Title :
Identification for hydraulic AGC system of strip mill based on neural networks
Author :
Wang, Haifang ; Rong, Yu ; Liu, Shengtao ; Cui, Jinhua
Author_Institution :
Coll. of Mech. & Electron. Eng., Hebei Normal Univ. Sci. & Technol., Qinhuangdao, China
Abstract :
A new adaptive identification method is presented based on analyzing the dynamic peculiarities of the components in the nonlinear hydraulic automatic gauge control press system of strip mill. A feed-forward and dynamic neural network structure is built based on the time series using enlarged back-propagation algorithm, and the nonlinear performance of press control system of the hydraulic automatic gauge control system can be forecasted. Based on the forecasted results, the characteristic parameters of linear system are identified by least square method. Finally, the applicability of the adaptive identification method is illustrated and verified by simulation results.
Keywords :
backpropagation; feedforward neural nets; gauges; hydraulic actuators; identification technology; least squares approximations; rolling mills; adaptive identification method; backpropagation algorithm; dynamic neural network structure; feedforward neural network structure; hydraulic AGC system identification; least square method; linear system; nonlinear hydraulic automatic gauge control press system; press control system; strip mill; time series; Adaptive control; Adaptive systems; Automatic control; Control systems; Milling machines; Neural networks; Nonlinear control systems; Nonlinear dynamical systems; Programmable control; Strips; AGC; BP algorithm; identification; least square; neural networks;
Conference_Titel :
Computer Design and Applications (ICCDA), 2010 International Conference on
Conference_Location :
Qinhuangdao
Print_ISBN :
978-1-4244-7164-5
Electronic_ISBN :
978-1-4244-7164-5
DOI :
10.1109/ICCDA.2010.5541406
