Enabling On-the-Fly Automotive Suspension Health Monitoring with Vision-based Vibration Model

• Leonardo Pezenatto da Silva UFSC
• Antônio Augusto Fröhlich UFSC
• José Luis Conradi Hoffmann UFSC
• Luiz Fernando Martins Pastuch UFSC

Resumo

Predictive Maintenance plays a vital role in improving cost-efficiency of commercial fleets while improving reliability and safety metrics. This work presents a lightweight, vision-based framework for vibration-based suspension health monitoring that leverages video-derived vertical acceleration signals to detect anomalies on-the-fly. By classifying driving events that naturally excite the suspension (e.g., traversing speed bumps and potholes), our approach triggers condition-aware assessment of suspension health that uses a deep Autoencoder trained solely on health behavior where the reconstruction error serves as a proxy for degradation severity. The proposed solution employs CARLA simulator with custom maps and suspension configuration to emulate a wide range of fault scenarios, overcoming the lack of high-fidelity, labeled datasets. Experimental results demonstrates the model’s ability to detect suspension degradation, with a mean detection error of 19.13%. The framework operates without the need for dedicated vibration sensors or labeled data, making it highly suitable for real-world deployment in fleet-scale predictive maintenance systems.

Palavras-chave: Vibrations, Degradation, Suspensions (mechanical systems), Computational modeling, Autoencoders, Sensors, Modeling, Monitoring, Predictive maintenance, Automotive engineering, Predictive Maintenance, Automotive Systems, Computer Vision