NF Waziralilah, A Abu, MH Lim… - MATEC Web of …, 2019 - matec-conferences.org
… [26–28] and convolutional neural network [29–32]. In this paper, the utilization of convolutional neural network (CNN) in diagnosing bearing faultdiagnosis is reviewed. CNN is widely …
… Convolutional neural network (CNN) provides an efficient … Inspired by the idea of CNN, we develop a novel diagnosis … CNN architecture is composed of dislocate layer, convolutional …
Z Chen, K Gryllias, W Li - Mechanical systems and signal processing, 2019 - Elsevier
… achieve fast, reliable and high-quality diagnosis in an automatic manner. In this paper, a novel faultdiagnosis approach integrating Convolutional Neural Networks (CNN) and Extreme …
G Jiang, H He, J Yan, P Xie - IEEE Transactions on Industrial …, 2018 - ieeexplore.ieee.org
… These traditional shallow learning models can only provide limited diagnosis ability. In summary, traditional intelligent faultdiagnosis methods still have some obvious drawbacks as …
W Sun, R Zhao, R Yan, S Shao… - IEEE Transactions on …, 2017 - ieeexplore.ieee.org
… in this paper is novel in the field of machinery faultdiagnosis and is able to learn invariant features based on the convolution and pooling architecture. Different from traditional CNN, a …
Z Chen, K Gryllias, W Li - IEEE Transactions on Industrial …, 2019 - ieeexplore.ieee.org
… for mechanical faultdiagnosis. In this paper, a novel TCNN architecture is proposed in order … 1, the 1-D raw vibration signals are first inputted into the first convolutional layer to achieve …
H Wu, J Zhao - Computers & chemical engineering, 2018 - Elsevier
… Over the past few years, deep convolutional neural network (DCNN) has shown excellent … In this paper, a faultdiagnosis method based on a DCNN model consisting of convolutional …
R Liu, F Wang, B Yang, SJ Qin - IEEE Transactions on Industrial …, 2019 - ieeexplore.ieee.org
… difficulties for faultdiagnosis. Therefore, … convolutional neural network (CNN) for motor fault diagnosis. Our contributions mainly fall into two aspects. First, we notice that each motor fault …
L Jing, M Zhao, P Li, X Xu - Measurement, 2017 - Elsevier
… In our opinion, the reason lies into the characteristic of the convolutionalarchitecture of CNN, which is able to overcome the small frequency shift of fault patterns by detecting the local …