CN118013892A - Gas turbine state real-time monitoring method and device based on multiple physical fields - Google Patents
Gas turbine state real-time monitoring method and device based on multiple physical fields Download PDFInfo
- Publication number
- CN118013892A CN118013892A CN202410404987.7A CN202410404987A CN118013892A CN 118013892 A CN118013892 A CN 118013892A CN 202410404987 A CN202410404987 A CN 202410404987A CN 118013892 A CN118013892 A CN 118013892A
- Authority
- CN
- China
- Prior art keywords
- gas turbine
- physical
- field information
- target
- real
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 77
- 238000012544 monitoring process Methods 0.000 title claims abstract description 12
- 230000007246 mechanism Effects 0.000 claims abstract description 26
- 238000002485 combustion reaction Methods 0.000 claims description 61
- 238000005259 measurement Methods 0.000 claims description 31
- 238000012549 training Methods 0.000 claims description 27
- 239000012530 fluid Substances 0.000 claims description 18
- 238000004088 simulation Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000007405 data analysis Methods 0.000 claims description 5
- 238000010998 test method Methods 0.000 claims description 5
- 238000010223 real-time analysis Methods 0.000 claims description 3
- 239000007789 gas Substances 0.000 description 99
- 239000011159 matrix material Substances 0.000 description 10
- 239000000446 fuel Substances 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000000513 principal component analysis Methods 0.000 description 4
- 230000003068 static effect Effects 0.000 description 4
- 239000013598 vector Substances 0.000 description 4
- 238000003745 diagnosis Methods 0.000 description 3
- 238000012806 monitoring device Methods 0.000 description 3
- 238000000354 decomposition reaction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000002737 fuel gas Substances 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000000567 combustion gas Substances 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004907 flux Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Landscapes
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention is suitable for the field of gas turbine state monitoring, and provides a gas turbine state real-time monitoring method and device based on multiple physical fields. Firstly, a mechanism model is built through characteristic line data of a gas turbine, virtual measuring point data corresponding to actual measuring point data of the gas turbine is obtained through the mechanism model, and then the actual measuring point data and the virtual measuring point data are input into a reduced order model determined based on the maximum range of boundary conditions of the gas turbine so as to determine internal multi-physical-field information of the gas turbine, and therefore the real-time state of the gas turbine is determined. The method solves the problems that the existing CFD method is overlarge in calculated amount, cannot acquire information of multiple physical fields in the gas turbine in real time and monitors the state of the gas turbine in real time.
Description
Technical Field
The application relates to the field of gas turbine state monitoring, in particular to a gas turbine state real-time monitoring method and device based on multiple physical fields.
Background
A gas turbine is a mechanical device which is composed of three parts, namely a gas compressor, a combustion chamber and a turbine, and converts fuel chemical energy into mechanical energy. During operation of a gas turbine, various problems arise from the intense and complex flow of fluids within the various components. For example, in the interior of the compressor, the flow separation phenomenon is caused by the reverse pressure gradient brought about in the pressurizing process, so that the harmful phenomena such as stall, surge and blade vibration of the compressor are caused; in the combustion chamber, high-pressure air and fuel are mixed and combusted to generate high-temperature fuel gas, the local high temperature of a fuel gas temperature field can cause the phenomena of burning of metal in the combustion chamber and the like, and meanwhile, the sound field (pressure field) in the combustion chamber and the combustion reaction can generate the phenomenon of mutual coupling, so that the phenomenon of thermoacoustic oscillation is caused; inside the turbine, the turbine blades are subjected to extreme thermal and mechanical loads under the enclosure of high temperature combustion gases, and uneven distribution of the fluid temperature field can greatly reduce turbine life and reliability. Therefore, if the conditions of physical fields such as internal temperature, pressure and the like can be known in real time in the operation process of the gas turbine, the method has positive significance for avoiding the problems and improving the operation safety of the gas turbine. The existing CFD method capable of calculating and obtaining the fluid multi-physical-field needs extremely large calculation amount, calculation time of a working condition needs several hours, and the purpose of obtaining the internal multi-physical-field information of the gas turbine in real time and monitoring the state of the gas turbine is difficult to achieve.
Disclosure of Invention
In view of the above, the application provides a method and a device for monitoring the state of a gas turbine in real time based on multiple physical fields, so as to solve the problems that the existing CFD method is too large in calculation amount, cannot acquire information of multiple physical fields in the gas turbine in real time, and monitors the state of the gas turbine in real time.
The first aspect of the application provides a gas turbine state real-time monitoring method based on multiple physical fields, which comprises the following steps:
Collecting characteristic line data of each sub-component of a target gas turbine, and constructing a mechanism model of the target gas turbine according to the characteristic line data, wherein the sub-components comprise a compressor, a combustion chamber and a turbine, and the characteristic lines represent the performances of the sub-components under different working conditions;
Obtaining actual measurement point data of the target gas turbine, obtaining virtual measurement point data corresponding to the actual measurement point data through the mechanism model, and enabling a pre-generated target reduced-order model to obtain internal multi-physical-field information of the gas turbine according to the actual measurement point data and the virtual measurement point data;
And determining the real-time state of the gas turbine according to the multi-physical-field information, and processing the gas turbine according to the real-time state.
Optionally, the method for generating the target reduced order model includes:
Obtaining the maximum range of boundary conditions of each sub-component of the target gas turbine through a preset method;
Inputting the boundary conditions into computational fluid dynamics software, and obtaining target training data through the fluid dynamics software, wherein the target training data comprises the corresponding relation between multi-physical-field information inside each sub-component simulated by the boundary conditions and the boundary conditions;
And constructing an initial reduced order model of each sub-component, and training the initial reduced order model through the target training data to generate a target reduced order model of each sub-component.
Optionally, the internal multi-physical field information of the gas turbine includes multi-physical field information of a compressor, multi-physical field information of a combustion chamber and multi-physical field information of a turbine, and the obtaining the internal multi-physical field information of the gas turbine according to the actual measurement point data and the virtual measurement point data by using the pre-generated target reduced order model includes:
Fusing the actual measuring point data and the virtual measuring point data to obtain actual boundary conditions of the compressor, the combustion chamber and the turbine;
Inputting the actual boundary condition of the air compressor into a target reduced-order model corresponding to the air compressor to obtain multi-physical-field information of the air compressor;
Inputting the actual boundary condition of the combustion chamber into a target reduced-order model corresponding to the combustion chamber to obtain multi-physical-field information of the combustion chamber;
Inputting the actual boundary condition of the air compressor into a target reduced-order model corresponding to the air compressor to obtain multi-physical-field information of the air compressor;
And inputting the actual boundary condition of the turbine into a target reduced order model corresponding to the turbine to obtain multi-physical-field information of the turbine.
Optionally, the determining the real-time state of the gas turbine according to the multi-physical-field information includes:
Displaying the real-time state of the gas turbine by a real-time three-dimensional picture method; or alternatively, the first and second heat exchangers may be,
And sending the multi-physical-field information to a third-party analysis program, and determining the real-time state of the gas turbine according to the analysis result of the third-party analysis program.
Optionally, the preset method includes:
DOE, simulation method, historical data analysis method and prototype test method.
A second aspect of the present application provides a gas turbine state real-time analysis apparatus based on multiple physical fields, wherein the apparatus includes:
the collecting and constructing unit is used for collecting characteristic line data of each sub-component of the target gas turbine and constructing a mechanism model of the target gas turbine according to the characteristic line data, wherein the sub-components comprise a gas compressor, a combustion chamber and a turbine, and the characteristic lines represent the performances of the sub-components under different working conditions;
The information acquisition unit is used for acquiring actual measurement point data of the target gas turbine, acquiring virtual measurement point data corresponding to the actual measurement point data through the mechanism model, and enabling a pre-generated target reduced-order model to acquire internal multi-physical-field information of the gas turbine according to the actual measurement point data and the virtual measurement point data;
And the determining unit is used for determining the real-time state of the gas turbine according to the multi-physical-field information and processing the gas turbine according to the real-time state.
Optionally, the method for generating the target reduced order model in the acquired information unit includes:
Obtaining the maximum range of boundary conditions of each sub-component of the target gas turbine through a preset method;
Inputting the boundary conditions into computational fluid dynamics software, and obtaining target training data through the fluid dynamics software, wherein the target training data comprises the corresponding relation between multi-physical-field information inside each sub-component simulated by the boundary conditions and the boundary conditions;
And constructing an initial reduced order model of each sub-component, and training the initial reduced order model through the target training data to generate a target reduced order model of each sub-component.
Optionally, the acquiring the internal multi-physical field information of the gas turbine in the information unit includes multi-physical field information of the gas compressor, multi-physical field information of the combustion chamber and multi-physical field information of the turbine, and the making the pre-generated target reduced order model obtain the internal multi-physical field information of the gas turbine according to the actual measurement point data and the virtual measurement point data includes:
Fusing the actual measuring point data and the virtual measuring point data to obtain actual boundary conditions of the compressor, the combustion chamber and the turbine;
Inputting the actual boundary condition of the air compressor into a target reduced-order model corresponding to the air compressor to obtain multi-physical-field information of the air compressor;
Inputting the actual boundary condition of the combustion chamber into a target reduced-order model corresponding to the combustion chamber to obtain multi-physical-field information of the combustion chamber;
Inputting the actual boundary condition of the air compressor into a target reduced-order model corresponding to the air compressor to obtain multi-physical-field information of the air compressor;
And inputting the actual boundary condition of the turbine into a target reduced order model corresponding to the turbine to obtain multi-physical-field information of the turbine.
Optionally, the determining, in the determining unit, the real-time state of the gas turbine according to the multiple physical fields information includes:
Displaying the real-time state of the gas turbine by a real-time three-dimensional picture method; or alternatively, the first and second heat exchangers may be,
And sending the multi-physical-field information to a third-party analysis program, and determining the real-time state of the gas turbine according to the analysis result of the third-party analysis program.
Optionally, the method for obtaining the preset information unit includes:
DOE, simulation method, historical data analysis method and prototype test method.
In the embodiment provided by the application, a mechanism model is firstly constructed through characteristic line data of the gas turbine, virtual measuring point data corresponding to actual measuring point data of the gas turbine is obtained through the mechanism model, and then the actual measuring point data and the virtual measuring point data are input into a reduced order model determined based on the maximum range of boundary conditions of the gas turbine so as to determine internal multi-physical-field information of the gas turbine, thereby determining the implementation state of the gas turbine. The method solves the problems that the existing CFD method is overlarge in calculated amount, cannot acquire information of multiple physical fields in the gas turbine in real time and monitors the state of the gas turbine in real time.
Drawings
FIG. 1 is a flow chart of a method according to an embodiment of the present application;
FIG. 2 is a flowchart of another method according to an embodiment of the present application;
Fig. 3 is a block diagram of an apparatus according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the application. Rather, they are merely examples of apparatus and methods consistent with aspects of the application as detailed in the accompanying claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.
It should be understood that although the terms first, second, third, etc. may be used herein to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the application. The word "if" as used herein may be interpreted as "at … …" or "at … …" or "in response to a determination" depending on the context.
The application provides a gas turbine fault diagnosis method and device, and aims to provide a gas turbine fault diagnosis method with higher accuracy.
The technical scheme of the application is described in detail below by specific examples. The following embodiments may be combined with each other, and some embodiments may not be repeated for the same or similar concepts or processes.
As shown in fig. 1, a flow chart of a method for monitoring the state of a gas turbine in real time based on multiple physical fields provided by the application may include the following steps:
and step S101, collecting characteristic line data of each sub-component of the target gas turbine, and constructing a mechanism model of the target gas turbine according to the characteristic line data.
In this embodiment, the above-described sub-components include a compressor, a combustor, and a turbine of a gas turbine, and the characteristic lines characterize the performance of the sub-components under different operating conditions.
When constructing the mechanism model, it is necessary to collect characteristic line data for each sub-component. These data typically include performance parameters such as pressure, temperature, flow, rotational speed, etc. under different operating conditions. Such data may be from manufacturer supplied specifications, experimental measurements, simulation simulations, or historical operating data.
Taking the compressor as an example, the characteristic line data collection may include parameters of several aspects: inlet pressure, inlet temperature, pressure ratio, efficiency. The pressure ratio is the ratio of the outlet pressure to the inlet pressure of the compressor, reflects the compression capacity of the compressor, and the efficiency is the ratio of the useful work to the input work of the compressor, and reflects the energy conversion efficiency of the compressor.
The data for these parameters may be obtained by experimental measurements or simulation. For example, the compressor is tested in a laboratory at different speeds and inlet conditions, and corresponding pressure ratio, efficiency, etc. data are recorded. Or performing performance simulation on the compressor by using a CFD simulation tool, and extracting data of related parameters. The acquired characteristic line data are shown in the following table:
| Sequence number | Relative folding rotational speed | Flow rate | Pressure Ratio (PR) | Efficiency (%) |
| 1 | 0.8 | 0.51 | 2.2 | 82 |
| 2 | 0.8 | 0.51 | 2.3 | 81.5 |
| 3 | 0.8 | 0.51 | 2.5 | 81 |
| 4 | 0.8 | 0.5 | 2.6 | 84 |
| 5 | 0.8 | 0.5 | 2.8 | 83.5 |
| 6 | 0.9 | 0.67 | 3.4 | 83 |
| 7 | 0.9 | 0.67 | 3.6 | 86 |
| 8 | 0.9 | 0.65 | 3.9 | 85.5 |
| 9 | 0.9 | 0.62 | 4.2 | 85 |
After the characteristic line data are obtained, the collected data are arranged, and the accuracy and consistency of the data are ensured. This may include processing steps such as interpolation, normalization, etc.
For the mechanism model of the compressor, a polynomial model may be selected to fit the characteristic line data. The polynomial model has the characteristics of simplicity and easiness in implementation, and generally has a good fitting effect on smooth characteristic line data. For example, the model selected in the present application is a quadratic polynomial model, which is of the form:
π = a1 * P1 + a2 * T1 + a3 * P1^2 + a4 * T1^2 + a5 * P1 * T1 + b；
η = c1 * P1 + c2 * T1 + c3 * P1^2 + c4 * T1^2 + c5 * P1 * T1 + d；
Where pi represents the pressure ratio, η represents the efficiency, P1 represents the inlet pressure, T1 represents the inlet temperature, a1, a2,..d is the coefficient of the model. The model is fitted by characteristic line data, and the model coefficients are determined by a least square method or other optimization algorithm to obtain a mechanism model of the compressor.
By the same method, the mechanism models of the combustion chamber and the turbine can be obtained, and the mechanism models of all the sub-components are integrated to form a complete mechanism model of the gas turbine. This integrated model should be able to describe the performance and behavior of the gas turbine throughout its operating range.
Step S102, obtaining actual measurement point data of the target gas turbine, obtaining virtual measurement point data corresponding to the actual measurement point data through the mechanism model, and enabling a pre-generated target reduced-order model to obtain internal multi-physical-field information of the gas turbine according to the actual measurement point data and the virtual measurement point data.
In this embodiment, the internal multi-physical field information of the gas turbine includes multi-physical field information of a compressor, multi-physical field information of a combustion chamber, and multi-physical field information of a turbine, and the obtaining the internal multi-physical field information of the gas turbine according to the actual measurement point data and the virtual measurement point data by the pre-generated target reduced order model includes:
Fusing the actual measuring point data and the virtual measuring point data to obtain actual boundary conditions of the compressor, the combustion chamber and the turbine;
Inputting the actual boundary condition of the air compressor into a target reduced-order model corresponding to the air compressor to obtain multi-physical-field information of the air compressor;
Inputting the actual boundary condition of the combustion chamber into a target reduced-order model corresponding to the combustion chamber to obtain multi-physical-field information of the combustion chamber;
Inputting the actual boundary condition of the air compressor into a target reduced-order model corresponding to the air compressor to obtain multi-physical-field information of the air compressor;
And inputting the actual boundary condition of the turbine into a target reduced order model corresponding to the turbine to obtain multi-physical-field information of the turbine.
In this embodiment, the function of the virtual measurement point is to supplement parameters that cannot be measured by the actual measurement point, but input parameters are needed to be performed during CFD calculation, and the determination method of the target reduced order model is described below, which is not described here again. Sensor readings and control parameters during operation of the gas turbine may be determined as actual site data. The test data are shown in the following table:
| Working condition numbering | Type of measurement point | Actual measurement point data | Virtual survey point data |
| 1 | Rotational speed of combustion engine | 6000rpm | - |
| 1 | Total inlet temperature of air compressor | 25℃ | - |
| 1 | Total pressure of inlet of air compressor | 101.3KPa | - |
| 1 | Static pressure at the outlet of the compressor | 1.51MPa | - |
| 1 | Total temperature of inlet of combustion chamber | 420℃ | - |
| 1 | Total pressure of inlet of combustion chamber | 1.54MPa | - |
| 1 | Total temperature of fuel inlet | 45℃ | - |
| 1 | Fuel inlet flow rate | 2.7kg/s | - |
| 1 | Static pressure at combustion chamber outlet | 1.47MPa | - |
| 1 | Total temperature of turbine inlet | - | 1280℃ |
| 1 | Turbine inlet total pressure | 1.48MPa | - |
| 1 | Total temperature of turbine outlet | - | 570℃ |
| 2 | Rotational speed of combustion engine | 5900rpm | - |
| 2 | Total inlet temperature of air compressor | 25℃ | - |
| 2 | Total pressure of inlet of air compressor | 101.3KPa | - |
| 2 | Static pressure at the outlet of the compressor | 1.41MPa | - |
| 2 | Total temperature of inlet of combustion chamber | 390℃ | - |
| 2 | Total pressure of inlet of combustion chamber | 1.43MPa | - |
| 2 | Total temperature of fuel inlet | 45℃ | - |
| 2 | Fuel inlet flow rate | 2.6kg/s | - |
| 2 | Static pressure at combustion chamber outlet | 1.42MPa | - |
| 2 | Total temperature of turbine inlet | - | 1260℃ |
| 2 | Turbine inlet total pressure | 1.43MPa | - |
| 2 | Total temperature of turbine outlet | - | 565℃ |
In the above table, a plurality of measurement point data under two different conditions (condition numbers 1 and 2) are counted. For each measurement point, the actual measurement point data and the virtual measurement point data calculated according to the mechanism model are respectively displayed.
For example, after the actual measurement point data and the virtual measurement point data are sent to the target reduced order model, internal multi-physical-field information estimated by the reduced order model can be obtained, and the corresponding physical-field (part) information of the working condition number 1 is shown in the following table:
| temperature distribution: | Pressure distribution: | Other physical quantities: |
| - | Gas inlet pressure 3.5 MPa | Combustor flow velocity profile: |
| Different area temperatures of the combustion chamber: | Different area pressures of the combustion chamber: | 30 m/s of premixed combustion zone |
| Premixed combustion zone 1400 DEG C | 1.5 MPa premixed combustion zone | Main combustion zone 20 m/s |
| Main combustion zone 1900 DEG C | Main Combustion zone 1.5 MPa | Secondary combustion zone 25m/s |
| Secondary combustion zone 1500 °c | Secondary combustion zone 1.5 MPa | The turbulence intensity has little significance for judging the performance of the combustion engine |
| Outlet temperature of the combustion chamber 1300 DEG C | - | - |
| Turbine blade different part temperatures: | - | - |
| Blade root 800 °c | - | - |
| In the leaves 870 DEG C | - | - |
| Blade tip 920 DEG C | - | - |
Based on the calculation of the target reduced order model, estimated values of temperature, pressure and other relevant physical quantities of a plurality of key positions inside the gas turbine can be obtained. Through the information, the operation state of the gas turbine can be more comprehensively known, and the key parameters comprise temperature distribution, pressure distribution, flow velocity, turbulence intensity, heat flux and the like.
Step S103, determining the real-time state of the gas turbine according to the multi-physical-field information, and processing the gas turbine according to the real-time state.
In this embodiment, a range value may be set for each field in the multi-physical field information through the history data, and when a certain field is not within the range, an alarm prompt may be sent at this time, so that relevant personnel perform corresponding processing. The real-time status of the gas turbine may also be monitored by changes in various fields in the multi-physical field information, such as by inferring turbine blade life from changes in the temperature of the internal blade surfaces of the turbine.
In another embodiment, the determining the real-time status of the gas turbine from the multi-physical field information includes:
Displaying the real-time state of the gas turbine by a real-time three-dimensional picture method; or alternatively, the first and second heat exchangers may be,
And sending the multi-physical-field information to a third-party analysis program, and determining the real-time state of the gas turbine according to the analysis result of the third-party analysis program.
In this embodiment, the multi-physical field information may be sent to a third party software, so that the third party software may display real-time data of each field in the multi-physical field information by using a three-dimensional picture method.
Thus, the flow shown in fig. 1 is completed.
In the embodiment of the application, a mechanism model is firstly constructed through characteristic line data of a gas turbine, virtual measuring point data corresponding to actual measuring point data of the gas turbine is obtained through the mechanism model, and then the actual measuring point data and the virtual measuring point data are input into a reduced order model determined based on the maximum range of boundary conditions of the gas turbine so as to determine internal multi-physical-field information of the gas turbine, thereby determining the implementation state of the gas turbine. The method solves the problems that the existing CFD method is overlarge in calculated amount, cannot acquire information of multiple physical fields in the gas turbine in real time and monitors the state of the gas turbine in real time.
The following describes the process of generating the target reduced order model in step S102, and as shown in fig. 2, is a flowchart of the method, and the flowchart includes the following steps:
S201, obtaining the maximum range of boundary conditions of each sub-component of the target gas turbine through a preset method.
In this embodiment, the boundary condition combination required for CFD calculation may also be obtained by means of DOE. Taking the maximum boundary condition acquisition of the compressor as an example, the above-mentioned process includes:
1. The pressure ratio is 15 according to the design point parameters of the compressor, such as 6000 rpm. According to experience, the calculated pressure ratio of the compressor is 1-15 x 1.5, and the rotating speed is 0-6000 x 1.3 rpm;
2. Generating 20 groups of working conditions to be calculated by using Latin hypercube design method in DOE, as shown in the following table:
| Sequence number | Calculating the pressure ratio | Calculating the rotation speed |
| 1 | 7.591153 | 4260.373 |
| 2 | 19.18423 | 2636.433 |
| 3 | 17.77023 | 4631.906 |
| 4 | 11.47064 | 4998.276 |
| 5 | 15.18993 | 5366.419 |
| 6 | 3.76123 | 3347.266 |
| 7 | 2.171054 | 1150.635 |
| 8 | 14.77951 | 1987.941 |
| 9 | 20.06641 | 6651.533 |
| 10 | 22.34355 | 1758.563 |
| 11 | 5.153726 | 6439.191 |
| 12 | 16.19051 | 3768.289 |
| 13 | 12.20182 | 7448.979 |
| 14 | 1.4839 | 635.9938 |
| 15 | 10.51917 | 3076.631 |
| 16 | 5.457992 | 1255.702 |
| 17 | 20.75629 | 7258.002 |
| 18 | 9.222726 | 295.7404 |
| 19 | 13.34826 | 5692.474 |
| 20 | 7.018056 | 6202.383 |
After the working condition is determined, a corresponding boundary condition is generated according to the working condition.
The method of generating the calculated boundary conditions is as follows: 1) The total inlet temperature and total pressure are selected to be 15 ℃ and 101.325KPa corresponding to ISO standard working conditions; 2) The impeller rotating speed is set as a calculated rotating speed; 3) The total outlet pressure is set to the total inlet pressure.
S202, inputting boundary conditions corresponding to the working conditions into computational fluid dynamics software, and obtaining target training data through the fluid dynamics software, wherein the target training data comprises the corresponding relation between multi-physical-field information inside each sub-component simulated by the boundary conditions and the boundary conditions.
Computational fluid dynamics (Computational Fluid Dynamics, CFD) software is a software that is specifically used to analyze, calculate, and predict flow fields. It can determine the corresponding physical field information based on the input boundary condition, but since the calculation amount thereof is large, it takes several hours to calculate one working condition, so that it is impossible to calculate the multi-physical field information by this method in step S102. In this embodiment, however, the real-time situation of multiple physical fields need not be obtained, and thus can be obtained by CFD software. The process of acquiring the information of multiple physical fields through the CFD software does not affect the inventive aspects of the present application, and the present application is not described herein.
S203, constructing an initial reduced model of each sub-component, and training the initial reduced model through the target training data to generate a target reduced model of each sub-component.
In the present embodiment, detailed data of the gas turbine subcomponents also needs to be obtained in advance. For example, assuming we are focusing on the combustion chamber of a gas turbine, we may need to collect data on parameters such as temperature, pressure, fuel flow, etc. However, unlike the mechanism model constructed in step S101, a low-dimensional model will be constructed using the dimension-reduction technique in this step. This can be achieved by various methods, such as Principal Component Analysis (PCA), singular Value Decomposition (SVD), etc. Assuming PCA is chosen as the dimension reduction technique, we project the raw data into a low-dimensional space consisting of principal components, resulting in a low-dimensional representation.
By way of example, assume that the collected subcomponent combustor data contains three parameters, temperature (T), pressure (P) and fuel flow (F), each having N data points. These data are first sorted into a matrix X,
X = [T1, P1, F1；
T2, P2, F2；
...
TN, PN, FN]
Wherein each row represents a data point and each column represents a parameter. Before PCA is performed, the data typically needs to be normalized to eliminate the dimensional effects between the different parameters. Each column of the normalized data matrix x_std will have zero mean and unit variance.
X_std = [
(T1-mean(T)), (P1-mean(P)), (F1-mean(F))
(T2-mean(T)), (P2-mean(P)), (F2-mean(F))
...
(TN-mean(T)), (PN-mean(P)), (FN-mean(F))
]。
And then calculating a covariance matrix C= (1/(N-1)). X_std.T. X_std of the standardized data matrix X_std, and carrying out feature decomposition on the covariance matrix C through a function eig to obtain a feature value lambda and a corresponding feature vector V, wherein the eig function is used for calculating the feature value and the feature vector of the square matrix.
And selecting the feature vectors corresponding to the first k largest feature values according to the sizes of the feature values, wherein the feature vectors form a projection matrix W. And then projecting the original data matrix X_std into a low-dimensional space formed by the projection matrix W through the formula X_pca=X_std, so as to obtain the data matrix X_pca after the dimension reduction. X_pca is a reduced-dimension data representation, namely the initial reduced-order model.
And training the initial reduced-order model through the target training data, and performing iterative optimization on the model to obtain the target reduced-order model.
Thus, the flow shown in fig. 2 is completed.
In the embodiment of the application, the initial boundary condition of the reduced order model is determined through the maximum range of the boundary condition of the gas turbine, the multi-physical-field information determined based on the initial boundary condition is obtained through computational fluid dynamics software, and training is carried out through the initial boundary condition and the corresponding multi-physical-field information to obtain the target reduced order model.
As shown in fig. 3, the present application further provides a gas turbine status real-time analysis device based on multiple physical fields, where the device includes:
A collection and construction unit 301, configured to collect characteristic line data of each sub-component of the target gas turbine, and construct a mechanism model of the target gas turbine according to the characteristic line data, where the sub-components include a compressor, a combustion chamber, and a turbine, and the characteristic lines represent performances of the sub-components under different working conditions;
An information obtaining unit 302, configured to obtain actual measurement point data of the target gas turbine, obtain virtual measurement point data corresponding to the actual measurement point data through the mechanism model, and enable a pre-generated target reduced order model to obtain internal multi-physical field information of the gas turbine according to the actual measurement point data and the virtual measurement point data;
and the determining unit 303 is used for determining the real-time state of the gas turbine according to the multi-physical-field information and processing the gas turbine according to the real-time state.
In another embodiment, the method for generating the target reduced order model in the acquired information unit includes:
Obtaining the maximum range of boundary conditions of each sub-component of the target gas turbine through a preset method;
Inputting the boundary conditions into computational fluid dynamics software, and obtaining target training data through the fluid dynamics software, wherein the target training data comprises the corresponding relation between multi-physical-field information inside each sub-component simulated by the boundary conditions and the boundary conditions;
And constructing an initial reduced order model of each sub-component, and training the initial reduced order model through the target training data to generate a target reduced order model of each sub-component.
In another embodiment, the acquiring the internal multi-physical field information of the gas turbine in the information unit includes multi-physical field information of the gas turbine, multi-physical field information of the combustion chamber, and multi-physical field information of the turbine, and the causing the pre-generated target reduced order model to obtain the internal multi-physical field information of the gas turbine according to the actual measurement point data and the virtual measurement point data includes:
Fusing the actual measuring point data and the virtual measuring point data to obtain actual boundary conditions of the compressor, the combustion chamber and the turbine;
Inputting the actual boundary condition of the air compressor into a target reduced-order model corresponding to the air compressor to obtain multi-physical-field information of the air compressor;
Inputting the actual boundary condition of the combustion chamber into a target reduced-order model corresponding to the combustion chamber to obtain multi-physical-field information of the combustion chamber;
Inputting the actual boundary condition of the air compressor into a target reduced-order model corresponding to the air compressor to obtain multi-physical-field information of the air compressor;
And inputting the actual boundary condition of the turbine into a target reduced order model corresponding to the turbine to obtain multi-physical-field information of the turbine.
In another embodiment, determining the real-time state of the gas turbine from the multi-physical field information in the determining unit includes:
Displaying the real-time state of the gas turbine by a real-time three-dimensional picture method; or alternatively, the first and second heat exchangers may be,
And sending the multi-physical-field information to a third-party analysis program, and determining the real-time state of the gas turbine according to the analysis result of the third-party analysis program.
In another embodiment, the method for obtaining the preset information unit includes:
DOE, simulation method, historical data analysis method and prototype test method.
The embodiment of the application provides a gas turbine state real-time monitoring method based on multiple physical fields, and provides a gas turbine state real-time monitoring device based on multiple physical fields.
The embodiment also discloses a computer device, which comprises a processor and a memory, wherein at least one instruction is stored in the memory, and the at least one instruction is loaded and executed by the processor to realize the gas turbine fault diagnosis method.
In addition, in the embodiment of the multi-physical-field-based gas turbine status real-time monitoring device, the logic division of each program module is merely illustrative, and in practical application, the function allocation may be performed by different program modules according to needs, for example, in view of configuration requirements of corresponding hardware or convenience of implementation of software, that is, the internal structure of the tunnel portal monitoring device management device is divided into different program modules, so as to complete all or part of the functions described above.
The foregoing description of the preferred embodiments of the application is not intended to be limiting, but rather to enable any modification, equivalent replacement, improvement or the like to be made within the spirit and principles of the application.
Claims (10)
1. A method for monitoring the state of a gas turbine in real time based on multiple physical fields, which is characterized by comprising the following steps:
Collecting characteristic line data of each sub-component of a target gas turbine, and constructing a mechanism model of the target gas turbine according to the characteristic line data, wherein the sub-components comprise a compressor, a combustion chamber and a turbine, and the characteristic lines represent the performances of the sub-components under different working conditions;
Obtaining actual measurement point data of the target gas turbine, obtaining virtual measurement point data corresponding to the actual measurement point data through the mechanism model, and enabling a pre-generated target reduced-order model to obtain internal multi-physical-field information of the gas turbine according to the actual measurement point data and the virtual measurement point data;
And determining the real-time state of the gas turbine according to the multi-physical-field information, and processing the gas turbine according to the real-time state.
2. The method according to claim 1, wherein the method for generating the target reduced order model comprises:
Obtaining the maximum range of boundary conditions of each sub-component of the target gas turbine through a preset method;
Inputting the boundary conditions into computational fluid dynamics software, and obtaining target training data through the fluid dynamics software, wherein the target training data comprises the corresponding relation between multi-physical-field information inside each sub-component simulated by the boundary conditions and the boundary conditions;
And constructing an initial reduced order model of each sub-component, and training the initial reduced order model through the target training data to generate a target reduced order model of each sub-component.
3. The method of claim 1, wherein the internal multi-field information of the gas turbine includes multi-field information of a compressor, multi-field information of a combustor, and multi-field information of a turbine, the causing a pre-generated target reduced order model to obtain the internal multi-field information of the gas turbine from the actual site data and the virtual site data includes:
Fusing the actual measuring point data and the virtual measuring point data to obtain actual boundary conditions of the compressor, the combustion chamber and the turbine;
Inputting the actual boundary condition of the air compressor into a target reduced-order model corresponding to the air compressor to obtain multi-physical-field information of the air compressor;
Inputting the actual boundary condition of the combustion chamber into a target reduced-order model corresponding to the combustion chamber to obtain multi-physical-field information of the combustion chamber;
Inputting the actual boundary condition of the air compressor into a target reduced-order model corresponding to the air compressor to obtain multi-physical-field information of the air compressor;
And inputting the actual boundary condition of the turbine into a target reduced order model corresponding to the turbine to obtain multi-physical-field information of the turbine.
4. The method of claim 1, wherein said determining the real-time status of the gas turbine from the multi-physical field information comprises:
Displaying the real-time state of the gas turbine by a real-time three-dimensional picture method; or alternatively, the first and second heat exchangers may be,
And sending the multi-physical-field information to a third-party analysis program, and determining the real-time state of the gas turbine according to the analysis result of the third-party analysis program.
5. The method according to claim 2, wherein the preset method comprises:
DOE, simulation method, historical data analysis method and prototype test method.
6. A gas turbine state real-time analysis device based on multiple physical fields, the device comprising:
the collecting and constructing unit is used for collecting characteristic line data of each sub-component of the target gas turbine and constructing a mechanism model of the target gas turbine according to the characteristic line data, wherein the sub-components comprise a gas compressor, a combustion chamber and a turbine, and the characteristic lines represent the performances of the sub-components under different working conditions;
The information acquisition unit is used for acquiring actual measurement point data of the target gas turbine, acquiring virtual measurement point data corresponding to the actual measurement point data through the mechanism model, and enabling a pre-generated target reduced-order model to acquire internal multi-physical-field information of the gas turbine according to the actual measurement point data and the virtual measurement point data;
And the determining unit is used for determining the real-time state of the gas turbine according to the multi-physical-field information and processing the gas turbine according to the real-time state.
7. The apparatus of claim 6, wherein the method for generating the target reduced order model in the acquired information unit comprises:
Obtaining the maximum range of boundary conditions of each sub-component of the target gas turbine through a preset method;
Inputting the boundary conditions into computational fluid dynamics software, and obtaining target training data through the fluid dynamics software, wherein the target training data comprises the corresponding relation between multi-physical-field information inside each sub-component simulated by the boundary conditions and the boundary conditions;
And constructing an initial reduced order model of each sub-component, and training the initial reduced order model through the target training data to generate a target reduced order model of each sub-component.
8. The apparatus of claim 6, wherein the internal multiphysics information of the gas turbine in the acquisition information unit includes multiphysics information of a compressor, multiphysics information of a combustor, and multiphysics information of a turbine, and wherein the causing the pre-generated target reduced order model to obtain the internal multiphysics information of the gas turbine from the actual site data and the virtual site data comprises:
Fusing the actual measuring point data and the virtual measuring point data to obtain actual boundary conditions of the compressor, the combustion chamber and the turbine;
Inputting the actual boundary condition of the air compressor into a target reduced-order model corresponding to the air compressor to obtain multi-physical-field information of the air compressor;
Inputting the actual boundary condition of the combustion chamber into a target reduced-order model corresponding to the combustion chamber to obtain multi-physical-field information of the combustion chamber;
Inputting the actual boundary condition of the air compressor into a target reduced-order model corresponding to the air compressor to obtain multi-physical-field information of the air compressor;
And inputting the actual boundary condition of the turbine into a target reduced order model corresponding to the turbine to obtain multi-physical-field information of the turbine.
9. The apparatus of claim 6, wherein determining the real-time status of the gas turbine from the multi-physical field information in the determining unit comprises:
Displaying the real-time state of the gas turbine by a real-time three-dimensional picture method; or alternatively, the first and second heat exchangers may be,
And sending the multi-physical-field information to a third-party analysis program, and determining the real-time state of the gas turbine according to the analysis result of the third-party analysis program.
10. The apparatus of claim 7, wherein the method for obtaining the preset information unit comprises:
DOE, simulation method, historical data analysis method and prototype test method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410404987.7A CN118013892A (en) | 2024-04-07 | 2024-04-07 | Gas turbine state real-time monitoring method and device based on multiple physical fields |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410404987.7A CN118013892A (en) | 2024-04-07 | 2024-04-07 | Gas turbine state real-time monitoring method and device based on multiple physical fields |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118013892A true CN118013892A (en) | 2024-05-10 |
Family
ID=90948744
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410404987.7A Pending CN118013892A (en) | 2024-04-07 | 2024-04-07 | Gas turbine state real-time monitoring method and device based on multiple physical fields |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118013892A (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1702305A (en) * | 2005-06-21 | 2005-11-30 | 上海电力学院 | Method for determining running state of gas turbine |
| WO2018109107A1 (en) * | 2016-12-16 | 2018-06-21 | Siemens Healthcare Gmbh | Monitoring system, monitoring apparatus, client, and monitoring method for medical device |
| CN112268011A (en) * | 2020-12-15 | 2021-01-26 | 中国航发上海商用航空发动机制造有限责任公司 | Method and device for estimating aerodynamic performance of multistage axial flow compressor |
| CN112861425A (en) * | 2021-01-13 | 2021-05-28 | 上海交通大学 | Method for detecting performance state of double-shaft gas turbine by combining mechanism and neural network |
| CN114970364A (en) * | 2022-06-09 | 2022-08-30 | 中国联合重型燃气轮机技术有限公司 | Method and device for determining component characteristics of gas turbine and electronic equipment |
| KR20220124987A (en) * | 2021-03-04 | 2022-09-14 | 인하대학교 산학협력단 | Method for Gas turbine control based on artificial intelligence and apparatus thereof |
| CN115292883A (en) * | 2022-06-26 | 2022-11-04 | 哈尔滨工程大学 | Combustion chamber performance online monitoring and predicting method and system based on chemical reactor network method |
| CN115618592A (en) * | 2022-10-10 | 2023-01-17 | 浙江大唐国际绍兴江滨热电有限责任公司 | Gas path fault diagnosis method, system, equipment and terminal for gas turbine of power plant |
| WO2023173624A1 (en) * | 2022-03-14 | 2023-09-21 | 西安热工研究院有限公司 | Soft measurement method for efficiency parameters of heavy-duty gas turbine key components |
| CN116822119A (en) * | 2023-01-31 | 2023-09-29 | 华电电力科学研究院有限公司 | Correction method and system for characteristic line of gas turbine component |
| CN117725700A (en) * | 2023-12-20 | 2024-03-19 | 哈尔滨工程大学 | System, method and equipment for managing split-axis gas turbine based on digital twin technology |
-
2024
- 2024-04-07 CN CN202410404987.7A patent/CN118013892A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1702305A (en) * | 2005-06-21 | 2005-11-30 | 上海电力学院 | Method for determining running state of gas turbine |
| WO2018109107A1 (en) * | 2016-12-16 | 2018-06-21 | Siemens Healthcare Gmbh | Monitoring system, monitoring apparatus, client, and monitoring method for medical device |
| CN112268011A (en) * | 2020-12-15 | 2021-01-26 | 中国航发上海商用航空发动机制造有限责任公司 | Method and device for estimating aerodynamic performance of multistage axial flow compressor |
| CN112861425A (en) * | 2021-01-13 | 2021-05-28 | 上海交通大学 | Method for detecting performance state of double-shaft gas turbine by combining mechanism and neural network |
| KR20220124987A (en) * | 2021-03-04 | 2022-09-14 | 인하대학교 산학협력단 | Method for Gas turbine control based on artificial intelligence and apparatus thereof |
| WO2023173624A1 (en) * | 2022-03-14 | 2023-09-21 | 西安热工研究院有限公司 | Soft measurement method for efficiency parameters of heavy-duty gas turbine key components |
| CN114970364A (en) * | 2022-06-09 | 2022-08-30 | 中国联合重型燃气轮机技术有限公司 | Method and device for determining component characteristics of gas turbine and electronic equipment |
| CN115292883A (en) * | 2022-06-26 | 2022-11-04 | 哈尔滨工程大学 | Combustion chamber performance online monitoring and predicting method and system based on chemical reactor network method |
| CN115618592A (en) * | 2022-10-10 | 2023-01-17 | 浙江大唐国际绍兴江滨热电有限责任公司 | Gas path fault diagnosis method, system, equipment and terminal for gas turbine of power plant |
| CN116822119A (en) * | 2023-01-31 | 2023-09-29 | 华电电力科学研究院有限公司 | Correction method and system for characteristic line of gas turbine component |
| CN117725700A (en) * | 2023-12-20 | 2024-03-19 | 哈尔滨工程大学 | System, method and equipment for managing split-axis gas turbine based on digital twin technology |
Non-Patent Citations (8)
| Title |
|---|
| 周奎;刘尚明;: "基于数据和神经网络的压气机性能预测研究", 热力透平, no. 03, 15 September 2017 (2017-09-15) * |
| 夏硕成;王辉;迟重然;臧述升;: "部件性能衰减影响燃机性能的试验与仿真研究", 工程热物理学报, no. 08, 15 August 2020 (2020-08-15) * |
| 张元哲;刘培;李政;: "燃气轮机机理建模与性能监测", 工程热物理学报, no. 03, 15 March 2020 (2020-03-15) * |
| 李;彭淑红;张会生;: "燃气轮机在线状态建模与仿真研究", 计算机仿真, no. 05, 15 May 2012 (2012-05-15) * |
| 李景轩;周登极;肖旺;张会生;: "燃气轮机机理-数据混合建模方法研究", 热能动力工程, no. 12 * |
| 王茜, 董学仁, 尉吉勇, 马玉真: "神经网络技术在智能传感器系统中的应用与发展", 自动化仪表, no. 07, 20 July 2004 (2004-07-20) * |
| 邢立立;杨马英;: "一类反应-换热网络的控制方法研究", 机电工程, no. 04, 20 April 2008 (2008-04-20) * |
| 黄伟;常俊;孙智滨;: "重型发电燃气轮机的建模与状态监测研究", 热能动力工程, no. 03 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Talaat et al. | A hybrid model of an artificial neural network with thermodynamic model for system diagnosis of electrical power plant gas turbine | |
| Hanachi et al. | A physics-based modeling approach for performance monitoring in gas turbine engines | |
| Tsoutsanis et al. | A component map tuning method for performance prediction and diagnostics of gas turbine compressors | |
| CN106404403B (en) | Method and system for analysis of a turbomachine | |
| Kong et al. | Component map generation of a gas turbine using genetic algorithms | |
| US9483605B2 (en) | Probabilistic high cycle fatigue (HCF) design optimization process | |
| JP5897824B2 (en) | Turbomachine risk analysis system and machine-readable medium for storing machine-readable instructions for causing a computer to create an inspection recommendation for the turbomachine | |
| Mohammadi et al. | Simulation of full and part-load performance deterioration of industrial two-shaft gas turbine | |
| Igie et al. | Evaluating gas turbine performance using machine-generated data: quantifying degradation and impacts of compressor washing | |
| Visser et al. | A generic approach for gas turbine adaptive modeling | |
| Li et al. | Study on gas turbine gas-path fault diagnosis method based on quadratic entropy feature extraction | |
| Clark et al. | The effect of airfoil scaling on the predicted unsteady loading on the blade of a 1 and 1/2 stage transonic turbine and a comparison with experimental results | |
| Fernelius et al. | Mapping efficiency of a pulsing flow-driven turbine | |
| Kurstak et al. | A statistical characterization of the effects and interactions of small and large mistuning on multistage bladed disks | |
| Musa et al. | Development of big data lean optimisation using different control mode for Gas Turbine engine health monitoring | |
| Kurstak et al. | A statistical characterization of the effects and interactions of small and large mistuning on multistage bladed disks | |
| Tsalavoutas et al. | Identifying faults in the variable geometry system of a gas turbine compressor | |
| CN118013892A (en) | Gas turbine state real-time monitoring method and device based on multiple physical fields | |
| JP6554162B2 (en) | Power plant performance evaluation method and power plant performance evaluation program | |
| Reutter et al. | Comparison of Experiments, Full-annulus Calculations and Harmonic-balance-calculations of a Multi-stage Compressor | |
| US11905892B2 (en) | Flow machine performance modelling | |
| Eustace | A real-world application of fuzzy logic and influence coefficients for gas turbine performance diagnostics | |
| JP2004093567A (en) | Evaluation method for operating condition of machine or equipment | |
| Mohajer et al. | Development of compression system dynamic simulation code for testing and designing of anti-surge control system | |
| Musa et al. | Energy Reports |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |