Feature Extraction Methods for Fault Classification of Rolling Element Bearing Based on Nonlinear Dimensionality Reduction and SVMs

Feature extraction is of great importance in condition monitoring and fault diagnosis of rolling machinery. Nonlinear dimensionality reduction (NDR) theories brought a new idea for recognizing and predicting the underlying nonlinear behavior. In this paper, we propose a NDR based feature extraction method for fault classification of rolling element bearing. Original feature spaces are constructed by time- and frequency-domain feature selection method, NDR based feature extraction scheme is proposed to acquire the low-dimensional embeddings from feature space, which provide a more truthful low-dimensional representation compared to the linear DR methods. In order to systematically and quantitatively investigate the performance of NDR method, we compare the three nonlinear DR methods: isometric mapping (Isomap), locally linear embedding (LLE), and local tangent space alignment (LTSA) with the intent of determining a reduced subspace representation in which the fault classes of rolling element bearing are more easily discriminable. Evaluation of the classification performance is done by support vector machine (SVM), a supervised classifiers. Additionally, with optimal neighborhood size, binary code combinations based on NDR embedded results are given for fault recognition. Experiments on 6 fault data sets are used for fault and severity classification. Quantitative evaluation results suggest that NDR methods are superior in identifying potential novel classes within the data.