Fuzzy Neural Network Based on Improved T-S Model and Its Application
Traditional fuzzy neural networks have many problems like long duration of training learning algorithm, slow convergence and possibility of getting into local dinky value in the network. In view of all these above, this paper proposes an improved training algorithm in fuzzy neural network which takes vantage of the excellent learning and expression ability of fuzzy neural networks based on T-S (Takagi-Sugeno) model. Improved T-S model introduces adaptive learning rate η and momentum factor γ into the learning algorithm which helps stabilize the network and makes acceleration weights of three adjusting parameters, including network membership function’s central value C ij and width σ ij and connection weight of output layer y kj , decrease along the reductive direction. Results of a simulation test with a two-dimensional nonlinear function show that improved network has high convergence rate and good generalization capability. Finally, T-S fuzzy model of hydro-turbine governing system based on the fuzzy neural network is presented, of which the results has indicated that the model has/its higher precision and good generalization ability.
KeywordsFuzzy neural network T-S model Adaptive learning rate Momentum factor Function approximation System identification
Unable to display preview. Download preview PDF.
- 3.Zhang, X.H., Xu, M.X., Zhang, S.Y.: The Response Control of Wind-excited Tall Building by T_S Fuzzy Controlier. Journal of System Simulation 15, 587–589 (2003)Google Scholar
- 4.Sun, Z.Q., Xu, H.B.: A Fuzzy Neural Network and its Application to Controls. Journal of Tsinghua University (Natural Sciences Edition) 37, 76–80 (1997)Google Scholar
- 5.Chen, B.G., Zhu, Y., Zhang, H.: An Enforced Fuzzy Neural Network. Journal of Harbin Institute of Techenology 33, 89–92 (2001)Google Scholar
- 6.Gan, S.Q., Liu, H.P., Shen, Z.J.: An Improved T-S Fuzzy Neural Network. Control Engineering of China 12, 442–445 (2005)Google Scholar
- 7.Zhang, D.Y., Zhong, H.B., Yang, Y.H.: Substation Alarm Message Dealing System Based on ANN and ES. Automatic of Electric Power Systems 25, 45–47 (2001)Google Scholar
- 8.Sun, Z.Q.: Intellignet Control Theory and Technology. Tsinghua University Press, Beijing (1997)Google Scholar
- 9.Li, N., Yue, J.P., Duan, P.: Improved Fuzzy Neural Network Model and its Application to Dam Monitoring. Hydropower Automation and Dam Monitoring 31, 74–76 (2007)Google Scholar
- 10.Yang, H.F., Wei, Y.: Research on Water Quality Assessment Model Based on Fuzzy Neural Network. Journal of Yunnan Nationalities University (Natural Sciences Edition) 16, 255–258 (2007)Google Scholar