摘要
根据球磨机制粉过程的特点及相应的动态数学模型,证明了系统的可逆性。进一步利用支持向量机(SVM)对非线性系统具有良好逼近能力的特性,通过其来辨识球磨机制粉过程的逆系统,可以很好解决球磨机制粉系统逆系统建模难的问题,将该逆模型与原系统串联可构成解耦后的伪线性复合系统。同时为了克服逆系统的建模误差,通过设计预测控制器对该复合系统进行闭环优化控制。仿真结果表明,提出的方法不依赖于球磨机制粉系统的精确数学模型能够适应系统模型的不确定性,可在大范围内克服系统非线性强耦合问题,实现了球磨机制粉系统的有效控制。
Based on the characteristics and the dynamic mathematical model of ball mill coal pulverizing system, the reversibility of the system is testified. Support vector machines (SVM) is applied to obtain the inverse system of ball mill coal pulverizing process which is combined with the original system. To overcome the modelling errors of SVM inverse system method, a predictive controller is de- signed to obtain the closed optimized control of the compound system. Simulation results show that the presented control approach is not depen dent on the exact process model and parameters, the good control performance of the ball mill coal pulverizing process and is obtained.
出处
《控制工程》
CSCD
北大核心
2011年第2期294-298,共5页
Control Engineering of China
基金
国家高技术研究发展计划基金资助项目(2007AA04Z195)
国家水体污染控制与治理科技重大专项课题基金资助项目(2008ZX07010-003)
关键词
球磨机制粉系统
逆系统
支持向量机
预测控制
ball mill coal pulverizing system
inverse system
SVM
predictive control