WPD-Enhanced Deep Graph Contrastive Learning Data Fusion for Fault Diagnosis of Rolling Bearing

Abstract

Rolling bearings are crucial mechanical components in the mechanical industry. Timely intervention and diagnosis of system faults are essential for reducing economic losses and ensuring product productivity. To further enhance the exploration of unlabeled time-series data and conduct a more comprehensive analysis of rolling bearing fault information, this paper proposes a fault diagnosis technique for rolling bearings based on graph node-level fault information extracted from 1D vibration signals. In this technique, 10 categories of 1D vibration signals from rolling bearings are sampled using a sliding window approach. The sampled data is then subjected to wavelet packet decomposition (WPD), and the wavelet energy from the final layer of the four-level WPD decomposition in each frequency band is used as the node feature. The weights of edges between nodes are calculated using the Pearson correlation coefficient (PCC) to construct a node graph that describes the feature information of rolling bearings under different health conditions. Data augmentation of the node graph in the dataset is performed by randomly adding nodes and edges. The graph convolutional neural network (GCN) is employed to encode the augmented node graph representation, and deep graph contrastive learning (DGCL) is utilized for the pre-training and classification of the node graph. Experimental results demonstrate that this method outperforms contrastive learning-based fault diagnosis methods for rolling bearings and enables rapid fault diagnosis, thus ensuring the normal operation of mechanical systems. The proposed WPDPCC-DGCL method offers two advantages: (1) the flexibility of wavelet packet decomposition in handling non-smooth vibration signals and combining it with the powerful multi-scale feature encoding capability of GCN for richer characterization of fault information, and (2) the construction of graph node-level fault samples to effectively capture underlying fault information. The experimental results demonstrate the superiority of this method in rolling bearing fault diagnosis over contrastive learning-based approaches, enabling fast and accurate fault diagnoses for rolling bearings and ensuring the normal operation of mechanical systems.

Review of research on signal decomposition and fault diagnosis of rolling bearing based on vibration signal

“…Fault category Experiment samples Diagnosis accuracy (%) [227] FKP-SGECNN 10 -99.63 [228] Improved graph convolutional network (GCN) 28 1400 99.12 [229] BCMFDE-RF-mRMR-KNN 10 550 99.09 [230] NWMF-CNN 10 4000 99.80 [231] Reinforcement neural architecture search CNN 12 3600 99.65 [232] Dimension expansion and AntisymNet lightweight CNN 10 10 000 99.70 [233] Multi-scale weighted graph-MCGCN 10 3000 99.45 [234] Improved (ICEEMDAN)-ICA-FuEn 10 10 000 99.91 [235] MAM-DSDCNN 7 2800 99.63 [236] Sparse representation deep learning (SR-DEEP) 4 2000 100.00 [237] Online sequential extreme learning machine (OS-ELM) 4 9466 99.62 [238] IFE + CBAM-enhanced InceptionNet 10 1000 99.5 [239] SSCL method based on MSA mechanism and MCL 10 2000 99.97 [240] MRDNN-AG 10 120 000 98.85 [241] AMCEEMD-1DCNN 7 3500 99.50 [242] Modified AlexNet-SVM 4 -99.60 [243] FC-CLDCNN 10 10 000 99.95 [244] PCA-ICEEMDAN and BiLSTM-SCN-CCAM 10 1024 99.92 [245] 2ADA + MK-MMD 10 1960 99.76 [246] 1D feature matching domain adaptation 3 9000 100.00 [247] ICEEMDAN-Hilbert transform-CBAM 10 30 000 95.2 [248] Ensemble MSRCNN-BiLSTM 4 4800 98.43 [249] WKN-BiLSTM-AM 10 1750 99.7 [250] MVO-MOMEDA-SVM 4 400 92.50 [251] WPDPCC-DGCL 10 6000 98.65 [252] I-PixelHop framework based on Spark-GPU 10 -98.93…”