Rolling Element Bearing Fault Diagnosis for Complex Equipment Based on FIFD and PNN

Abstract

The bearing fault feature for complex equipment in early failure period is so weak and susceptible to complicated transmission path and random noise that it’s very difficult to be extracted, so Fast Iterative Filtering Decomposition (FIFD) with Probabilistic Neural Network (PNN) are combined for diagnosing the bearing fault. A bearing simulator was used to collect vibration signals of bearing under different fault locations, and then FIFD was applied to decompose them into several Intrinsic Mode Functions, where their energy entropy as an feature vector was calculated respectively. Finally PNN was used to classify different bearing faults. The bearing fault simulator shows that this method can quickly and accurately identify the different fault locations of bearings.