scholarly journals A gas turbine thermal performance prediction method based on dynamic neural network

2021 ◽  
Vol 1207 (1) ◽  
pp. 012014
Author(s):  
Yansong Hao ◽  
Yunfeng Jin ◽  
Chao Liu ◽  
Jiangang Hao ◽  
Haizhou Huang ◽  
...  
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Gas Turbine ◽  
Prediction Method ◽  
Calculation Model ◽  
Dynamic Neural Network ◽  
Safety And Reliability ◽  
Validation Set ◽  
Gas Turbine Compressor ◽  
Isentropic Efficiency

Abstract In order to ensure safety and reliability of energy transportation, it is necessary to understand and predict the performance of the gas turbine components. A prediction frame of the gas turbine compressor isentropic efficiency is established using the neural time series theory based on the Dynamic Neural Network. In order to obtain appropriate parameters for the network, a validation set is introduced to generalize the model. The compressor isentropic efficiency can be predicted based on the suggested model which provides an effective technical mean for the early warning of gas turbine performance. The experiment verified that the performance calculation model and the isentropic entropy efficiency prediction model based on the neural time series are effective.

GRU-corr Neural Network Optimized by Improved PSO Algorithm for Time Series Prediction

2020 ◽  
Vol 29 (07n08) ◽  
pp. 2040010
Author(s):  
Shao-Pei Ji ◽  
Yu-Long Meng ◽  
Liang Yan ◽  
Gui-Shan Dong ◽  
Dong Liu
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Time Series Data ◽  
Time Series Prediction ◽  
Prediction Method ◽  
Pso Algorithm ◽  
Series Data ◽  
Multi Scale ◽  
Network Parameters ◽  
Angle Data

Time series data from real problems have nonlinear, non-smooth, and multi-scale composite characteristics. This paper first proposes a gated recurrent unit-correction (GRU-corr) network model, which adds a correction layer to the GRU neural network. Then, a adaptive staged variation PSO (ASPSO) is proposed. Finally, to overcome the drawbacks of the imprecise selection of the GRU-corr network parameters and obtain the high-precision global optimization of network parameters, weight parameters and the hidden nodes number of GRU-corr is optimized by ASPSO, and a time series prediction model (ASPSO-GRU-corr) is proposed based on the GRU-corr optimized by ASPSO. In the experiment, a comparative analysis of the optimization performance of ASPSO on a benchmark function was performed to verify its validity, and then the ASPSO-GRU-corr model is used to predict the ship motion cross-sway angle data. The results show that, ASPSO has better optimization performance and convergence speed compared with other algorithms, while the ASPSO-GRU-corr has higher generalization performance and lower architecture complexity. The ASPSO-GRU-corr can reveal the intrinsic multi-scale composite features of the time series, which is a reliable nonlinear and non-steady time series prediction method.

Time Series Prediction Method Based on Variant LSTM Recurrent Neural Network

2020 ◽  
Vol 52 (2) ◽  
pp. 1485-1500
Author(s):  
Jiaojiao Hu ◽  
Xiaofeng Wang ◽  
Ying Zhang ◽  
Depeng Zhang ◽  
Meng Zhang ◽  
...  
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Recurrent Neural Network ◽  
Time Series Prediction ◽  
Prediction Method

A Prediction Method for Nonlinear Correlative Time Series

2010 ◽  
Vol 40-41 ◽  
pp. 930-936 ◽  
Author(s):  
Cong Gui Yuan ◽  
Xin Zheng Zhang ◽  
Shu Qiong Xu
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Mutual Information ◽  
Orthogonal Polynomial ◽  
Time Series Prediction ◽  
Prediction Method ◽  
Nonlinear Time Series ◽  
Iterative Learning ◽  
Polynomial Basis

A nonlinear correlative time series prediction method is presented in this paper.It is based on the mutual information of time series and orthogonal polynomial basis neural network. Inputs of network are selected by mutual information, and orthogonal polynomial basis is used as active function.The network is trained by an error iterative learning algorithm.This proposed method for nonlinear time series is tested using two well known time series prediction problems:Gas furnace data time series and Mackey-Glass time series.

A Chaotic Prediction Method to Time Series Data

2010 ◽  
Vol 113-116 ◽  
pp. 1367-1370 ◽  
Author(s):  
Bin Sheng Liu ◽  
Ying Wang ◽  
Xue Ping Hu
Keyword(s):  
Neural Network ◽  
Water Quality ◽  
Time Series ◽  
Drinking Water ◽  
Time Series Data ◽  
Prediction Method ◽  
Drinking Water Quality ◽  
Series Data ◽  
Gray Model ◽  
Forecast Method

There are many ways to predict drinking water quality such as neural network, gray model, ARIMA. But the prediction precise is need to improve. This paper proposes a new forecast method according the characteristic of drinking water quality and the evidence showed that the prediction is effectively. So it is able to being used in actual prediction.

A Study of On-Line and Off-Line Turbine Washing to Optimize the Operation of a Gas Turbine

2005 ◽  
Author(s):  
Meherwan P. Boyce ◽  
Francisco Gonzalez
Keyword(s):  
Gas Turbine ◽  
Condition Monitoring ◽  
Thermal Efficiency ◽  
Heat Rate ◽  
Time Period ◽  
On Line ◽  
One Year ◽  
Gas Turbine Compressor ◽  
Isentropic Efficiency ◽  
Proper Condition

This paper highlights the procedure followed in order to establish an effective on-line and off line water wash program on a fleet of 36 small industrial turbines. To determine the efficacy of water washing a program of tests under controlled conditions was organized. With proper condition monitoring techniques, a set of tests were developed in order to identify the proper water wash frequency and the dissolving agent used to water wash. The goal of the water wash program is to maximize turbine power, and efficiency; while minimizing maintenance labor, and material. The Gas Turbine Compressor Isentropic Efficiency, the overall heat rate, and the overall thermal efficiency were used to compare the tests and evaluate the performance of different water wash frequencies and solvents. 8760 points defined each test as the data was taken over a one year time period, at a one hour interval.

Sign in / Sign up

Export Citation Format

Share Document