Integrated Online Monitoring and Adaption of Process Model Predictive Controllers
This addresses the need for robust and efficient online adaption in process control systems, though it appears incremental by building on existing monitoring and learning techniques.
The paper tackles the problem of performance degradation in model predictive control under changing conditions by proposing an event-triggered adaption method based on statistical monitoring of performance indicators, validated on a district heating system simulation.
This paper addresses the design of an event-triggered, data-based, and performance-oriented adaption method for model predictive control (MPC). The performance of such a strategy strongly depends on the accuracy of the prediction model, which may require online adaption to prevent performance degradation under changing operating conditions. Unlike existing methods that continuously update model and control parameters from data, potentially leading to catastrophic forgetting and unnecessary control modifications, we propose a novel approach based on statistical monitoring of closed-loop performance indicators. This framework enables the detection of performance degradation, and, when required, controller adaption is performed via reinforcement learning and identification techniques. The proposed strategy is validated on a high-fidelity simulation of a district heating system benchmark.