Fault Detection and Identification Using a Novel Process Decomposition Algorithm for Distributed Process Monitoring
This work addresses fault monitoring for control engineers in industrial processes, offering a straightforward implementation based on process flowsheets, but it is incremental as it builds on existing PCA and decomposition techniques.
The paper tackles fault detection and identification in distributed process monitoring by introducing a novel process decomposition algorithm that groups interacting measurements into blocks and applies PCA at the block level, along with a contributions map for visualizing faults, achieving fault detection rates comparable to sophisticated methods on the Tennessee Eastman Plant benchmark.
Recent progress in fault detection and identification increasingly relies on sophisticated techniques for fault detection, applied through either centralized or distributed approaches. Instead of increasing the sophistication of the fault detection method, this work introduces a novel algorithm for determining process blocks of interacting measurements and applies principal component analysis (PCA) at the block level to identify fault occurrences. Additionally, we define a novel contributions map that scales the magnitudes of disparate faults to facilitate the visual identification of abnormal values of measured variables and analysis of fault propagation. Bayesian aggregate fault index and block fault indices vs. time pinpoint origins of the fault. The proposed method yields fault detection rates on par with most sophisticated centralized or distributed methods on the Tennessee Eastman Plant benchmark. Since the decomposition algorithm relies on the process flowsheet and control loop structures, practicing control engineers can implement the proposed method in a straightforward manner.