4.8 Article

Novel L1 Regularized Extreme Learning Machine for Soft-Sensing of an Industrial Process

期刊

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
卷 18, 期 2, 页码 1009-1017

出版社

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TII.2021.3065377

关键词

Optimization; Linear programming; Bayes methods; Extreme learning machines; Training; Neurons; Inference algorithms; Extreme learning machine (ELM); machine learning; soft sensing; variational Bayesian (VB) inference

资金

  1. National Natural Science Foundation of China [51775385, 61703279, 71371142]
  2. Strategy Research Project of Artificial Intelligence Algorithms of Ministry of Education of China

向作者/读者索取更多资源

This article proposes a novel L1 norm-based extreme learning machine (ELM) by integrating bound optimization theory with variational Bayesian inference. The proposed method efficiently solves the overfitting problem and demonstrates competitive performance in an industrial case study.
Extreme learning machine (ELM) is suitable for nonlinear soft sensor development. Yet it faces an overfitting problem. To overcome it, this work integrates bound optimization theory with variational Bayesian (VB) inference to derive novel L1 norm-based ELMs. An L1 term is attached to the squared sum cost of prediction errors to formulate an objective function. Considering the nonconvexity and nonsmoothness of the objective function, this article uses bound optimization theory, and constructs a proper surrogate function to equivalently convert a challenging L1 norm-based optimization problem into easy one. Then, VB inference is adopted for optimizing the converted problem. Thus, an L1 norm-based ELM can be efficiently optimized by an alternating optimization algorithm with a proved convergence. Finally, a soft sensor is developed based on the proposed algorithm. An industrial case study is carried out to demonstrate that the proposed soft sensor is competitive against recent ones.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.8
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据