Deep Nonlinear Dynamic Feature Extraction for Quality Prediction Based on Spatiotemporal Neighborhood Preserving SAE
Chenliang Liu, Kai Wang, Yalin Wang, Shengli Xie, Chunhua Yang
Abstract
Complex industrial process data often exhibit nonlinear static and dynamic characteristics. Traditional deep learning methods like stacked autoencoder (SAE) have excellent nonlinear static feature learning capabilities, but they ignore the dynamic correlation existing in process data. Feature learning based on manifold learning using neighborhood structure preserving has been widely used in industrial dynamic process monitoring. However, most of manifold learning methods extract linear features and the complex nonlinearities in process data are ignored. Therefore, a novel spatiotemporal neighborhood preserving stack autoencoder (STNP-SAE) is proposed to simultaneously learn deep nonlinear static and dynamic features of process data in this paper. By constructing the spatial and temporal adjacent graphs, STNP-SAE can capture the spatiotemporal neighborhood structure information of process data during the feature learning process. Then, STNP-SAE is utilized to construct a soft sensor framework for quality prediction. The prediction performance of the proposed method is validated on a practical industrial process.