Data-Driven Methodology for Predictive Maintenance of Commercial Vehicle Turbochargers

Predictive maintenance plays an important role in ensuring the profitability of companies that rely on commercial vehicles as a core durable asset in the transportation industry. However, developing accurate and reliable predictive models for such equipment requires specific data analysis methodologies. This work proposes a data-driven methodology for predictive maintenance of commercial vehicles, comprising three main steps adapted from generic data mining methods: Problem Understanding, Data Understanding, and Data Preparation. We used a case study that uses operational data and maintenance history of turbochargers to demonstrate the feasibility of the proposed methodology that is based on the collection and analysis of real industry data for detailed analysis of relevant variables and prepare the dataset for construction of a predictive model. In this way, it is possible to identify trends and patterns that allow for the prediction of possible failures in vehicles before they occur, increasing their uptime reducing maintenance costs.