Logistic classification for tool life modeling in machining

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper describes the application of logistic classification for tool life modeling and prediction in an industrial setting using shop floor data. Tool life is treated as a classification problem since tool wear can only be measured at the time of tool replacement in a production environment. Laboratory tool wear experiments are used to simulate shop floor wear data by two states: not worn (class 0); and worn (class 1). To incorporate non-linearity in logistic classification, a log-transformation of input features is performed. The logistic classification approach, results, and interpretability of the logistic model are presented.

Original languageEnglish
Title of host publication9th CIRP Conference on High Performance Cutting, HPC 2020
EditorsErdem Ozturk, David Curtis, Hassan Ghadbeigi
PublisherElsevier B.V.
Pages106-109
Number of pages4
ISBN (Electronic)9781713835431
DOIs
StatePublished - 2020
Event9th CIRP Conference on High Performance Cutting, HPC 2020 - Virtual, Online
Duration: May 24 2021May 26 2021

Publication series

NameProcedia CIRP
Volume101
ISSN (Print)2212-8271

Conference

Conference9th CIRP Conference on High Performance Cutting, HPC 2020
CityVirtual, Online
Period05/24/2105/26/21

Funding

This research was supported by the DOE Office of Energy Efficiency and Renewable Energy (EERE), Energy and Transportation Science Division, and used resources at the Manufacturing Demonstration Facility, a DOE-EERE User Facility at Oak Ridge National Laboratory.

FundersFunder number
DOE-EERE
Office of Energy Efficiency and Renewable Energy
Oak Ridge National Laboratory

    Keywords

    • Logistic classification
    • Machine learning
    • Tool wear

    Fingerprint

    Dive into the research topics of 'Logistic classification for tool life modeling in machining'. Together they form a unique fingerprint.

    Cite this