FeO Content Prediction for an Industrial Sintering Process based on Supervised Deep Belief Network
Xiaofeng Yuan, Yongjie Gu, Yalin Wang, Zhiwen Chen, Bei Sun, Chunhua Yang
Abstract
In industrial sintering processes, it is very important to monitor and control key quality indicators, which are often difficult to measure online. Soft sensor technology is a good solution for online prediction of quality indicators. Nowadays, deep learning is widely used in soft sensors due to its powerful ability in processing nonlinear data. In this paper, a supervised deep belief network (SDBN) is proposed by introducing quality variable into the input variables at each restricted Boltzmann machine to extract quality-related features for soft sensor. With case study on an actual industrial sintering process, SDBN shows much better prediction performance than the original deep belief network and stacked autoencoder.