針對交流電弧爐電極控制系統(tǒng)具有非線性時(shí)變、多變量、強(qiáng)耦合及存在隨機(jī)干擾的特點(diǎn)，采用基于最近鄰聚類方法的徑向基函數(shù)(RBF)神經(jīng)網(wǎng)絡(luò)快速學(xué)習(xí)算法，通過實(shí)時(shí)在線辨識，建立電弧爐電極系統(tǒng)的精確逆模型并用于控制，實(shí)現(xiàn)了將具有強(qiáng)耦合特性的多變量輸入/輸出(MIMO)系統(tǒng)解耦成單個(gè)獨(dú)立的偽線性對象，并提出一種基于RBF神經(jīng)網(wǎng)絡(luò)逆控制與比例微分(P/D)控制相結(jié)合的雙?？刂撇呗浴?yīng)用結(jié)果證實(shí)了該控制策略具有快速適應(yīng)對象和過程變化的能力及較強(qiáng)的魯棒性。
關(guān) 鍵 詞 電弧爐; 解耦; 雙模控制; 電極系統(tǒng); 逆控制; 神經(jīng)網(wǎng)絡(luò)

Abstract An exact inverse model controller is constructed, which in accordance with the characteristics of the electrode control system in arc furnace. The arc furnace model can be identified on-line. The nonlinear multiple-input-multiple-output (MIMO) plant is converted into isolated dynamic decoupling pseudo linear system based on radial basis function (RBF) neural network that applies nearest neighbor clustering algorithm. A dual-mode control strategy is presented, which is based on the proposed RBF neural network inverse controller and a proportion differential (PD) controller. Result shows that the controller has rapid compliant ability of process changing and good robust performance in practical applications.
Key words arc furnace; decoupling; dual-mode control; electrode system; inverse control; neural network