Article
Thermodynamics
Dexing Zheng, Weifang Chen, Dateng Zheng
Summary: This paper focuses on the thermal estimation of angular contact ball bearings with vibration effect. Through experiments and modeling analysis, a novel forecasting model for bearing power loss is proposed.
INTERNATIONAL JOURNAL OF THERMAL SCIENCES
(2021)
Article
Engineering, Multidisciplinary
Chen Wang, Min Wang, Bin Yang, Kaiyu Song, Yiling Zhang, Liming Liu
Summary: A computational model was developed to extract fault-excited harmonic components from an induction motor, and a new evaluating indicator FHD was proposed to describe the relationship between fault sizes and severity of fault-excited harmonic distortion. Experimental results validated the accuracy and robustness of the proposed approach in fault size estimation.
Article
Engineering, Electrical & Electronic
Zhiliang Liu, Huan Wang, Junjie Liu, Yong Qin, Dandan Peng
Summary: This article explores the potential of using multitask learning to improve the fault diagnosis performance of bearings, introducing speed identification task and load identification task as auxiliary tasks, and proposing a multitask one-dimensional convolutional neural network (MT-1DCNN). Experimental results demonstrate that multitask learning can enhance the fault diagnosis performance of the network.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Engineering, Mechanical
H. Zhang, J. Ma, X. Li, S. Xiao, F. Gu, A. Ball
Summary: The study found that wear-induced narrowband spatial components on the journal surface can excite random vibrations in the bearing, and the vibration behavior dependent on speed is an effective indicator of surface defects.
TRIBOLOGY INTERNATIONAL
(2021)
Article
Computer Science, Artificial Intelligence
Xudong Li, Jianhua Zheng, Mingtao Li, Wenzhen Ma, Yang Hu
Summary: The paper introduces a one-shot NAS method for fault diagnosis that utilizes a supernet to evaluate candidate networks in a given search space. The supernet measures the difference between its output probability and true labels to assess the actual performance of candidate networks. Networks with excellent performance can be searched based on the predictions of the supernet, using common search methods like random search or evolutionary algorithm.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Automation & Control Systems
Tantao Lin, Yongsheng Zhu, Zhijun Ren, Kai Huang, Dawei Gao
Summary: This paper proposes a convolution and cross-fusion transformer (CCFT) method to enhance the accuracy of intelligent fault diagnosis (IFD) by fusing acoustic and vibration information. The CCFT method combines convolution and transformers to improve feature extraction and introduces cross-fusion transformers to enhance the correlation between acoustic and vibration features. Two case studies demonstrate that CCFT outperforms other fusion methods.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2023)
Article
Engineering, Multidisciplinary
Guoqian Jiang, Chenling Jia, Shiqiang Nie, Xin Wu, Qun He, Ping Xie
Summary: This paper proposes a new multiview enhanced fault diagnosis framework for wind turbine gearboxes. By learning the correlated and complementary features from vibration and current signals, the proposed method achieves more accurate fault diagnosis.
Article
Automation & Control Systems
Hocine Bendjama
Summary: This paper presents a novel feature extraction method that combines CEEMD, TKEO, and SOM to enhance the identification accuracy of bearing characteristics. The proposed method effectively suppresses noise, extracts features, and identifies fault conditions of rolling bearings.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Juan Xu, Long Zhou, Weihua Zhao, Yuqi Fan, Xu Ding, Xiaohui Yuan
Summary: A Zero-shot Learning Compound Fault Diagnosis Model for bearings was proposed to address the challenge of diagnosing unknown compound faults without sufficient labeled samples. By embedding the semantic features of faults into the visual space of fault data, the model achieved a high accuracy of identifying compound faults even without any compound fault samples during training.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Bayu Adhi Tama, Malinda Vania, Seungchul Lee, Sunghoon Lim
Summary: This review provides a comprehensive overview of deep learning-based fault diagnosis methods using vibration signals. By synthesizing a large number of studies, researchers can gain an in-depth understanding of the latest developments in this field and explore future research directions.
ARTIFICIAL INTELLIGENCE REVIEW
(2023)
Article
Chemistry, Analytical
Mohammad Mohiuddin, Md. Saiful Islam, Shirajul Islam, Md. Sipon Miah, Ming-Bo Niu
Summary: In this research, a novel technique is proposed to effectively solve the problems of traditional CNN in bearing fault diagnosis. By modifying the traditional CNN model, selecting the best pre-trained model, and identifying the best classifier, the proposed technique achieves high reliability and efficiency in detecting and classifying bearing faults under different load conditions and noisy environments.
Article
Engineering, Mechanical
R. Bertoni, H. Andre
Summary: Early detection of bearing faults has been a major topic of research in the industry. Accelerometry is the most widely used method, but it has limitations in cases of high background noise or when environmental conditions do not allow proximity to the bearing. This paper proposes a fault detection method using incremental encoders to detect early bearing faults in a helicopter drive train.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2023)
Article
Engineering, Mechanical
Marco Cocconcelli, Matteo Strozzi, Jacopo Cavalaglio Camargo Molano, Riccardo Rubini
Summary: Hjorth's parameters are statistical time-domain parameters introduced by Bo Hjorth in 1970, commonly used for feature extraction and health monitoring. In this paper, they are applied to vibration signals for fault detection in ball bearings, with a new parameter "Detectivity" introduced for continuous monitoring of machines. The study shows that Hjorth's parameters have good performance in monitoring the health of bearings.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2022)
Article
Engineering, Electrical & Electronic
Gianluca Salata, Linga Reddy Cenkeramaddi, Van Khang Huynh, Kjell Gunnar Robbersmyr, Ajit Jha
Summary: In this article, the use of millimeter-wave (mmW) radar for noncontact, nondestructive detection, characterization, and prediction of motor failure probability is proposed and experimentally demonstrated. The features extracted from time-frequency representations distinguish faulty bearings from healthy bearings. The probability of motor failure is quantified using a probabilistic approach and model parameters.
IEEE SENSORS JOURNAL
(2023)
Article
Engineering, Electrical & Electronic
Juntao Ma, Weiguo Huang, Yi Liao, Xingxing Jiang, Chuancang Ding, Jun Wang, Juanjuan Shi
Summary: The diagnosis of early bearing faults is crucial for machine condition monitoring. The existing sparse low-rank (SLR) methods have limitations in accurately estimating amplitude and approximating singular values (SVs). To address this, a novel SLR matrix estimation method with nonconvex enhancement (SLRNE) is proposed in this article. The method extracts fault transients from observed noisy signals, leveraging their sparse and low-rank properties in the time-frequency domain. Simulated and experimental signals confirm the effectiveness of SLRNE, and contrast experiments demonstrate its superiority.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)