Abstract
A convolutional neural network (CNN) has been used to successfully realize end-to-end bearing fault diagnosis due to its powerful feature extraction ability. However, the CNN is prone to focus on local information, ignoring the relationship between the whole and the part of the signal due to its unique structure. In addition, it extracts some fault features with poor robustness under noisy environment. A novel diagnosis model based on feature fusion and feature selection, GL-mRMR-SVM, is proposed to address this problem in this paper. First, the model combines the global features in the time-domain and frequency-domain of the raw data with the local features extracted by CNN to make full use of the signal information and overcome the weakness of traditional CNNs neglecting the overall signal. Then, the max-relevance min-redundancy (mRMR) algorithm is used to automatically extract the discriminative features from the fused features without any prior knowledge. Finally, the extracted discriminative features are input into the SVM for training and output the fault recognition results. The proposed GL-mRMR-SVM model was evaluated through experiments on bearing data of Case Western Reserve University (CWRU) and CUT-2 platform. The experimental results show that the proposed method is more effective than other intelligent diagnosis methods.
Highlights
Rolling bearings play an important role in maintaining the stability of the mechanical system, but they are extremely susceptible to damage
When k ≥ 10, the average accuracy of the model is above 98.78%, which indicates that the proposed GL-max-relevance min-redundancy (mRMR)-support vector machines (SVM) model has excellent performance in fault diagnosis
Well as traditional convolutional neural network (CNN) in noisy situations. This is because a large amount of noise is incorporated when signal-to-noise ratios (SNR) isasgreater than 0, the test performance of GL-mRMR-SVM even increases to 98% at a stable into the global features, which results in the performance degradation of the model
Summary
Rolling bearings play an important role in maintaining the stability of the mechanical system, but they are extremely susceptible to damage. The convolutional neural network (CNN) is a commonly used deep learning method, which directly acts on the original signal through weight sharing and local connection to achieve end-to-end fault diagnosis. Gong et al [13] proposed an improved CNN-SVM method and inputted multiple sensors data to the model. Proposed a method of converting vibration signals of multiple sensors into images By this method, CNN can extract richer features. To overcome the problems above, inspired from the work of Yan et al [20], an intelligent fault diagnosis model (GL-mRMR-SVM) based on feature fusion and feature selection is proposed. The model is relatively easy to implement, and the information of the raw signal can be fully utilized by the model This model performs well in noisy environment and can process the raw data directly without any pre-denoising method.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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
