AUTHOR=Lee Jangwon , Kumar Ankur , Flores-Cerrillo Jesus , Wang Jin , He Q. Peter TITLE=Feature-based statistical process monitoring for pressure swing adsorption processes JOURNAL=Frontiers in Chemical Engineering VOLUME=Volume 4 - 2022 YEAR=2022 URL=https://www.frontiersin.org/journals/chemical-engineering/articles/10.3389/fceng.2022.1064221 DOI=10.3389/fceng.2022.1064221 ISSN=2673-2718 ABSTRACT=Pressure swing adsorption (PSA) is a widely used technology to separate a gas product from impurities in a variety of fields. Due to the complexity of PSA operations, process and instrument faults can occur at different parts and/or steps of the process. Thus, effective process monitoring is critical for ensuring the efficient and safe operation of the PSA systems. One of the key characteristics of the PSA process is that it is operated in a periodic or cyclical fashion, making the monitoring of such a process significantly more challenging than that of a process operated at a steady state. In this work, we propose a feature-based statistical process monitoring (SPM) framework for PSA processes, namely feature space monitoring (FSM). We show that FSM can naturally handle some of the challenges in monitoring PSA processes, such as unequal step and cycle durations that otherwise require trajectory alignment or synchronization for the traditional SPM methods. The performance of FSM is compared to the conventional SPM methods using both simulated and real faults from an industrial PSA process. The results demonstrate FSM's superior performance in fault detection and fault diagnosis compared to the traditional SPM methods.