A Hierarchical Decision Fusion Diagnosis Method for Rolling Bearings

In order to achieve accurate fault diagnosis of rolling bearings, a hierarchical decision fusion method for bearings is proposed. The back propagation neural networks (BPNNs) architecture includes detection layer, isolation layer and degree identification which reduce the calculation cost enhance maintainability algorithm. By wavelet packet decomposition signal reconstruction raw vibration bearing, time-domain features reconstructed signals are extracted as input each BPNN accuracy detection, estimation improved. using majority voting method, results multiple BPNNs fused, avoids missed misdiagnosis caused by insensitivity characteristic specific fault. Finally, proposed verified experimentally. show that can accurately detect recognize location estimate severity under different operating conditions.