Abstract
Deep learning has been applied in intelligent fault diagnosis of machines since it trains deep neural networks to simultaneously learn features and recognize faults. In the intelligent fault diagnosis methods based on deep learning, feature learning and fault recognition are achieved by solving a multi-class classification problem. The multi-class classification, however, has not considered the relationships of fault labels, leading to two weaknesses of these methods. One is that it cannot ensure to learn the correlated features for related faults and the other is that it cannot handle missing label problem. To overcome these weaknesses, we introduce a concept of multi-label classification into intelligent fault diagnosis and propose a deep multi-label learning framework called multi-label convolutional neural network (MLCNN). MLCNN builds the relationship between the labels, and thus it is able to learn the correlated features from mechanical vibration signals and be well trained using the samples with missing labels. A motor bearing diagnosis case and a compound fault diagnosis case are used to verify the proposed method, respectively. The results show that the relationships between features are learned by MLCNN, and the classification accuracies of MLCNN are higher than traditional methods when the missing label problem occurs.
Highlights
In modern industries, machines have been more precise and automatic than ever before
The results of motor bearing diagnosis case show that the relationships between features are learned by multi-label convolutional neural network (MLCNN), and the results of compound fault diagnosis case show that the classification accuracies of MLCNN are higher than traditional methods when some attributes of the labels are missing
With the increase of the missing ratio, the area under the curve (AUC) of MLCNN vary a little and the AUCs of convolutional neural networks (CNNs) and SVM decrease largely. These results demonstrate that the MLCNN performs better than CNN and SVM when missing label phenomenon occurs, and MLCNN is able to handle the missing label problem in intelligent fault diagnosis
Summary
Machines have been more precise and automatic than ever before. The relationship between the labels can be represented by these sub-labels so as to learn correlated features and deal with the missing label problem Inspired by this multi-label concept [31], we propose a deep multi-label learning framework for the intelligent fault diagnosis of machines, which is called multi-label convolutional neural network (MLCNN). The results of motor bearing diagnosis case show that the relationships between features are learned by MLCNN, and the results of compound fault diagnosis case show that the classification accuracies of MLCNN are higher than traditional methods when some attributes of the labels are missing These results demonstrate the effectiveness of the proposed method in intelligent diagnosis of machines.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have