基于LS-SVM的陶瓷窑炉温度预测控制

摘要

In accordance with the technical features of large capacity, non - linear and dead time temperature resistance ceramics kiln system , a method of dynamic matrix control based on least squares support vector machine is proposed. The model of the controlled plant is built by least squares support vector machine based on Attractive and Repulsive Particle Swarm Optimizer algorithm. In the process of system operation, the dynamic matrix control algorithm is employed to implement the predictive control of the controlled plant. Compared with the Smith predictor and internal model control for ceramics kiln temperature, the simulation results show the dynamic and static performances of the system are excellent, It is also shown that the system has strong robustness.%针对陶瓷窑炉大热容量、大滞后、非线性等特点,提出了一种基于最小二乘支持向量机动态矩阵控制方法;首先,采用保证种群多样性微粒群算法优化的最小二乘支持向量机离线建立被控对象模型;然后在系统运行过程中,用动态矩阵预测算法实现对被控系统的预测控制;并以陶瓷窑炉温度为控制对象,与Smith预估控制以及内模控制算法进行了比较;仿真结果证明了所提控制方法具有很好的动、静态性能和强鲁棒性.