6.3.1 - Mitigation of Chemical Sensor Drift through Calibration Transfer in Edge AI

Event

EUROSENSORS 2026
2026-09-06 - 2026-09-09
Zurich

Band

Lectures

Chapter

Signal Analysis, Machine Learning and Artificial Intelligence for Sensing

Author(s)

J. Fonollosa - Universitat Politècnica de Catalunya,Barcelona (Spain)

Pages

210 - 210

DOI

10.5162/eurosensors2026/6.3.1

ISBN

978-3-910600-12-6

Price

free

Abstract

Railway operators increasingly require predictive tools that transform continuous tiltmeter sensing into actionable structural health indicators. This work presents a physics-informed data-driven framework for rail and sleeper monitoring and validates it on a dataset collected from several tiltmeters with hourly sampling deployed in Spain over more than two years. The pipeline combines robust preprocessing, feature engineering, multi horizon forecasting and temperature aware anomaly detection. Results show accurate one week forecasting and effective separation of temperature-driven behaviour from structural deviations, supporting earlier maintenance decisions. The framework is designed for real-world deployment and scalability across large railway networks.