針對交流電弧爐電極控制系統具有非線性時變、多變量、強耦合及存在隨機干擾的特點，采用基于最近鄰聚類方法的徑向基函數(RBF)神經網絡快速學習算法，通過實時在線辨識，建立電弧爐電極系統的精確逆模型并用于控制，實現了將具有強耦合特性的多變量輸入/輸出(MIMO)系統解耦成單個獨立的偽線性對象，并提出一種基于RBF神經網絡逆控制與比例微分(P/D)控制相結合的雙模控制策略。應用結果證實了該控制策略具有快速適應對象和過程變化的能力及較強的魯棒性。
關 鍵 詞 電弧爐; 解耦; 雙模控制; 電極系統; 逆控制; 神經網絡

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