Defect detection in railway catenary systems: A survey

Abstract

The railway catenary system plays a critical role in ensuring the safe and stable operation of rail transport. However, defects in catenary components pose significant risks to operational safety and can lead to severe threats to both human life and property. With recent advances in artificial intelligence, particularly in deep learning and computer vision, intelligent defect detection technologies have become increasingly prominent in monitoring railway catenary systems. This survey provides a comprehensive overview of recent progress in intelligent defect detection for railway catenary infrastructure. We first classify existing approaches into four major model categories and examine the key techniques employed within each. Subsequently, we analyze representative implementations that apply these techniques to address the challenges associated with catenary component defect detection. A comparative analysis is conducted to evaluate the strengths and limitations of each model type, offering guidance on model selection based on specific detection requirements. Finally, we discuss emerging trends and future research directions in this field, aiming to provide a roadmap for advancing intelligent defect detection in railway catenary systems.