Abstract
To overcome the difficulty of having only part of compressor characteristic maps including on-design operating point, and accurately calculate compressor thermodynamic performance under variable working conditions, this paper proposes a novel compressor performance modelling method based on support vector machine nonlinear regression algorithm. It is compared with the other three neural network algorithms (i.e. back propagation (BP), radial basis function (RBF) and Elman neural networks) from the perspective of interpolation and extrapolation accuracy as well as calculation time, to prove the validity of the proposed method. Application analyses indicate that the proposed method has better interpolation and extrapolation performance than the other three neural networks. In terms of flow characteristic map representation, the root mean square error (RMSE) of the extrapolation performance at higher and lower speed operating area by the proposed method is 0.89% and 2.57%, respectively. And the total RMSE by the proposed method is 2.72%, which is more accurate by 47% than the Elman algorithm. For efficiency characteristic map representation, the RMSE of the extrapolation performance at higher and lower speed operating area by the proposed method is 2.85% and 1.22%, respectively. And the total RMSE by the proposed method is 1.81%, which is more accurate by 35% than the BP algorithm. Moreover, the proposed method has better real-time performance compared with the other three neural network algorithms.
Highlights
The gas turbine is an internal combustion type power machine which uses a continuously flowing gas as working medium to drive an impeller to rotate at high speed and converts thermic energy into mechanical work
In order to further improve the accuracy of the compressor performance model in a small amount of experimental data, this paper puts forward a novel method for representing the compressor characteristic maps based on support vector machine (SVM) nonlinear regression algorithm
The highlights of the paper are as follows: (a) A novel method based on support vector machine nonlinear regression algorithm is proposed for representing the characteristic maps to accurately realize the thermodynamic calculation of compressor performance under variable working conditions
Summary
The gas turbine is an internal combustion type power machine which uses a continuously flowing gas as working medium to drive an impeller to rotate at high speed and converts thermic energy into mechanical work. A lot of efficacious methods have been proposed to improve the calculation precision of the thermodynamic performance model for gas turbine engines, mainly through correcting the known component characteristic maps [12,13,14] or producing new ones [15] based on gas path measurable parameters. In order to further improve the accuracy of the compressor performance model in a small amount of experimental data, this paper puts forward a novel method for representing the compressor characteristic maps based on support vector machine (SVM) nonlinear regression algorithm. (a) A novel method based on support vector machine nonlinear regression algorithm is proposed for representing the characteristic maps to accurately realize the thermodynamic calculation of compressor performance under variable working conditions.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have