Highly Accurate Machine Fault Diagnosis Using Deep Transfer Learning

TLDR

The authors present a deep transfer‑learning framework that converts sensor data into time‑frequency images and fine‑tunes a pretrained network to diagnose machine faults across induction motors, gearboxes, and bearings. The method transforms raw sensor signals into wavelet‑based images, extracts low‑level features with a pretrained network, and fine‑tunes higher‑level layers on labeled time‑frequency images, with datasets available at mlmechanics.ics.uci.edu. The approach trains faster and achieves near‑100 % accuracy, improving gearbox fault detection from 94.8 % to 99.64 % and outperforming existing methods on all three datasets.

Abstract

We develop a novel deep learning framework to achieve highly accurate machine fault diagnosis using transfer learning to enable and accelerate the training of deep neural network. Compared with existing methods, the proposed method is faster to train and more accurate. First, original sensor data are converted to images by conducting a Wavelet transformation to obtain time-frequency distributions. Next, a pretrained network is used to extract lower level features. The labeled time-frequency images are then used to fine-tune the higher levels of the neural network architecture. This paper creates a machine fault diagnosis pipeline and experiments are carried out to verify the effectiveness and generalization of the pipeline on three main mechanical datasets including induction motors, gearboxes, and bearings with sizes of 6000, 9000, and 5000 time series samples, respectively. We achieve state-of-the-art results on each dataset, with most datasets showing test accuracy near 100%, and in the gearbox dataset, we achieve significant improvement from 94.8% to 99.64%. We created a repository including these datasets located at mlmechanics.ics.uci.edu.