Due to the industry 4.0 revolution massive automation is being carried out all over. One important aspect of this revolution
is to determine the Tool wear must. This is due to the fact that a worn tool leads to reduced work piece surface quality,
higher production costs and times. Tool wear is non-linear and depends on many influencing variables. In practice, the
optical determination of tool wear is a time-consuming and costly process, and the quality of manual wear determination is
prone to errors. Our approach is to apply machine learning and deep learning technologies to make this process
economical and free of human errors.
%0 Report
%1 girioptical
%A Giri, Siddhartha
%A Noske, Hendrik
%A Zerr, Sergej
%B Symposium “Maschinelles Lernen – Intelligente Digitalisierung”
%D 2018
%K myown
%T Optical inspection of tool wear using machine learning methods
%U https://machine-learning.ama-academy.eu/
%X Due to the industry 4.0 revolution massive automation is being carried out all over. One important aspect of this revolution
is to determine the Tool wear must. This is due to the fact that a worn tool leads to reduced work piece surface quality,
higher production costs and times. Tool wear is non-linear and depends on many influencing variables. In practice, the
optical determination of tool wear is a time-consuming and costly process, and the quality of manual wear determination is
prone to errors. Our approach is to apply machine learning and deep learning technologies to make this process
economical and free of human errors.
@techreport{girioptical,
abstract = {Due to the industry 4.0 revolution massive automation is being carried out all over. One important aspect of this revolution
is to determine the Tool wear must. This is due to the fact that a worn tool leads to reduced work piece surface quality,
higher production costs and times. Tool wear is non-linear and depends on many influencing variables. In practice, the
optical determination of tool wear is a time-consuming and costly process, and the quality of manual wear determination is
prone to errors. Our approach is to apply machine learning and deep learning technologies to make this process
economical and free of human errors.
},
added-at = {2020-03-27T12:57:41.000+0100},
author = {Giri, Siddhartha and Noske, Hendrik and Zerr, Sergej},
biburl = {https://www.bibsonomy.org/bibtex/27f7b1ab0a540bd583a8afe72b6e67d92/zerr},
booktitle = {Symposium “Maschinelles Lernen – Intelligente Digitalisierung”},
institution = {L3S Research Center},
interhash = {84c01c00a97c0855571fe9b777bc9f71},
intrahash = {7f7b1ab0a540bd583a8afe72b6e67d92},
keywords = {myown},
timestamp = {2020-03-27T13:00:31.000+0100},
title = {Optical inspection of tool wear using machine learning methods},
url = {https://machine-learning.ama-academy.eu/},
year = 2018
}