OASIS-P: Operable Adaptive Sparse Identification of Systems for fault Prognosis of chemical processes

With the increasing process complexities, data-driven fault prognosis has emerged as a promising fault management tool that predicts and manages abnormal events well in advance. In this paper, we develop a fault prognosis framework named 'OASIS-P' by integrating operable adaptive sparse identification of systems (OASIS), which is a data-driven adaptive modeling technique, with a risk based process monitoring approach and contribution plots. Firstly, OASIS is employed with the risk assessment procedure for the prediction of impending faults. As the OASIS model is adaptive, it copes with the initial fault symptoms and forecasts the future behavior of the process under faulty conditions reasonably well, thereby providing an early fault prediction. Next, the fault isolation step is immediately initiated using contribution plots to identify the faulty variables. Unlike in fault diagnosis, the problem of ambiguity in interpreting contribution results due to fault propagation is not an issue in fault prognosis, if the fault isolation step is implemented at an early stage of the fault before it affects the other variables. Hence, the contribution plots together with OASIS can proactively monitor the process in real-time. As a case study, we demonstrate OASIS-P for fault prognosis of a reactor-separator system. (C) 2021 Elsevier Ltd. All rights reserved.

Automated summary

With the integration of OASIS, risk assessment, and contribution plots, the 'OASIS-P' framework can provide early fault prediction by adapting to initial fault symptoms and isolating faulty variables using contribution plots. This proactive monitoring approach is demonstrated in a case study of a reactor-separator system for fault prognosis.