Review and Perspectives of Data-Driven Distributed Monitoring for Industrial Plant-Wide Processes

• DOI: 10.1021/acs.iecr.9b02391
• Publication Date: 2019-07-09T02:46:16Z
• Authors: Qingchao Jiang; Xuefeng Yan; Biao Huang
• Keywords: Statistical Process Control; Process state

Process monitoring is crucial for maintaining favorable operating conditions and has received considerable attention in previous decades. Currently, a plant-wide process generally consists of multiple operational units large number measured variables. The correlation among the variables complex results imperative but challenging such processes. With rapid advancement industrial sensing techniques, data with meaningful information are collected. Data-driven multivariate statistical (DMSPPM) become popular. key idea DMSPPM first decomposing into subprocesses then establishing data-driven model process, which variable decomposition important guaranteeing performance. In current review, we introduce basics highlight necessity designing distributed scheme. Then state-of-the-art methods revisited. Finally, opportunities challenges to discussed.