TOOL FOR OPTIMIZING PARAMETERIZATION OF THE HDPE PIPE EXTRUSION PROCESS BASED ON ARTIFICIAL INTELLIGENCE

• Grant number: 24/04511-4
• Support Opportunities: Research Grants - Innovative Research in Small Business - PIPE
• Start date: November 01, 2024
• End date: October 31, 2025
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: Eduardo Cherobin Martins
• Grantee: Eduardo Cherobin Martins
• Company: EDUARDO CHEROBIN MARTINS CONSULTORIA TECNOLOGIA DA INFORMACAO LTDA
• CNAE: Fabricação de tubos e acessórios de material plástico para uso na construção
• City: São Carlos
• Associated scholarship(s): 24/20145-8 - Tool for optimizing parameterization of the hdpe pipe extrusion process based on artificial intelligence, BP.PIPE

Abstract

The parameterization of tube extrusion is a process that involves multiple parameters and variables and is carried out by an operator using the trial and error method until obtaining a tube with the desired wall thickness. If the wall thickness of the resulting tube is below specifications, the tube is discarded; if it is above, more material is used than necessary. This process results in losses of material, time and energy. Preliminary consultations in the industry showed that 6% to 8% of HDPE pipe production is lost exclusively during the parameterization process. Furthermore, the use of mixtures of recycled and virgin raw materials in varying proportions contributes to the instability of final product specifications and the need for frequent readjustments of parameters. In this work, we propose to study the commercial viability of a tool that performs the automatic parameterization of the extruder to reduce losses related to the trial and error method, using data collected in HDPE (high density polyethylene) tube extruders. The tool will calculate the parameters based on a combination of artificial neural networks and genetic algorithm, taking into account the mixture of recycled and virgin raw materials. It is expected to significantly reduce the company's losses of material, energy and time in the manufacture of tubes, consequently increasing productivity. (AU)