Fault prediction of fan bearing using time series d ata mining
Xingjie Chen, Wenfa Zhu · 2014
The fault symptoms are regarded as a sort of tempor al patterns hidden in a time series. A novel method based on time series data mining is proposed for the predict ion of fan bearing fault. The time series, which is formed by large numbers of fan bearing vibration data, is embedded into a reconstructed phase space with time-delay. Iphase space, Genetic Algorithms are used to search for th e optimal temporal pattern clusters which are the cto identify temporal patterns. The optimal collection of temporal pattern clusters is then used to test tbearing vibration data of fan. Once the symptoms are detect ed, the fault is forecasted. The simulation results show the method is efficient.