Application of Machine Learning in Industrial Boilers: Fault Detection, Diagnosis, and Prognosis. Issue 5 (14th August 2021)

• Record Type: Journal Article
• Authors: Meng, Yang; Wu, Xinyun; Oladejo, Jumoke; Dong, Xinyue; Zhang, Zhiqian; Deng, Jie; Yan, Yuxin; Zhao, Haitao; Lester, Edward; Wu, Tao; Pang, Cheng Heng
• Is Part Of: ChemBioEng reviews. Volume 8:Issue 5(2021)
• Page Start: 535
• Page End: 544
• Publication Date: 2021-08-14
• Subjects: Diagnosis system -- Fault detection -- Industrial boiler -- Machine learning -- Prognostics; Chemical engineering -- Periodicals; Biochemical engineering -- Periodicals; Biotechnology -- Periodicals; 660.05
• DOI: 10.1002/cben.202100008
• Languages: English
• ISSNs: 2196-9744

Abstract

Abstract: Enhancement in boiler efficiency via controlled operation could lead to energy savings and reduction in pollutant emission. Activities such as scheduled maintenance could be improved by increasing boiler availability and reducing running costs. However, the time interval between recommended maintenance is varied depending on boilers. The application of fault detection, diagnosis and prognosis (FDDP) in industrial boilers plays an important role in optimizing operation, early‐warning of faults, and identification of root causes. This review discusses the application of machine learning (ML)‐based algorithms (knowledge‐driven and data‐driven) for FDDP, thus allowing the identification of fit‐for‐purpose techniques for specific applications leading to improved efficiency, operability, and safety. Abstract : This study presents an introduction to fault detection, diagnosis and prognosis (FDDP) technique and its significance in industrial boilers. Then, the challenges associated with FDDP system are emphasized. Thirdly, the applications of machine learning‐based FDDP are reviewed, namely knowledge‐driven and data‐driven approaches. Finally, main findings and perspectives are summarized.