Detection of Damage on Inner and Outer Races of Ball Bearings Using a Low-Cost Monitoring System and Deep Convolution Neural Networks DOI Creative Commons

Handeul You,

Dongyeon Kim, J.-H. Kim

et al.

Machines, Journal Year: 2024, Volume and Issue: 12(12), P. 843 - 843

Published: Nov. 25, 2024

Bearings are vital components in machinery, and their malfunction can result equipment damage reduced productivity. As a result, considerable research attention has been directed toward the early detection of bearing faults. With recent rapid advancements machine learning algorithms, there is increasing interest proactively diagnosing faults by analyzing signals obtained from bearings. Although numerous studies have introduced methods for fault diagnosis, high costs associated with sensors data acquisition devices limit practical application industrial environments. Additionally, aimed at identifying root causes through diagnostic algorithms progressed relatively slowly. This study proposes cost-effective monitoring system to improve economic feasibility. Its primary benefits include significant cost savings compared traditional high-priced equipment, along versatility ease installation, enabling straightforward attachment removal. The collects measuring vibrations both normal faulty bearings under various operating conditions on test bed. Using these data, deep neural network trained enable real-time feature extraction classification conditions. Furthermore, an explainable AI technique applied extract key values identified algorithm, providing method support analysis causes.

Language: Английский

A novel domain feature disentanglement method for multi-target cross-domain mechanical fault diagnosis DOI
Zhenyu Liu,

Haowen Zheng,

Hui Liu

et al.

ISA Transactions, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

Language: Английский

Citations

0
Cross-domain bearing fault diagnosis under missing labels with uncertainty modeling and digital twin correction DOI
Z. Zhou, Wenhua Chen

Measurement, Journal Year: 2025, Volume and Issue: unknown, P. 116869 - 116869

Published: Jan. 1, 2025

Language: Английский

Citations

0
Multi-scale quadratic convolutional neural network for bearing fault diagnosis based on multi-sensor data fusion DOI

Yingying Ji,

Jun Gao, Xing Shao

et al.

Nonlinear Dynamics, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 17, 2025

Citations

0
Spatial-temporal graph attention contrastive learning for semi-supervised bearing fault diagnosis with limited labeled samples DOI

Wenbin Cai,

Dezun Zhao, Tianyang Wang

et al.

Computers & Industrial Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 111106 - 111106

Published: April 1, 2025

Language: Английский

Citations

0
Digital twin-inspired methods for rotating machinery intelligent fault diagnosis and remain useful life prediction: A state-of-the-art review and future challenges DOI
Kun Yu, Caizi Fan, Yongchao Zhang

et al.

Mechanical Systems and Signal Processing, Journal Year: 2025, Volume and Issue: 232, P. 112770 - 112770

Published: April 21, 2025

Language: Английский

Citations

0
Research and Prospects of Digital Twin-Based Fault Diagnosis of Electric Machines DOI Creative Commons
Jia Hu, Xiao Han, Zhihao Ye

et al.

Sensors, Journal Year: 2025, Volume and Issue: 25(8), P. 2625 - 2625

Published: April 21, 2025

This paper focuses on the application of digital twins in field electric motor fault diagnosis. Firstly, it explains origin, concept, key technology and areas twins, compares analyzes advantages disadvantages twin traditional methods diagnosis, discusses depth including data acquisition processing, modeling, analysis mining, visualization technology, etc., enumerates examples fields induction motors, permanent magnet synchronous wind turbines other fields. A concept multi-phase generator diagnosis based is given, challenges future development directions are discussed.

Language: Английский

Citations

0
A new bearing fault diagnosis method based on digital twin-assisted domain adaptation transfer learning DOI

Ke Jiang,

Yanping Cai, Deshuai Han

et al.

Structural Health Monitoring, Journal Year: 2025, Volume and Issue: unknown

Published: April 25, 2025

The demand for advanced monitoring and fault diagnosis technologies critical mechanical components is growing rapidly. Early detection of rolling bearing faults essential preventing performance degradation, unplanned downtime, safety risks. This article presents a novel method that leverages digital twin technology transfer learning to address the limitations existing approaches in terms data dependency cross-domain effectiveness. Initially, precise model developed using finite element analysis accurately simulate dynamics under various operating conditions, generating extensive simulation data. These compensate scarcity are valuable training diagnostic models. To reduce noise level real-world data, snow ablation optimizer algorithm employed optimize variational mode decomposition reduction. Subsequently, techniques utilized treat as source domain actual vibration signals target domain, enabling domain-adaptive learning. approach facilitates feature alignment knowledge transfer, further optimized through adversarial loss maximum kernel mean discrepancy metric. Moreover, deep combines residual convolutional neural networks with Transformer developed, significantly enhancing extraction classification accuracy. Experimental validation conducted on XJTU-SY dataset demonstrates proposed exhibits superior small sample outperforming methods.

Language: Английский

Citations

0
Circular supply chain for smart production in Industry 4.0 DOI
Kuo-Yi Lin

Computers & Industrial Engineering, Journal Year: 2024, Volume and Issue: 198, P. 110682 - 110682

Published: Oct. 31, 2024

Language: Английский

Citations

0
Intelligent fault diagnosis in power distribution networks using LSTM-DenseNet network DOI

Lipeng Ji,

Xin Tian, Zhonghao Wei

et al.

Electric Power Systems Research, Journal Year: 2024, Volume and Issue: 239, P. 111202 - 111202

Published: Nov. 10, 2024

Language: Английский

Citations

0
Meta-learning-based fault diagnosis method for rolling bearings under cross working-conditions DOI
Zhijie Xie,

Hao Zhan,

Yu Wang

et al.

Measurement Science and Technology, Journal Year: 2024, Volume and Issue: 36(1), P. 016218 - 016218

Published: Nov. 12, 2024

Abstract Accurate prediction of bearing failures is crucial for reducing maintenance costs and enhancing production efficiency in rotating machinery. However, the variable speed conditions complex working environments encountered during operation pose significant challenges to fault diagnosis. Problems such as domain shift insufficient sample quantity may occur diagnosis under cross-working conditions, which can decrease accuracy generalization deep learning algorithms. In this paper, we introduce a framework grounded meta-learning. Centered on dual-channel feature fusion network employing meta-learning training paradigm, not only performs well cross-condition tasks but also demonstrates superior performance few-shot scenarios. Firstly, used extract classification features different domains, are fused. Next, conducted using strategy acquire prior knowledge, enabling rapid model adaptation addressing challenge limited samples. Finally, two public rolling data sets demonstrate efficacy proposed method across operational conditions. Prior this, selected appropriate length through experimental validation. The has good cross-device tasks. results verify effective capability robustness method. Furthermore, comparisons with other approaches confirm our ablation experiments validated importance irreplaceability each component

Language: Английский

Citations

0