Online calibration method and system for sensor parameters of gas turbine

Abstract

The invention relates to an online calibration method and system for sensor parameters of a gas turbine, and the method comprises the steps: building a sensor parameter mechanism model based on the thermodynamic relation of the gas turbine under a typical working condition, and enabling the sensor parameter mechanism model to be used for calculating the sensor parameters of the gas turbine; according to the operation state of the gas turbine, a data driving model based on a neural network is constructed and trained; and compensating and calibrating the sensor parameters of the gas turbine, which are calculated by the sensor parameter mechanism model, according to an output result of the data driving model. By means of the gas turbine sensor parameter online calibration method and device, online calibration of the sensor parameters based on mechanism analysis and data driving is achieved, the respective advantages of a mechanism analysis method and a data driving method are combined, the online calibration precision of the gas turbine sensor parameters is greatly improved, and the problem of how to improve the online calibration precision of the gas turbine sensor parameters is solved.

Description

Technical Field

[0001] The present application relates to the technical field of thermal power generation, and in particular to an online calibration method and system for sensor parameters of a gas turbine. Background Art

[0002] Online calibration of gas turbine sensor parameters is an important basis for the research of sensor fault-tolerant control. At present, the control systems of foreign gas turbine manufacturers have the function of training sensor models, but the specific technology is strictly kept confidential. my country is promoting the independent design of heavy-duty gas turbines, so it is very necessary to carry out research on the construction method of sensor online calibration model.

[0003] The current methods for building online calibration models for sensor parameters mainly include mechanism analysis and data-driven methods. Gas turbines have strong nonlinearity, and the relationship between state parameters is extremely complex. When using the mechanism analysis method to build a calibration model, only a large number of assumptions can be made to simplify the calculation, which will lead to a decrease in model accuracy. Therefore, the mechanism analysis method has certain limitations; data-driven methods, such as neural networks, directly perform analytical model training based on data without having to know the specific mathematical relationship between parameters, which simplifies modeling. However, the mapping relationship between heavy-duty gas turbine parameters is very complex, which brings certain difficulties to neural network training. It is not easy to obtain good training results, and a lot of effort needs to be spent on improving the neural network.

[0004] Currently, no effective solution has been proposed for the problem of how to improve the online calibration accuracy of gas turbine sensor parameters in related technologies. Summary of the invention

[0005] The embodiments of the present application provide a method and system for online calibration of sensor parameters of a gas turbine, so as to at least solve the problem of how to construct an online calibration model of sensor parameters of a gas turbine in the related art.

[0006] In a first aspect, an embodiment of the present application provides a method for online calibration of sensor parameters of a gas turbine, the method comprising:

[0007] Based on the thermodynamic relationship of the gas turbine under typical operating conditions, a sensor parameter mechanism model is constructed, wherein the sensor parameter mechanism model is used to calculate the sensor parameters of the gas turbine;

[0008] Build and train a neural network-based data-driven model based on the operating status of the gas turbine;

[0009] The sensor parameters of the gas turbine calculated by the sensor parameter mechanism model are compensated and calibrated through the output results of the data-driven model.

[0010] In some embodiments, according to the operating state of the gas turbine, building and training a data-driven model based on a neural network includes:

[0011] Determining input parameters of a data-driven model according to an operating state of the gas turbine, wherein the data-driven model is a model based on a feedforward neural network;

[0012] Comparing the output result calculated by the sensor parameter mechanism model with the actually measured sensor parameters to obtain true error data;

[0013] The data driven model is trained based on the input parameters and the true error data.

[0014] In some embodiments, training the data-driven model based on the input parameters and the true error data includes:

[0015] Inputting data corresponding to the input parameters into the data-driven model, and outputting prediction error data through the data-driven model;

[0016] The difference between the predicted error data and the true error data is minimized through the mean square error loss function to optimize and adjust the network parameters of the data-driven model.

[0017] In some embodiments, determining the input parameters of the data-driven model according to the operating state of the gas turbine includes:

[0018] If the operating state of the gas turbine is the starting state, the neural network input of the data-driven model is the first input parameter;

[0019] If the operating state of the gas turbine is a full-speed no-load state, the neural network input of the data-driven model is a second input parameter;

[0020] If the operating state of the gas turbine is a load adjustment state, the neural network input of the data-driven model is the third input parameter.

[0021] In some embodiments, the method comprises:

[0022] The first input parameter Where θ is the compressor air guide vane angle, W f is the fuel flow rate, N0 is the rated speed of the engine, and N is the real-time speed of the engine;

[0023] The second input parameter Where θ is the compressor air guide vane angle, W fis the fuel flow rate, N0 is the rated speed of the engine, N is the real-time speed of the engine, p1 is the compressor inlet pressure, p2 is the compressor outlet pressure, T1 is the compressor inlet temperature, and T2 is the compressor outlet temperature;

[0024] The third input parameter Where θ is the compressor air guide vane angle, W f is the fuel flow rate, p1 is the compressor inlet working fluid pressure, p2 is the compressor outlet pressure, T1 is the compressor inlet working fluid temperature, and T2 is the compressor outlet temperature.

[0025] In some embodiments, the method comprises:

[0026] The typical operating conditions include an irreversible adiabatic compression process in a compressor, an isobaric heating process in a combustion chamber, an irreversible adiabatic expansion process in a turbine, and an isobaric heat release process discharged into the atmosphere. The sensor parameter mechanism model includes a first thermodynamic relationship and a second thermodynamic relationship.

[0027] In some embodiments, based on the thermodynamic relationship of the gas turbine under typical operating conditions, constructing the sensor parameter mechanism model includes:

[0028] Based on the thermodynamic relationship among the irreversible adiabatic compression process in the compressor, the isobaric heating process in the combustion chamber, the irreversible adiabatic expansion process in the turbine, and the isobaric heat release process discharged into the atmosphere, the first thermodynamic relationship and the second thermodynamic relationship of the sensor parameter mechanism model are constructed.

[0029] In some embodiments, the first thermodynamic relationship for constructing the sensor parameter mechanism model includes:

[0030] The first thermodynamic relationship for constructing the sensor parameter mechanism model is:

[0031]

[0032] Where p2 is the outlet pressure of the compressor, T2 is the outlet temperature of the compressor, and η c is the compressor efficiency; T1 is the compressor inlet working fluid temperature, p1 is the compressor inlet working fluid pressure, and k is the specific heat ratio of air.

[0033] In some embodiments, the second thermodynamic relationship for constructing the sensor parameter mechanism model includes:

[0034] The second thermodynamic relationship for constructing the sensor parameter mechanism model is:

[0035]

[0036] Among them, p4 is the outlet pressure of the turbine, T4 is the outlet temperature of the turbine, η t is the turbine efficiency, T3 is the turbine inlet working fluid temperature, p3 is the turbine inlet working fluid pressure, k g is the specific heat ratio of the gas.

[0037] In a second aspect, an embodiment of the present application provides an online calibration system for sensor parameters of a gas turbine, the system being used to execute the method described in any one of the first aspects above, the system comprising a mechanism model building module, a data model building module and a compensation calibration module;

[0038] The mechanism model building module is used to build a sensor parameter mechanism model according to the thermodynamic relationship of the gas turbine under typical operating conditions, wherein the sensor parameter mechanism model is used to calculate the sensor parameters of the gas turbine;

[0039] The data model building module is used to build and train a data-driven model based on a neural network according to the operating status of the gas turbine;

[0040] The compensation calibration module is used to perform compensation calibration on the sensor parameters of the gas turbine calculated by the sensor parameter mechanism model according to the output results of the data-driven model.

[0041] Compared with the related art, an embodiment of the present application provides a method and system for online calibration of sensor parameters of a gas turbine, wherein the method constructs a sensor parameter mechanism model based on the thermodynamic relationship of the gas turbine under typical operating conditions, wherein the sensor parameter mechanism model is used to calculate the sensor parameters of the gas turbine; according to the operating state of the gas turbine, a data-driven model based on a neural network is constructed and trained; and through the output results of the data-driven model, the sensor parameters of the gas turbine calculated by the sensor parameter mechanism model are compensated and calibrated, thereby realizing online calibration of sensor parameters based on mechanism analysis and data-driven, combining the respective advantages of the mechanism analysis method and the data-driven method, greatly improving the online calibration accuracy of the gas turbine sensor parameters, and solving the problem of how to improve the online calibration accuracy of the gas turbine sensor parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0043] Figure 1 is a flowchart of the steps of the method for online calibration of gas turbine sensor parameters according to an embodiment of the present application;

[0044] Figure 2is a schematic structural diagram of a gas turbine according to an embodiment of the present application;

[0045] Figure 3 is a structural diagram of a data-driven model according to an embodiment of the present application;

[0046] Figure 4 is a structural block diagram of a gas turbine sensor parameter online calibration system according to an embodiment of the present application;

[0047] Figure 5 It is a schematic diagram of the internal structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0049] Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. In addition, it can also be understood that although the efforts made in this development process may be complicated and lengthy, for ordinary technicians in this field related to the content disclosed in this application, some changes in design, manufacturing or production based on the technical content disclosed in this application are just conventional technical means, and should not be understood as insufficient content disclosed in this application.

[0050] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0051] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantitative limitation, and may represent the singular or plural. The terms "include", "comprise", "have" and any of their variations involved in this application are intended to cover non-exclusive inclusions; 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 that are not listed, or may also include other steps or units inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0052] The present application embodiment provides a method for online calibration of sensor parameters of a gas turbine. Figure 1 is a flowchart of the steps of the on-line calibration method of gas turbine sensor parameters according to an embodiment of the present application, such as Figure 1 As shown, the method comprises the following steps:

[0053] Step S102, constructing a sensor parameter mechanism model based on the thermodynamic relationship of the gas turbine under typical operating conditions, wherein the sensor parameter mechanism model is used to calculate the sensor parameters of the gas turbine, and the sensor parameter mechanism model includes a first thermodynamic relationship and a second thermodynamic relationship;

[0054] Further, Figure 2 is a schematic diagram of the structure of a gas turbine according to an embodiment of the present application, such as Figure 2 As shown, the core components of the gas turbine include a compressor, a combustion chamber and a turbine. The thermodynamic cycle of the working fluid in the core components belongs to the actual Brayton cycle process, and the actual Brayton cycle (typical operating conditions) includes an irreversible adiabatic compression process in the compressor, an isobaric heating process in the combustion chamber, an irreversible adiabatic expansion process in the turbine and an isobaric heat release process discharged into the atmosphere.

[0055] Step S102 specifically includes the following steps:

[0056] Step S1021, based on the thermodynamic relationship of the gas turbine's irreversible adiabatic compression process in the compressor, the isobaric heating process in the combustion chamber, the irreversible adiabatic expansion process in the turbine, and the isobaric heat release process discharged into the atmosphere, a first thermodynamic relationship of the sensor parameter mechanism model is constructed:

[0057]

[0058] Where p2 is the outlet pressure of the compressor, T2 is the outlet temperature of the compressor, and η c is the compressor efficiency; T1 is the compressor inlet working fluid temperature, p1 is the compressor inlet working fluid pressure, and k is the specific heat ratio of air.

[0059] Step S1022, based on the thermodynamic relationship of the gas turbine's irreversible adiabatic compression process in the compressor, the isobaric heating process in the combustion chamber, the irreversible adiabatic expansion process in the turbine, and the isobaric heat release process discharged into the atmosphere, a second thermodynamic relationship of the sensor parameter mechanism model is constructed:

[0060]

[0061] Among them, p4 is the outlet pressure of the turbine, T4 is the outlet temperature of the turbine, η t is the turbine efficiency, T3 is the turbine inlet working fluid temperature, p3 is the turbine inlet working fluid pressure, k g is the specific heat ratio of the gas.

[0062] It should be noted that the sensor parameter mechanism model is a model under ideal conditions. However, in actual engineering, due to factors such as environmental conditions and changes in working fluid composition, k and k g It is impossible to be a constant value, so this embodiment subsequently corrects the deviation by constructing a data-driven model, combining the respective advantages of the mechanism analysis method and the data-driven method, thereby greatly improving the online calibration accuracy of the gas turbine sensor parameters.

[0063] Step S104, constructing and training a data-driven model based on a neural network according to the operating state of the gas turbine;

[0064] Step S104 specifically includes the following steps:

[0065] Step S1041, determining input parameters of a data-driven model according to the operating state of the gas turbine, wherein the data-driven model is a model based on a feedforward neural network;

[0066] Specifically, step S1041 determines the input parameters of the model according to the operating state of the gas turbine:

[0067] If the gas turbine is in the startup state, the neural network input of the data-driven model is the first input parameter Where θ is the compressor air guide vane angle, W f is the fuel flow rate, N0 is the rated speed of the engine, and N is the real-time speed of the engine;

[0068] If the gas turbine is running at full speed and no-load, the neural network input of the data-driven model is the second input parameter Where θ is the compressor air guide vane angle, W f is the fuel flow rate, N0 is the rated speed of the engine, N is the real-time speed of the engine, p1 is the inlet pressure of the compressor, p2 is the outlet pressure of the compressor, T1 is the inlet temperature of the compressor, and T2 is the outlet temperature of the compressor;

[0069] If the gas turbine is in load adjustment mode, the neural network input of the data-driven model is the third input parameter Where θ is the compressor air guide vane angle, W f is the fuel flow rate, p1 is the compressor inlet working fluid pressure, p2 is the compressor outlet pressure, T1 is the compressor inlet working fluid temperature, and T2 is the compressor outlet temperature.

[0070] It should be noted that Figure 3 is a schematic diagram of the structure of a data driven model according to an embodiment of the present application, such as Figure 3 As shown, a feedforward neural network is used to establish a data-driven model, where U is the input parameter of the data-driven model and Y is the output result of the data-driven model. Specifically, the data-driven model is used to calculate the output result Y of the sensor parameter mechanism model. m The actual measured sensor parameter Y r The prediction error data between r -Y m ,based on Figure 3 As shown, the prediction error data can be obtained as:

[0071]

[0072] It should be further explained that the gas turbine goes through 7 processes from starting to shutting down, including cranking, cleaning, joint acceleration, independent acceleration, full-speed no-load, load adjustment and shutdown. There are three main operating states: starting state, full-speed no-load state and load adjustment state. The control mode of the gas turbine is different in different operating states. In order to speed up the convergence speed of neural network training and improve the accuracy of the final data-driven model, it is considered to optimize the neural network input parameters under different operating states and train the neural network in segments. In other words, if the operating state of the gas turbine is the starting state, the neural network input of the data-driven model is the first input parameter, if the operating state of the gas turbine is the full-speed no-load state, the neural network input of the data-driven model is the second input parameter, and if the operating state of the gas turbine is the load adjustment state, the neural network input of the data-driven model is the third input parameter.

[0073] Step S1042, comparing the output result calculated by the sensor parameter mechanism model with the actually measured sensor parameters to obtain true error data;

[0074] Step S1043, training the data-driven model based on the input parameters and the true error data.

[0075] Specifically, step S1043 inputs the data corresponding to the input parameters into the data-driven model, and outputs the prediction error data through the data-driven model; through the mean square error loss function, the difference between the prediction error data and the true error data is minimized to optimize and adjust the network parameters of the data-driven model.

[0076] It should be noted that the performance of the trained model will be very different if the number of neurons in the hidden layer of the neural network is different and the training algorithm is different. For data sets at different stages, in order to obtain the corresponding data-driven model with the best performance, it is necessary to evaluate the performance of different network structures. Usually, empirical methods or trial and error methods are used, but it takes a lot of time. Therefore, this embodiment establishes an automatic network architecture search program to automatically search for the optimal neural network structure suitable for a certain data set. The program input is: training function group, hidden layer transfer function group, maximum number of hidden layer neurons a, training data set D; program output is: neural network, best performance of verification set, best performance of test set. Use exhaustive method to search and verify in sequence.

[0077] The performance evaluation index of the neural network adopts the mean square error MSE (loss function):

[0078]

[0079] in, is the error estimate of the neural network output, yi is the actual error, and M is the number of samples.

[0080] After the search is completed, all neural networks are sorted in order from small to large mean square error. Considering the generalization ability of the neural network, when the mean square error of the training set is small, the network with the smallest mean square error of the test set is selected for training to obtain a data-driven model.

[0081] Step S106, compensating and calibrating the gas turbine sensor parameters calculated by the sensor parameter mechanism model through the output result of the data-driven model.

[0082] Step S106 Specifically, the output result p of the data-driven model 2_A , T 2_A ,,p 4_A , T 4_A They are:

[0083] P 2_A or p 4_A =f p,2 [W p,2 ·f p,1 (W p,1 ·U+b p,1 )+b p，2 ]

[0084] T 2_A or T 4_A =f T,2 [W T，2 ·f T,1 (W T,1 ·U+b T，1 )+b T,2 ]

[0085] Among them, f, W and b are the network parameters of the data-driven model. The first subscript of f, W and b represents the parsed parameter type, and the second subscript represents the layer of the neural network.

[0086] The outlet pressure p2 and outlet temperature T2 of the compressor calculated by the first thermodynamic relationship of the sensor parameter mechanism model, and the outlet pressure p4 and outlet temperature T4 of the turbine calculated by the second thermodynamic relationship of the sensor parameter mechanism model, the compensation calibration of p2, T2, p4 and T4 is specifically as follows:

[0087]

[0088] Through the above steps in the embodiment of the present application, online calibration of sensor parameters based on mechanism analysis and data-driven is realized, combining the respective advantages of the mechanism analysis method and the data-driven method, greatly improving the online calibration accuracy of the gas turbine sensor parameters, and solving the problem of how to improve the online calibration accuracy of the gas turbine sensor parameters.

[0089] It should be noted that the steps shown in the above process or the flowchart in the accompanying drawings 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 can be executed in an order different from that shown here.

[0090] The present application embodiment provides a gas turbine sensor parameter online calibration system, Figure 4 is a structural block diagram of a gas turbine sensor parameter online calibration system according to an embodiment of the present application, such as Figure 4 As shown, the system includes a mechanism model building module, a data model building module and a compensation calibration module;

[0091] A mechanism model building module is used to build a sensor parameter mechanism model according to the thermodynamic relationship of the gas turbine under typical operating conditions, wherein the sensor parameter mechanism model is used to calculate the sensor parameters of the gas turbine;

[0092] A data model building module, used to build and train a neural network-based data-driven model according to the operating status of the gas turbine;

[0093] The compensation calibration module is used to compensate and calibrate the sensor parameters of the gas turbine calculated by the sensor parameter mechanism model through the output results of the data-driven model.

[0094] Through the mechanism model building module, data model building module and compensation calibration module in the embodiments of the present application, online calibration of sensor parameters based on mechanism analysis and data-driven is realized, combining the respective advantages of the mechanism analysis method and the data-driven method, greatly improving the online calibration accuracy of the gas turbine sensor parameters, and solving the problem of how to improve the online calibration accuracy of the gas turbine sensor parameters.

[0095] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0096] This embodiment further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0097] 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.

[0098] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0099] In addition, in combination with the gas turbine sensor parameter online calibration method in the above embodiment, the present application embodiment can provide a storage medium for implementation. The storage medium stores a computer program; when the computer program is executed by a processor, any of the gas turbine sensor parameter online calibration methods in the above embodiment is implemented.

[0100] In one embodiment, a computer device is provided, which may be a terminal. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for online calibration of sensor parameters of a gas turbine is implemented. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball, or touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0101] In one embodiment, Figure 5 is a schematic diagram of the internal structure of an electronic device according to an embodiment of the present application, such as Figure 5 As shown, an electronic device is provided, which may be a server, and its internal structure diagram may be as shown in Figure 5 As shown. The electronic device includes a processor, a network interface, an internal memory and a non-volatile memory connected through an internal bus, wherein the non-volatile memory stores an operating system, a computer program and a database. The processor is used to provide computing and control capabilities, the network interface is used to communicate with an external terminal through a network connection, the internal memory is used to provide an environment for the operation of the operating system and the computer program, the computer program is executed by the processor to implement an online calibration method for sensor parameters of a gas turbine, and the database is used to store data.

[0102] Those skilled in the art will understand that Figure 5The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the electronic device to which the scheme of 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 a different arrangement of components.

[0103] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0104] Those skilled in the art should understand that the technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are 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.

[0105] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for online calibration of sensor parameters of a gas turbine, characterized in that: The method comprises: Based on the thermodynamic relationship of the gas turbine under typical operating conditions, a sensor parameter mechanism model is constructed, wherein the sensor parameter mechanism model is used to calculate the sensor parameters of the gas turbine; Build and train a neural network-based data-driven model based on the operating status of the gas turbine; The sensor parameters of the gas turbine calculated by the sensor parameter mechanism model are compensated and calibrated through the output results of the data-driven model.

2. The method according to claim 1, characterized in that: According to the operating status of the gas turbine, the neural network-based data-driven model is constructed and trained, including: Determining input parameters of a data-driven model according to an operating state of the gas turbine, wherein the data-driven model is a model based on a feedforward neural network; Comparing the output result calculated by the sensor parameter mechanism model with the actually measured sensor parameters to obtain true error data; The data driven model is trained based on the input parameters and the true error data.

3. The method according to claim 2, characterized in that Based on the input parameters and the true error data, training the data-driven model includes: Inputting data corresponding to the input parameters into the data-driven model, and outputting prediction error data through the data-driven model; The difference between the predicted error data and the true error data is minimized through the mean square error loss function to optimize and adjust the network parameters of the data-driven model.

4. The method according to claim 2, characterized in that: According to the operating status of the gas turbine, the input parameters of the data-driven model are determined to include: If the operating state of the gas turbine is the starting state, the neural network input of the data-driven model is the first input parameter; If the operating state of the gas turbine is a full-speed no-load state, the neural network input of the data-driven model is a second input parameter; If the operating state of the gas turbine is a load adjustment state, the neural network input of the data-driven model is the third input parameter.

5. The method according to claim 4, characterized in that The method comprises: The first input parameter Where θ is the compressor air guide vane angle, W f is the fuel flow rate, N0 is the rated speed of the engine, and N is the real-time speed of the engine; The second input parameter Where θ is the compressor air guide vane angle, W f is the fuel flow rate, N0 is the rated speed of the engine, N is the real-time speed of the engine, p1 is the compressor inlet pressure, p2 is the compressor outlet pressure, T1 is the compressor inlet temperature, and T2 is the compressor outlet temperature; The third input parameter Where θ is the compressor air guide vane angle, W f is the fuel flow rate, p1 is the compressor inlet working fluid pressure, p2 is the compressor outlet pressure, T1 is the compressor inlet working fluid temperature, and T2 is the compressor outlet temperature.

6. The method according to claim 1, characterized in that The method comprises: The typical operating conditions include an irreversible adiabatic compression process in a compressor, an isobaric heating process in a combustion chamber, an irreversible adiabatic expansion process in a turbine, and an isobaric heat release process discharged into the atmosphere. The sensor parameter mechanism model includes a first thermodynamic relationship and a second thermodynamic relationship.

7. The method according to claim 6, characterized in that Based on the thermodynamic relationship of the gas turbine under typical operating conditions, the sensor parameter mechanism model is constructed including: Based on the thermodynamic relationship among the irreversible adiabatic compression process in the compressor, the isobaric heating process in the combustion chamber, the irreversible adiabatic expansion process in the turbine, and the isobaric heat release process discharged into the atmosphere, the first thermodynamic relationship and the second thermodynamic relationship of the sensor parameter mechanism model are constructed.

8. The method according to claim 7, characterized in that The first thermodynamic relationship for constructing the sensor parameter mechanism model includes: The first thermodynamic relationship for constructing the sensor parameter mechanism model is: Where p2 is the outlet pressure of the compressor, T2 is the outlet temperature of the compressor, and η c is the compressor efficiency; T1 is the compressor inlet working fluid temperature, p1 is the compressor inlet working fluid pressure, and k is the specific heat ratio of air.

9. The method according to claim 7, characterized in that: The second thermodynamic relationship for constructing the sensor parameter mechanism model includes: The second thermodynamic relationship for constructing the sensor parameter mechanism model is: Among them, p4 is the outlet pressure of the turbine, T4 is the outlet temperature of the turbine, η t is the turbine efficiency, T3 is the turbine inlet working fluid temperature, p3 is the turbine inlet working fluid pressure, k g is the specific heat ratio of the gas.

10. A gas turbine sensor parameter online calibration system, characterized in that: The system is used to perform the method according to any one of claims 1 to 9, and the system comprises a mechanism model building module, a data model building module and a compensation calibration module; The mechanism model building module is used to build a sensor parameter mechanism model according to the thermodynamic relationship of the gas turbine under typical operating conditions, wherein the sensor parameter mechanism model is used to calculate the sensor parameters of the gas turbine; The data model building module is used to build and train a data-driven model based on a neural network according to the operating status of the gas turbine; The compensation calibration module is used to perform compensation calibration on the sensor parameters of the gas turbine calculated by the sensor parameter mechanism model according to the output results of the data-driven model.

Images