PROJECT TITLE :

Weighted Data-Driven Fault Detection and Isolation: A Subspace-Based Approach and Algorithms

ABSTRACT:

Well-established theory of subspace system identification and model-primarily based fault detection and isolation (FDI) enable the birth of subspace-primarily based knowledge-driven FDI approach. During this paper, we have a tendency to develop subspace-based mostly FDI approach with a scheme of weighted historical and operating knowledge. We propose 2 sorts of weighted knowledge-driven fault detection algorithms and present fault isolation algorithm and its changed version incorporated with forgetting factors. Analysis of sensitivity and precision shows the weighted algorithms can get additional correct results without loss of sensitivity. Effectiveness and enhancements of the proposed algorithms are validated on the widely used benchmark platform of Tennessee-Eastman method (TEP).