Gated Stacked Target-Related Autoencoder: A Novel Deep Feature Extraction and Layerwise Ensemble Method for Industrial Soft Sensor Application

These days, data-driven soft sensors have been widely applied to estimate the difficult-to-measure quality variables in the industrial process. How to extract effective feature representations from complex process data is still the difficult and hot spot in the soft sensing application field. Deep learning (DL), which has made great progresses in many fields recently, has been used for process monitoring and quality prediction purposes for its outstanding nonlinear modeling and feature extraction abilities. In this work, deep stacked autoencoder (SAE) is introduced to construct a soft sensor model. Nevertheless, conventional SAE-based methods do not take information related to target values in the pretraining stage and just use the feature representations in the last hidden layer for final prediction. To this end, a novel gated stacked target-related autoencoder (GSTAE) is proposed for improving modeling performance in view of the above two issues. By adding prediction errors of target values into the loss function when executing a layerwise pretraining procedure, the target-related information is used to guide the feature learning process. Besides, gated neurons are utilized to control the information flow from different layers to the final output neuron that take full advantage of different levels of abstraction representations and quantify their contributions. Finally, the effectiveness and feasibility of the proposed approach are verified in two real industrial cases.

I. Introduction

In modern industrial processes, it is of great importance to monitor the quality of products and other key variables, in order to keep the process in a safe state and provide an effective control and optimization style [1], [2]. However, due to poor measuring environments and expensive analytic costs, it is hard to measure those important variables in time for process control. Therefore, soft sensing technology emerges as the times require which selects a set of measurable variables (auxiliary variables) related to those to be estimated variables (dominant variables), and then constructs a mathematical model with auxiliary variables as input and dominant variables as output to estimate those variables that cannot be measured directly [3], [4].