Data-Driven Investigation of Vehicle Failures, Maintenance Expenditure, and Reliability Improvement in Indian Heavy Commercial Fleet Operations

Heavy commercial vehicle fleets are critical to transportation, logistics, mining, and construction sectors, where vehicle reliability and maintenance efficiency significantly influence operational performance and profitability. Frequent vehicle failures, increasing maintenance expenditure, and downtime losses have created a growing need for data-driven maintenance strategies. This review article presents a comprehensive analysis of vehicle failure mechanisms, maintenance cost modeling, reliability assessment techniques, and emerging technologies used in fleet management. Reliability engineering approaches such as Weibull analysis, Markov models, Reliability Block Diagrams (RBD), and Remaining Useful Life (RUL) prediction are examined along with modern data analytics and machine learning applications. The study further reviews preventive, condition-based, predictive, and reliability-centered maintenance strategies for enhancing fleet availability and reducing operational costs. The role of Industry 4.0 technologies, including IoT, Digital Twins, Cloud Computing, and Artificial Intelligence, is also discussed. Research gaps, future trends, and opportunities for intelligent fleet maintenance systems are identified. The review provides valuable insights for researchers and practitioners seeking to improve fleet reliability, maintenance effectiveness, and long-term operational sustainability.