A Weighted-Transfer Domain-Adaptation Network Applied to Unmanned Aerial Vehicle Fault Diagnosis

Sensors, Год журнала: 2025, Номер 25(6), С. 1924 - 1924

Опубликована: Март 19, 2025

With the development of UAV technology, composition UAVs has become increasingly complex, interconnected, and tightly coupled. Fault features are characterized by weakness, nonlinearity, coupling, uncertainty. A promising approach is use deep learning methods, which can effectively extract useful diagnostic information from weak, coupled, nonlinear data inputs with background noise. However, due to diversity flight environments missions, distribution obtained sample varies. The types fault corresponding labels under different conditions unknown, it time-consuming expensive label data. These challenges reduce performance traditional models in anomaly detection. To overcome these challenges, a novel weighted-transfer domain-adaptation network (WTDAN) method introduced realize online detection diagnosis electromagnetic-sensitive based on unsupervised transfer learning, knowledge learnt existing datasets solve problems target domain. contains three multiscale modules: feature extractor, used multidimensional input; domain discriminator, improve imbalance between source domain; classifier, classify categories for Multilayer adaptation distance distributions. WTDAN assigns weights samples order weight contributions problem during training process. dataset adopts not only open website but also test experiments evaluate transferability proposed model. experimental results show that, condition fewer anomalous samples, had classification accuracy up 90%, higher than that other compared performed superior cross-domain datasets. capability provide prognostics health management (PHM) UAVs, which, turn, would reliability, repairability, safety systems.

Язык: Английский

---

Graph convolutional network for traffic incidents duration classification

Engineering Applications of Artificial Intelligence, Год журнала: 2025, Номер 151, С. 110570 - 110570

Опубликована: Март 29, 2025

Язык: Английский

---

Collaborative multiview time series modeling for vehicle maintenance demand prediction

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Апрель 16, 2025

Язык: Английский

---

Integration of multi-relational graph oriented fault diagnosis method for nuclear power circulating water pumps

Measurement, Год журнала: 2024, Номер unknown, С. 115811 - 115811

Опубликована: Сен. 1, 2024

Язык: Английский

---

EI-ISOA-VMD: Adaptive denoising and detrending method for nuclear circulating water pump impeller

Measurement, Год журнала: 2024, Номер unknown, С. 115890 - 115890

Опубликована: Окт. 1, 2024

Язык: Английский

---

Latent space alignment based domain adaptation (LSADA) for fault diagnosis of rotating machinery

Advanced Engineering Informatics, Год журнала: 2024, Номер 62, С. 102862 - 102862

Опубликована: Окт. 1, 2024

Язык: Английский

---

Digital twin-enabled entropy regularized wavelet attention domain adaptation network for gearboxes fault diagnosis without fault data

Advanced Engineering Informatics, Год журнала: 2024, Номер 64, С. 103055 - 103055

Опубликована: Дек. 19, 2024

Язык: Английский

---

A novel feature dimensionality reduction method for gearbox fault diagnosis with HMSDE, DANCo-DDMA and KELM

Nonlinear Dynamics, Год журнала: 2024, Номер 112(16), С. 14071 - 14091

Опубликована: Июнь 17, 2024

Язык: Английский

---

Train-Induced Vibration and Structure-Borne Noise Measurement and Prediction of Low-Rise Building

Buildings, Год журнала: 2024, Номер 14(9), С. 2883 - 2883

Опубликована: Сен. 12, 2024

The advancement of urban rail transit is increasingly confronted with environmental challenges related to vibration and noise. To investigate the critical issues surrounding propagation generation structure-borne noise, a two-story frame building was selected for on-site measurements both its induced collected data were analyzed in time frequency domains explore correlation between these phenomena, leading proposal hybrid prediction method structural noise that subsequently compared measured results. findings indicate excitation produces significant waveforms within sound signals. characteristic 25–80 Hz, as well train-induced vibration. Furthermore, there exists positive whereby increased levels correspond more pronounced noise; additionally, indoor distribution patterns are non-uniform, corner wall areas exhibiting greater intensity than central room locations. Finally, methodology semi-analytical semi-empirical introduced. approach derives dynamic response predictions structure through analytical solutions, estimating secondary building’s interior using newly formulated empirical equation facilitate rapid regarding vibrations noises by subway train operations.

Язык: Английский

---

DSTF-Net: A Novel Framework for Intelligent Diagnosis of Insulated Bearings in Wind Turbines with Multi-Source Data and Its Interpretability

Renewable Energy, Год журнала: 2024, Номер unknown, С. 121965 - 121965

Опубликована: Ноя. 1, 2024

Язык: Английский

---