An end-milling condition decision support system using data-mining for difficult-to-cut materials

Hiroyuki Kodama, Masatoshi Shindou, Toshiki Hirogaki, Eiichi Aoyama, Keiji Ogawa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

We proposed the data-mining methods using hierarchical and non-hierarchical clustering methods to help engineers decide appropriate end-milling conditions. The aim of our research is to construct a system that uses clustering techniques and tool catalog data to support the decision of end-milling conditions for difficult-to-cut materials. We used variable cluster analysis and the K-means method to find tool shape parameters that had a linear relationship with the end-milling conditions listed in the catalog. We used the response surface method and significant tool shape parameters obtained by clustering to derive end-milling condition. Milling experiments using a square end mill under two sets of end-milling conditions (conditions derived from the end-milling condition decision support system and conditions suggested by expert engineers) for difficult-to-cut materials (austenite stainless steel) showed that catalog mining can be used to derive guidelines for deciding end-milling conditions.

Original languageEnglish
Title of host publicationAdvances in Abrasive Technology XV
Pages472-477
Number of pages6
Volume565
DOIs
Publication statusPublished - 2012
Externally publishedYes
Event15th International Symposium on Advances in Abrasive Technology, ISAAT 2012 - , Singapore
Duration: Sep 25 2012Sep 28 2012

Publication series

NameAdvanced Materials Research
Volume565
ISSN (Print)1022-6680

Other

Other15th International Symposium on Advances in Abrasive Technology, ISAAT 2012
CountrySingapore
Period9/25/129/28/12

Fingerprint

Decision support systems
Data mining
Engineers
Cluster analysis
Austenite
Stainless steel
Experiments

Keywords

  • Catalog data
  • Data mining
  • Difficult-to-cut materials
  • End-milling
  • Hierarchical and non-hierarchical clustering
  • Jis sus310s
  • Response surface method

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Kodama, H., Shindou, M., Hirogaki, T., Aoyama, E., & Ogawa, K. (2012). An end-milling condition decision support system using data-mining for difficult-to-cut materials. In Advances in Abrasive Technology XV (Vol. 565, pp. 472-477). (Advanced Materials Research; Vol. 565). https://doi.org/10.4028/www.scientific.net/AMR.565.472

An end-milling condition decision support system using data-mining for difficult-to-cut materials. / Kodama, Hiroyuki; Shindou, Masatoshi; Hirogaki, Toshiki; Aoyama, Eiichi; Ogawa, Keiji.

Advances in Abrasive Technology XV. Vol. 565 2012. p. 472-477 (Advanced Materials Research; Vol. 565).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kodama, H, Shindou, M, Hirogaki, T, Aoyama, E & Ogawa, K 2012, An end-milling condition decision support system using data-mining for difficult-to-cut materials. in Advances in Abrasive Technology XV. vol. 565, Advanced Materials Research, vol. 565, pp. 472-477, 15th International Symposium on Advances in Abrasive Technology, ISAAT 2012, Singapore, 9/25/12. https://doi.org/10.4028/www.scientific.net/AMR.565.472
Kodama H, Shindou M, Hirogaki T, Aoyama E, Ogawa K. An end-milling condition decision support system using data-mining for difficult-to-cut materials. In Advances in Abrasive Technology XV. Vol. 565. 2012. p. 472-477. (Advanced Materials Research). https://doi.org/10.4028/www.scientific.net/AMR.565.472
Kodama, Hiroyuki ; Shindou, Masatoshi ; Hirogaki, Toshiki ; Aoyama, Eiichi ; Ogawa, Keiji. / An end-milling condition decision support system using data-mining for difficult-to-cut materials. Advances in Abrasive Technology XV. Vol. 565 2012. pp. 472-477 (Advanced Materials Research).
@inproceedings{df777592c1de49838de53acc01aa4c75,
title = "An end-milling condition decision support system using data-mining for difficult-to-cut materials",
abstract = "We proposed the data-mining methods using hierarchical and non-hierarchical clustering methods to help engineers decide appropriate end-milling conditions. The aim of our research is to construct a system that uses clustering techniques and tool catalog data to support the decision of end-milling conditions for difficult-to-cut materials. We used variable cluster analysis and the K-means method to find tool shape parameters that had a linear relationship with the end-milling conditions listed in the catalog. We used the response surface method and significant tool shape parameters obtained by clustering to derive end-milling condition. Milling experiments using a square end mill under two sets of end-milling conditions (conditions derived from the end-milling condition decision support system and conditions suggested by expert engineers) for difficult-to-cut materials (austenite stainless steel) showed that catalog mining can be used to derive guidelines for deciding end-milling conditions.",
keywords = "Catalog data, Data mining, Difficult-to-cut materials, End-milling, Hierarchical and non-hierarchical clustering, Jis sus310s, Response surface method",
author = "Hiroyuki Kodama and Masatoshi Shindou and Toshiki Hirogaki and Eiichi Aoyama and Keiji Ogawa",
year = "2012",
doi = "10.4028/www.scientific.net/AMR.565.472",
language = "English",
isbn = "9783037854679",
volume = "565",
series = "Advanced Materials Research",
pages = "472--477",
booktitle = "Advances in Abrasive Technology XV",

}

TY - GEN

T1 - An end-milling condition decision support system using data-mining for difficult-to-cut materials

AU - Kodama, Hiroyuki

AU - Shindou, Masatoshi

AU - Hirogaki, Toshiki

AU - Aoyama, Eiichi

AU - Ogawa, Keiji

PY - 2012

Y1 - 2012

N2 - We proposed the data-mining methods using hierarchical and non-hierarchical clustering methods to help engineers decide appropriate end-milling conditions. The aim of our research is to construct a system that uses clustering techniques and tool catalog data to support the decision of end-milling conditions for difficult-to-cut materials. We used variable cluster analysis and the K-means method to find tool shape parameters that had a linear relationship with the end-milling conditions listed in the catalog. We used the response surface method and significant tool shape parameters obtained by clustering to derive end-milling condition. Milling experiments using a square end mill under two sets of end-milling conditions (conditions derived from the end-milling condition decision support system and conditions suggested by expert engineers) for difficult-to-cut materials (austenite stainless steel) showed that catalog mining can be used to derive guidelines for deciding end-milling conditions.

AB - We proposed the data-mining methods using hierarchical and non-hierarchical clustering methods to help engineers decide appropriate end-milling conditions. The aim of our research is to construct a system that uses clustering techniques and tool catalog data to support the decision of end-milling conditions for difficult-to-cut materials. We used variable cluster analysis and the K-means method to find tool shape parameters that had a linear relationship with the end-milling conditions listed in the catalog. We used the response surface method and significant tool shape parameters obtained by clustering to derive end-milling condition. Milling experiments using a square end mill under two sets of end-milling conditions (conditions derived from the end-milling condition decision support system and conditions suggested by expert engineers) for difficult-to-cut materials (austenite stainless steel) showed that catalog mining can be used to derive guidelines for deciding end-milling conditions.

KW - Catalog data

KW - Data mining

KW - Difficult-to-cut materials

KW - End-milling

KW - Hierarchical and non-hierarchical clustering

KW - Jis sus310s

KW - Response surface method

UR - http://www.scopus.com/inward/record.url?scp=84869450013&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84869450013&partnerID=8YFLogxK

U2 - 10.4028/www.scientific.net/AMR.565.472

DO - 10.4028/www.scientific.net/AMR.565.472

M3 - Conference contribution

SN - 9783037854679

VL - 565

T3 - Advanced Materials Research

SP - 472

EP - 477

BT - Advances in Abrasive Technology XV

ER -