关键词: 核函数, 时间窗, 在线建模, 最小二乘支持矢量机

Abstract: Least squares support vector machines (LS-SVM) is a perfect model-learning algorithm with good accuracy and high speed. In order to solve the online multivariable-modeling problem of a Lithopone calcination process in rotary kiln, a new kind of online modeling algorithm based on time window in LS-SVM is proposed. The purpose is to show its powerful identification performances. First, the main mechanism of LS-SVM is presented, and then the optimization algorithm of the time window is discussed. The current feature of the model has strong relationship with L updated data. Karush-Kuhn- Tucker (KKT) optimization condition decides whether to do the retraining at each updating procedure and avoids unnecessary recalculations. Finally, the simulation results are presented. The good performance of this algorithm shows its broad prospect on dynamic identifications of complex nonlinear processes.

Key words: Kernels, Least squares support vector machines(LS-SVM), Online modeling, Time window