Abstract
Intelligent fault diagnosis methods based on deep learning becomes a research hotspot in the fault diagnosis field. Automatically and accurately identifying the incipient micro-fault of rotating machinery, especially for fault orientations and severity degree, is still a major challenge in the field of intelligent fault diagnosis. The traditional fault diagnosis methods rely on the manual feature extraction of engineers with prior knowledge. To effectively identify an incipient fault in rotating machinery, this paper proposes a novel method, namely improved the convolutional neural network-support vector machine (CNN-SVM) method. This method improves the traditional convolutional neural network (CNN) model structure by introducing the global average pooling technology and SVM. Firstly, the temporal and spatial multichannel raw data from multiple sensors is directly input into the improved CNN-Softmax model for the training of the CNN model. Secondly, the improved CNN are used for extracting representative features from the raw fault data. Finally, the extracted sparse representative feature vectors are input into SVM for fault classification. The proposed method is applied to the diagnosis multichannel vibration signal monitoring data of a rolling bearing. The results confirm that the proposed method is more effective than other existing intelligence diagnosis methods including SVM, K-nearest neighbor, back-propagation neural network, deep BP neural network, and traditional CNN.
Highlights
The health condition monitoring and fault diagnosis of rotating machinery are of great importance in modern industry [1,2]
The proposed convolutional neural network-support vector machine (CNN-support vector machine (SVM)) method focuses on a rolling bearing intelligence fault diagnosis without any manual feature extraction or signal preprocessing, which is totally different from the traditional methods
As an emerging machine learning algorithm, deep learning is gradually applied in the field of intelligent fault diagnosis
Summary
The health condition monitoring and fault diagnosis of rotating machinery are of great importance in modern industry [1,2]. Different from the traditional fault diagnosis methods based on signal processing technology, the intelligent diagnosis algorithm can automatically extract the useful representative features from monitoring data [2]. Zhang et al [33] directly put a 2-D representation of raw vibration signals input into a CNN model for the fault diagnosis of bearings Their methods were without the manual feature extraction from raw data, a shortcoming still existed in their research. CNN-SVM method does not use any manual feature extraction and signal processing on the raw vibration data It can get rid of the dependence on expert experience and prior knowledge. The proposed method is applied to the diagnosis of rolling bearing 2-channel experimental vibration signal data and is compared with traditional intelligent diagnosis methods including SVM, KNN, BPNN, deep BP neural network (DBPN), and traditional CNN.
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call