Advancements in Industrial Monitoring and Control

The field of industrial monitoring and control is experiencing a significant shift towards data-driven approaches, leveraging machine learning and artificial intelligence to enhance operational efficiency, resilience, and trust. Hybrid solutions that combine the transparency of rule-based logic with the analytical power of machine learning are emerging as a promising direction. Notable papers in this area include:

  • A Comparative Study of Rule-Based and Data-Driven Approaches in Industrial Monitoring, which proposes a basic framework to evaluate the key properties of these methodologies and suggests hybrid solutions as a future direction.
  • Real-Time Thermal State Estimation and Forecasting in Laser Powder Bed Fusion, which presents a real-time thermal state forecasting framework for additive manufacturing, enabling predictive thermal control and paving the way toward closed-loop control.
  • Process-Informed Forecasting of Complex Thermal Dynamics in Pharmaceutical Manufacturing, which introduces process-informed forecasting models for temperature in pharmaceutical lyophilization, outperforming data-driven counterparts in terms of accuracy, physical plausibility, and noise resilience.

Sources

A Comparative Study of Rule-Based and Data-Driven Approaches in Industrial Monitoring

Real-Time Thermal State Estimation and Forecasting in Laser Powder Bed Fusion

BULL-ODE: Bullwhip Learning with Neural ODEs and Universal Differential Equations under Stochastic Demand

Accounting for Uncertainty in Machine Learning Surrogates: A Gauss-Hermite Quadrature Approach to Reliability Analysis

Probabilistic Machine Learning for Uncertainty-Aware Diagnosis of Industrial Systems

Remaining Time Prediction in Outbound Warehouse Processes: A Case Study (Short Paper)

Process-Informed Forecasting of Complex Thermal Dynamics in Pharmaceutical Manufacturing

Built with on top of