Extreme learning Machine-based classifier for fault diagnosis of rotating Machinery using a residual network and continuous wavelet transform

• A ResNet-ELM framework is proposed for the fault diagnosis of rotating machinery. • The Resnet provided more advanced and significant fault features for the ELM. • Output information of the ELM is closer to sample labels. • The practicability of the ResNet-ELM was proved by means of an industrial dataset. • Our results prove compound faults are more challenging than single fault to diagnose. Effective fault diagnosis of rotating machinery is essential for the predictive maintenance of modern industries. In this study, a novel framework that combines a residual network (ResNet) as a backbone and an extreme learning machine (ELM) as a classifier (RNELM) is proposed to diagnose faults of rotating machinery. Firstly, continuous wavelet transform (CWT) is used to convert the raw time-domain signal into time–frequency domain images. Subsequently, the ResNet backbone in the framework extracts advanced features from the images for the ELM classifier, substantially improving the fault diagnosis performance. The performance of the framework is compared with four other methods using four evaluation metrics on datasets from Case Western Reserve University (CWRU), laboratory results and industrial applications. The experimental results show that the RNELM achieves outstanding results on the test samples of the three datasets, demonstrating the excellent performance and practicability of the proposed framework for fault diagnosis.