CN111428414A - Temperature field virtual reality real-time reconstruction method for monitoring service performance of steam turbine - Google Patents
Temperature field virtual reality real-time reconstruction method for monitoring service performance of steam turbine Download PDFInfo
- Publication number
- CN111428414A CN111428414A CN202010251727.2A CN202010251727A CN111428414A CN 111428414 A CN111428414 A CN 111428414A CN 202010251727 A CN202010251727 A CN 202010251727A CN 111428414 A CN111428414 A CN 111428414A
- Authority
- CN
- China
- Prior art keywords
- temperature field
- steam turbine
- sampling point
- temperature
- sampling
- 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.)
- Granted
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E30/00—Energy generation of nuclear origin
Landscapes
- Control Of Turbines (AREA)
Abstract
The invention discloses a temperature field virtual reality real-time reconstruction method for monitoring service performance of a steam turbine. Carrying out finite element analysis on the steam turbine to obtain a finite element analysis result of the simulated temperature field, selecting a sampling point set of the steam turbine, and calculating the half-variance between every two points on the simulated temperature field; randomly selecting a sampling point on the simulated temperature field, reconstructing the spatial distribution of the temperature field, and presenting the change condition of the temperature field when the steam turbine operates in real time by taking the finally obtained reconstructed temperature field as a result. According to the invention, by reconstructing the real-time finite element temperature field of the steam turbine, the temperature change condition of each structure in the running state of the steam turbine can be presented in real time in a visual visualization mode in a virtual reality environment, and the performance monitoring of the running state of the steam turbine is realized.
Description
Technical Field
The invention relates to a real-time processing method for a temperature field of a steam turbine, in particular to a virtual reality real-time reconstruction method for the service performance monitoring of the steam turbine.
Background
The steam turbine is the most widely applied prime motor in the power generation equipment of the modern thermal power station and the nuclear power station, has the outstanding advantages of high efficiency, large single machine capacity, long service life and stable operation process, and plays an important role in the fields of energy and industry.
With the development of modern industrial technology, the improvement of steam parameters and the emergence of various complex variable working conditions also present considerable challenges to the requirements of steam turbine power generation sets. The steam inlet temperature is increased, so that the temperature gradient in the steam turbine is increased, and the thermal stress of solid parts can be increased; in the variable working condition operation process, the main parameters of the temperature, the pressure and the like of the fluid in the whole unit are continuously changed. In order to reduce the leakage loss, the clearance between a rotor part and a stator part of the through-flow part of the steam turbine is generally very small, and the metal parts are unevenly expanded due to the uneven and constantly changing temperature field, so that dynamic and static rubbing can be caused. Meanwhile, unstable working conditions can cause low-cycle fatigue damage of metal, the difficulty of service life prediction is increased, and the service life of a unit is shortened. Therefore, the research on the temperature field of the steam turbine is particularly important.
In the aspect of research means, the main research means for the temperature field of the steam turbine comprises theory, experiment and simulation, and the three means have advantages and disadvantages respectively. The main idea at present is to combine the three, take theory as the basis, take experiment or simulation as the main, and mutually prove. However, a large amount of manpower and material resources are needed to be consumed for building the full-size experiment table of the low-pressure cylinder, and the experiment table is not easy to implement. And due to the limitation of measurement means, only limited positions can be observed in the experiment, and limited flow information can be obtained. The last stage blades and exhaust runners of low pressure cylinders typically operate in the wet steam region, and there is no effective way to measure the enthalpy of the wet steam. The numerical simulation method just overcomes the defects, so in recent years, the research on the pneumatic performance of the low-pressure cylinder is mainly numerical simulation and is verified by experimental data.
For the complex fluid-solid coupling heat transfer problem in the steam turbine, the conjugate heat transfer theory is the mainstream solution at present. Compared with the traditional method only solving the solid domain, the conjugate heat transfer method has obvious precision advantage in processing the complex heat transfer problem. However, because the components in the low-pressure cylinder are numerous and the through flow is complex, the time consumption of finite element simulation calculation by adopting fluid-solid coupling is long, and the heat dissipation analysis of real-time data drive in the operation process of the steam turbine cannot be realized.
Disclosure of Invention
In order to solve the problems in the background art, the invention provides a temperature field virtual reality real-time reconstruction method for monitoring the service performance of a steam turbine.
The method can overcome the defects of the existing method, and can display the temperature change condition of each structure in the running state of the steam turbine in real time in a visual and visual form in a virtual reality environment by reconstructing the real-time finite element temperature field of the steam turbine so as to realize the performance monitoring of the running state of the steam turbine.
In order to achieve the purpose, the implementation of the technical scheme of the invention comprises the following specific steps:
the steam turbine operating parameters are specifically the pressure and temperature of the main steam and the reheated steam.
S11, carrying out finite element analysis on the steam turbine under K different working condition conditions to obtain K finite element analysis results of the simulated temperature field, and selecting a sampling point set of the simulated temperature field of the steam turbine;
s12, calculating x of every two points on the simulation temperature field according to the finite element analysis result of each simulation temperature fieldiAnd xjHalf variance r betweenij：
Wherein, y(k)(xi) Is the k-th simulated temperature field midpoint xiA temperature value of (a);
s13, randomly selecting M sampling points on the simulation temperature field, and reconstructing the spatial distribution of the temperature field according to the following mode:
s131, constructing a sampling point semivariance matrix R by utilizing the selected M sampling pointsijAnd arbitrary point semivariance matrix
Wherein the sampling point is a semivariance matrix RijThe ith row and the jth column in the middle are half variances between the temperature value of the ith sampling point and the temperature value of the jth sampling point, and the half variance moment of any pointMatrix of
The ith row and the jth column in the middle are half variances between the temperature value of the ith sampling point and the temperature value of the jth sampling point;
s132. solving a linear equation set
Obtaining a coefficient matrix w, wherein u represents a Lagrangian multiplier;
s133. according to the known sampling points of the simulation temperature field, collecting temperature values
Obtaining the spatial distribution of the temperature field as a reconstruction temperature field, specifically:
where T denotes a matrix transpose.
S14, calculating the error between the temperature values of the sampling points at the same positions of the reconstructed temperature field and the original simulation temperature field, confirming a sampling point set if the error is smaller than a preset error threshold value, and otherwise, carrying out the next step;
s15, adding the sampling point with the largest error into the sampling point set, removing one sampling point from the sampling point set, wherein the removed sampling point has the smallest average half variance with other sampling points, and then returning to the step S13, and continuously repeating the processing until the error between the temperature values of the sampling points at the same positions of the reconstructed temperature field and the original simulation temperature field is smaller than a preset error threshold value;
and S16, taking the finally obtained reconstructed temperature field as a result, and presenting the change condition of the temperature field in the running process of the steam turbine in real time in a virtual reality environment so as to assist in carrying out subsequent operation on the steam turbine.
The finite element analysis for the steam turbine is specifically a finite element performance field real-time reconstruction method based on a proxy model.
The simulation temperature field sampling point set temperature value
Is obtained by the fitting of a proxy model of performance values of a plurality of sampling points.
Firstly, selecting a proper simulation temperature field sampling point set for a finite element analysis result of the steam turbine under different working conditions, and establishing a proxy model for mapping between steam turbine operating parameters and temperature values of each sampling point in the simulation temperature field sampling point set. And then reconstructing the spatial distribution of the temperature field based on the temperature values of the sampling point set. And calculating the error between the temperature values of the sampling points at the same positions of the reconstructed temperature field and the original simulation temperature field, so that the error of the temperature values of all the sampling points is smaller than the preset error and the threshold. And finally, obtaining a steam turbine reconstruction temperature field, and presenting the change condition of the temperature field when the steam turbine operates in real time in a virtual reality environment so as to assist technicians to make corresponding decisions.
Compared with the prior art and method, the method has the following advantages:
the invention can enable an operator to directly observe the temperature change condition of each structure of the steam turbine in a visual and visual manner in a remote monitoring virtual reality environment without visiting the site, thereby greatly reducing the cost of manpower and material resources consumed by product maintenance.
The invention can more accurately realize the remote fault diagnosis of the steam turbine and clearly present the corresponding relation between the product fault reason and the structural state in the virtual reality environment, thereby simplifying the complex process experienced by the fault troubleshooting of the steam turbine and greatly accelerating the whole process of troubleshooting and maintenance.
Drawings
FIG. 1 is a schematic flow diagram of the process of the present invention.
FIG. 2 is a flow chart illustrating a process for reconstructing a real-time temperature field of a turbine rotor according to an embodiment of the present invention.
FIG. 3 is a finite element analysis of (local) temperature distribution behavior of 48 sets of turbine rotor blades in an example of the present invention.
FIG. 4 shows a set of 9 sampling points selected on a finite element mesh in accordance with an embodiment of the present invention.
FIG. 5 is a graph of error statistics and fit results versus fit error for each model at Isight in an example of the invention.
Detailed Description
The invention is further illustrated by the following specific examples in conjunction with the accompanying drawings:
as shown in fig. 1, an embodiment of the present invention is described by taking a steam turbine as an example, and specifically includes the following steps:
s1, selecting a simulation temperature field sampling point set of a steam turbine;
the method comprises the steps of firstly collecting temperature state data of a section of a steam turbine in which a rotor is accelerated from the beginning to reach a stable rotating speed, and then carrying out compaction and lossless compression coding on the collected data.
S11. for K (K)>48) Calculating the x of each two points on the temperature field according to the finite element analysis result of the simulation temperature fieldiAnd xjHalf variance between:
wherein, y(k)(xi) Is the point x in the k resultiA temperature value of (a);
s12, randomly selecting M sampling points on the simulation temperature field;
s13, constructing a sampling point semivariance matrix R by utilizing the selected M sampling pointsijAnd arbitrary point semivariance matrix
Wherein the sampling point is a semivariance matrix RijThe ith row and the jth column in the middle are half-variances between the temperature value of the ith sampling point and the temperature value of the jth sampling point, and a half-variance matrix of any point
The ith row and the jth column in the middle are half variances between the temperature value of the ith sampling point and the temperature value of the jth sampling point;
s14, solving a linear equation set
A coefficient matrix w is obtained where u represents the lagrangian multiplier.
S2, establishing a parameterized finite element model of the steam turbine;
s21, obtaining a turbine rotor model from a geometric design model of the turbine;
s22, symmetrically dividing the model, and then dividing grids to obtain a finite element grid model, wherein the grid model of each fan blade is 14381 nodes and 12953 units.
S23, according to the operating conditions of the turbine of the actual power plant, 48 groups of working state variables are selected, wherein the 48 groups of working state variables comprise a combination of air relative flow velocity v ∈ {0.05, 0.1, 0.15} (m/s) caused by mechanism movement, a waiting time interval T ∈ {8, 12, 16, 20 }(s) from the beginning of acceleration of the rotor to the reaching of a stable rotating speed, and ambient temperature T ∈ {26, 28, 30, 32} (° C).
S3, reconstructing the spatial distribution of the temperature field according to the fitting value result of the sampling point set, wherein the specific working process is shown in figure 2:
s31, solving the DOE by using Ansys Fluent to obtain 48 groups of rotor blade (local) temperature distribution performance results, as shown in FIG. 3;
s32, analyzing the parameterized finite element model to obtain 48 groups of temperature value data, integrating, and using the step S11 half-variance calculation method to obtain 9 sampling points to form a sampling point set 1, as shown in the left side of the graph 4; meanwhile, 9 sampling points which are evenly distributed in space are selected to form a sampling point set 2 for comparison;
and S33, testing the reconstruction accuracy on 5 groups of working state variables according to 48 groups of temperature value data fitting coefficient matrixes w. The 5 groups of working state variables comprise 2 groups of test points, and also comprise 3 groups of intermediate values and two extreme values selected from 48 groups: (0.1, 12, 28), (0.15, 20, 26) and (0.05, 8, 32), referred to as the fitting points 1, 2, 3, respectively.
A least squares (least square error, L SE) reconstructed model was used as a control, again with polynomial fit to estimate
Solving a linear equation system by adopting a least square method:
wherein W' is the matrix of optimized coefficients,
is the temperature data of the jth element in the ith row of Y sampling points, YijIs the temperature data of the jth element in the ith row in the Y nodes.
The least squares model was also tested on 5 sets of temperature data of the operating state variables, comparing the reconstruction accuracy.
The temperature field was reconstructed by the method proposed by the invention and the L SE method using sample point set 1 and sample point set 2, respectively, with the average percentage error:
and maximum percent error:
two parameters are used to measure the reconstruction accuracy, wherein
Representing x over the reconstructed temperature fieldiTemperature value at node, y (x)i) Representing finite elementsX in simulated temperature fieldiThe temperature value at the node. The results are shown in Table 1.
TABLE 1 temperature field reconstruction accuracy
As can be seen from the fitting precision results in the table, the reconstruction method of the invention is superior to the least square method in fitting precision on the test point 1, the test point 2 and the fitting point 1. The main reason is that compared with the least square, the method not only minimizes the second-order error term, but also adds the first-order unbiased estimation constraint, thereby strengthening the integrity of the field data. The least square method has better precision at the boundary of the working state variable, namely the fitting point 2 and the fitting point 3. The possible reason is that under the two working state variables, the temperature values of all nodes on the grid are the maximum value or the minimum value of the training set, and are not consistent with the steady-state random field hypothesis of the method. However, in the application of state presentation, the actual working state variables all belong to the middle of the training interval, and the boundary value is generally not obtained, so that the method disclosed by the invention has a better effect in the actual application. In addition to the inter-method comparison, it can also be seen from the table that the fitting accuracy of the sampling point set 1 is better than that of the sampling point set 2. The reason is that compared with the sampling point set 2 which is uniformly distributed in space, the sampling point set 1 is more suitable for the overall distribution of the fitting performance field due to the consideration of the correlation characteristics of the temperature values on the sampling points and the temperature values of other nodes.
The method with higher fitting precision in the classical model method can be selected by fitting the mapping relation between the working state variables and the sampling point temperature values, and the model is selected by using optimization software Isight in the embodiment. The "Approximation" module in Isight provides four model methods of polynomial Response Surface (RSM), Radial Basis Function (RBF), Orthogonal Polynomial (OPM) and Kriging (Kriging) and parameter settings thereof. The 48 groups of working state variables and the corresponding 9 sampling point temperature values are respectively used as input and output data of model training, the working state variables and the sampling point temperature values of 2 testing points are used as precision verification, and the fitting error result of each model is obtained as shown in fig. 5 (wherein, OPM refers to Chebyshev orthogonal polynomial, and besides, the fitting precision of the Crigy model is poor in the application and is not listed in the figure). According to the error result, the radial basis function model in the application has high precision, the average error of 9 sampling points is 2.10%, and the maximum error of a single sampling point is 3.73%. And (4) deriving coefficients of the radial basis function model from the Isight fitting result, and constructing the model to be applied to virtual monitoring.
In the embodiment, firstly, a proper simulation temperature field sampling point set is selected for a finite element analysis result of the steam turbine under different working conditions, and a proxy model for mapping between steam turbine operation parameters and temperature values of each sampling point in the simulation temperature field sampling point set is established. And then reconstructing the spatial distribution of the temperature field based on the temperature values of the sampling point set, and enabling the temperature value errors of all the sampling points to be smaller than the preset error and threshold value by calculating the error between the reconstructed temperature field and the temperature value of each sampling point at the same position of the original simulation temperature field. Finally, the reconstructed temperature field model of the steam turbine obtained by the method is compared with the reconstructed model obtained by the least square method, and the fact that the reconstruction method of the invention is superior to the least square method in fitting precision in the actual working state is shown.
Claims (3)
1. A temperature field virtual reality real-time reconstruction method for monitoring service performance of a steam turbine is characterized by comprising the following steps: the method comprises the following steps:
s11, carrying out finite element analysis on the steam turbine under K different working condition conditions to obtain K finite element analysis results of the simulated temperature field, and selecting a sampling point set of the simulated temperature field of the steam turbine;
s12, calculating x of every two points on the simulation temperature field according to the finite element analysis result of each simulation temperature fieldiAnd xjHalf variance r betweenij：
Wherein, y(k)(xi) Is the k < th > oneSimulation temperature field midpoint xiA temperature value of (a);
s13, randomly selecting M sampling points on the simulation temperature field, and reconstructing the spatial distribution of the temperature field according to the following mode:
s131, constructing a sampling point semivariance matrix R by utilizing the selected M sampling pointsijAnd arbitrary point semivariance matrix
Wherein the sampling point is a semivariance matrix RijThe ith row and the jth column in the middle are half-variances between the temperature value of the ith sampling point and the temperature value of the jth sampling point, and a half-variance matrix of any point
The ith row and the jth column in the middle are half variances between the temperature value of the ith sampling point and the temperature value of the jth sampling point;
s132. solving a linear equation set
Obtaining a coefficient matrix w, wherein u represents a Lagrangian multiplier;
s133. collecting temperature values according to sampling points of the simulation temperature field
Obtaining the spatial distribution of the temperature field as a reconstruction temperature field, specifically:
wherein T represents a matrix transpose;
s14, calculating the error between the temperature values of the sampling points at the same positions of the reconstructed temperature field and the original simulation temperature field, confirming a sampling point set if the error is smaller than a preset error threshold value, and otherwise, carrying out the next step;
s15, adding the sampling point with the largest error into the sampling point set, removing one sampling point from the sampling point set, wherein the removed sampling point has the smallest average half variance with other sampling points, and then returning to the step S13, and continuously repeating the processing until the error between the temperature values of the sampling points at the same positions of the reconstructed temperature field and the original simulation temperature field is smaller than a preset error threshold value;
and S16, taking the finally obtained reconstructed temperature field as a result, and presenting the change condition of the temperature field when the steam turbine operates in real time in a virtual reality environment.
2. The method for reconstructing the virtual reality of the temperature field used for monitoring the service performance of the steam turbine in real time according to the claim 1, is characterized in that: the finite element analysis for the steam turbine is specifically a finite element performance field real-time reconstruction method based on a proxy model.
3. The method for reconstructing the virtual reality of the temperature field used for monitoring the service performance of the steam turbine in real time according to the claim 1, is characterized in that: the simulation temperature field sampling point set temperature value
Is obtained by the fitting of a proxy model of performance values of a plurality of sampling points.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010251727.2A CN111428414B (en) | 2020-04-01 | 2020-04-01 | Temperature field virtual reality real-time reconstruction method for monitoring service performance of steam turbine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010251727.2A CN111428414B (en) | 2020-04-01 | 2020-04-01 | Temperature field virtual reality real-time reconstruction method for monitoring service performance of steam turbine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111428414A true CN111428414A (en) | 2020-07-17 |
| CN111428414B CN111428414B (en) | 2022-05-17 |
Family
ID=71550535
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010251727.2A Active CN111428414B (en) | 2020-04-01 | 2020-04-01 | Temperature field virtual reality real-time reconstruction method for monitoring service performance of steam turbine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111428414B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112874378A (en) * | 2021-01-27 | 2021-06-01 | 一汽解放汽车有限公司 | Method, device and equipment for processing battery sampling temperature and vehicle |
| CN114355790A (en) * | 2021-12-22 | 2022-04-15 | 重庆长安汽车股份有限公司 | Method and system for designing limited automatic driving traversal test scene and computer readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102880746A (en) * | 2012-09-04 | 2013-01-16 | 上海发电设备成套设计研究院 | Method for determining inertial element coefficients for calculation of volume average temperature of turbine rotor |
| CN104775856A (en) * | 2015-03-03 | 2015-07-15 | 国家电网公司 | Rapid starting control method and rapid starting control system for steam turbine of combined cycle generating unit |
| CN106444628A (en) * | 2016-09-28 | 2017-02-22 | 大连理工大学 | Numerically-controlled machine tool spindle thermal extension error real-time compensation method |
| CN106714336A (en) * | 2016-10-25 | 2017-05-24 | 南京邮电大学 | Wireless sensor network temperature monitoring method based on improved Kriging algorithm |
| US20170182562A1 (en) * | 2012-11-08 | 2017-06-29 | Georgia Tech Research Corporation | Systems and methods for additive manufacturing and repair of metal components |
| CN110866358A (en) * | 2019-11-12 | 2020-03-06 | 桂林电子科技大学 | Measured temperature data-based reflow welding process simulation model correction method |
-
2020
- 2020-04-01 CN CN202010251727.2A patent/CN111428414B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102880746A (en) * | 2012-09-04 | 2013-01-16 | 上海发电设备成套设计研究院 | Method for determining inertial element coefficients for calculation of volume average temperature of turbine rotor |
| US20170182562A1 (en) * | 2012-11-08 | 2017-06-29 | Georgia Tech Research Corporation | Systems and methods for additive manufacturing and repair of metal components |
| CN104775856A (en) * | 2015-03-03 | 2015-07-15 | 国家电网公司 | Rapid starting control method and rapid starting control system for steam turbine of combined cycle generating unit |
| CN106444628A (en) * | 2016-09-28 | 2017-02-22 | 大连理工大学 | Numerically-controlled machine tool spindle thermal extension error real-time compensation method |
| CN106714336A (en) * | 2016-10-25 | 2017-05-24 | 南京邮电大学 | Wireless sensor network temperature monitoring method based on improved Kriging algorithm |
| CN110866358A (en) * | 2019-11-12 | 2020-03-06 | 桂林电子科技大学 | Measured temperature data-based reflow welding process simulation model correction method |
Non-Patent Citations (2)
| Title |
|---|
| TONG MA ET AL: "Neural networks for 3D temperature field reconstruction via acoustic signals", 《MECHANICAL SYSTEMS AND SIGNAL PROCESSING》 * |
| 景亚兵: "小型发电机组噪声源灵敏度分析与低噪声结构设计研究", 《中国博士学位论文全文数据库电子期刊 工程科技II辑》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112874378A (en) * | 2021-01-27 | 2021-06-01 | 一汽解放汽车有限公司 | Method, device and equipment for processing battery sampling temperature and vehicle |
| CN114355790A (en) * | 2021-12-22 | 2022-04-15 | 重庆长安汽车股份有限公司 | Method and system for designing limited automatic driving traversal test scene and computer readable storage medium |
| CN114355790B (en) * | 2021-12-22 | 2023-05-16 | 重庆长安汽车股份有限公司 | Method, system and computer readable storage medium for designing limited autopilot traversal test scene |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111428414B (en) | 2022-05-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109522600B (en) | Complex equipment residual service life prediction method based on combined deep neural network | |
| CN111428414B (en) | Temperature field virtual reality real-time reconstruction method for monitoring service performance of steam turbine | |
| CN106404403B (en) | Method and system for analysis of a turbomachine | |
| CN113570138B (en) | Method and device for predicting residual service life of equipment of time convolution network | |
| CN111859746B (en) | Method for predicting variable working condition performance of turbomachinery based on flow field reconstruction | |
| CN102135021B (en) | Method for predicting shaft power of industrial extraction condensing steam turbine | |
| KR102354253B1 (en) | Method and apparatus for assuming internal state of heat machine | |
| CN110083910B (en) | NSGA-II based chaotic time sequence prediction sample acquisition method | |
| CN110428185B (en) | Pseudo measurement model-based robust state estimation method for electricity-heat interconnection comprehensive energy system | |
| CN112287580A (en) | Axial flow compressor surge boundary calculation method based on full three-dimensional numerical simulation | |
| CN109356798B (en) | Wind driven generator gearbox state monitoring method based on co-integration analysis | |
| Li et al. | Study on gas turbine gas-path fault diagnosis method based on quadratic entropy feature extraction | |
| CN113552854A (en) | Virtual twin system for power plant operation | |
| CN112862347A (en) | Equipment abnormity monitoring method and system based on federal learning, storage medium and terminal | |
| CN115048743A (en) | Liquid cooling plate model construction method based on digital twinning | |
| CN114577484A (en) | Method for correcting test performance of core machine | |
| Pavlenko et al. | Using Computer Modeling and Artificial Neural Networks for Ensuring the Vibration Reliability of Rotors. | |
| CN110442956B (en) | Component level simulation method for gas turbine | |
| Salar et al. | A hybrid EKF-fuzzy approach to fault detection and isolation of industrial gas turbines | |
| CN107256294B (en) | SSS clutch dynamics modeling method based on equivalent stiffness method | |
| Sladojevic et al. | Investigation of the influence of aerodynamic coupling on response levels of mistuned bladed discs with weak structural coupling | |
| CN116227086A (en) | Aeroengine gas circuit fault simulation method | |
| CN117454805B (en) | Fan wake influence calculation method and system based on fluid reduced-order simulation | |
| CN117272212B (en) | Method for selecting optimal operation parameters of refrigeration system based on real-time data | |
| CN117543628B (en) | Photovoltaic power station partitioning method and system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |