Surface roughness estimation and chatter vibration identification using vision-based deep learning

Achmad Pratama Rifai, Rvo Fukuda, Hideki Aoyama

Research output: Contribution to journalArticle

Abstract

This study presents the development of an automatic, low-cost, fast, and reliable non-contact system for surface roughness estimation and chatter vibration identification based on machine vision. The developed system focuses on predicting two critical problems in the machining process, which are surface roughness and chatter vibration, using images as input. Deep learning with convolutional neural networks is integrated into the system to bypass the feature extraction method traditionally used in conventional vision-based roughness and chattel predictions. Two systems are proposed: Separate models that work specifically for each problem, and a combined model Thai aims to predict both problems in one process. Four deep learning architectures are proposed for both systems. The proposed models are built and tested on turned and milled surface datasets. A set of machining experiments are performed with various cutting conditions to generate the training and testing data. The result of the prediction model is then analyzed and compared with the measured data using a contact-based profilomctcr. The results indicate that the proposed system performs favorably in terms of accuracy and processing time, thus offering a promising alternative for quick inspection of surface quality.

Original languageEnglish
Pages (from-to)658-666
Number of pages9
JournalSeimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering
Volume85
Issue number7
DOIs
Publication statusPublished - 2019 Jan 1

Fingerprint

Surface roughness
Machining
Computer vision
Surface properties
Feature extraction
Inspection
Neural networks
Deep learning
Testing
Processing
Costs
Experiments

Keywords

  • Chattcr vibration
  • Deep learning
  • Machinc vision
  • Surface roughness estimation

ASJC Scopus subject areas

  • Mechanical Engineering

Cite this

Surface roughness estimation and chatter vibration identification using vision-based deep learning. / Rifai, Achmad Pratama; Fukuda, Rvo; Aoyama, Hideki.

In: Seimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering, Vol. 85, No. 7, 01.01.2019, p. 658-666.

Research output: Contribution to journalArticle

@article{cd3a354673be4a69ac2bfacfb6c09d27,
title = "Surface roughness estimation and chatter vibration identification using vision-based deep learning",
abstract = "This study presents the development of an automatic, low-cost, fast, and reliable non-contact system for surface roughness estimation and chatter vibration identification based on machine vision. The developed system focuses on predicting two critical problems in the machining process, which are surface roughness and chatter vibration, using images as input. Deep learning with convolutional neural networks is integrated into the system to bypass the feature extraction method traditionally used in conventional vision-based roughness and chattel predictions. Two systems are proposed: Separate models that work specifically for each problem, and a combined model Thai aims to predict both problems in one process. Four deep learning architectures are proposed for both systems. The proposed models are built and tested on turned and milled surface datasets. A set of machining experiments are performed with various cutting conditions to generate the training and testing data. The result of the prediction model is then analyzed and compared with the measured data using a contact-based profilomctcr. The results indicate that the proposed system performs favorably in terms of accuracy and processing time, thus offering a promising alternative for quick inspection of surface quality.",
keywords = "Chattcr vibration, Deep learning, Machinc vision, Surface roughness estimation",
author = "Rifai, {Achmad Pratama} and Rvo Fukuda and Hideki Aoyama",
year = "2019",
month = "1",
day = "1",
doi = "10.2493/jjspe.85.658",
language = "English",
volume = "85",
pages = "658--666",
journal = "Seimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering",
issn = "0912-0289",
publisher = "Japan Society for Precision Engineering",
number = "7",

}

TY - JOUR

T1 - Surface roughness estimation and chatter vibration identification using vision-based deep learning

AU - Rifai, Achmad Pratama

AU - Fukuda, Rvo

AU - Aoyama, Hideki

PY - 2019/1/1

Y1 - 2019/1/1

N2 - This study presents the development of an automatic, low-cost, fast, and reliable non-contact system for surface roughness estimation and chatter vibration identification based on machine vision. The developed system focuses on predicting two critical problems in the machining process, which are surface roughness and chatter vibration, using images as input. Deep learning with convolutional neural networks is integrated into the system to bypass the feature extraction method traditionally used in conventional vision-based roughness and chattel predictions. Two systems are proposed: Separate models that work specifically for each problem, and a combined model Thai aims to predict both problems in one process. Four deep learning architectures are proposed for both systems. The proposed models are built and tested on turned and milled surface datasets. A set of machining experiments are performed with various cutting conditions to generate the training and testing data. The result of the prediction model is then analyzed and compared with the measured data using a contact-based profilomctcr. The results indicate that the proposed system performs favorably in terms of accuracy and processing time, thus offering a promising alternative for quick inspection of surface quality.

AB - This study presents the development of an automatic, low-cost, fast, and reliable non-contact system for surface roughness estimation and chatter vibration identification based on machine vision. The developed system focuses on predicting two critical problems in the machining process, which are surface roughness and chatter vibration, using images as input. Deep learning with convolutional neural networks is integrated into the system to bypass the feature extraction method traditionally used in conventional vision-based roughness and chattel predictions. Two systems are proposed: Separate models that work specifically for each problem, and a combined model Thai aims to predict both problems in one process. Four deep learning architectures are proposed for both systems. The proposed models are built and tested on turned and milled surface datasets. A set of machining experiments are performed with various cutting conditions to generate the training and testing data. The result of the prediction model is then analyzed and compared with the measured data using a contact-based profilomctcr. The results indicate that the proposed system performs favorably in terms of accuracy and processing time, thus offering a promising alternative for quick inspection of surface quality.

KW - Chattcr vibration

KW - Deep learning

KW - Machinc vision

KW - Surface roughness estimation

UR - http://www.scopus.com/inward/record.url?scp=85073706198&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073706198&partnerID=8YFLogxK

U2 - 10.2493/jjspe.85.658

DO - 10.2493/jjspe.85.658

M3 - Article

AN - SCOPUS:85073706198

VL - 85

SP - 658

EP - 666

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 - 7

ER -