Article
Engineering, Multidisciplinary
Li Zou, Heung Fai Lam, Jun Hu
Summary: This study proposes a novel fault diagnosis method utilizing adaptive resize-residual deep neural networks, which converts vibration signals into time-frequency images using continuous wavelet transform, enhances image contrast with histogram equalization algorithm, and achieves superior recognition accuracy.
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL
(2023)
Article
Engineering, Multidisciplinary
Hao Wei, Qinghua Zhang, Minghu Shang, Yu Gu
Summary: A novel framework combining a residual network and extreme learning machine was proposed for fault diagnosis of rotating machinery. By converting raw signals into time-frequency domain images, extracting features, and classification, the framework achieved outstanding fault diagnosis performance.
Article
Computer Science, Artificial Intelligence
Yiwei Cheng, Manxi Lin, Jun Wu, Haiping Zhu, Xinyu Shao
Summary: The proposed data-driven fault diagnosis approach based on CWTLBCNN model builds an end-to-end mechanism for fault diagnosis of rotating machinery, capturing features adaptively and diagnosing faults automatically. Compared to traditional methods, it has faster training speed and more reliable prediction accuracy.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Physics, Multidisciplinary
Qiyang Xiao, Sen Li, Lin Zhou, Wentao Shi
Summary: This paper proposes an intelligent diagnosis method for rotating machinery faults using improved variational mode decomposition and convolutional neural network to process non-stationary signals. The method automatically optimizes the number of modes and extracts time-domain features for fault diagnosis. The decomposed signal components are analyzed and correlated, and the high correlated components are selected to reconstruct the original signal. The method utilizes the continuous wavelet transform to extract two-dimensional time-frequency domain features, which are then applied to a convolutional neural network for fault feature identification.
Article
Engineering, Multidisciplinary
Shihang Yu, Min Wang, Shanchen Pang, Limei Song, Sibo Qiao
Summary: This paper proposes a ResNet06 neural network structure for high-accuracy machinery fault diagnosis. The visualization of the model and its results using Grad-CAM and Eigen-CAM prove the correctness of the model.
Article
Computer Science, Artificial Intelligence
Binsen Peng, Hong Xia, Xinzhi Lv, M. Annor-Nyarko, Shaomin Zhu, Yongkuo Liu, Jiyu Zhang
Summary: A novel fault diagnosis method for rotating machinery based on deep residual neural network and data fusion is proposed, which shows more effectiveness and robustness in feature learning, model training, anti-noise, fault tolerance, and fault diagnosis compared to other fusion learning methods and single sensor-based methods. Multi-source information fusion is key to ensuring the reliable operation of rotating machinery.
APPLIED INTELLIGENCE
(2022)
Article
Chemistry, Analytical
Atik Faysal, Wai Keng Ngui, Meng Hee Lim, Mohd Salman Leong
Summary: In this study, NEEEMD was used for fault feature extraction, combined with a CNN classifier for classification. A generalized CNN architecture was proposed, using 64x64x3 pixels RGB scalograms as input, and data augmentation was done using DCGAN, leading to improved classifier performance.
Article
Engineering, Mechanical
Huan Wang, Zhiliang Liu, Dandan Peng, Ming J. Zuo
Summary: This paper proposes a multilayer wavelet attention convolutional neural network (MWA-CNN) for noise-robust machinery fault diagnosis. The framework aims to learn discriminative fault features from the wavelet domain, which allows the model to obtain better interpretability and superior performance than conventional time-domain-based CNNs. Experiments on high-speed aeronautical bearing and motor bearing datasets prove that the proposed method has excellent fault diagnosis ability and noise robustness, and the visual analysis of the attention mechanism contributes to the interpretability of CNN in the field of fault diagnosis.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2023)
Article
Computer Science, Information Systems
Varun Khemani, Michael H. Azarian, Michael G. Pecht
Summary: This paper introduces a novel technique called learnable wavelet scattering networks for fault diagnosis of circuits and rotating machinery. By optimizing the operators of this network, higher fault diagnosis accuracy can be achieved, and it also has good generalization and transfer learning performance in fault diagnosis in different domains.
Article
Automation & Control Systems
Wenliao Du, Pengjie Hu, Hongchao Wang, Xiaoyun Gong, Shuangyuan Wang
Summary: In this article, a one-dimension in tandem with 2-D joint convolutional neural network (1D-2D JCNN) is proposed for rotating machinery fault diagnosis. It uses 1-D convolution to obtain multiscale feature vectors, constructs them into 2-D maps, and feeds them into a 2-D convolutional neural network. Experimental results show the excellent classification performance of 1D-2D JCNN in bearing and gear fault diagnosis.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2023)
Article
Automation & Control Systems
Haidong Shao, Min Xia, Jiafu Wan, Clarence W. de Silva
Summary: In this article, a modified stacked autoencoder (MSAE) that uses adaptive Morlet wavelet is proposed for automatically diagnosing various fault types and severities of rotating machinery. Experimental results show that the proposed method is superior to other state-of-the-art methods.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2022)
Article
Computer Science, Interdisciplinary Applications
Roberto M. Souza, Erick G. S. Nascimento, Ubatan A. Miranda, Wenisten J. D. Silva, Herman A. Lepikson
Summary: The paper introduces a Predictive Maintenance model with Convolutional Neural Network (PdM-CNN) for automatic fault classification in rotating equipment, achieving accuracies of 99.58% and 97.3% on two different databases. The model demonstrates the capability to accurately detect and classify faults, which can help companies improve financial performance by reducing sensor acquisition costs and embracing digital transformation for the fourth industrial revolution.
COMPUTERS & INDUSTRIAL ENGINEERING
(2021)
Article
Computer Science, Interdisciplinary Applications
Masoud Jalayer, Carlotta Orsenigo, Carlo Vercellis
Summary: The paper proposes a new feature engineering model and develops a novel Convolutional Long Short-Term Memory (CLSTM) model to improve the accuracy of fault detection and diagnosis of rotating machinery. The study demonstrates the superior performance of the model in fault diagnosis on different datasets.
COMPUTERS IN INDUSTRY
(2021)
Article
Engineering, Mechanical
Li Jiang, Lin Wu, Yu Tian, Yibing Li
Summary: A novel ensemble method based on wavelet packet transform and convolutional neural networks is proposed for fault diagnosis of rotating machinery. The method transforms raw signals into multiple wavelet packet coefficients and a reconstructed signal through WPT, then feeds them into corresponding CNN models for diagnosis. The results show better diagnostic performance compared to traditional methods.
PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART C-JOURNAL OF MECHANICAL ENGINEERING SCIENCE
(2022)
Article
Engineering, Multidisciplinary
Shoucong Xiong, Hongdi Zhou, Shuai He, Leilei Zhang, Tielin Shi
Summary: The study proposes a novel method for bearing fault diagnosis based on wavelet packet transform and a lightweight variant of deep residual network, aiming to address the issue of excessive parameters in deep learning models. Experimental results demonstrate the significant potential of the method for industrial fault diagnosis applications.
MEASUREMENT SCIENCE AND TECHNOLOGY
(2021)
Review
Acoustics
Su Jiang, Jianping Xuan, Jian Duan, Jianbin Lin, Hongfei Tao, Qi Xia, Ruizhen Jing, Shoucong Xiong, Tielin Shi
Summary: A dual attention dense convolutional network was proposed to address the gradient vanishing issue in deep neural networks and enhance network performance using dense connections and attention mechanisms. The method showed higher accuracy and faster convergence under complex operational conditions in comparison with other traditional and deep learning approaches.
JOURNAL OF VIBRATION AND CONTROL
(2021)
Article
Chemistry, Analytical
Shoucong Xiong, Hongdi Zhou, Shuai He, Leilei Zhang, Qi Xia, Jianping Xuan, Tielin Shi