Intelligent Classification Method for Rail Defects in Magnetic Flux Leakage Testing Based on Feature Selection and Parameter Optimization
Sensors · 26.06.2025 · 25 (13) · 3962
DOI: 10.3390/s25133962 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 26.06.2025. Verfasst von Kailun Ji und 2 weiteren Autor:innen. Beteiligte Einrichtung: College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Scientific Research Projects of China Academy of Railway Sciences, Jiangsu Province Scientific Research and Practical Innovation Program, Scientific Research Projects of China Academy of Railway Sciences.
Abstract (Originalsprache)
This study addresses the critical challenge of insufficient classification accuracy for different defect signals in rail magnetic flux leakage (MFL) detection by proposing an enhanced intelligent classification framework based on particle swarm optimized radial basis function neural network (PSO-RBF). Three key innovations drive this research: (1) A dynamic PSO algorithm incorporating adaptive learning factors and nonlinear inertia weight for precise RBF parameter optimization; (2) A hierarchical feature processing strategy combining mutual information selection with correlation-based dimensionality reduction; (3) Adaptive model architecture adjustment for small-sample scenarios. Experimental validation shows breakthrough performance: 87.5% accuracy on artificial defects (17.5% absolute improvement over conventional RBF), with macro-F1 = 0.817 and MCC = 0.733. For real-world limited samples (100 sets), adaptive optimization achieved 80% accuracy while boosting minority class (“spalling”) F1-score by 0.25 with 50% false alarm reduction. The optimized PSO-RBF demonstrates superior capability in extracting MFL signal patterns, particularly for discriminating abrasions, spalling, indentations, and shelling defects, setting a new benchmark for industrial rail inspection.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China.
ORCID-Profile: Kailun Ji
Förderung
- the Scientific Research Projects of China Academy of Railway Sciences
- Jiangsu Province Scientific Research and Practical Innovation Program
- Scientific Research Projects of China Academy of Railway Sciences
Zitieren
APA
Ji, K., Wang, P., & Jia, Y. (2025). Intelligent Classification Method for Rail Defects in Magnetic Flux Leakage Testing Based on Feature Selection and Parameter Optimization. Sensors, 25(13), 3962. https://doi.org/10.3390/s25133962
Vancouver
Ji K, Wang P, Jia Y. Intelligent Classification Method for Rail Defects in Magnetic Flux Leakage Testing Based on Feature Selection and Parameter Optimization. Sensors. 2025;25(13):3962. doi:10.3390/s25133962
BibTeX
@article{Ji2025,
author = {Ji, Kailun and Wang, Ping and Jia, Yinliang},
title = {Intelligent Classification Method for Rail Defects in Magnetic Flux Leakage Testing Based on Feature Selection and Parameter Optimization},
journal = {Sensors},
year = {2025},
volume = {25},
number = {13},
pages = {3962},
doi = {10.3390/s25133962}
}
EUVIMED