Bearing Fault Diagnosis Based on RF-PCA-LSTM Model

To realize accurate fault diagnosis of rolling bearing under random noise, a novel fault diagnosis method based on random forest (RF) - principal component analysis (PCA) and long short-term memory (LSTM) neural network is proposed in this paper. The vibration signal is decomposed into several intrinsic mode functions (IMFs) with ensemble empirical mode decomposition (EEMD) to eliminate the random noise interference from the original vibration signal. It is vital to choose sensitive features from both the time and frequency domain of IMF components with importance rank by using RF. Then PCA is conducted to eliminate the correlation among sensitive features. On this basis, this paper utilizes LSTM neural network to get better diagnosis performance in complicated working conditions and hybrid faults. Comparing with the traditional feature extraction method, RF-PCA can get fewer but more representative characteristics. At the same time, the introduction of the LSTM neural network can provide a simple and practical resolution for rolling bearing fault diagnosis.