A novel key performance indicator oriented hierarchical monitoring and propagation path identification framework for complex industrial processes.

As the first protective layer for modern complex industrial processes, process monitoring and fault diagnosis (PM-FD) systems play a vital role in ensuring product quality, overall equipment effectiveness and process safety, which have recently become one of the hotspots both in academic research and practical application domains. Different from previous frameworks, this paper dedicates on industrial practices and theoretical methods for hierarchical monitoring and propagation path identification of key performance indicator (KPI) oriented faults in complex industrial processes, which can not only help field engineers to timely and purposefully keep track of the state of the process, but also help them to take appropriate remedial actions to remove the abnormal behaviors from the process. For these purposes, firstly, a new data-driven gap metric approach is proposed for monitoring KPI oriented faults in the block level. Then, Bayesian fusion is implemented to form monitoring decisions from the plant-wide level. After that, a neural network architecture-based Granger causality analysis method is developed for propagation path identification of KPI oriented faults. Finally, the proposed methods are validated in Tennessee Eastman process, where detailed simulation processes are presented and better performance is shown compared with the existing approaches.