Dual-FBG bearing fault probe based on a CNN-LSTM-encoder network

Abstract

A centimeter-sized bearing fault probe based on dual-fiber Bragg grating vibration sensing is proposed. The probe can provide multi-carrier heterodyne vibration measurements based on swept source optical coherence tomography technology and the synchrosqueezed wavelet transform method to obtain a wider vibration frequency response range and collect more accurate vibration data. For the sequential characteristics of bearing vibration signals, we propose a convolutional neural network with long short-term memory and transformer encoder. This method is proven in bearing fault classification under variable working conditions, and the accuracy rate reaches 99.65%.