Fatigue monitoring and maneuver identification for vehicle fleets using a virtual sensing approach

TL;DR

This paper introduces a virtual sensing method for vehicle fleet fatigue monitoring that uses minimal strain gauges and accelerometers, leveraging scattering transform and PCA for damage assessment from unlabeled data.

Contribution

It presents a novel measurement-based virtual sensing approach combining scattering transform and PCA for fatigue damage regression with minimal sensor requirements.

Findings

Effective fatigue damage regression demonstrated on eBike data

Reduced sensor setup with only a few reference vehicles

Physical interpretation of data representation achieved

Abstract

Extensive monitoring comes at a prohibitive cost, limiting Predictive Maintenance strategies for vehicle fleets. This paper presents a measurement-based virtual sensing technique where local strain gauges are only required for few reference vehicles, while the remaining fleet relies exclusively on accelerometers. The scattering transform is used to perform feature extraction, while principal component analysis provides a reduced, low dimensional data representation. This enables direct fatigue damage regression, parameterized from unlabeled usage data. Identification measurements allow for a physical interpretation of the reduced representation. The approach is demonstrated using experimental data from a sensor equipped eBike, which is made publicly available.