A health-adaptive time-scale representation (HTSR) embedded convolutional neural network for gearbox fault diagnostics
TLDR
Wang et al. as discussed by the authors proposed a health-adaptive time-scale representation (HTSR) embedded CNN, which is designed to exploit the concept of TSR, informed by the physics of the time and frequency characteristics induced by the faultrelated signals.About:
This article is published in Mechanical Systems and Signal Processing.The article was published on 2022-03-15 and is currently open access. It has received 16 citations till now. The article focuses on the topics: Convolutional neural network & Computer science.read more
Citations
More filters
Journal ArticleDOI
A comprehensive review of digital twin — part 1: modeling and twinning enabling technologies
Adam Thelen,Xiaoye Zhang,Olga Fink,Yan Lu,Sayan Ghosh,Byeng D. Youn,Michael D. Todd,Sankaran Mahadevan,Chao Hu,Zhenxiu Hu +9 more
TL;DR: In this paper , the fundamental role of different modeling techniques, twinning enabling technologies, and uncertainty quantification and optimization methods commonly used in digital twins are examined, and a battery digital twin is demonstrated, and more perspectives on the future of digital twin are shared.
Journal ArticleDOI
Deep convolutional generative adversarial network with semi-supervised learning enabled physics elucidation for extended gear fault diagnosis under data limitations
TL;DR: In this paper , a semi-supervised learning approach is proposed to detect and diagnose unseen and unknown faults in gear systems using a deep convolutional generative adversarial network (DCGAN).
Journal ArticleDOI
Bayesian deep-learning for RUL prediction: An active learning perspective
Journal ArticleDOI
Variable three-term conjugate gradient method for training artificial neural networks
TL;DR: In this article , a variable three-term conjugate gradient (VTTCG) method was proposed to enhance search direction and uses a variable step size to achieve improved convergence stability, and the experimental results show that the performance of the VTTCG method is superior to that of four conventional methods including SGD, Adam, AMSGrad, and AdaBelief.
Journal ArticleDOI
Physics-informed ensemble learning for online joint strength prediction in ultrasonic metal welding
Yuquan Meng,Chenhui Shao +1 more
TL;DR: In this article , a hierarchical physics-informed ensemble learning (PIEL) framework was developed for accurate online prediction of UMW joint strength using both physical knowledge and online sensing data.
References
More filters
Journal ArticleDOI
Multibranch and Multiscale CNN for Fault Diagnosis of Wheelset Bearings Under Strong Noise and Variable Load Condition
TL;DR: The experimental results on the wheelset bearing dataset demonstrate that the proposed method has better antinoise ability and load domain adaptability and can diagnose 12 fault types more accurately when compared with the five state-of-the-art networks.
Journal ArticleDOI
Time-reassigned synchrosqueezing transform: The algorithm and its applications in mechanical signal processing
TL;DR: In this article, a time-reassigned synchrosqueezing transform (TSST) was proposed for impulsive-like signal whose TF ridge curves is nearly parallel with the frequency axis.
Journal ArticleDOI
Compound Fault Diagnosis of Gearboxes via Multi-label Convolutional Neural Network and Wavelet Transform
TL;DR: A novel compound fault diagnosis method of the gearbox is proposed by integrating convolutional neural network with wavelet transform (WT) and multi-label (ML) classification, namely WT-MLCNN, which can achieve higher accuracy than other existing methods in literatures.
Journal ArticleDOI
Physics-Based Convolutional Neural Network for Fault Diagnosis of Rolling Element Bearings
Mohammadkazem Sadoughi,Chao Hu +1 more
TL;DR: A novel approach, namely physics-based convolutional neural network (PCNN), for fault diagnosis of rolling element bearings is proposed and the performance of PCNN in machinery fault diagnosis is compared with that of traditional machine learning- and deep learning-based approaches reported in the literature.
Journal ArticleDOI
Early fault detection in gearboxes based on support vector machines and multilayer perceptron with a continuous wavelet transform
Łukasz Jedliński,Józef Jonak +1 more
TL;DR: An attempt at early fault detection in a gearbox using ANN using wavelet transform has proved to improve significantly the accuracy of condition evaluation and the results obtained by the two networks are consistent with one another.