Graph-Guided Higher-Order Attention Network for Industrial Rotating Machinery Intelligent Fault Diagnosis
- 10 March 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (2) , 1113-1123
Abstract
Data-driven approaches have gained great success in the field of rotating machinery fault diagnosis for its powerful feature representation capability. However, in most of the current studies, model training process requires massive fault data which are costly to gather or even unavailable in some extreme operating conditions. At the same time, structural relationships between samples are not fully exploited to facilitate the model performance. In response to these problems, a novel GHOAN for rotating machinery fault diagnosis is proposed in this study. Specifically, the proposed approach incorporates the advantages of improved graph attention network model and the multiorder neighborhood feature perception to achieve richer feature representation by aggregating features from multiple neighborhood domains. In this way, effective fault diagnosis may be achieved by using fewer training samples based on vibration signal analysis. The results of experiments conducted on two benchmarking datasets and a practical experimental platform show that the proposed GHOAN achieve superior performance.Keywords
Funding Information
- National Natural Science Foundation of China (62002099)
- Natural Science Foundation of Jiangsu Province of China (BK20200184)
- Changzhou Foundation of Science and Technology (CJ20220052)
- Open Fund of State Key Laboratory of Robotics (2022-KF-22-10)
This publication has 32 references indexed in Scilit:
- A convolutional neural network based on a capsule network with strong generalization for bearing fault diagnosisNeurocomputing, 2019
- Learning Deep Correlated Representations for Nonlinear Process MonitoringIEEE Transactions on Industrial Informatics, 2018
- Information Fusion and Semi-Supervised Deep Learning Scheme for Diagnosing Gear Faults in Induction Machine SystemsIEEE Transactions on Industrial Electronics, 2018
- Preprocessing-Free Gear Fault Diagnosis Using Small Datasets With Deep Convolutional Neural Network-Based Transfer LearningIEEE Access, 2018
- Real-Time Fault Detection and Identification for MMC Using 1-D Convolutional Neural NetworksIEEE Transactions on Industrial Electronics, 2018
- Remaining useful life estimation of engineered systems using vanilla LSTM neural networksNeurocomputing, 2018
- Fault Prognosis and Remaining Useful Life Prediction of Wind Turbine Gearboxes Using Current Signal AnalysisIEEE Transactions on Sustainable Energy, 2017
- Capturing High-Discriminative Fault Features for Electronics-Rich Analog System via Deep LearningIEEE Transactions on Industrial Informatics, 2017
- A sparse auto-encoder-based deep neural network approach for induction motor faults classificationMeasurement, 2016
- A nonparametric classification method based on K-associated graphsInformation Sciences, 2011