《计算机应用研究》|Application Research of Computers

改进粒子群优化的极限学习机软测量建模方法

Soft sensor modeling of extreme learning machine based on improved particle swarm optimization

免费全文下载 (已被下载 次)  
获取PDF全文
作者 盛晓晨,史旭东,熊伟丽
机构 江南大学 a.物联网工程学院;b.轻工过程先进控制教育部重点实验室,江苏 无锡 214122
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2020)06-016-1683-05
DOI 10.19734/j.issn.1001-3695.2018.11.0863
摘要 工业过程常含有显著的非线性、时变等复杂特性,传统的极限学习机有时无法充分利用数据信息,所建软测量模型预测性能较差。为了提高极限学习机的泛化能力和预测精度,提出一种改进粒子群优化的极限学习机软测量建模方法。首先,利用高斯函数正态分布的特点实现惯性权重的自适应更新,并线性变化学习因子以提高粒子群优化算法的收敛速度和搜索性能;然后将该算法用于优化极限学习机的惩罚系数和核宽,得到一组最优超参数;最后将该方法应用于脱丁烷塔过程软测量建模中。仿真结果表明,优化后的极限学习机模型预测精度有明显的提高,验证了所提方法不仅是可行的,而且具有良好的预测精度和泛化性能。
关键词 软测量建模; 极限学习机; 粒子群优化算法; 自适应权重
基金项目 国家自然科学基金资助项目(61773182)
江苏高校优势学科建设工程资助项目(PAPD)
本文URL http://www.arocmag.com/article/01-2020-06-016.html
英文标题 Soft sensor modeling of extreme learning machine based on improved particle swarm optimization
作者英文名 Sheng Xiaochen, Shi Xudong, Xiong Weili
机构英文名 a.School of Internet of Things Engineering,b.Key Laboratory of Advanced Process Control for Light Industry of Ministry of Education,Jiangnan University,Wuxi Jiangsu 214122,China
英文摘要 Industrial processes often contain significant strong nonlinearity and time-varying behavior. Traditional ELM based soft sensor sometimes fails to make use of data information effectively and has poor prediction performance. This paper proposed an improved particle swarm optimization algorithm, which had better convergence speed and search ability than standard PSO. This algorithm used the characteristics of Gaussian distribution to update the inertia weight adaptively and changed learning factor linearly. It optimized the penalty coefficient and kernel parameter of ELM to obtain a group of optimal parameters. This algorithm was applied to soft sensor modeling for the debutanizer column process. The simulation results verify that the proposed method has good prediction accuracy and generalization performance.
英文关键词 soft sensor modeling; extreme learning machine(ELM); particle swarm optimization(PSO); adaptive weight
参考文献 查看稿件参考文献
 
收稿日期 2018/11/7
修回日期 2019/1/2
页码 1683-1687
中图分类号 TP273.1
文献标志码 A