Application Of Machine Learning To The Electromechanical Impedance (EMI) For Monitoring Machining Processes

• Grant number: 24/15800-7
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: January 01, 2025
• End date: December 31, 2025
• Field of knowledge: Engineering - Electrical Engineering
• Principal Investigator: Fábio Isaac Ferreira
• Grantee: Luis Virgilio Malagi Carani Felipe
• Host Institution: Faculdade de Engenharia (FE). Universidade Estadual Paulista (UNESP). Campus de Bauru. Bauru , SP, Brazil

Abstract

The electromechanical impedance (EMI) technique has been used to monitor the integrity of different structures, such as parts produced by manufacturing processes. However, implementing the technique in the manufacturing environment is still a challenge due to the variables that affect EMI measurement, such as temperature and vibration. For this reason, the aim of this work is to investigate machine learning (ML) models to help predict and classify faults during additive manufacturing processes using EMI signals. To this end, ML models that can be applied to EMI signals will initially be investigated. Then, additive manufacturing (3D printing) tests will be carried out, in which EMI signals will be collected using piezoelectric diaphragms for different printing conditions. The EMI signals will be digitally processed and used to train the ML algorithms. The aim is to develop a low-cost monitoring system for additive manufacturing processes using the EMI technique with ML algorithms, avoiding failures during the process. It is worth noting that, in addition to the scientific contribution of the proposal, the subject of this work will have synergy with the research group of the Industrial Automation Research Laboratory (LAI) of the University of São Paulo (USP), in São Carlos/SP, and with the research group of the Aerospace and Technology Campus of Kansas State University, in Salina/USA.