An Intelligent Fault Diagnosis Method Using Unsupervised Feature Learning Towards Mechanical Big Data

TLDR

Intelligent fault diagnosis can rapidly process mechanical big data, yet traditional methods depend on labor‑intensive, manually extracted features. This study proposes a two‑stage unsupervised feature‑learning approach for machine fault diagnosis. The method first applies sparse filtering to learn features from vibration signals, then uses softmax regression to classify machine health states. The approach achieves high diagnosis accuracy, surpassing existing methods on motor bearings, and reduces human labor by learning features adaptively.

Abstract

Intelligent fault diagnosis is a promising tool to deal with mechanical big data due to its ability in rapidly and efficiently processing collected signals and providing accurate diagnosis results. In traditional intelligent diagnosis methods, however, the features are manually extracted depending on prior knowledge and diagnostic expertise. Such processes take advantage of human ingenuity but are time-consuming and labor-intensive. Inspired by the idea of unsupervised feature learning that uses artificial intelligence techniques to learn features from raw data, a two-stage learning method is proposed for intelligent diagnosis of machines. In the first learning stage of the method, sparse filtering, an unsupervised two-layer neural network, is used to directly learn features from mechanical vibration signals. In the second stage, softmax regression is employed to classify the health conditions based on the learned features. The proposed method is validated by a motor bearing dataset and a locomotive bearing dataset, respectively. The results show that the proposed method obtains fairly high diagnosis accuracies and is superior to the existing methods for the motor bearing dataset. Because of learning features adaptively, the proposed method reduces the need of human labor and makes intelligent fault diagnosis handle big data more easily.