Journal of Computer Applications ›› 2017, Vol. 37 ›› Issue (3): 668-672.DOI: 10.11772/j.issn.1001-9081.2017.03.668

Previous Articles     Next Articles

Soft-sensing modeling based on improved extreme learning machine

ZHOU Xin, WANG Guoyin, YU Hong   

  1. Chongqing Key Laboratory of Computational Intelligence, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
  • Received:2016-09-23 Revised:2016-10-10 Online:2017-03-10 Published:2017-03-22
  • Supported by:
    This work is supported by the National Natural Science Foundation of China (61533020).

基于改进极限学习机的软测量建模

周馨, 王国胤, 于洪   

  1. 重庆邮电大学 计算智能重庆市重点实验室, 重庆 400065
  • 通讯作者: 周馨
  • 作者简介:周馨(1990-),女,四川武胜人,硕士研究生,CCF会员,主要研究方向:智能信息处理、数据挖掘;王国胤(1970-),男,重庆人,教授,博士,CCF会员,主要研究方向:粗糙集、粒计算、神经网络、机器学习、数据挖掘、人工智能不确定性;于洪(1972-),女,重庆人,教授,博士,CCF会员,主要研究方向:粗糙集、三支决策、智能信息处理。
  • 基金资助:
    国家自然科学基金资助项目(61533020)。

Abstract: Extreme Learning Machine (ELM) has become a new method in soft-sensing due to its good generalization and fast training speed. However, ELM often needs more hidden layer nodes and its generalization is reduced in the parameter modeling for aluminum electrolysis production process. To solve the problem, a soft-sensing model based on Improved Extreme Learning Machine (IELM) was proposed. Firstly, rough set theory was applied to reduce the unnecessary, unrelated or reductant input variables, reducing the complexity of ELM input. After analyzing the relationship between the input variables and output variables by partial correlation coefficient, the input data was divided into two parts, namely the positive part and the negative part. Then, the corresponding ELM model was built according to the two parts. Finally, the soft-sensing model of molecular ratio based on the improved ELM was built. The simulation experimental results show that the soft-sensing model based on the IELM has better generalization and stability.

Key words: Extreme Learning Machine (ELM), soft-sensing, rough set, partial correlation coefficient

摘要: 极限学习机(ELM)因其泛化能力好和学习速度快而成为软测量的新方法,但当应用到铝电解工艺参数建模时,ELM通常需要较多隐层节点并且泛化能力较低。针对这一问题,提出一种基于改进极限学习机(IELM)的软测量模型。首先,利用粗糙集中的约简理论剔除输入变量中的冗余或不相关属性,以降低ELM的输入复杂性;然后,利用偏相关系数对输入变量和输出变量间的相关性进行分析,将输入数据分为正输入和负输入两部分,分别对这两部分建立输入单元,重新构建ELM网络;最后,建立了基于改进极限学习机的铝电解分子比软测量模型。仿真实验结果表明,基于改进极限学习机的软测量模型具有较好的泛化能力和稳定性。

关键词: 极限学习机, 软测量, 粗糙集, 偏相关系数

CLC Number: