Gaussian mixture deep dynamic latent variable model with application to soft sensing for multimode industrial processes

Abstract

The data-driven deep probabilistic latent variable model (DPLVM) has attracted much attention for industrial process soft sensing in recent years. The DPLVM has well handled the nonlinear characteristics of the processes with powerful feature extracting capability. However, the multimode process property and the dynamic data features seldom be considered in those applications. To tackle the two issues, the article starts from the basic DPLVM, i.e., the Variational Autoencoder (VAE), to build a deep dynamic latent variable regression model (i.e., the Gated Recurrent Unit-based VAE regression, GVAER), where GRU cells are utilized to capture dynamic features from the process time sequence data. With the GVAER, a Gaussian Mixture GVAER (GM-GVAER) model is proposed. The Gaussian Mixture priors are used in the latent space to characterize the multimode process data features. In particular, a semi-supervised learning scheme is also proposed for the model to deal with the unequal scale of input and output data. A numerical example and a real chemical process case are provided to verify the feasibility and effectiveness of the proposed soft sensor model.