2D image-based electrical contact surface degradation and its health assessment DOI
Guojin Liu,

Yuze Yang,

Lekang Wang

et al.

tm - Technisches Messen, Journal Year: 2025, Volume and Issue: unknown

Published: May 7, 2025

Abstract Assessing the degradation of electrical contact surfaces using three-dimensional (3D) measurements is often costly and complex, limiting their use in real-time monitoring. To address this, a two-dimensional (2D) image-based approach proposed as an efficient practical alternative. The method uses 2D texture features, such Gray-Level Co-occurrence Matrix (GLCM) Local Binary Patterns (LBP), to quantify surface degradation. A novel Image-Based Degradation Index (IDI) introduced, its relationship with extent modeled Random Forest (RF) algorithm optimized by Particle Swarm Optimization (PSO). Validation against 3D data confirms accuracy predictions. results show that imaging provides reliable cost-effective solution for assessing health, strong agreement between predictions measurements.

Language: Английский

Landslide susceptibility along National Highway-7 in the Himalayas using random forest-based machine learning tool DOI
Khyati Gupta,

Ali P. Yunus,

Tariq Siddique

et al.

Journal of Earth System Science, Journal Year: 2025, Volume and Issue: 134(2)

Published: March 25, 2025

Language: Английский

Citations

0
Dynamic response evaluation of landslide to ambient noise using the HVSR method, the case of golay landslide in North Khorasan Province, Iran DOI

Mojtaba Hosseinzadeh,

Abdollah Sohrabi‐Bidar, Reza Khajevand

et al.

Bulletin of Engineering Geology and the Environment, Journal Year: 2025, Volume and Issue: 84(5)

Published: May 1, 2025

Language: Английский

Citations

0
2D image-based electrical contact surface degradation and its health assessment DOI
Guojin Liu,

Yuze Yang,

Lekang Wang

et al.

tm - Technisches Messen, Journal Year: 2025, Volume and Issue: unknown

Published: May 7, 2025

Abstract Assessing the degradation of electrical contact surfaces using three-dimensional (3D) measurements is often costly and complex, limiting their use in real-time monitoring. To address this, a two-dimensional (2D) image-based approach proposed as an efficient practical alternative. The method uses 2D texture features, such Gray-Level Co-occurrence Matrix (GLCM) Local Binary Patterns (LBP), to quantify surface degradation. A novel Image-Based Degradation Index (IDI) introduced, its relationship with extent modeled Random Forest (RF) algorithm optimized by Particle Swarm Optimization (PSO). Validation against 3D data confirms accuracy predictions. results show that imaging provides reliable cost-effective solution for assessing health, strong agreement between predictions measurements.

Language: Английский

Citations

0