Multiscale Convolutional Neural Networks for Fault Diagnosis of Wind Turbine Gearbox

This paper proposes a novel intelligent fault diagnosis method to automatically identify different health conditions of wind turbine (WT) gearbox. Unlike traditional approaches, where feature extraction and classification are separately designed and performed, this paper aims to automatically learn effective fault features directly from raw vibration signals while classify the type of faults in a single framework, thus providing an end-to-end learning-based fault diagnosis system for WT gearbox without additional signal processing and diagnostic expertise. Considering the multiscale characteristics inherent in vibration signals of a gearbox, a new multiscale convolutional neural network (MSCNN) architecture is proposed to perform multiscale feature extraction and classification simultaneously. The proposed MSCNN incorporates multiscale learning into the traditional CNN architecture, which has two merits: 1) high-level fault features can be effectively learned by the hierarchical learning structure with multiple pairs of convolutional and pooling layers; and 2) multiscale learning scheme can capture complementary and rich diagnosis information at different scales. This greatly improves the feature learning ability and enables better diagnosis performance. The proposed MSCNN approach is evaluated through experiments on a WT gearbox test rig. Experimental results and comprehensive comparison analysis with respect to the traditional CNN and traditional multiscale feature extractors have demonstrated the superiority of the proposed method.

I. Introduction

In recent years, wind energy has experienced a remarkable expansion in response to the increase of worldwide energy demand [1], and accordingly, wind turbines (WTs) have been extensively installed both onshore and offshore. Usually, these turbines are located in remote areas and are exposed to harsh environments, suffering from constantly varying loads and experiencing extreme operational temperature and humidity changes. As a result, they are prone to failures and result in high operation and maintenance (O&M) costs. Gearbox, as a critical component in WTs, often suffers from various failures, such as bearing damage, tooth breakage, and gear crack, and has shown high failure rates and resulted in high maintenance costs  [2] due to its long downtimes and complex repair procedures. Statistically, maintenance cost caused by the gearbox is about 13% of the overall WT cost  [3]. Therefore, condition monitoring and fault diagnosis of WT gearbox have gained considerable attentions from both academia and industry  [4]–[8].