Grain truck unloading prediction supported by Predictive Modeling Based on Machine Learning techniques

• Grant number: 24/16143-0
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: November 01, 2024
• End date: October 31, 2025
• Field of knowledge: Engineering - Production Engineering - Production Management
• Principal Investigator: Renan Favarão da Silva
• Grantee: Bruno Fernandez Tonso
• Host Institution: Escola Politécnica (EP). Universidade de São Paulo (USP). São Paulo , SP, Brazil

Abstract

The growth in grain production and, consequently, in Brazilian exports, creates a need for efficiency and productivity in the supply chain. Port terminals are key points in this transportation system where the loading and unloading of cargo and vehicles take place, facilitating the transfer between different modes of transportation. In this context, the grain truck unloading process at solid bulk port terminals represents one of the most critical stages of this logistics chain. Therefore, this study aims to develop and evaluate predictive models to forecast the unloading time of grain trucks at port terminals using different supervised machine learning techniques. To achieve this, the study will begin with a literature review concerning the current state of grain truck unloading forecasting and planning, focusing on approaches used, applications, and gaps. Subsequently, this process will be modeled using a standardized graphical language, considering the operational context of a port terminal, and predictive models will be trained, tested, and evaluated to forecast the unloading time of grain trucks. Finally, recommendations will be made for the implementation of the best-performing predictive model in the operational context of the port terminal.