Quality monitoring method implementation for polymeric extrusion through supervised machine learning

• Grant number: 21/07921-0
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: December 01, 2021
• End date: November 30, 2022
• Field of knowledge: Engineering - Mechanical Engineering - Manufacturing Processes
• Principal Investigator: Gustavo Franco Barbosa
• Grantee: Eduardo Raimundo Parra
• Host Institution: Centro de Ciências Exatas e de Tecnologia (CCET). Universidade Federal de São Carlos (UFSCAR). São Carlos , SP, Brazil

Abstract

In the context of modern industry, additive manufacturing technology has been developed to enable productivity and quality gains in fabrication processes. In order to keep manufacturing effectiveness, machine learning techniques have been applied to assist processes quality control. Thus, this project aims to create a quality monitoring method for a large single-screw extruder, which will be used for 3D printing of polymeric parts up to 1m3 of volume. For that, temperature, humidity and acceleration sensors will be integrated to a fast-prototyping board. The collected data will be use as the input for supervised machine learning, with the objective of finding patterns that indicate failures in the extrusion operation.