Abstract:

Predictive maintenance in the automotive industry is evolving with the integration of Machine Learning (ML) and Internet of Things (IoT) technologies to enhance operational efficiency and cost savings. By continuously monitoring vehicle health, companies can proactively detect failures and optimize maintenance schedules, reducing downtime and service costs. However, existing methods often rely heavily on centralized cloud processing, leading to issues such as latency, network dependency, and inefficient real-time decision-making. These challenges hinder timely fault detection and can result in increased maintenance expenses and operational disruptions. To address these limitations, this paper proposes a novel framework: Predictive Maintenance using Edge Computing with IoT Sensors and Machine Learning (IoT-S-ML). This approach leverages IoT sensors embedded in automotive components for real-time data collection, edge computing devices for localized data processing, and ML algorithms for accurate predictive analysis, minimizing the reliance on distant cloud servers. The proposed method allows faster fault detection, real-time decision-making, reduced network congestion, and enhanced system reliability. Automotive manufacturers and service providers can utilize this system to optimize maintenance operations, extend vehicle lifespan, and achieve substantial cost efficiencies. Experimental results demonstrate that the IoT-S-ML framework improves prediction accuracy by 18% and reduces maintenance costs by 22% compared to traditional cloud-based predictive maintenance models. This validates the potential of edge-enabled smart maintenance systems in revolutionizing the automotive sector.