Advance spectral approach for condition evaluation of rolling element bearings

The Performance of rolling element bearings has a significant influence on reliability and safety in the various engineering fields. While heading toward the condition evaluation of rolling element bearings, the higher dimensionality of feature space became a crucial concern. Thus, to have a check on the hurdles, this paper proposes a novel approach of bearing condition assessment utilizing Local mean decomposition (LMD) and spectral clustering (SC). Spectral Clustering (SC) is an influential tool, which heals the curse of dimensionality and facilitates the model by imparting a systematized structure. SC focuses more on connectivity rather than geometrical vicinity; moreover, the provision of a similarity matrix makes SC more reliable and increases its performance. To enrich the efficiency of SC, a novel decision criterion, PI (Parting Index) aiming the optimal number of clusters based on a new similarity indicator and disorder indicator coined as Synergic Association Index (SAI) and Separation Index (SI) respectively, has been proposed. The work aims to achieve better performance degradation assessment (PDA) by the application of the new SC-PI approach with the following steps; the first step is the decomposition of vibration signal into product functions (PFs) utilizing LMD; the second step involves the extraction of proper fault features; third, the extracted features are classified with the SC-PI method; finally the feature or attribute vectors are endowed to trained model and confidence value (CV) is calculated. The proposed method is validated on two datasets of different fault types. The results so obtained indicates that the SC-PI method easily differentiates the various stages when compared to different assessment techniques i.e. time-domain features, self-organizing map (SOM), k-medoids and Gaussian mixture model (GMM).