Early Bearing Fault Diagnosis of Rotating Machinery by 1D Self-Organized Operational Neural Networks

TL;DR

This paper introduces a novel 1D Self-organized Operational Neural Network approach for early bearing fault severity classification in rotating machinery, outperforming traditional CNNs in accuracy and learning capability.

Contribution

The study proposes a new 1D Self-ONN model with generative neurons for fault severity classification, enhancing early diagnosis and continuous monitoring of bearing faults.

Findings

Self-ONNs outperform 1D CNNs in fault severity classification accuracy.

Experimental results show significant performance improvements on benchmark datasets.

The proposed method maintains similar computational complexity to existing CNN-based approaches.

Abstract

Preventive maintenance of modern electric rotating machinery (RM) is critical for ensuring reliable operation, preventing unpredicted breakdowns and avoiding costly repairs. Recently many studies investigated machine learning monitoring methods especially based on Deep Learning networks focusing mostly on detecting bearing faults; however, none of them addressed bearing fault severity classification for early fault diagnosis with high enough accuracy. 1D Convolutional Neural Networks (CNNs) have indeed achieved good performance for detecting RM bearing faults from raw vibration and current signals but did not classify fault severity. Furthermore, recent studies have demonstrated the limitation in terms of learning capability of conventional CNNs attributed to the basic underlying linear neuron model. Recently, Operational Neural Networks (ONNs) were proposed to enhance the learning capability of CNN by introducing non-linear neuron models and further heterogeneity in the network configuration. In this study, we propose 1D Self-organized ONNs (Self-ONNs) with generative neurons for bearing fault severity classification and providing continuous condition monitoring. Experimental results over the benchmark NSF/IMS bearing vibration dataset using both x- and y-axis vibration signals for inner race and rolling element faults demonstrate that the proposed 1D Self-ONNs achieve significant performance gap against the state-of-the-art (1D CNNs) with similar computational complexity.