Data-driven prescriptive maintenance toward fault-tolerant multiparametric control

Prescriptive maintenance can improve system effectiveness and system safety via integrated production and maintenance optimization. However due to system disruptions there is potential for abnormal operations and an undesirable increased occurrence of process safety incidents. This research provides a multiparametric-based framework for safety-aware, maintenance-aware, and disruption-aware process control. It leverages ensemble classification via machine learning classifiers for fault detection, mixed-integer nonlinear programming for integrated safety-aware production and maintenance scheduling, as well as hybrid multiparametric model predictive control for fault-tolerant setpoint tracking. The results show that the ensemble classifier outperforms the individual classifiers in terms of fault detection accuracy, sensitivity, and specificity. Furthermore, it is seen that the developed controllers are able to reconfigure the control actions based on process disruption information. The framework is illustrated with a chemical complex system, and a cooling water system. The approach can be used to help improve the safety and productivity of industrial processes.

Automated summary

Prescriptive maintenance improves system effectiveness and safety, but system disruptions may lead to abnormal operations and safety incidents. This research proposes a multiparametric framework for safety-aware process control, utilizing ensemble classifiers for fault detection, mixed-integer nonlinear programming for scheduling, and multiparametric model predictive control for fault-tolerant tracking. Results show superior performance in fault detection and ability to reconfigure control actions based on disruptions. The approach has been demonstrated on chemical and cooling water systems to enhance industrial process safety and productivity.