Deep Learning-Based Feature Representation and Its Application for Soft Sensor Modeling With Variable-Wise Weighted SAE

TLDR

Soft sensors are essential for process control, and recent deep‑learning approaches have shown promise for extracting high‑level feature representations. This work proposes a variable‑wise weighted stacked autoencoder (VW‑SAE) to build hierarchical output‑related feature representations for soft sensor modeling. The method assigns weights to input variables based on their correlation with the output and stacks weighted autoencoders to form a deep network. In an industrial case study, VW‑SAE outperformed conventional multilayer neural networks and standard SAE in prediction accuracy.

Abstract

In modern industrial processes, soft sensors have played an important role for effective process control, optimization, and monitoring. Feature representation is one of the core factors to construct accurate soft sensors. Recently, deep learning techniques have been developed for high-level abstract feature extraction in pattern recognition areas, which also have great potential for soft sensing applications. Hence, deep stacked autoencoder (SAE) is introduced for soft sensor in this paper. As for output prediction purpose, traditional deep learning algorithms cannot extract high-level output-related features. Thus, a novel variable-wise weighted stacked autoencoder (VW-SAE) is proposed for hierarchical output-related feature representation layer by layer. By correlation analysis with the output variable, important variables are identified from other ones in the input layer of each autoencoder. The variables are assigned with different weights accordingly. Then, variable-wise weighted autoencoders are designed and stacked to form deep networks. An industrial application shows that the proposed VW-SAE can give better prediction performance than the traditional multilayer neural networks and SAE.