An automatic and efficient fault diagnosis strategy for air conditioning units by combining attention mechanisms DOI
Zhen Jia, Jian G. Qin, Qiqi Yang

et al.

Science and Technology for the Built Environment, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 11

Published: Oct. 25, 2024

Language: Английский

Deep learning-based modelling of polyvinyl chloride tube-confined concrete columns under different load eccentricities DOI

Li Shang,

Haytham F. Isleem, Mostafa M. Alsaadawi

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2025, Volume and Issue: 145, P. 110217 - 110217

Published: Feb. 13, 2025

Language: Английский

Citations

1
Multi-damage index-based interfacial debonding prediction for steel-concrete composite structures with percussion method DOI
Yuanyuan Li,

Qingrui Yue,

Hong‐Nan Li

et al.

Journal of Building Engineering, Journal Year: 2024, Volume and Issue: 94, P. 109964 - 109964

Published: June 20, 2024

Language: Английский

Citations

5
A trimaran structure damage identification method based on machine learning DOI Creative Commons
Haoyun Tang,

Deyuan Ren,

Bai-Qiao Chen

et al.

Ocean Engineering, Journal Year: 2025, Volume and Issue: 320, P. 120315 - 120315

Published: Jan. 11, 2025

Language: Английский

Citations

0
An evolutionary deep learning approach using flexible variable-length dynamic stochastic search for anomaly detection of robot joints DOI
Qi Liu, Yongchao Yu, Boon Siew Han

et al.

Applied Soft Computing, Journal Year: 2024, Volume and Issue: unknown, P. 112493 - 112493

Published: Nov. 1, 2024

Language: Английский

Citations

1
A Health Monitoring Model for Circulation Water Pumps in a Nuclear Power Plant Based on Graph Neural Network Observer DOI Creative Commons

Jianyong Gao,

Liyi Ma, Qing Chen

et al.

Sensors, Journal Year: 2024, Volume and Issue: 24(14), P. 4486 - 4486

Published: July 11, 2024

The health monitoring of CRF (circulation water) pumps is essential for prognostics and management in nuclear power plants. However, the operational status can vary due to environmental factors human intervention, interrelationships between parameters are often complex. Consequently, existing methods face challenges effectively assessing pumps. In this study, we propose a model utilizing meta graph transformer (MGT) observer. Initially, transformer, temporal–spatial learning model, employed predict trends across various pump. Subsequently, fault observer constructed generate early warnings potential faults. proposed was validated using real data from plant. results demonstrate that average Mean Absolute Percentage Error (MAPE), (MAE), Root Square (RMSE) normal predictions were reduced 1.2385, 0.5614, 2.6554, respectively. These findings indicate our achieves higher prediction accuracy compared provide at least one week advance.

Language: Английский

Citations

0
A Novel Cross-Domain Mechanical Fault Diagnosis Method Fusing Acoustic and Vibration Signals by Vision Transformer DOI Creative Commons
Zhenyun Chu, Shuo Xing, Baokun Han

et al.

Sensors, Journal Year: 2024, Volume and Issue: 24(16), P. 5120 - 5120

Published: Aug. 7, 2024

Changes in operating conditions often cause the distribution of signal features to shift during bearing fault diagnosis process, which will result reduced diagnostic accuracy model. Therefore, this paper proposes a dual-channel parallel adversarial network (DPAN) based on vision transformer, extracts from acoustic and vibration signals through networks enhances feature robustness training fusion process. In addition, Wasserstein distance is used reduce domain differences fused features, thereby enhancing network’s generalization ability. Two sets experiments were conducted validate effectiveness proposed method. The experimental results show that method achieves higher compared other methods. can exceed 98%.

Language: Английский

Citations

0
The Research on Intelligent News Advertisement Recommendation Algorithm Based on Prompt Learning in End-to-End Large Language Model Architecture DOI Creative Commons
Yunxiang Gan, Diwei Zhu

Deleted Journal, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 19

Published: Aug. 30, 2024

With the explosive growth of information on internet, users are increasingly facing problem overload, making precise news and ad recommendations an important area research. While traditional recommendation algorithms can meet user needs to some extent, they still have limitations in dealing with complex changing behaviors dynamic content environments. This paper addresses shortcomings existing systems by proposing intelligent algorithm based end-to-end large language model architecture. Firstly, we utilize BERT as foundation, leveraging its powerful text representation capabilities achieve deep semantic understanding content, thereby capturing more detailed features. Secondly, apply prompt learning fine-tune model, designing specific prompts for better understand implicit preferences users. Finally, integrate these steps into architecture, enabling automated optimization throughout entire process from input output, thus improving precision efficiency recommendations. Experimental results demonstrate that proposed method significantly outperforms methods task recommendation, not only enhancing accuracy relevance but also effectively model's interpretability flexibility. research explores new possibilities application models systems.

Language: Английский

Citations

0
A Non-Contact AI-Based Approach to Multi-Failure Detection in Avionic Systems DOI Creative Commons
Chengxin Liu, Michele Ferlauto, Haiwen Yuan

et al.

Aerospace, Journal Year: 2024, Volume and Issue: 11(11), P. 864 - 864

Published: Oct. 22, 2024

The increasing electrification and integration of advanced controls in modern aircraft designs have significantly raised the number complexity installed printed circuit boards (PCBs), posing new challenges for efficient maintenance rapid failure detection. Despite self-diagnostic features current avionics systems, damage multiple simultaneous failures may arise, compromising safety diagnostic accuracy. To address these challenges, this paper aims to develop a fast, accurate, non-destructive, multi-failure diagnosis algorithm PCBs. proposed method combines self-attention mechanism with an adaptive graph convolutional neural network enhance precision. A residual connections extracts from scalar magnetic field data, ensuring robust input diversity. model was tested on typical dual-phase amplitude boosting up four different failures, achieving experimental results 99.08%, 98.50%, 98.78%, 98.01%, 98.93%, 98.25%, 97.03%, 99.77% across metrics including overall precision, per-class recall, F1 measure, measure. demonstrated its effectiveness feasibility diagnosing complex PCBs indicating algorithm’s potential improve performance offer promising PCB solution aerospace applications.

Language: Английский

Citations

0
An automatic and efficient fault diagnosis strategy for air conditioning units by combining attention mechanisms DOI
Zhen Jia, Jian G. Qin, Qiqi Yang

et al.

Science and Technology for the Built Environment, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 11

Published: Oct. 25, 2024

Language: Английский

Citations

0