribution of a gas turbine. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0041] First, a representative gas turbine model is selected and a three-dimensional full-scale model is constructed. After the modeling is completed, the three-dimensional full-scale model is meshed and imported into the CFD software for numerical calculation. The boundary conditions required for the numerical calculation are calculated using the one-dimensional thermal balance simulation software Thermoflow-GTPro. During the numerical calculation process, the inlet and outlet flow, pressure, and temperature data of the main air circulation channels are monitored in real time.

[0042] Secondly, in order to verify the accuracy of the machine learning model, the convolutional neural network (CNN) machine learning algorithm is used to take the compressor 1 intake flow, temperature and pressure data, turbine 3 outlet temperature and pressure data, fuel flow, temperature and pressure data as input, and obtain the combustion chamber 2 inlet, combustion chamber 2 fuel nozzle inlet and outlet, combustion chamber 2 cooling hole inlet and outlet, combustion chamber 2 outlet, turbine 3 inlet, turbine 3 various levels of dynamic and static blade cooling channel inlet and outlet data, rotor 4 inlet and outlet data, train the prediction model, and evaluate the prediction model performance through the test set and validation set. Finally, by comparing the results of CFD numerical calculation and machine learning algorithm, the accuracy of the machine learning algorithm is verified.

[0043] By adopting the gas turbine gas path flow distribution calculation method of the present invention, compared with traditional test measurement methods, it has the advantages of short cycle and low cost, thereby reducing research and development costs. In addition, the present invention is not limited by the measurement equipment, measurement space and structural dimensions of the components to be measured. It can model components that are difficult to measure in practice and monitor inlet and outlet flows, which is more flexible. At the same time, the gas path flow distribution results obtained by the machine learning algorithm can effectively guide the design, optimization and improvement of gas turbine body components.

[0044] In the embodiment, by comparing the results of CFD numerical calculation and machine learning algorithm, the accuracy of the machine learning algorithm can be verified, which shows that the method of the present invention not only saves computing resources, but also further reduces computing costs.

[0045] Example 3, reference Figure 5 , as an embodiment of the present invention, provides a calculation system suitable for gas turbine gas path flow distribution, including a numerical calculation module, a model training module, and a data prediction module.

[0046] Among them, the numerical calculation module is used to establish a gas turbine model and perform numerical calculations on the gas turbine model; the model training module is used to build a database based on the numerical calculation data, train the database through a machine learning algorithm, and obtain a gas turbine prediction model; the data prediction module is used to obtain the gas turbine gas path flow distribution data under atypical operating conditions based on the gas turbine prediction model.

[0047] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program code.

[0048] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0049] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0050] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having logic gate circuits for implementing logical functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc. It should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention and are not intended to be limiting. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced with equivalents without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications should be encompassed by the claims of the present invention.

[0051] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A calculation method for gas flow distribution in a gas turbine, characterized in that: include: Establish a gas turbine model and perform numerical calculations on the gas turbine model; A database is constructed based on numerical calculation data, and the database is trained using a machine learning algorithm to obtain a gas turbine prediction model; According to the gas turbine prediction model, the gas turbine gas path flow distribution data under atypical operating conditions is obtained.

2. The calculation method for gas flow distribution in a gas turbine according to claim 1, wherein: The gas turbine model establishment includes three-dimensional full-scale modeling of the air circulation part of the gas turbine; The air circulation part includes the air circulation parts on the compressor (1) side, the combustion chamber (2) side, the turbine (3) side, and the rotor (4) side.

3. The calculation method for gas flow distribution in a gas turbine according to claim 2, wherein: The numerical calculation includes meshing the gas turbine model and importing it into CFD software for numerical calculation; The boundary conditions of the parameters in the numerical calculations are calculated by one-dimensional thermal balance simulation software; During the numerical calculation process, the flow rate, pressure and temperature data of the inlet and outlet of the air circulation channel are monitored in real time; When the monitoring data converges or no longer changes significantly with the number of iteration steps, the calculation ends and numerical calculations are performed under other working conditions to obtain the gas turbine gas path flow data under typical working conditions; The typical operating conditions include gas turbine ignition conditions, gas turbine speed-up conditions, gas turbine grid-connected conditions, gas turbine load-increasing conditions, gas turbine load-reducing conditions, and gas turbine shutdown conditions.

4. The calculation method for gas flow distribution in a gas turbine according to claim 3, wherein: The database construction includes organizing the gas turbine data under typical working conditions input and output by numerical calculations into a database.

5. The calculation method for gas flow distribution in a gas turbine according to claim 4, characterized in that: The gas turbine prediction model is obtained by classifying the data in the database, and using the compressor (1) inlet flow, temperature and pressure data, the turbine (3) outlet temperature and pressure data, and the fuel flow, temperature and pressure data as inputs of the machine learning algorithm; Outputting combustion chamber (2) inlet data, combustion chamber (2) fuel nozzle inlet and outlet data, combustion chamber (2) cooling hole inlet and outlet data, combustion chamber (2) outlet data, turbine (3) inlet data, and turbine (3) various levels of moving and stationary blade cooling channel inlet and outlet data; The input and output data of the machine learning algorithm are divided into training set, test set, and validation set according to the ratio of 8:1:1; Use machine learning algorithms to train the training set and use the test set and validation set to evaluate the performance of the model; When the loss functions and prediction results of the test set and validation set meet the requirements, the training is completed and the prediction model is obtained.

6. The calculation method for gas flow distribution in a gas turbine according to claim 5, characterized in that: The obtaining of the gas turbine prediction model further includes constructing a relationship model between the gas turbine gas path flow data under typical working conditions and the actual gas turbine operation data by using a regression analysis method; The actual operating data of the gas turbine is used as the input of the relational model, and the actual data missing from the gas turbine is output; A database is constructed using the actual operating data of the gas turbine and the actual data missing from the gas turbine. The database is trained using a machine learning algorithm to obtain a prediction model. The actual data missing from the gas turbine include the outlet data of the exhaust pipes of each stage of the gas turbine compressor (1), the inlet and outlet data of the combustion chamber (2), the inlet and outlet data of the cooling holes of the combustion chamber (2), the inlet and outlet data of the cooling channels of the moving and stationary blades of each stage of the turbine (3), and the inlet and outlet data of the rotor (4).

7. The calculation method for gas flow distribution in a gas turbine according to claim 6, characterized in that: The obtaining of the gas turbine gas path flow distribution result under the atypical operating condition includes calculating the gas turbine boundary conditions under the atypical operating condition by one-dimensional heat balance simulation software; The boundary conditions of the gas turbine under atypical operating conditions are input into the prediction model to obtain the gas path flow distribution data of the gas turbine under atypical operating conditions.

8. A system using the calculation method for gas flow distribution in a gas turbine according to any one of claims 1 to 7, characterized in that: Including numerical calculation module, model training module, and data prediction module; The numerical calculation module is used to establish a gas turbine model and perform numerical calculations on the gas turbine model; The model training module is used to build a database based on numerical calculation data, and train the database through a machine learning algorithm to obtain a gas turbine prediction model; The data prediction module is used to obtain gas turbine gas path flow distribution data under atypical operating conditions based on a gas turbine prediction model.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the processor implements the steps of the calculation method for gas path flow distribution of a gas turbine according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the calculation method for gas path flow distribution of a gas turbine according to any one of claims 1 to 7 are implemented.

Images