Research of available machine learning techniques applied to a product and its production chain

• Grant number: 24/05805-1
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: July 01, 2024
• End date: June 30, 2025
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Agreement: MCTI/MC
• Principal Investigator: Flávio Soares Corrêa da Silva
• Grantee: Gustavo Vaz Pinto
• Host Institution: Instituto de Matemática e Estatística (IME). Universidade de São Paulo (USP). São Paulo , SP, Brazil
• Company: Secretaria de Desenvolvimento Econômico (São Paulo - Estado). Instituto de Pesquisas Tecnológicas S/A (IPT)
• Associated research grant: 20/09850-0 - Applied Artificial Intelligence Research Center: accelerating the evolution of industries toward standard 5.0, AP.PCPE

Abstract

The objective of this project is to study machine learning techniques, such as prediction or decision-making algorithms, applied to a product and its production chain, aiming to dynamically adapt its chain, in order to reduce environmental impact.Among the products with the greatest presence in industries, paper and its derivatives have a fundamental highlight, since the final procedure for a commodity is its packaging. During the Covid-19 pandemic, for example, the world was faced with a growth in online shopping, leading to an increase in packaging production and redirecting resources to more urgent sectors. In many companies and industries, packaging production represents a critical point in terms of environmental impact. From the selection of raw materials to the manufacturing and distribution process, there are a number of areas where improvements can be implemented to reduce this impact. The problem lies in the lack of adaptability and flexibility of the production chain, which often operates on fixed standards that are not optimized for environmental efficiency. This results in waste of natural resources, excess carbon emissions and pollution associated with waste. The challenge, therefore, is to develop a machine learning-based system that can dynamically analyze and optimize all aspects of packaging production, from raw material inventory management to the design and production of more sustainable packaging, taking into account variables such as seasonality, market demand and availability of recyclable resources.