Feature reconstruction based on t-SNE: An approach for fault diagnosis of rotating machinery

Abstract

It is crucial to effectively and accurately diagnose the faults of rotating machinery. However, the high-dimensional characteristic of the features, which are extracted from the vibration signals of rotating machinery, makes it difficult to accurately recognize the fault mode. To resolve this problem, t-distributed stochastic neighbor embedding (t-SNE) is introduced to reduce the dimensionality of the feature vector in this paper. Therefore, the article describes a proposed method for fault diagnosis of rotating machinery based on local characteristic decomposition-sample entropy (LCD-SampEn), t-SNE and random forest (RF). First, the original vibration signals of rotating machinery are decomposed to a number of intrinsic scale components (ISCs) by the LCD. Next, the feature vector is obtained through calculating SampEn of each ISC. Subsequently, t-SNE is used to reduce the dimension of the feature vectors. Finally, the reconstructed feature vectors are applied to the RF for implementing the classification of the fault patterns. Two cases are studied based on the experimental data of the fault diagnoses of a bearing and a hydraulic pump. The proposed method can achieve a diagnosis rate of 98.22 % and 98.75 % for the bearing and the hydraulic pump, respectively. Compared with the other methods, the proposed approach exhibits the best performance. The results validate the effectiveness and superiority of the proposed method.