Deep Convolutional Transfer Learning Network: A New Method for Intelligent Fault Diagnosis of Machines With Unlabeled Data

Generally, the health conditions of rotating machinery are complicated and changeable. Meanwhile, its fault labeled information is mostly unknown. Therefore, it is man-sized to automatically capture the useful fault labeled information from the monitoring raw vibration signals. That is to say, the intelligent unsupervised learning approach has a significant influence on fault diagnosis of rotating machinery. In this study, a span-new unsupervised deep learning network can be constructed based on the proposed feature extractor (L12 sparse filtering (L12SF)) and the designed clustering extractor (Weighted Euclidean Affinity Propagation) for resolving the issue that the acquisition of fault sample labeled information is burdensome, yet costly. Naturally, the novel intelligent fault diagnosis method of rotating machinery based on unsupervised deep learning network is first presented in this study. Thereinto, the proposed unsupervised deep learning network consists of two layers of unsupervised feature extractor (L12SF) and one layer of unsupervised clustering (Weighted Euclidean Affinity Propagation). L12SF can improve the regularization performance of sparse filtering, and Weighted Euclidean Affinity Propagation can get rid of the traditional Euclidean distance in affinity propagation that cannot highlight the contribution of different features in fault clustering. To make a long story short, the frequency spectrum signals are first entered into the constructed unsupervised deep learning network for fault feature representation; afterward, the unsupervised feature learning and unsupervised fault classification of rotating machinery can be implemented. The superiority of the proposed algorithms and method is validated by two cases of rolling bearing fault dataset. Ultimately, the proposed unsupervised fault diagnosis method can provide a theoretical basis for the development of intelligent unsupervised fault diagnosis technology for rotating machinery.

Download Full-text

A domain adaptation model for early gear pitting fault diagnosis based on deep transfer learning network

Proceedings of the Institution of Mechanical Engineers Part O Journal of Risk and Reliability ◽

10.1177/1748006x19867776 ◽

2019 ◽

Vol 234 (1) ◽

pp. 168-182 ◽

Cited By ~ 4

Author(s):

Jialin Li ◽

Xueyi Li ◽

David He ◽

Yongzhi Qu

Keyword(s):

Neural Network ◽

Fault Diagnosis ◽

Transfer Learning ◽

Working Conditions ◽

Deep Neural Network ◽

Domain Adaptation ◽

Diagnostic Model ◽

Target Domain ◽

Vibration Signals ◽

Learning Network

In recent years, research on gear pitting fault diagnosis has been conducted. Most of the research has focused on feature extraction and feature selection process, and diagnostic models are only suitable for one working condition. To diagnose early gear pitting faults under multiple working conditions, this article proposes to develop a domain adaptation diagnostic model–based improved deep neural network and transfer learning with raw vibration signals. A particle swarm optimization algorithm and L2 regularization are used to optimize the improved deep neural network to improve the stability and accuracy of the diagnosis. When using the domain adaptation diagnostic model for fault diagnosis, it is necessary to discriminate whether the target domain (test data) is the same as the source domain (training data). If the target domain and the source domain are consistent, the trained improved deep neural network can be used directly for diagnosis. Otherwise, the transfer learning is combined with improved deep neural network to develop a deep transfer learning network to improve the domain adaptability of the diagnostic model. Vibration signals for seven gear types with early pitting faults under 25 working conditions collected from a gear test rig are used to validate the proposed method. It is confirmed by the validation results that the developed domain adaptation diagnostic model has a significant improvement in the adaptability of multiple working conditions.

Download Full-text