Abstract
Intelligent diagnosis is an important manner for mechanical fault diagnosis in the era of industrial big data, and deep network has received extensive attention in this field because of automatically learning features and classifying entered samples. As a classic deep learning model, Convolutional Neural Network has been applied in mechanical intelligent fault diagnosis. However, the limitation is that entered samples must be balanced to achieve satisfactory recognition rate. During the operation of machinery, the normal samples are abundant and the fault samples are rare. Therefore, the recognition rate of the minority category is minor when processing the imbalanced data with Convolutional Neural Network. To solve the above problem, an intelligent classification method for imbalanced mechanical data based on Deep Cost Adaptive Convolutional Network is proposed. According to this model, first, it learns intrinsic state characteristics in mechanical raw signals through multiple convolution and pooling operations. Second, it maps these characteristics to mechanical health condition by fully connected layers. Finally, the cost adaptive loss function adaptively assigns different misclassification costs for all categories and keeps updating them in training process to effectively classify the imbalanced mechanical data. The proposed method is verified by bearing data and milling cutter data with different imbalanced ratio, and compared with other methods. The experimental results show that the proposed method is robust and is able to effectively classify the imbalanced mechanical data.
Highlights
The structural complexity and functional coupling of machinery determine that any minor fault may trigger a chain reaction
In view of the above problems, we propose an intelligent fault diagnosis method based on Deep Cost Adaptive Convolutional Network (DCACN) in this paper
The results show that DCACN can achieve higher accuracy of minority category while guaranteeing higher accuracy of overall samples, even if the proportion of majority category is large
Summary
The structural complexity and functional coupling of machinery determine that any minor fault may trigger a chain reaction. X. Dong et al.: Deep Cost Adaptive Convolutional Network: Classification Method imbalanced distribution of samples in different mechanical health condition. Jia et al [24] proposed a mechanical intelligent fault diagnosis method based on deep normalized convolutional neural network, which provided an effective idea for solving the problem of imbalanced mechanical data classification. In view of the above problems, we propose an intelligent fault diagnosis method based on Deep Cost Adaptive Convolutional Network (DCACN) in this paper. It is expected that the recognition rate of minority samples will be improved while achieving a higher classification accuracy of overall samples The difference between this method and the existing cost-sensitive learning methods is that it introduces two evaluation indexes in training process to adaptively set appropriate misclassification costs for different categories, thereby achieving effective classification of imbalanced datasets. By comparing with the conventional methods, the superiority of DCACN in classifying imbalanced mechanical data is verified
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have