A novel ensemble convex hull-based classification model for bevel gearbox fault diagnosis

Abstract

Abstract The kernel-based geometric learning model has been successfully applied in bevel gearbox fault diagnosis. However, due to its shallow architecture and problems with its sensitivity to noise and outliers, its generalization ability and robustness need to be further improved. Ensemble learning can improve the classification accuracy of sub-classifiers, but it is effective only when the sub-classifiers meet the requirements of difference and accuracy at the same time. However, as strong classifiers, geometric learning models are difficult to produce sub-classifiers with differences. To solve these problems, this study proposes a novel ensemble model, the ensemble convex hull (CH)-based (EnCH) classification model. CH has the advantages of clear geometric meaning and is easy to deform. This paper considers the clustering characteristics of the sample points in the feature space, or both distance and density, and performs differential shrinkage deformation on the original CH. For one thing, this can produce differential CHs to build differential sub-classifiers for the ensemble. Also, it can suppress the interference of noise and outliers to improve robustness. The results of our experiments on the fault dataset of a bevel gear box indicate that the EnCH classification model can improve the generalization of the geometric learning model and has excellent tolerance to noise and outliers.