Sensor Fusion for Track Geometry Monitoring: Integrating On-Board Data and Degradation Models via Kalman Filtering

2025-06-02

AI Summary

Conventional track recording cars (TRCs) offer high measurement accuracy but suffer from low inspection frequency and high operational costs. To address this limitation, this study proposes a high-frequency, low-cost monitoring method for track geometry states using in-service trains. The approach innovatively integrates real-time, low-accuracy onboard sensor measurements with a physics-informed track degradation model within a Kalman filtering framework, enabling synergistic modeling of heterogeneous multi-source data and prior dynamic knowledge. We first quantify an inverse relationship between sampling frequency and prediction confidence interval width, demonstrating that high-frequency noise can be effectively mitigated through uncertainty propagation to suppress long-term prediction divergence. Experimental results confirm substantial improvements in the reliability of geometric parameter predictions, providing both theoretical foundations and quantitative guidance for optimizing low-cost sensor deployment and monitoring strategies.

Technology Category

• Computer Vision: Motion & Tracking
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Intelligent Robots: State Estimation

Application Category

• Security and Privacy: Tracking, profiling, and countermeasures against them
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Track geometry monitoring is essential for maintaining the safety and efficiency of railway operations. While Track Recording Cars (TRCs) provide accurate measurements of track geometry indicators, their limited availability and high operational costs restrict frequent monitoring across large rail networks. Recent advancements in on-board sensor systems installed on in-service trains offer a cost-effective alternative by enabling high-frequency, albeit less accurate, data collection. This study proposes a method to enhance the reliability of track geometry predictions by integrating low-accuracy sensor signals with degradation models through a Kalman filter framework. An experimental campaign using a low-cost sensor system mounted on a TRC evaluates the proposed approach. The results demonstrate that incorporating frequent sensor data significantly reduces prediction uncertainty, even when the data is noisy. The study also investigates how the frequency of data recording influences the size of the credible prediction interval, providing guidance on the optimal deployment of on-board sensors for effective track monitoring and maintenance planning.

Problem

• Enhancing track geometry prediction reliability via sensor fusion
• Integrating low-accuracy on-board sensors with degradation models
• Reducing prediction uncertainty using frequent noisy sensor data

Innovation

• Integrates on-board sensors with degradation models
• Uses Kalman filter to enhance prediction reliability
• Optimizes sensor frequency for reduced uncertainty