Skip-Feedback Neural Network With Unsupervised Feature Learning for Railway Crack Distance Estimation

Abstract

Accurate crack distance estimation is critical for railway safety and structural health monitoring. This paper proposes a Skip-Feedback Neural Network (SFNN) for single-sensor acoustic emission (AE) based crack distance estimation in railway rails. Unlike conventional multi-sensor or high-cost inspection systems, the proposed framework employs a single AE sensor and entropy-based signal representations to capture distance-dependent crack propagation characteristics under noisy operating conditions. The SFNN integrates learnable skip and feedback pathways to enhance feature reuse, stabilize gradient propagation, and improve robustness against signal attenuation. Experimental evaluation was conducted using controlled pencil lead break simulations at multiple crack-to-sensor distances and field measurements at real crack locations validated by phased array ultrasonic testing. Results demonstrate that the proposed SFNN consistently outperforms baseline neural network models across different distance ranges. The proposed approach provides a cost-efficient, noise-resilient, and scalable solution for AE-based railway crack monitoring and future structural health monitoring applications.