Combining kernel principal component analysis and spatial group-wise enhance convolutional neural network for fault recognition of rolling element bearings

Abstract

Data-driven deep learning methods have been widely used in the fault diagnosis of rolling bearings, while general network structures are complex with numerous parameters and computationally intensive calculations, leading to limited real-time performance and delayed fault detection. To address these challenges, this paper presents a novel hybrid framework, termed FKP-SGECNN, for efficient and accurate bearing fault identification. The proposed framework combines the strengths of kernel principal component analysis (KPCA), Fishercriterion, spatial grouping enhancement network (SGENet), and convolutional neural network (CNN). In the proposed framework, FKP incorporates Fisher's criterion to optimize the kernel functions in KPCA, effectively reducing information redundancy in the input data. Furthermore, SGENet is integrated to streamline the network structure and enhance the model's generalization capability, while maintaining high diagnostic accuracy. The performance of the hybrid framework implies a great potential, which was evaluated by several case studies using multi-class data of bearing faults.

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…”

Deep learning-based wind noise prediction study for automotive clay model

“…A smaller MSE indicates better prediction accuracy. The formulations for MSE and FMSE are given by equations ( 17) and (18), respectively, Under the condition that the number of CNN convolutional layers and the size of the convolutional kernels are fixed, as the number of convolutional kernels increases, the computation time also increases [57]. By determining the number of convolutional kernels for C1 and C2 as 12 and 24 respectively, and further selecting different kernel sizes of 2 × 1 and 1 × 1 for each convolutional layer, the results are presented in table 2.…”

An adaptive enhanced envelope spectrum technique for bearing fault detection in conditions characterized by strong noise

“…Rolling bearing defects account for more than 50% of the faults in rotating machinery [1]. Once a rolling bearing fails, it will seriously affect the safety and reliability of the mechanical system [2][3][4]. Hence, dependable techniques for bearing fault detection are essential to avoid potential risks such as machinery damage and casualties [5].…”