INTEGRATED DATA-DRIVEN PROCESS MONITORING AND EXPLICIT FAULT-TOLERANT MULTIPARAMETRIC CONTROL

We propose a novel active fault-tolerant control strategy that combines machine learning based process monitoring and explicit/multiparametric model predictive control (mp-MPC). The strategy features (i) data-driven fault detection and diagnosis models by using Support Vector Machine (SVM) algorithm, (ii) feature ranking via nonlinear, Kernel-dependent, SVM-based feature selection algorithm, (iii) data-driven regression models for fault magnitude estimation via Random Forest algorithm, and (iv) Parametric Optimization and Control (PAROC) framework for the design of the explicit/multiparametric model predictive controller. The resulting explicit control strategies correspond to affine functions of the system states and the magnitude of the detected fault. A semi-batch process, example for penicillin production, is presented to demonstrate how the proposed framework ensures smart operation where rapid switches between a priori computed explicit control action strategies are enabled by continuous process mon...