A Survey on Deep Learning for Data-Driven Soft Sensors

TLDR

Soft sensors are essential for process monitoring and quality prediction, yet evolving industrial processes have exposed limitations of traditional modeling, motivating the adoption of data‑driven deep learning techniques. This article seeks to demonstrate the necessity and significance of deep learning for soft sensor applications by evaluating its advantages and aligning them with current industrial trends. The authors review mainstream deep‑learning architectures, training tricks, and available frameworks, and analyze existing studies to identify practical demands and challenges in deploying soft sensors. The survey concludes with outlooks and key takeaways that chart future research directions for soft sensor development.

Abstract

Soft sensors are widely constructed in process industry to realize process monitoring, quality prediction, and many other important applications. With the development of hardware and software, industrial processes have embraced new characteristics, which lead to the poor performance of traditional soft sensor modeling methods. Deep learning, as a kind of data-driven approach, shows its great potential in many fields, as well as in soft sensing scenarios. After a period of development, especially in the last five years, many new issues have emerged that need to be investigated. Therefore, in this article, the necessity and significance of deep learning for soft sensor applications are demonstrated first by analyzing the merits of deep learning and the trends of industrial processes. Next, mainstream deep learning models, tricks, and frameworks/toolkits are summarized and discussed to help designers propel the developing progress of soft sensors. Then, existing works are reviewed and analyzed to discuss the demands and problems occurred in practical applications. Finally, outlook and conclusions are given.