An Ensemble Prognostic Method of Francis Turbine Units Using Low-Quality Data under Variable Operating Conditions

• Published in: Sensors (Basel, Switzerland) Vol. 22; no. 2; p. 525
• Main Authors: Duan, Ran, Liu, Jie, Zhou, Jianzhong, Wang, Pei, Liu, Wei
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 01.01.2022; MDPI
• Subjects: Accuracy; Algorithms; Analysis; Confidence intervals; Data Accuracy; Data integrity; Datasets; DBSCAN; degradation trend prediction; Environmental engineering; Fault diagnosis; Francis turbine unit; Gaussian mixture model; Genetic algorithms; Hydroelectric power; Information management; Methods; Normal Distribution; Optimization algorithms; Performance evaluation; performance state evaluation; Prognosis; prognostic; Reproducibility of Results; Turbines; prognostic; NSGA-II; performance state evaluation; Francis turbine unit; Gaussian process regression; DBSCAN; degradation trend prediction; Gaussian mixture model
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s22020525

The prognostic is the key to the state-based maintenance of Francis turbine units (FTUs), which consists of performance state evaluation and degradation trend prediction. In practical engineering environments, there are three significant difficulties: low data quality, complex variable operation con...