期刊
IFAC PAPERSONLINE
卷 54, 期 3, 页码 639-646出版社
ELSEVIER
DOI: 10.1016/j.ifacol.2021.08.314
关键词
Machine learning; Long short-term memory; Noisy data; Model predictive control; Nonlinear systems; Chemical processes
资金
- National Science Foundation
- Department of Energy
A co-teaching learning algorithm is proposed in this study to capture the ground truth of chemical processes using LSTM networks from noisy data. Experimental results demonstrate that the co-teaching LSTM model is more accurate in predicting process dynamics and achieves better closed-loop performance under model predictive control compared to the standard training process.
Machine learning modeling of chemical processes using noisy data is practically a challenging task due to the occurrence of overfitting during learning. In this work, we propose a co-teaching learning algorithm that develops Long short-term memory (LSTM) networks to capture the ground truth (i.e., underlying process dynamics) from noisy data. We consider an industrial chemical reactor example and use Aspen Plus Dynamics to generate process operational data that is corrupted by sensor noise generated by industrial noisy measurements. An LSTM model is developed using the co-teaching method with additional noise-free data generated from simulations of the reactor first-principles model. Through open-loop and closed-loop simulations, we demonstrate that compared to the LSTM model developed from the standard training process, the co-teaching LSTM model is more accurate in predicting process dynamics, and therefore, achieves better closed-loop performance under model predictive control. Copyright (C) 2021 The Authors.
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。
推荐
暂无数据