Supervised Deep Belief Network for Quality Prediction in Industrial Processes
Xiaofeng Yuan, Yongjie Gu, Yalin Wang
Abstract
Deep belief network (DBN) has recently been applied for soft sensor modeling with its excellent feature representation capacity. However, DBN cannot guarantee that the extracted features are quality-related and beneficial for further quality prediction. To solve this problem, a novel supervised DBN (SDBN) is proposed in this article by introducing the quality information into the training phase. SDBN consists of multiple supervised restricted Boltzmann machines (SRBMs) with a stacked structure. In each SRBM, the quality variables are added to the visible layer for network pretraining and feature learning. Thus, the pretrained weights can act as better initializations for the whole network for fine-tuning. Moreover, it can ensure that the learned features are largely quality-related for soft sensor. Finally, the SDBN-based soft sensor model is applied to two industrial plants of a debutanizer column and a hydrocracking process for quality prediction.