Self-supervised graph feature enhancement and scale attention for mechanical signal node-level representation and diagnosis

Advanced Engineering Informatics, Год журнала: 2025, Номер 65, С. 103197 - 103197

Опубликована: Фев. 15, 2025

Язык: Английский

---

Spatial-temporal graph feature learning driven by time–frequency similarity assessment for robust fault diagnosis of rotating machinery

Advanced Engineering Informatics, Год журнала: 2024, Номер 62, С. 102711 - 102711

Опубликована: Июль 13, 2024

Язык: Английский

---

Semi-supervised few-shot fault diagnosis driven by multi-head dynamic graph attention network under speed fluctuations

Digital Signal Processing, Год журнала: 2024, Номер 151, С. 104528 - 104528

Опубликована: Апрель 28, 2024

Язык: Английский

---

Graph Optimization Algorithm Enhanced by Dual-Scale Spectral Features with Contrastive Learning for Robust Bearing Fault Diagnosis

Knowledge-Based Systems, Год журнала: 2025, Номер unknown, С. 113275 - 113275

Опубликована: Март 1, 2025

Язык: Английский

---

A novel interpretable semi-supervised graph learning model for intelligent fault diagnosis of hydraulic pumps

Knowledge-Based Systems, Год журнала: 2024, Номер 305, С. 112598 - 112598

Опубликована: Окт. 5, 2024

Язык: Английский

---

Noise-tolerant universal representation learning for multivariate time series from global-to-local perspective

Knowledge-Based Systems, Год журнала: 2025, Номер unknown, С. 113137 - 113137

Опубликована: Фев. 1, 2025

Язык: Английский

---

A multi-scale deep feature memory and recovery network for multi-sensor fault diagnosis in the channel missing scenario

Engineering Applications of Artificial Intelligence, Год журнала: 2025, Номер 145, С. 110228 - 110228

Опубликована: Фев. 13, 2025

Язык: Английский

---

Self-supervised learning for vehicle bearing fault diagnosis based on time–frequency dual-domain contrast and fusion

Nonlinear Dynamics, Год журнала: 2025, Номер unknown

Опубликована: Апрель 4, 2025

Язык: Английский

---

Condition monitoring of train transmission systems based on multimodal fusion improved transformer network

Sound&Vibration, Год журнала: 2025, Номер 59(2), С. 2904 - 2904

Опубликована: Апрель 25, 2025

The train transmission system is a critical component of railway operations, playing pivotal role in ensuring service safety and reliability. However, existing condition monitoring approaches face two major challenges: (1) the coupling rich multimodal signals, such as vibration, acoustics, current, rotational speed, often overlooked, limiting accuracy; (2) small data problem signals adversely affects performance neural networks. To address these issues, this paper proposes Multimodal Fusion Improved Transformer Network for Condition Monitoring Train Transmission Systems. proposed network first explores interdependencies among different modalities compresses to reduced dimensions through correlation analysis. It then infers global dependencies computing self-attention scores based on Q, K, V matrices. approach better than traditional CNN-based models handling single-modality constraints, with former demonstrated be more accurate trustworthy publicly available datasets.

Язык: Английский

---

Evaluation of Hand-Crafted Feature Extraction for Fault Diagnosis in Rotating Machinery: A Survey

Sensors, Год журнала: 2024, Номер 24(16), С. 5400 - 5400

Опубликована: Авг. 21, 2024

This article presents a comprehensive collection of formulas and calculations for hand-crafted feature extraction condition monitoring signals. The documented features include 123 the time domain 46 frequency domain. Furthermore, machine learning-based methodology is presented to evaluate performance in fault classification tasks using seven data sets different rotating machines. evaluation involves ranking methods select best ten per method each database, be subsequently evaluated by three types classifiers. process applied exhaustively groups, combining our databases with an external benchmark. A summary table results classifiers also presented, including percentage number required achieve that value. Through graphic resources, it has been possible show prevalence certain over others, how they are associated order importance assigned methods. In same way, finding which have highest appearance percentages database all experiments possible. suggest effective technique low computational cost high interpretability identification diagnosis.

Язык: Английский

---