Image based identification of cutting tools in turning-milling machines

Achmad Pratama Rifai, Ryo Fukuda, Hideki Aoyama

Research output: Contribution to journalArticle

Abstract

A large number of tools in turning-milling machines run the risk of collisions during the machining process owing to their wrong disposition, mistakes in their recognition, and lack of proper communication feedback. As the system is unable to intelligently identify the tools, it fails to avoid collisions, already from the early steps of machining. This study is aimed at developing a fast, precise, and robust automatic identification method for cutting tools in turning-milling machines. To classify the large number of types of tools in those machines, the applicability of deep convolutional neural networks is explored, employing images of the tools as data input. Subsequently, feature detection, description, and matching are performed to improve accuracy. In the second phase, on-machine dimension measurement is performed by utilizing a contact-based displacement sensor with considering the output of identification phase. The proposed approach results in high accuracy of tool identification and accurately measures the correct dimensions of the tools.

Original languageEnglish
Pages (from-to)159-166
Number of pages8
JournalSeimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering
Volume85
Issue number2
DOIs
Publication statusPublished - 2019 Jan 1

Fingerprint

Milling machines
Cutting tools
Machining
Neural networks
Feedback
Communication
Sensors

Keywords

  • And matching
  • Convolutional neural network
  • Description
  • Feature detection
  • On-machine measurement
  • Tool identification
  • Turning-milling machine

ASJC Scopus subject areas

  • Mechanical Engineering

Cite this

Image based identification of cutting tools in turning-milling machines. / Rifai, Achmad Pratama; Fukuda, Ryo; Aoyama, Hideki.

In: Seimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering, Vol. 85, No. 2, 01.01.2019, p. 159-166.

Research output: Contribution to journalArticle

@article{2d145107c3ef4e5bae77e7c7ca8ecccd,
title = "Image based identification of cutting tools in turning-milling machines",
abstract = "A large number of tools in turning-milling machines run the risk of collisions during the machining process owing to their wrong disposition, mistakes in their recognition, and lack of proper communication feedback. As the system is unable to intelligently identify the tools, it fails to avoid collisions, already from the early steps of machining. This study is aimed at developing a fast, precise, and robust automatic identification method for cutting tools in turning-milling machines. To classify the large number of types of tools in those machines, the applicability of deep convolutional neural networks is explored, employing images of the tools as data input. Subsequently, feature detection, description, and matching are performed to improve accuracy. In the second phase, on-machine dimension measurement is performed by utilizing a contact-based displacement sensor with considering the output of identification phase. The proposed approach results in high accuracy of tool identification and accurately measures the correct dimensions of the tools.",
keywords = "And matching, Convolutional neural network, Description, Feature detection, On-machine measurement, Tool identification, Turning-milling machine",
author = "Rifai, {Achmad Pratama} and Ryo Fukuda and Hideki Aoyama",
year = "2019",
month = "1",
day = "1",
doi = "10.2493/jjspe.85.159",
language = "English",
volume = "85",
pages = "159--166",
journal = "Seimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering",
issn = "0912-0289",
publisher = "Japan Society for Precision Engineering",
number = "2",

}

TY - JOUR

T1 - Image based identification of cutting tools in turning-milling machines

AU - Rifai, Achmad Pratama

AU - Fukuda, Ryo

AU - Aoyama, Hideki

PY - 2019/1/1

Y1 - 2019/1/1

N2 - A large number of tools in turning-milling machines run the risk of collisions during the machining process owing to their wrong disposition, mistakes in their recognition, and lack of proper communication feedback. As the system is unable to intelligently identify the tools, it fails to avoid collisions, already from the early steps of machining. This study is aimed at developing a fast, precise, and robust automatic identification method for cutting tools in turning-milling machines. To classify the large number of types of tools in those machines, the applicability of deep convolutional neural networks is explored, employing images of the tools as data input. Subsequently, feature detection, description, and matching are performed to improve accuracy. In the second phase, on-machine dimension measurement is performed by utilizing a contact-based displacement sensor with considering the output of identification phase. The proposed approach results in high accuracy of tool identification and accurately measures the correct dimensions of the tools.

AB - A large number of tools in turning-milling machines run the risk of collisions during the machining process owing to their wrong disposition, mistakes in their recognition, and lack of proper communication feedback. As the system is unable to intelligently identify the tools, it fails to avoid collisions, already from the early steps of machining. This study is aimed at developing a fast, precise, and robust automatic identification method for cutting tools in turning-milling machines. To classify the large number of types of tools in those machines, the applicability of deep convolutional neural networks is explored, employing images of the tools as data input. Subsequently, feature detection, description, and matching are performed to improve accuracy. In the second phase, on-machine dimension measurement is performed by utilizing a contact-based displacement sensor with considering the output of identification phase. The proposed approach results in high accuracy of tool identification and accurately measures the correct dimensions of the tools.

KW - And matching

KW - Convolutional neural network

KW - Description

KW - Feature detection

KW - On-machine measurement

KW - Tool identification

KW - Turning-milling machine

UR - http://www.scopus.com/inward/record.url?scp=85064531571&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064531571&partnerID=8YFLogxK

U2 - 10.2493/jjspe.85.159

DO - 10.2493/jjspe.85.159

M3 - Article

VL - 85

SP - 159

EP - 166

JO - Seimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering

JF - Seimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering

SN - 0912-0289

IS - 2

ER -