An Empirical Study on Predictive Maintenance for Component X in Heavy-Duty Scania Trucks

2026-06-10

AI Summary

This study addresses the challenges in failure prediction for heavy-duty truck Component X, where existing approaches struggle to balance cost-effectiveness and modeling complexity while underutilizing sensor data. Leveraging the assumption that component wear progresses as a monotonically non-decreasing time series, the proposed method simplifies raw time-series data into tabular form containing only the most recent observations. By integrating AutoML with tabular-data-oriented machine learning classifiers, the approach enables efficient, lightweight condition-driven predictive maintenance. Experimental results on the Scania Component X dataset demonstrate that this strategy significantly reduces implementation costs while maintaining strong predictive performance and substantially improving modeling efficiency.

Abstract

Condition-based Predictive Maintenance (PdM) for truck fleets has gained momentum in recent years. This maintenance strategy aims to minimize unplanned downtimes and reduce costs by monitoring the health status of vehicles and taking proactive action based on their condition. However, the implementation of condition-based PdM systems is challenging due to the large volume of data generated by the trucks, the inherent complexity of detecting failures through sensor data and the difficulties in finding cost-effective trade-offs in the solution's implementation. In this paper, we define and validate a condition-based PdM methodology built on the assumption that the wear-and-tear state of the monitored component can be represented as a monotonically non-decreasing time series. It involves selecting only the most recent observations from the time series and transforming them into a tabular format for classification using machine learning (ML) models designed for tabular data. Our results indicate that the proposed methodology reduces costs on the Scania Component X dataset compared to current state-of-the-art (SOTA) approaches, while also simplifying the modeling process through AutoML.

Problem

• Predictive Maintenance
• Condition-based Maintenance
• Heavy-Duty Trucks
• Sensor Data
• Cost-effectiveness

Innovation

• Predictive Maintenance
• Monotonic Time Series
• Tabular Data Transformation
• AutoML
• Condition-based Maintenance