Abstract
A novel bearing fault diagnosis method based on improved locality-constrained linear coding (LLC) and adaptive PSO-optimized support vector machine (SVM) is proposed. In traditional LLC, each feature is encoded by using a fixed number of bases without considering the distribution of the features and the weight of the bases. To address these problems, an improved LLC algorithm based on adaptive and weighted bases is proposed. Firstly, preliminary features are obtained by wavelet packet node energy. Then, dictionary learning with class-wise K-SVD algorithm is implemented. Subsequently, based on the learned dictionary the LLC codes can be solved using the improved LLC algorithm. Finally, SVM optimized by adaptive particle swarm optimization (PSO) is utilized to classify the discriminative LLC codes and thus bearing fault diagnosis is realized. In the dictionary leaning stage, other methods such as selecting the samples themselves as dictionary and K-means are also conducted for comparison. The experiment results show that the LLC codes can effectively extract the bearing fault characteristics and the improved LLC outperforms traditional LLC. The dictionary learned by class-wise K-SVD achieves the best performance. Additionally, adaptive PSO-optimized SVM can greatly enhance the classification accuracy comparing with SVM using default parameters and linear SVM.
Highlights
Rolling bearings have been widely used in rotating machinery
The feature extraction method based on improved locality-constrained linear coding (LLC) codes by combining class-wise K-means singular value decomposition (K-SVD) with improved LLC algorithm acquires the highest accuracy, which validates the superiority of the improved LLC codes
The proposed method based on class-wise K-SVD and improved LLC has the highest accuracy for ball fault (REF), which shows that the proposed method can improve the classification accuracy of ball fault
Summary
Rolling bearings have been widely used in rotating machinery. rolling bearings suffer faults due to their structural characteristics and serious mechanical failure maybe occurs. Feature extraction and pattern recognition are two crucial steps for machinery fault diagnosis using vibration signals. Liu et al proposed a feature extraction scheme with sparse coding and realized bearing fault diagnosis [12]. Tang et al used shift-invariant dictionary learning method to decompose the vibration signal into a series of latent components and detected the bearing and gear faults [13]. Feature extraction methods based on K-SVD algorithm have been employed for machinery fault diagnosis recently. A novel method based on improved LLC algorithm and adaptive PSO-optimized SVM is proposed for bearing fault diagnosis. Afterwards, based on the learned dictionary LLC codes can be solved using the improved LLC algorithm and employed as the input feature vectors of SVM.
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
