Multireceptive Field Denoising Residual Convolutional Networks for Fault Diagnosis

Abstract

Recent progress on intelligent fault diagnosis is mainly attributed to the explosive development of convolutional neural networks (CNNs). Many existing CNN-based fault diagnosis models can extract abundant features from the measured vibration signals but cannot explore enough discriminative features under strong noise conditions. This poses a challenge for industrial applications. To address this problem, we develop a new deep CNN model, called a multireceptive field denoising residual convolutional network (MF-DRCN). The major contributions are: a multireceptive field denoising (MFD) block is designed to enhance the deep features extracted by the CNN model and filter out the interference feature information; an adaptive feature integration (AFI) module is embedded in the CNN model to adaptively integrate features, so as to make better use of the extracted information; and an end-to-end CNN model called MF-DRCN is developed based on MFD and AFI. The experimental results demonstrate that the MF-DRCN has better feature extraction and antiinterference capabilities than the other seven competitive methods. Specifically, under strong noise conditions with SNR = −6 dB, the MF-DRCN achieves 84.51% and 86.45% diagnostic accuracy, respectively, on the planetary gearbox dataset and the industrial pump dataset, which suggests the MF-DRCN is a promising intelligent fault diagnosis approach.