Hui Wang
Southeast University
16 Papers
11 Citations
Hui Wang is an academic researcher from Southeast University. The author has contributed to research in topics: Computer science & Medicine. The author has an hindex of 3, co-authored 6 publications.
Chat about Author
Papers
A New Intelligent Bearing Fault Diagnosis Method Using SDP Representation and SE-CNN
TL;DR: A new and intelligent bearing fault diagnostic method by combining symmetrized dot pattern (SDP) representation with squeeze-and-excitation-enabled convolutional neural network (SE-CNN) model that achieves the classification rate over 99% but also has better generalization ability and stability.
273
Intelligent Bearing Fault Diagnosis Using Multi-Head Attention-Based CNN
TL;DR: The proposed diagnostic method can achieve effective bearing fault diagnosis with relatively fewer CNN model parameters, and has some generalization ability.
87
Bearing Degradation Evaluation Using Improved Cross Recurrence Quantification Analysis and Nonlinear Auto-Regressive Neural Network
Pu Wang,Hui Wang,Ruqiang Yan +2 more
TL;DR: An improved cross recurrence quantitative analysis (CRQA) method for bearing degradation evaluation is presented and nonlinear auto-regressive neural network (NARNN) is developed to predict future degradation trend.
Precise Positioning of Linear Motor Mover Directly From the Phase Difference Analysis
TL;DR: This article presents a new visual detection method with high precision, robustness, and processing rate to estimate the linear motor displacements by using the phase-difference matrix and a structured aperiodic fence stripe to determine the mover location of linear motor.
11
Multiscale Deep Attention Q Network: A New Deep Reinforcement Learning Method for Imbalanced Fault Diagnosis in Gearboxes
Hui Wang,Zheng Zhou,Liuyang Zhang,Ruqiang Yan +3 more
TL;DR: A novel approach called multiscale deep attention Q network (MDAQN) is proposed for imbalanced gearbox fault diagnosis from a deep reinforcement learning (DRL) perspective that exhibits superior feature extraction ability and generalization and achieves an accuracy over 99.0% when compared to multiple existing approaches.
7