摘要
回转干燥窑由于干燥速率难以在线测量,其干燥速率模型的建立一直是一大难题。在分析干燥速率建模的基础上,提出将最小二乘支持向量机运用到干燥速率建模,及其基于免疫-果蝇优化算法的最小二乘支持向量机回归参数优化方法(IAFOALSSVR)。首先利用预处理的干燥过程数据进行模型的训练,利用免疫-果蝇算法对模型参数进行寻优,然后获得最优参数并建立最优模型,通过使用该改进方法建立干燥速率模型与其他算法优化的模型进行对比,结果表明该优化方式在干燥速率建模精度上与其它智能算法相当,在计算效率上要优于其它算法。
It is difficult to obtain the model of drying rate because the reliable online measurement for the drying rate is hardly available. Based on analysis of the drying process of rotary dryer kiln, the least squares support vector machine applied to the drying rate modeling and the least squares support vector machine regression parameters optimization based on IA-FOA（lAFOALSSVR） are presented. Pretreatment drying process data are used for training the model and IA - F0A algorithm is used to optimize the model parameters, so that the optimal parameters are obtained and the optimal model is established. The improved model is compared with other models optimized by other algorithms. Simulation results show that the accuracy is the same with other algorithms on the drying rate modeling but computational efficiency is much better than others.
出处
《控制工程》
CSCD
北大核心
2012年第4期630-633,638,共5页
Control Engineering of China
基金
国家自然科学基金资助(21106036
61074067)
湖南省教育厅优秀青年项目资助(11B038)。
