A dynamic evolution method and system of a gas turbine mechanism simulation model

Abstract

The application relates to a dynamic evolution method and system of a gas turbine mechanism simulation model, wherein the method comprises the following steps: analyzing the mass-energy relationship of a unit module in the gas turbine, and then constructing a mechanism simulation model of the gas turbine; acquiring key characteristic parameters from the mechanism simulation model of the gas turbine; constructing a corresponding data-driven evolution model according to the key characteristic parameters; and superimposing the output result of the data-driven evolution model to the mechanism simulation model to dynamically evolve the mechanism simulation model. Through the application, the problem that the initial gas turbine simulation model has low monitoring precision of the thermal performance of the unit in a dynamic working process is solved, the distortion of the mechanism simulation model caused by the component recession in the operation process of the gas turbine is avoided, the error of the key characteristic parameters of the mechanism simulation model is dynamically corrected in a data-driven manner, and the thermal performance prediction precision of the mechanism simulation model is improved.

Description

Technical Field

[0001] This application relates to the field of gas turbine simulation technology, and in particular to a dynamic evolution method and system for a gas turbine mechanism simulation model. Background Technology

[0002] As the level of informatization and automation of gas turbine units increases, the gas turbine simulation model based on the principle of thermal balance includes multiple characteristic parameters, such as the characteristic parameter curves of the compressor and turbine, in order to monitor various parameter indicators of the gas turbine unit during operation and ensure the safety and reliability of the unit components.

[0003] Existing gas turbine simulation models are typically built upon initial gas turbine units. However, as the unit operates over time, inevitable component degradation occurs, causing the initial gas turbine simulation model to deviate from actual operating conditions. The greater the degree of performance degradation, the lower the accuracy of the thermodynamic performance monitoring of the initial gas turbine simulation model.

[0004] Currently, no effective solution has been proposed to address the issue of low accuracy in monitoring the thermodynamic performance of the unit during dynamic operation using the initial gas turbine simulation model in related technologies. Summary of the Invention

[0005] This application provides a method and system for the dynamic evolution of a gas turbine mechanism simulation model, which at least solves the problem of low accuracy in monitoring the thermodynamic performance of the unit during dynamic operation in the initial gas turbine simulation model in related technologies.

[0006] In a first aspect, embodiments of this application provide a dynamic evolution method for a gas turbine mechanism simulation model, the method comprising:

[0007] Mass-energy relationship analysis is performed on the unit modules in the gas turbine, and then a mechanism simulation model of the gas turbine is constructed.

[0008] Key characteristic parameters were obtained from the mechanism simulation model of the gas turbine.

[0009] Based on the key feature parameters, a corresponding data-driven evolution model is constructed;

[0010] The output of the data-driven evolution model is superimposed onto the mechanism simulation model to dynamically evolve the mechanism simulation model.

[0011] In some embodiments, mass-energy relationship analysis is performed on the unit modules in the gas turbine, and a mechanism simulation model of the gas turbine is constructed, including:

[0012] Based on the laws of conservation of mass and energy, a mass-energy relationship analysis is performed on the unit modules in a gas turbine, wherein the unit modules include a compressor module, a turbine module, and a combustion chamber module;

[0013] Based on the results of the mass-energy relationship analysis, a mechanistic simulation model of the gas turbine is constructed.

[0014] In some embodiments, the mass-energy relationship analysis of the unit modules in the gas turbine, based on the laws of conservation of mass and energy, includes:

[0015] Based on the laws of conservation of mass and energy, and combined with the flow relationship of the working fluid and the direction of energy transfer in the gas turbine, the energy balance relationship between the compressor module and the turbine module is established, the energy balance relationship between the chemical energy and the internal energy of the working fluid in the combustion conversion process of the combustion chamber module is established, and the mass balance relationship of the gas flow path between the compressor module, the turbine module and the combustion chamber module is established.

[0016] In some embodiments, constructing a mechanistic simulation model of the gas turbine based on the results of the mass-energy equivalence analysis includes:

[0017] Based on the results of the mass-energy relationship analysis, a mechanistic simulation model of the gas turbine is constructed. The boundary conditions of the mechanistic simulation model include the inlet temperature T1 of the compressor module, the inlet pressure p1 of the compressor module, the rotational speed n, the outlet pressure p4 of the turbine module, and the power P.

[0018] In some embodiments, key characteristic parameters are obtained from the mechanistic simulation model of the gas turbine, including:

[0019] Key characteristic parameters were selected from the mechanism simulation model of the gas turbine, including the outlet temperature T2 of the compressor module, the outlet pressure p2 of the compressor module, and the outlet temperature T4 of the turbine module.

[0020] In some embodiments, constructing a corresponding data-driven evolutionary model based on the key feature parameters includes:

[0021] Based on the key feature parameters, the Long Short-Term Memory Neural Network (LSTM) is used as the algorithm for the data-driven evolutionary model, and the data-driven evolutionary model is obtained by training with running data.

[0022] In some embodiments, the input to the data-driven evolution model is the boundary conditions in the operating data, wherein the boundary conditions include the compressor module inlet temperature T1, the compressor module inlet pressure p1, the compressor module rotational speed n, the turbine module outlet pressure p4, and the power P.

[0023] In some embodiments, the output of the data-driven evolution model is the deviation value of the key feature parameters, wherein the deviation value includes the outlet temperature deviation dT2 of the compressor module, the outlet pressure deviation dp2 of the compressor module, and the outlet temperature deviation dT4 of the turbine module.

[0024] In some embodiments, the output of the data-driven evolution model is superimposed onto the mechanism simulation model, and the dynamic evolution of the mechanism simulation model includes:

[0025] The output of the data-driven evolution model is superimposed onto the mechanism simulation model using the formulas T'2 = T2 + dT2, p'2 = p2 + dp2, and T'4 = T4 + dT4 to dynamically evolve the mechanism simulation model. Here, dT2, dp2, and dT4 are the output of the data-driven evolution model, T2, p2, and T4 are the key feature parameters of the mechanism simulation model, and T'2, p'2, and T'4 are the key feature parameters after dynamic evolution.

[0026] Secondly, embodiments of this application provide a dynamic evolution system for a gas turbine mechanism simulation model, the system comprising a mechanism model construction module, a feature selection module, a data model construction module, and a dynamic evolution module;

[0027] The mechanism model construction module is used to perform mass-energy relationship analysis on the unit modules in the gas turbine, and then construct the mechanism simulation model of the gas turbine.

[0028] The feature selection module is used to obtain key feature parameters from the mechanism simulation model of the gas turbine;

[0029] The data model construction module is used to construct a corresponding data-driven evolution model based on the key feature parameters.

[0030] The dynamic evolution module is used to superimpose the output of the data-driven evolution model onto the mechanism simulation model, thereby dynamically evolving the mechanism simulation model.

[0031] Compared to related technologies, this application provides a dynamic evolution method and system for a gas turbine mechanism simulation model. This method analyzes the mass-energy relationship of the unit modules within the gas turbine to construct a mechanism simulation model. Key characteristic parameters are obtained from the gas turbine mechanism simulation model. Based on these parameters, a corresponding data-driven evolution model is constructed. The output of the data-driven evolution model is superimposed onto the mechanism simulation model, dynamically evolving the model. This solves the problem of low accuracy in monitoring the thermodynamic performance of the unit during dynamic operation using the initial gas turbine simulation model. It also avoids distortion of the mechanism simulation model caused by component degradation during gas turbine operation. Furthermore, it achieves dynamic correction of errors in the key characteristic parameters of the mechanism simulation model using a data-driven approach, improving the accuracy of thermodynamic performance prediction. Attached Figure Description

[0032] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments of this application and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0033] Figure 1 This is a flowchart illustrating the steps of a dynamic evolution method for a gas turbine mechanism simulation model according to an embodiment of this application.

[0034] Figure 2 This is a structural block diagram of the dynamic evolution system of the gas turbine mechanism simulation model according to an embodiment of this application;

[0035] Figure 3 This is a schematic diagram of the internal structure of an electronic device according to an embodiment of this application.

[0036] Figure labels: 21. Mechanism model construction module; 22. Feature selection module; 23. Data model construction module; 24. Dynamic evolution module. Detailed Implementation

[0037] To make the objectives, technical solutions, and advantages of this application clearer, the application is described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. All other embodiments obtained by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.

[0038] Obviously, the accompanying drawings described below are merely some examples or embodiments of this application. Those skilled in the art can apply this application to other similar scenarios based on these drawings without any inventive effort. Furthermore, it is understood that although the efforts made in this development process may be complex and lengthy, for those skilled in the art related to the content disclosed in this application, any changes to design, manufacturing, or production based on the technical content disclosed in this application are merely conventional technical means and should not be construed as insufficient disclosure of the content of this application.

[0039] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that is mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0040] Unless otherwise defined, the technical or scientific terms used in this application shall have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms “a,” “an,” “an,” “the,” and similar words used in this application do not indicate quantity limitation and may indicate singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units not listed, or may include other steps or units inherent to these processes, methods, products, or devices. The terms “connected,” “linked,” “coupled,” and similar words used in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. “Multiple” used in this application refers to two or more. “And / or” describes the relationship between related objects, indicating that three relationships may exist; for example, “A and / or B” can represent: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following objects are in an "or" relationship. The terms "first," "second," and "third" used in this application are merely to distinguish similar objects and do not represent a specific ordering of the objects.

[0041] This application provides a method for the dynamic evolution of a gas turbine mechanism simulation model. Figure 1 This is a flowchart illustrating the steps of a dynamic evolution method for a gas turbine mechanism simulation model according to an embodiment of this application, as shown below. Figure 1 As shown, the method includes the following steps:

[0042] Step S102: Perform mass-energy relationship analysis on the unit modules in the gas turbine, and then construct a mechanism simulation model of the gas turbine;

[0043] Specifically, step S102 involves performing a mass-energy relationship analysis on the unit modules of the gas turbine based on the laws of conservation of mass and energy. The unit modules include the compressor module, turbine module, and combustion chamber module. Then, based on the results of the mass-energy relationship analysis, a mechanistic simulation model of the gas turbine is constructed.

[0044] Preferably, in step S102, based on the laws of conservation of mass and energy, and combined with the flow relationship of the working fluid and the direction of energy transfer in the gas turbine, an energy balance relationship is established between the compressor module and the turbine module, an energy balance relationship is established between the chemical energy of the combustion chamber module and the internal energy of the working fluid during the combustion conversion process, and a mass balance relationship is established between the gas flow path of the compressor module, the turbine module and the combustion chamber module.

[0045] Based on the results of the mass-energy relationship analysis, a mechanistic simulation model of the gas turbine is constructed. The boundary conditions of the mechanistic simulation model include the inlet temperature T1 of the compressor module, the inlet pressure p1 of the compressor module, the rotational speed n, the outlet pressure p4 of the turbine module, and the power P.

[0046] It should be noted that a gas turbine mainly consists of three major components: a compressor, a combustion chamber, and a turbine. When a gas turbine is operating, the compressor continuously draws in air filtered by the intake system from the atmosphere and compresses it. The compressed high-pressure air then enters the combustion chamber, where it mixes with fuel (primarily natural gas) injected into the combustion chamber and burns. The resulting high-temperature gas flows into the turbine, expands, and performs work, driving the turbine blades and rotating the compressor blades. Because the work-performing capacity of the heated high-temperature gas is significantly increased, the turbine, while driving the compressor, still has surplus useful work to provide as output mechanical work for the gas turbine, which can be used for driving, power generation, etc.

[0047] Step S104: Obtain key characteristic parameters from the mechanism simulation model of the gas turbine;

[0048] Specifically, in step S104, key characteristic parameters are selected from the mechanism simulation model of the gas turbine. The key characteristic parameters include the outlet temperature T2 of the compressor module, the outlet pressure p2 of the compressor module, and the outlet temperature T4 of the turbine module.

[0049] Therefore, it can be seen that selecting the key characteristic parameters T2, p2 and T4, which are closely related to the calculation of the gas engine's thermal performance, in step S104 reduces the amount of calculation required for the subsequent dynamic evolution through the data-driven evolution model, which not only ensures the accuracy of the gas engine's thermal performance calculation but also improves the calculation efficiency.

[0050] Step S106: Construct the corresponding data-driven evolution model based on the key feature parameters;

[0051] Specifically, in step S106, based on the selected key characteristic parameters of the gas turbine, the Long Short-Term Memory Neural Network (LSTM) is used as the algorithm for the data-driven evolution model, and the data-driven evolution model is obtained by training with running data.

[0052] In step S106, the input and output of the data-driven evolution model are preferably based on the principle of Long Short-Term Memory Neural Network (LSTM). The boundary conditions in the operating data are used as the input of the data-driven evolution model. The boundary conditions include the inlet temperature T1 of the compressor module, the inlet pressure p1 of the compressor module, the rotational speed n, the outlet pressure p4 of the turbine module, and the power P. The deviation values ​​of the key feature parameters are used as the output of the data-driven evolution model. The deviation values ​​include the outlet temperature deviation dT2 of the compressor module, the outlet pressure deviation dp2 of the compressor module, and the outlet temperature deviation dT4 of the turbine module.

[0053] Therefore, it can be seen that by reasonably selecting the input parameters T1, p1, n, p4 and P of the data-driven evolution model in step S106, the dT2, dp2 and dT4 calculated by the evolution model are more reasonable and accurate, and the mechanism simulation model after dynamic evolution of the evolution model can more accurately calculate the thermodynamic performance of the gas engine.

[0054] It should be noted that the LSTM model, by introducing three gates—forget gate, input gate, and output gate—can solve the gradient problem that occurs in recurrent neural networks when calculating data over long periods, thus making it suitable for predicting time series samples. The output of the hidden layer of an LSTM neural network not only goes to the output terminal but also serves as input to the hidden layer of the next time step, thus it can pass the information and data calculated in one time step to the next. For gas turbine systems, there is an inherent correlation between the operating characteristics of the previous time step and the operating characteristics of the next time step; therefore, LSTM neural networks can be well used for the evolution of gas turbine simulation models.

[0055] The principle formula for the LSTM model is as follows:

[0056] f=σ(W f [h t-1 ,x t]+b f )

[0057] i = σ(W i [h t-1 ,x t ]+b i )

[0058] j = tanh(W) j [h t-1 ,x t ]+b j )

[0059] C t =f*C t-1 +i*j

[0060] o=σ(W o [h t-1 ,x t ]+b o )

[0061] h t =o*tanh(C t )

[0062] In the formula: f is the output of the forget gate; W f The weight of the forget gate; b f σ is the bias of the forget gate; σ is the sigmoid activation function; x t Input for the current time; h t-1 This is the output of the hidden layer at the previous time step; W i and W j b represents the weights of the sigmoid and tanh activation functions; i and b j C is the bias value; t-1 The state of the cell at the previous time step; W o b represents the output gate weights; o This is the output gate bias.

[0063] Step S108: The output of the data-driven evolution model is superimposed onto the mechanism simulation model to dynamically evolve the mechanism simulation model.

[0064] Specifically, the output of the data-driven evolution model is superimposed onto the mechanism simulation model using the formulas T'2 = T2 + dT2, p'2 = p2 + dp2, and T'4 = T4 + dT4, thereby dynamically evolving the mechanism simulation model. Here, dT2, dp2, and dT4 are the output of the data-driven evolution model, T2, p2, and T4 are the key feature parameters of the mechanism simulation model, and T'2, p'2, and T'4 are the key feature parameters after dynamic evolution.

[0065] It should be noted that the mechanistic model (white box, the mechanistic simulation model in this embodiment is a mechanistic model): a precise mathematical model established based on the internal mechanism of the object, production process, or the transmission mechanism of material flow. It is a mathematical model of the object or process obtained based on mass balance equations, energy balance equations, momentum balance equations, phase balance equations, as well as certain physical property equations, chemical reaction laws, and basic circuit laws. The advantage of the mechanistic model is that its parameters have very clear physical meanings. This type of model is applied in various industries, requires sufficient input conditions, and obtains output through the model, simulating the entire process (e.g., the mechanistic simulation model in this embodiment simulates the entire working process of a gas turbine).

[0066] Therefore, the shortcomings of the mechanistic model are that everything is too complex, the laws that humans have mastered are limited, and they are often idealized and simplified, so they cannot completely match the real things, and sometimes they are even far from them.

[0067] Data models (black box, gray box, non-mechanistic models; in this embodiment, the data-driven evolutionary model is a data model): Artificial intelligence, represented by neural networks, but also including decision trees, genetic algorithms, and support vector machines, etc. These models have incomplete inputs; they collect massive amounts of data through mobile internet or other related software, organize the data to form information, then integrate and refine the relevant information, and based on the data, train and fit to form an automated decision-making model.

[0068] Therefore, the shortcomings of data models are: first, they require a large amount of data; second, the distribution of data must be reasonable; and third, the analysis methods (algorithms) must be appropriate. Otherwise, the model based on the data may not match the facts.

[0069] Therefore, this application embodiment makes full use of the large amount of operating data generated during the operation of the gas turbine unit (this operating data contains rich information and can reflect the operating status of the unit in real time). Through a data-driven approach (constructing a data-driven evolution model), the key feature data of the initial mechanism simulation model of the gas turbine are adaptively and dynamically evolved to ensure the accuracy of the thermodynamic performance calculation of the mechanism simulation model throughout the entire operating cycle.

[0070] Through steps S102 to S108 in the embodiments of this application, the problem of low accuracy of the initial gas turbine simulation model in monitoring the thermodynamic performance of the unit during dynamic operation is solved, the distortion of the mechanism simulation model caused by component degradation during gas turbine operation is avoided, and the error of the key characteristic parameters of the mechanism simulation model is dynamically corrected in a data-driven manner, thereby improving the accuracy of the thermodynamic performance prediction of the mechanism simulation model.

[0071] It should be noted that the steps shown in the above process or in the flowchart of the accompanying figures can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0072] This application provides a dynamic evolution system for a gas turbine mechanism simulation model. Figure 2 This is a structural block diagram of the dynamic evolution system of the gas turbine mechanism simulation model according to an embodiment of this application, as shown below. Figure 2 As shown, the system includes a mechanism model construction module 21, a feature selection module 22, a data model construction module 23, and a dynamic evolution module 24;

[0073] Mechanism model construction module 21 is used to perform mass-energy relationship analysis on the unit modules in the gas turbine, and then construct the mechanism simulation model of the gas turbine.

[0074] Feature selection module 22 is used to obtain key feature parameters from the mechanism simulation model of the gas turbine;

[0075] Data model building module 23 is used to build corresponding data-driven evolution models based on key feature parameters;

[0076] The dynamic evolution module 24 is used to superimpose the output of the data-driven evolution model onto the mechanism simulation model, thereby dynamically evolving the mechanism simulation model.

[0077] The mechanism model construction module 21, feature selection module 22, data model construction module 23, and dynamic evolution module 24 in this embodiment solve the problem of low accuracy in monitoring the thermodynamic performance of the unit during dynamic operation of the initial gas turbine simulation model, avoid the distortion of the mechanism simulation model caused by component degradation during gas turbine operation, realize the dynamic correction of the error of key feature parameters of the mechanism simulation model in a data-driven manner, and improve the accuracy of thermodynamic performance prediction of the mechanism simulation model.

[0078] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can reside in the same processor; or the above modules can be located in different processors in any combination.

[0079] This embodiment also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0080] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0081] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0082] Furthermore, in conjunction with the dynamic evolution method of the gas turbine mechanism simulation model in the above embodiments, this application embodiment can provide a storage medium for implementation. This storage medium stores a computer program; when executed by a processor, the computer program implements any of the dynamic evolution methods of the gas turbine mechanism simulation model in the above embodiments.

[0083] In one embodiment, a computer device is provided, which may be a terminal. The computer device includes a processor, memory, a network interface, a display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, it implements a dynamic evolution method for a gas turbine mechanism simulation model. The display screen may be a liquid crystal display (LCD) or an e-ink display. The input devices may be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0084] In one embodiment, Figure 3 This is a schematic diagram of the internal structure of an electronic device according to an embodiment of this application, such as... Figure 3 As shown, an electronic device is provided, which can be a server, and its internal structure diagram can be as follows. Figure 3 As shown, the electronic device includes a processor, a network interface, internal memory, and non-volatile memory connected via an internal bus. The non-volatile memory stores the operating system, computer programs, and a database. The processor provides computing and control capabilities, the network interface communicates with external terminals via a network, the internal memory provides an environment for the operation of the operating system and computer programs, the computer programs are executed by the processor to implement a dynamic evolution method for a gas turbine mechanism simulation model, and the database stores data.

[0085] Those skilled in the art will understand that Figure 3The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0086] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0087] Those skilled in the art should understand that the technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments have been described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0088] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A dynamic evolution method for a gas turbine mechanism simulation model, characterized in that, The method includes: Mass-energy relationship analysis is performed on the unit modules in the gas turbine, and then a mechanism simulation model of the gas turbine is constructed. Key characteristic parameters were selected from the mechanism simulation model of the gas turbine, including the outlet temperature of the compressor module. T 2. Compressor module outlet pressure p 2. Turbine module outlet temperature T 4; Based on the key feature parameters, a corresponding data-driven evolutionary model is constructed; the output of the data-driven evolutionary model is the deviation value of the key feature parameters, wherein the deviation value includes the outlet temperature deviation of the compressor module. dT 2. Compressor module outlet pressure deviation dp 2. Temperature deviation between the turbine module and the outlet temperature dT 4; Through formula T' 2= T 2+ dT 2. p' 2= p 2+ dp 2 and T' 4= T 4+ dT 4. The output of the data-driven evolutionary model is superimposed onto the mechanism simulation model to dynamically evolve the mechanism simulation model, wherein... dT 2. dp 2 and dT 4 represents the output of the data-driven evolutionary model. T 2. p 2 and T 4 represents the key feature parameters of the mechanism simulation model. T' 2. p' 2. T' 4 represents the key characteristic parameters after dynamic evolution.

2. The method according to claim 1, characterized in that, The mass-energy relationship analysis of the unit modules in the gas turbine, and the subsequent construction of the mechanism simulation model of the gas turbine, includes: Based on the laws of conservation of mass and energy, a mass-energy relationship analysis is performed on the unit modules in a gas turbine, wherein the unit modules include a compressor module, a turbine module, and a combustion chamber module; Based on the results of the mass-energy relationship analysis, a mechanistic simulation model of the gas turbine is constructed.

3. The method according to claim 2, characterized in that, Based on the laws of conservation of mass and energy, the mass-energy relationship analysis of the unit modules in a gas turbine includes: Based on the laws of conservation of mass and energy, and combined with the flow relationship of the working fluid and the direction of energy transfer in the gas turbine, the energy balance relationship between the compressor module and the turbine module is established, the energy balance relationship between the chemical energy and the internal energy of the working fluid in the combustion conversion process of the combustion chamber module is established, and the mass balance relationship of the gas flow path between the compressor module, the turbine module and the combustion chamber module is established.

4. The method according to claim 2, characterized in that, Based on the results of the mass-energy relationship analysis, the mechanism simulation model of the gas turbine is constructed as follows: Based on the results of the mass-energy equivalence analysis, a mechanistic simulation model of the gas turbine is constructed. The boundary conditions of the mechanistic simulation model include the inlet temperature of the compressor module. T 1. Inlet pressure of the compressor module p 1. Rotation speed n Turbine module outlet pressure p 4 and power P .

5. The method according to claim 1, characterized in that, Based on the key feature parameters, the corresponding data-driven evolution model is constructed as follows: Based on the key feature parameters, the Long Short-Term Memory Neural Network (LSTM) is used as the algorithm for the data-driven evolutionary model, and the data-driven evolutionary model is obtained by training with running data.

6. The method according to claim 5, characterized in that, The input to the data-driven evolution model is the boundary conditions in the operating data, wherein the boundary conditions include the inlet temperature of the compressor module. T 1. Inlet pressure of the compressor module p 1. Rotation speed n Turbine module outlet pressure p 4 and power P .

7. A dynamic evolution system for a gas turbine mechanism simulation model, characterized in that, The system includes a mechanism model construction module, a feature selection module, a data model construction module, and a dynamic evolution module; The mechanism model construction module is used to perform mass-energy relationship analysis on the unit modules in the gas turbine, and then construct the mechanism simulation model of the gas turbine. The feature selection module is used to select key feature parameters from the mechanism simulation model of the gas turbine, including the outlet temperature of the compressor module. T 2. Compressor module outlet pressure p 2. Turbine module outlet temperature T 4; The data model construction module is used to construct a corresponding data-driven evolution model based on the key feature parameters. The dynamic evolution module is used to use formulas T' 2= T 2+ dT 2. p' 2= p 2+ dp 2 and T' 4= T 4+ dT 4. The output of the data-driven evolutionary model is superimposed onto the mechanism simulation model to dynamically evolve the mechanism simulation model, wherein... dT 2. dp 2 and dT 4 represents the output of the data-driven evolutionary model. T 2. p 2 and T 4 represents the key feature parameters of the mechanism simulation model. T' 2. p' 2. T' 4 represents the key characteristic parameters after dynamic evolution.

Images