Deep Learning–Based Fault Identification Testing Experiment for Bellows Valves DOI Creative Commons
Jianwen Guo, Yuwei Cai,

Zihan Chen

et al.

Science and Technology of Nuclear Installations, Journal Year: 2024, Volume and Issue: 2024(1)

Published: Jan. 1, 2024

This study focuses on the fault identification of pneumatic bellows valve. valve plays an essential role in regulating system pressure to ensure smooth progress tritium removal process. To conduct research health status and timely identify potential faults anomalies, we developed a dedicated experimental platform assessed performance various deep learning models, including recurrent neural networks (RNNs), single‐layer long short–term memory (LSTMs), double‐layer LSTM, multilayer gated unit (GRU), bidirectional GRU, identification. The outcomes reveal that RNN GRU models exhibit superior terms accuracy model fit, particularly scenarios involving normal operations, leakage faults, head contact faults. These findings offer new perspectives methodologies for detection prevention contributing operational stability safety valves.

Language: Английский

Switch ON/OFF learning of one-dimensional convolutional neural network and one-dimensional generative adversarial network for fault detection DOI

Seunghwan Song,

Kyuchang Chang,

Cheolsoon Park

et al.

Journal of Intelligent Manufacturing, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 10, 2025

Language: Английский

Citations

0
Lightweight anomaly detection in federated learning via separable convolution and convergence acceleration DOI
Bin Jiang, Guangfeng Wang, Xuerong Cui

et al.

Internet of Things, Journal Year: 2025, Volume and Issue: unknown, P. 101518 - 101518

Published: Jan. 1, 2025

Language: Английский

Citations

0
Online prognostic failure AIoT system for industrial generators maintenance service based two-stage deep learning algorithm DOI
Da-Thao Nguyen, Phuong Nguyen Thanh, Ming-Yuan Cho

et al.

Control Engineering Practice, Journal Year: 2025, Volume and Issue: 157, P. 106263 - 106263

Published: Jan. 30, 2025

Language: Английский

Citations

0
Cloud-based AIoT intelligent infrastructure for firefighting pump fault diagnosis-based hybrid CNN-GRU deep learning technique DOI
Da-Thao Nguyen, Phuong Nguyen Thanh, Ming-Yuan Cho

et al.

The Journal of Supercomputing, Journal Year: 2025, Volume and Issue: 81(3)

Published: Feb. 4, 2025

Language: Английский

Citations

0
Fault Detection in Steel Belts of Tires Using Magnetic Sensors and Different Deep Learning Models DOI Creative Commons
Sercan Yalçın

Firat University Journal of Experimental and Computational Engineering, Journal Year: 2025, Volume and Issue: 4(1), P. 85 - 99

Published: Feb. 18, 2025

Tire failures pose significant safety risks, necessitating advanced inspection techniques. This research investigates the application of magnetic sensors and deep learning for detecting defects in steel belts tires. It was aim to develop a robust accurate fault detection system by measuring field variations caused defects. In this study, image sensor circuit had been designed then images obtained from it have classified as none, crack, delamination type belt errors. Various models their hybrid architectures, were explored compared. Experimental results demonstrate that all exhibit strong performance, with Transformer model achieving highest accuracy 96.12%. The developed offers potential solution improving tire reducing maintenance costs industries.

Language: Английский

Citations

0
A Mold Damage Monitoring Algorithm for Power Metallurgy Molding Machines Using Bidirectional Long Short-Term Memory on an Internet of Things Platform DOI Creative Commons

Hao-Pu Lin,

Yuan-Chieh Chen,

Chin‐Chuan Han

et al.

Sensors, Journal Year: 2025, Volume and Issue: 25(7), P. 2143 - 2143

Published: March 28, 2025

In this paper, an analysis and monitoring algorithm is proposed for mold health evaluation using vibration data. Two inertial measurement units (IMUs) embedded system are first used to acquire data from a powder metallurgy molding machine. These collected on Internet of Things (IoT) platform the Message Queueing Telemetry Transport (MQTT) protocol. For analysis, signal Z axis segmented label contact section upper middle molds, corresponding stamping friction X, Y, axes extracted. Using only historical normal stamping, Bidirectional Long Short-Term Memory (Bi-LSTM) model with attention mechanism trained predict vibrations several minutes in advance. By comparing predicted observed at current time, mean square errors (MSEs) calculated evaluate status mold. Several ablation experiments were conducted assess performance model. The average MSE values samples abnormal smaller than 0.5 larger 1.0, respectively. experimental results confirm that prediction indicators can effectively notify operators An early warning damage was successfully implemented, enhancing predictive maintenance.

Language: Английский

Citations

0
An incorporation of metaheuristic algorithm and two-stage deep learnings for fault classified framework for diesel generator maintenance DOI
Phuong Nguyen Thanh

Engineering Applications of Artificial Intelligence, Journal Year: 2025, Volume and Issue: 151, P. 110688 - 110688

Published: April 6, 2025

Language: Английский

Citations

0
A Comparative Analysis of Anomaly Detection Methods in IoT Networks: An Experimental Study DOI Creative Commons

Emanuel Krzysztoń,

Izabela Rojek, Dariusz Mikołajewski

et al.

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(24), P. 11545 - 11545

Published: Dec. 11, 2024

The growth of the Internet Things (IoT) and its integration with Industry 4.0 5.0 are generating new security challenges. One key elements IoT systems is effective anomaly detection, which identifies abnormal behavior in devices or entire systems. This paper presents a comprehensive overview existing methods for detection networks using machine learning (ML). A detailed analysis various ML algorithms, both supervised (e.g., Random Forest, Gradient Boosting, SVM) unsupervised Isolation Autoencoder), was conducted. results tests conducted on popular datasets (IoT-23 CICIoT-2023) were collected analyzed detail. performance selected algorithms evaluated commonly used metrics (Accuracy, Precision, Recall, F1-score). experimental showed that Forest Autoencoder highly detecting anomalies. article highlights importance appropriate data preprocessing to improve accuracy. Furthermore, limitations centralized approach context distributed discussed. also potential directions future research field IoT.

Language: Английский

Citations

2
Deep Learning–Based Fault Identification Testing Experiment for Bellows Valves DOI Creative Commons
Jianwen Guo, Yuwei Cai,

Zihan Chen

et al.

Science and Technology of Nuclear Installations, Journal Year: 2024, Volume and Issue: 2024(1)

Published: Jan. 1, 2024

This study focuses on the fault identification of pneumatic bellows valve. valve plays an essential role in regulating system pressure to ensure smooth progress tritium removal process. To conduct research health status and timely identify potential faults anomalies, we developed a dedicated experimental platform assessed performance various deep learning models, including recurrent neural networks (RNNs), single‐layer long short–term memory (LSTMs), double‐layer LSTM, multilayer gated unit (GRU), bidirectional GRU, identification. The outcomes reveal that RNN GRU models exhibit superior terms accuracy model fit, particularly scenarios involving normal operations, leakage faults, head contact faults. These findings offer new perspectives methodologies for detection prevention contributing operational stability safety valves.

Language: Английский

Citations

0