Maqola

Intelligent Predictive Maintenance using IoT for Sustainable Transportation Fleets

Naga Sathya Lakshman Kumar KanullaUniversity of the Cumberlands,Department of Information Technology,Williamsburg,Kentucky,USAMalokhat SaidmuratovaUrgench State University,Department of Pedagogy and Psychology,Urgench,UzbekistanT. Rajasanthosh KumarPuducherry Technological University,Department of Mechanical Engineering,Puducherry,IndiaZokir MamadiyarovTermez University of Economics and Service,Department of Finance and Tourism,Termez,Uzbekistan

2025

Ochiq kirish: yoʻq

ABI

Annotatsiya

As transportation fleets grow in scale and complexity, maintaining sustainability and operational efficiency has become increasingly vital. This study presents an enhanced IoT-enabled predictive maintenance framework that leverages sensor data and advanced machine learning algorithms to optimize vehicle upkeep. Building on existing models, the proposed system significantly improves maintenance forecasting accuracy—achieving a 22% improvement in oil change predictions and a 30% enhancement in anomaly detection. Through tailored maintenance schedules, the framework reduces downtime, extends component lifespans, and minimizes unnecessary servicing. These gains translate into a 15% reduction in emissions and a 12% boost in fuel efficiency, affirming the model’s dual value in environmental and economic sustainability. This research demonstrates the real-world viability of smart, data-driven fleet maintenance as a cornerstone for sustainable transportation systems.

Hali tarjima qilinmagan

Mavzular

Machine Fault Diagnosis Techniques Traffic Prediction and Management Techniques Reliability and Maintenance Optimization

Identifikatorlar

DOI: 10.1109/iccams65118.2025.11234465

Iqtiboslar va manbalar

0 ta iqtibos13 ta foydalanilgan manba