ICONS 2019 Paper Abstract

Close

Paper ThB1SP.3

Morales-Menendez, Ruben (Tecnologico de Monterrey), Escajeda Ochoa, Luis Enrique (Tecnológico de Monterrey), Ruiz Quinde, Israel Benjamin (Tecnológico de Monterrey), Chuya Sumba, Jorge (Tecnológico de Monterrey), Vallejo, Antonio (Tecnologico de Monterrey)

New Approach Based on Autoencoders to Monitor a Tool Wear Condition in HSM

Scheduled for presentation during the Regular Session "Fault Detection, Diagnosis and Fault-tolerant Control II" (ThB1SP), Thursday, August 22, 2019, 16:40−17:00,

5th IFAC International Conference on Intelligent Control and Automation Sciences, August 21-23, 2019, Queen’s University Belfast, Northern Ireland

This information is tentative and subject to change. Compiled on November 29, 2021

Keywords Diagnosis, fault detection and fault tolerant control, Learning, adaptation and evaluation, Signal processing

Abstract

Tool condition monitoring systems in High Speed Machining (HSM) are of great importance to maintain the quality of the products and diagnose the useful life of the tools. These systems are highly demanded for the suppliers of molds and dies in the aeronautic and automotive industry. A new methodology to diagnose the tool wear condition by using a Stacked Sparse AutoEncoder(SSAE) neural network is presented. The methodology evaluates diferent signals obtained from diferent sensors (accelerometer, dynamometer and acoustic emission), which were recorded during the machining of aluminum workpieces, with diferent hardness, tools and cutting trajectories. The methodology presents a fairly acceptable performance (99.63%) in the prediction of the tool wear condition especially with the signals of the acoustic emission. SSAE neural network outperforms traditional neural network.

 

Technical Content Copyright © IFAC. All rights reserved.


This site is protected by copyright and trademark laws under US and International law.
All rights reserved. © 2002-2021 PaperCept, Inc.
Page generated 2021-11-29  03:46:50 PST   Terms of use