Defect diagnostics of rolling element bearing using fuzzy dichotomy technique

The monitoring and diagnostics of the bearing have been received considerab le attention for many years because the majority of problems in rotating ma chines are caused by faulty bearings. The malfunction of rotating machinery in plants due to some defects may cause shutdown of the plants, resulting in high maintenance cost. Overly generalized predictions are problematic du e to concept classification. In particular, the boundaries among classes ar e not always clearly defined. To avoid such problems, the idea of fuzzy cla ssification was proposed. In this paper, in order to automatize the diagnos is of a rolling element bearing using the fuzzy classification along with t heir construction algorithm, the fuzzy dichotomy technique as an acquisitio n of structured knowledge from field case history data is used for validati ng the diagnosis capability.