A Novel Spiking Graph Attention Network for Intelligent Fault Diagnosis of Planetary Gearboxes

As an essential component in the power transmission system of rotating machinery, planetary gearboxes are often subjected to extreme operating conditions, including heavy loads and low speeds, which can cause key components to fail over time. Early planetary gearbox fault features are weak, coupled with the impact of strong noise in the industrial field, which brings great challenges to the accurate identification and diagnosis of planetary gearbox faults. To address these issues, we propose a novel spiking graph attention network (Spiking-GAT) for intelligent fault diagnosis of planetary gearboxes, which realizes synchronous extraction of temporal and spatial features of the original signal, to accurately identify the fault category and severity of planetary gearbox. First, a graph data construction method based on the chaos theory is proposed. A multiphase coupled chaotic oscillator array based on Duffing (MP-COAD) is established to reconstruct the original signal, and the K-nearest neighbor (KNN) classifier is used to construct the reconstructed signal as graph data. Second, a novel Spiking-GAT intelligent fault diagnosis framework has been developed, which provides an adaptive spiking coding approach for graph data and deep mining and extraction of spatial–temporal features to accurately identify the health status of planetary gearboxes. Finally, the experimental and industrial fault simulation test rigs of the planetary gearbox are designed, and three cases are studied to verify the accuracy and stability of Spiking-GAT. The results show that the classification accuracy of Spiking-GAT reaches 100% on the datasets of the two test rigs and has excellent noise robustness.

[1]  Liangwei Zhang,et al.  A nearly end-to-end deep learning approach to fault diagnosis of wind turbine gearboxes under nonstationary conditions , 2023, Eng. Appl. Artif. Intell..

[2]  Ruqiang Yan,et al.  Improved spiking neural network for intershaft bearing fault diagnosis , 2022, Journal of Manufacturing Systems.

[3]  Jing Zhao,et al.  MST-GAT: A multimodal spatial-temporal graph attention network for time series anomaly detection , 2022, Inf. Fusion.

[4]  Kongliang Zhang,et al.  Motor Current Signal Analysis Using Hypergraph Neural Networks for Fault Diagnosis of Electromechanical System , 2022, SSRN Electronic Journal.

[5]  Shuilong He,et al.  Semi-supervised multi-scale attention-aware graph convolution network for intelligent fault diagnosis of machine under extremely-limited labeled samples , 2022, Journal of Manufacturing Systems.

[6]  Hongkun Li,et al.  An improved chaotic recognition method for weak signal frequency and its application to fault diagnosis of planetary gearboxes , 2022, Measurement science and technology.

[7]  Chao Liu,et al.  A low-frequency fault detection method for low-speed planetary gearbox based on acoustic signals , 2022, Applied Acoustics.

[8]  Yang Liu,et al.  A rotor fault diagnosis method based on BP-Adaboost weighted by non-fuzzy solution coefficients , 2022, Measurement.

[9]  Fengjie Xu,et al.  A multi-layer spiking neural network-based approach to bearing fault diagnosis , 2022, Reliab. Eng. Syst. Saf..

[10]  V. Muralidharan,et al.  Feature extraction using Discrete Wavelet Transform for fault classification of planetary gearbox – A comparative study , 2022, Applied Acoustics.

[11]  Guanqiu Qi,et al.  Deep residual networks-based intelligent fault diagnosis method of planetary gearboxes in cloud environments , 2022, Simul. Model. Pract. Theory.

[12]  Hongkun Li,et al.  Investigation on planetary gearbox fault mechanism under variable speed conditions based on rigid-flexible coupling dynamics model , 2021, Engineering Failure Analysis.

[13]  Byonghyo Shim,et al.  Weak Signal Frequency Detection Using Chaos Theory: A Comprehensive Analysis , 2021, IEEE Transactions on Vehicular Technology.

[14]  Hongkun Li,et al.  Intelligent fault diagnosis of planetary gearbox based on adaptive normalized CNN under complex variable working conditions and data imbalance , 2021 .

[15]  Yuxing Peng,et al.  An improved complementary ensemble empirical mode decomposition method and its application in rolling bearing fault diagnosis , 2021, Digit. Signal Process..

[16]  Wenhu Huang,et al.  Intelligent fault diagnosis of planetary gearbox based on refined composite hierarchical fuzzy entropy and random forest. , 2020, ISA transactions.

[17]  Yao Hu,et al.  New imbalanced fault diagnosis framework based on Cluster-MWMOTE and MFO-optimized LS-SVM using limited and complex bearing data , 2020, Eng. Appl. Artif. Intell..

[18]  Xiaoqin Zhou,et al.  Adaptive variational mode decomposition and its application to multi-fault detection using mechanical vibration signals. , 2020, ISA transactions.

[19]  Wenlong Fu,et al.  Coordinated approach fusing time-shift multiscale dispersion entropy and vibrational Harris hawks optimization-based SVM for fault diagnosis of rolling bearing , 2020 .

[20]  Xiangyu Zhou,et al.  Fault feature extraction for rolling bearings based on parameter-adaptive variational mode decomposition and multi-point optimal minimum entropy deconvolution , 2020 .

[21]  Yu Liu,et al.  A spiking neural network-based approach to bearing fault diagnosis , 2020, Journal of Manufacturing Systems.

[22]  Hongkun Li,et al.  Identification of planetary gearbox weak compound fault based on parallel dual-parameter optimized resonance sparse decomposition and improved MOMEDA , 2020 .

[23]  Zichen Deng,et al.  Intelligent fault identification of rotary machinery using refined composite multi-scale Lempel–Ziv complexity , 2020, Journal of Manufacturing Systems.

[24]  Xiao-Sheng Si,et al.  A rotating machinery fault diagnosis method based on multi-scale dimensionless indicators and random forests , 2020 .

[25]  Xiangdong Wang,et al.  Multiscale local features learning based on BP neural network for rolling bearing intelligent fault diagnosis , 2020, Measurement.

[26]  Byonghyo Shim,et al.  Detection of weak multi-target with adjacent frequency based on chaotic system , 2019, Int. J. Distributed Sens. Networks.

[27]  Farid Najafi,et al.  Application of a new EWT-based denoising technique in bearing fault diagnosis , 2019, Measurement.

[28]  Xin Huang,et al.  Intelligent fault diagnosis method of planetary gearboxes based on convolution neural network and discrete wavelet transform , 2019, Comput. Ind..

[29]  Wenwu Zhu,et al.  Deep Learning on Graphs: A Survey , 2018, IEEE Transactions on Knowledge and Data Engineering.

[30]  Jing Lin,et al.  A multivariate encoder information based convolutional neural network for intelligent fault diagnosis of planetary gearboxes , 2018, Knowl. Based Syst..

[31]  Jure Leskovec,et al.  How Powerful are Graph Neural Networks? , 2018, ICLR.

[32]  Bahadir Kasap,et al.  Dynamic parallelism for synaptic updating in GPU-accelerated spiking neural network simulations , 2018, Neurocomputing.

[33]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[34]  Georges Kaddoum,et al.  Wireless Chaos-Based Communication Systems: A Comprehensive Survey , 2016, IEEE Access.

[35]  Bruno Cessac,et al.  Overview of facts and issues about neural coding by spikes , 2010, Journal of Physiology-Paris.

[36]  Dezhe Z Jin,et al.  Fast convergence of spike sequences to periodic patterns in recurrent networks. , 2002, Physical review letters.

[37]  Lamiaa M. Elshenawy,et al.  Fault detection and diagnosis strategy based on k-nearest neighbors and fuzzy C-means clustering algorithm for industrial processes , 2022, J. Frankl. Inst..

[38]  Jinde Zheng,et al.  Cyclic symplectic component decomposition with application in planetary gearbox fault diagnosis , 2022, Mechanism and Machine Theory.

[39]  Ruqiang Yan,et al.  The emerging graph neural networks for intelligent fault diagnostics and prognostics: A guideline and a benchmark study , 2022, Mechanical Systems and Signal Processing.

[40]  Hongbo Shi,et al.  Fault detection and diagnosis via standardized k nearest neighbor for multimode process , 2020 .

[41]  Qi Jin,et al.  Planetary gearbox fault feature learning using conditional variational neural networks under noise environment , 2019, Knowl. Based Syst..

[42]  Gao Qing-wei,et al.  Gearbox fault diagnosis based on empirical mode decomposition and Teager energy spectrum , 2010 .

[43]  Liangsheng Qu,et al.  Applications of chaotic oscillator in machinery fault diagnosis , 2007 .

[44]  K. Goebel,et al.  Planetary gearbox fault diagnosis using bidirectional-convolutional LSTM networks , 2022 .