Machine learning for industrial sensing and control: A survey and practical perspective

TL;DR

This paper addresses how machine learning can enhance sensing and control in process industries by organizing methods into knowledge-driven, data-driven, and hybrid categories and by detailing traditional serial/parallel hybrid structures alongside emerging trends. It highlights soft sensing as the most mature industrial application, driven by data-driven approaches, while control-oriented ML (including deep RL) shows promise but faces data efficiency and validation hurdles. The work emphasizes hybrid modeling, physics-informed strategies, multi-fidelity approaches, and surrogate-based optimization as practical pathways for industry adoption, and discusses challenges in interpretability, data availability, and online maintenance. Overall, it argues for a unified framework that tightly integrates modeling, sensing, and control to realize robust, scalable, and transparent data-driven automation in the process industries.

Abstract

With the rise of deep learning, there has been renewed interest within the process industries to utilize data on large-scale nonlinear sensing and control problems. We identify key statistical and machine learning techniques that have seen practical success in the process industries. To do so, we start with hybrid modeling to provide a methodological framework underlying core application areas: soft sensing, process optimization, and control. Soft sensing contains a wealth of industrial applications of statistical and machine learning methods. We quantitatively identify research trends, allowing insight into the most successful techniques in practice. We consider two distinct flavors for data-driven optimization and control: hybrid modeling in conjunction with mathematical programming techniques and reinforcement learning. Throughout these application areas, we discuss their respective industrial requirements and challenges. A common challenge is the interpretability and efficiency of purely data-driven methods. This suggests a need to carefully balance deep learning techniques with domain knowledge. As a result, we highlight ways prior knowledge may be integrated into industrial machine learning applications. The treatment of methods, problems, and applications presented here is poised to inform and inspire practitioners and researchers to develop impactful data-driven sensing, optimization, and control solutions in the process industries.

Figures (5)

• Figure 1: Typology of hybrid models (see VonStosch2014). A and C represent serial structures: under A, a data-driven model is used as input to a knowledge-driven model; C is the reverse. B represents a parallel structure in which knowledge-driven predictions are corrected by data-driven predictions.
• Figure 2: Distribution of soft sensor applications.
• Figure 3: Research publication in soft sensors from $2015$ to $2023$.
• Figure 4: Distribution of global and adaptive soft sensors.
• Figure 5: Application of RL for tuning PI controllers in a lab setting. The policy plays the role of PI controller and receives updates towards improved performance. $J$ is a general long-term cost function and $k_p, k_i$ are controller gains. Adapted from lawrence2022deep.