Distributed dynamic modeling and monitoring for large-scale industrial processes under closed-loop control
This work addresses the issue of unnecessary alarms in industrial process monitoring for engineers and operators, but it is incremental as it builds on existing distributed methods by incorporating dynamic modeling.
The paper tackled the problem of distinguishing real faults from normal operating condition changes in large-scale industrial processes under closed-loop control, by proposing a distributed monitoring method that concurrently explores static and dynamic characteristics, resulting in improved fault detection as demonstrated in case studies with benchmark and real industrial data.
For large-scale industrial processes under closed-loop control, process dynamics directly resulting from control action are typical characteristics and may show different behaviors between real faults and normal changes of operating conditions. However, conventional distributed monitoring approaches do not consider the closed-loop control mechanism and only explore static characteristics, which thus are incapable of distinguishing between real process faults and nominal changes of operating conditions, leading to unnecessary alarms. In this regard, this paper proposes a distributed monitoring method for closed-loop industrial processes by concurrently exploring static and dynamic characteristics. First, the large-scale closed-loop process is decomposed into several subsystems by developing a sparse slow feature analysis (SSFA) algorithm which capture changes of both static and dynamic information. Second, distributed models are developed to separately capture static and dynamic characteristics from the local and global aspects. Based on the distributed monitoring system, a two-level monitoring strategy is proposed to check different influences on process characteristics resulting from changes of the operating conditions and control action, and thus the two changes can be well distinguished from each other. Case studies are conducted based on both benchmark data and real industrial process data to illustrate the effectiveness of the proposed method.