Supercharge Your Innovation With Domain-Expert AI Agents!

Modeling method and equipment for predicting output data of gas turbine in starting process

A start-up process, gas turbine technology, applied in nuclear methods, electrical digital data processing, computer-aided design, etc., can solve the problems of low model accuracy and low versatility

Pending Publication Date: 2020-11-20
新奥能源动力科技(上海)有限公司
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The invention provides a modeling method and equipment for predicting the output data of the gas turbine start-up process, which are used to solve the problems of low model accuracy and low versatility existing in the existing modeling methods for predicting the output data of the gas turbine start-up process

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Modeling method and equipment for predicting output data of gas turbine in starting process
  • Modeling method and equipment for predicting output data of gas turbine in starting process
  • Modeling method and equipment for predicting output data of gas turbine in starting process

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0103] The embodiment of the present invention provides a modeling method for predicting the output data of the start-up process of the gas turbine, which is applied to the identification and modeling scene of the start-up process of the micro-gas turbine, such as figure 1 As shown, the method includes:

[0104] Step S101, performing parameter collection during multiple start-ups of the gas turbine, and correspondingly obtaining a plurality of training samples;

[0105] The embodiment of the present invention conducts identification modeling based on the operating data of the start-up process of the micro-gas turbine, uses the parameters collected from the start-up process of the micro-gas turbine as training samples, performs identification modeling and model training, and obtains an output prediction model, which will be described in detail below.

[0106] During multiple start-ups of the gas turbine, at least one type of parameter whose coupling degree does not exceed a set...

Embodiment 2

[0154] In this embodiment, a micro gas turbine with a stand-alone power range of 30KW-1MW is taken as an example for illustration.

[0155] When establishing the output data prediction model of the gas turbine start-up process in this embodiment, first obtain the training samples, select multiple sets of start-up process data of the above-mentioned micro gas turbine, take the time interval of 0.5s as the sampling point, and select the gas turbine start-up process according to the characteristics of the gas turbine. Smallest set of variables. Extract 33 groups of minimum variable group data in the start-up process of micro gas turbines operating at different ambient temperatures, that is, the input data. Among them, 32 groups of gas turbine start-up process data are used as training samples, and 1 group of gas turbine start-up process data is used as test samples. Each group of samples contains 1322 For the data, in this embodiment, it is required that the error of the dynamic ...

example 1

[0172] Using the SVM optimization modeling method, only using the SVM algorithm, the ambient temperature, compressor inlet pressure, natural gas flow and starting current are used as the input data of the model, and the gas turbine speed and exhaust temperature are used as the output data of the model for model training.

[0173] refer to Figure 13 , is the prediction result graph of the SVM-optimized gas turbine speed provided by the embodiment of the present invention;

[0174] refer to Figure 14 , is a graph of the prediction results of the exhaust gas temperature optimized by the SVM provided by the embodiment of the present invention.

[0175] When this embodiment only uses the SVM algorithm to perform model training on the above data, the results of the model-predicted gas turbine speed and exhaust temperature are as follows: Figure 13 , Figure 14 As shown, according to the calculation of the prediction results, it can be known that the mean square error of the ga...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a modeling method and equipment for predicting output data of a gas turbine in a starting process, and the method comprises the steps: carrying out the parameter collection in aplurality of starting processes of the gas turbine, and correspondingly obtaining a plurality of training samples; taking part of data in the training sample as input data of a network model; and analyzing control parameters of an input data prediction support vector machine (SVM) algorithm by utilizing a grey wolf optimization (GWO) algorithm, and adjusting model parameters of the network modelby taking the other part of data in the output training sample as a target according to the input data under the control of the control parameters by utilizing the SVM algorithm to obtain an output prediction model. According to the modeling method and device for predicting the output data of the gas turbine in the starting process, the problems that an existing modeling method for predicting theoutput data of the gas turbine in the starting process is low in model precision and universality are solved.

Description

technical field [0001] The invention relates to the technical field of gas turbines, in particular to a modeling method and equipment for predicting the output data of the gas turbine start-up process. Background technique [0002] The gas turbine is one of the core components of the gas-steam combined cycle, which has the advantages of high efficiency, fast start-up, and low environmental pollution. Gas turbine start-up refers to the process in which the gas turbine reaches a certain speed from a stationary (cranking) state. In the study of gas turbine start-up characteristics, the method of establishing a mathematical simulation model for performance evaluation is generally adopted, and the actual operation process of the gas turbine is simulated by establishing a model, and performance analysis and prediction are performed, so as to obtain the control law, control the operation of the gas turbine, and ensure the gas turbine operation. efficient and stable operation. [...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F30/27G06F30/28G06N20/10G06F113/08G06F119/08G06F119/14
CPCG06F30/27G06F30/28G06N20/10G06F2113/08G06F2119/14G06F2119/08
Inventor 张孟然张琪鲍其雷刘青山刘德玉毕辉阮健斌
Owner 新奥能源动力科技(上海)有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com