Development of Optimization Technique for Difficult-to-cut Material Processing Technology Using Tool Catalog Data-mining System

• Project/Area Number: 15K17952
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Production engineering/Processing studies
• Research Institution: Okayama University (2017); University of Hyogo (2015-2016)
• Principal Investigator: Kodama Hiroyuki 岡山大学, 自然科学研究科, 講師 (60743755)
• Project Period (FY): 2015-04-01 – 2018-03-31
• Project Status: Completed (Fiscal Year 2017)
• Budget Amount: ¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000); Fiscal Year 2017: ¥520,000 (Direct Cost: ¥400,000、Indirect Cost: ¥120,000); Fiscal Year 2016: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000); Fiscal Year 2015: ¥3,250,000 (Direct Cost: ¥2,500,000、Indirect Cost: ¥750,000)
• Keywords: エンドミル / 難削材 / データマイニング / クラスタリング / 切削条件 / 溝加工 / 小径エンドミル / 難削材料 / 微細加工 / エンドミル加工

Outline of Final Research Achievements

The data-mining methods using hierarchical and non-hierarchical clustering methods to help engineers decide appropriate end-milling conditions were proposed in this study. 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 the K-means method and variable cluster analysis to find tool shape parameters that had a significant relationship with the end-milling conditions listed in the catalog. We used both the principal component analysis and the response surface method to derive end-milling condition by suing significant tool shape parameters obtained by clustering. Milling experiments using a square end mill under two sets of end-milling conditions for difficult-to-cut materials showed that catalog mining can be used to derive guidelines for deciding end-milling conditions.

Research Products

• [Journal Article] Aiding of Micro End-Milling Condition Decision Using Data-Mining from Tool Catalog Data (2018)
  • Author(s): Hiroyuki Kodama, Koichi Okuda, and Kazuhiro Tanaka
  • Journal Title: International Journal of Automation Technology Volume: 12 Issue: 2 Pages: 238-245
  • DOI: 10.20965/ijat.2018.p0238
  • NAID: 130007505929
  • ISSN: 1881-7629, 1883-8022
  • Year and Date: 2018-03-05
  • Peer Reviewed
• [Journal Article] Chip Formation during Precision Cutting of Metallic Glass (2015)
  • Author(s): Hiroyuki Kodama, Koichi Okuda, and Tsukasa Inada
  • Journal Title: Advanced Materials Research Volume: 1136 Pages: 265-270
  • DOI: 10.4028/www.scientific.net/amr.1136.265
  • Peer Reviewed / Int'l Joint Research
• [Journal Article] An Experimental Study on Slotting of Inconel 718 Thin Sheet (2015)
  • Author(s): Hiroyuki Kodama, Koichi Okuda and Tomoya Hayase
  • Journal Title: Journal of Mechanics Engineering and Automation Volume: 5 Issue: 11 Pages: 601-608
  • DOI: 10.17265/2159-5275/2015.11.002
  • Peer Reviewed / Open Access / Int'l Joint Research
• [Presentation] Using Catalog Data Mining in Support of Determining Micro End-milling Conditions (2016)
  • Author(s): 児玉紘幸
  • Organizer: ISFA2016 International Symposium on Flexible Automation
  • Place of Presentation: Cleveland, Ohio
  • Year and Date: 2016-08-01
  • Int'l Joint Research
• [Presentation] Decision Methodology of Micro end-milling Condition Using Tool Catalog Data-Mining System (2016)
  • Author(s): 児玉紘幸
  • Organizer: euspen’s 16th International Conference & Exhibition
  • Place of Presentation: Nottingham, UK
  • Year and Date: 2016-05-30
  • Int'l Joint Research
• [Presentation] 工具カタログマイニングによるエンドミル切削条件の決定支援システム (2015)
  • Author(s): 児玉紘幸
  • Organizer: 産学交流研究シーズ発表会
  • Place of Presentation: あましんアルカイックホール・オクト（兵庫県尼崎市）
  • Year and Date: 2015-10-15
  • Invited
• [Presentation] 工具カタログデータマイニング手法を適用した難削材加工用の切削条件決定支援システム (2015)
  • Author(s): 児玉紘幸，奥田孝一，布引雅之
  • Organizer: 2015年度精密工学会秋季大会
  • Place of Presentation: 東北大学（宮城県仙台市）
  • Year and Date: 2015-09-04
  • Int'l Joint Research