Tool wear and its mechanism in turning aluminum alloys with image processing and machine learning methods

Korkmaz M. E., Gupta M. K., Çelik E., Ross N. S., Günay M.

Tribology International, cilt.191, 2024 (SCI-Expanded) identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 191
  • Basım Tarihi: 2024
  • Doi Numarası: 10.1016/j.triboint.2023.109207
  • Dergi Adı: Tribology International
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Aerospace Database, Applied Science & Technology Source, Chimica, Communication Abstracts, Compendex, INSPEC, Metadex, Civil Engineering Abstracts
  • Anahtar Kelimeler: Aluminum alloy, Image processing, Machine learning, Machining, Tool wear
  • Yıldız Teknik Üniversitesi Adresli: Hayır

Özet

Tool wear is intimately related to intelligent operation and maintenance of automated production, workpiece surface quality, dimension accuracy, and tool life. Therefore, it is necessary to improve the production efficiency and quality by predicting tool wear values. The purpose of this research is to use machine learning and image processing methods in estimating the tool wear values when turning AA7075 aluminum alloy. In addition, the in-depth analysis of cutting tools at different parameters were examined with SEM and EDS analysis. The results shown that there was a 44.40% increase in tool wear when the cutting speed was raised by 100% while feed rates were maintained at the same level. On the other hand, there was a 22.78% increase in tool wear seen when the cutting speed was maintained at the same level. In addition, the difference between the actual values and the image processing model is 3.5%, and the difference between the Multilayer Perception (MLP) model and the linear regression (LR) model is 5% and 7%, respectively.