A Domain-Aware Federated Learning Study for CNC Tool Wear Estimation

Kaleli I. S., Unal P., Deveci B. U., Albayrak Ö., Ozbayoglu A. M.

20th International Conference on Mobile Web and Intelligent Information Systems, MobiWIS 2024, Vienna, Avusturya, 19 - 21 Ağustos 2024, cilt.14792 LNCS, ss.250-265, (Tam Metin Bildiri) identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası: 14792 LNCS
  • Doi Numarası: 10.1007/978-3-031-68005-2_18
  • Basıldığı Şehir: Vienna
  • Basıldığı Ülke: Avusturya
  • Sayfa Sayıları: ss.250-265
  • Anahtar Kelimeler: condition monitoring, federated learning, Industry 4.0, predictive maintenance, tool wear
  • TED Üniversitesi Adresli: Evet

Özet

This study proposes a cutting tool condition monitoring platform for CNC machines used in metal part manufacturing to estimate tool wear values. The PHM 2010 Dataset, along with operational and situational data from CNC machines and sensors, were analyzed using artificial intelligence algorithms to support total equipment performance with current tool wear values. The innovation lies in developing an artificial intelligence application that incorporates the Federated Learning method with artificial neural networks. This application is among the first to monitor machine cutting tools using Federated Learning. An efficient and accurate predictive tool wear estimation method is presented through the application of Federated Learning with Long-Short Term Memory models. This novel approach holds great potential for industrial applications, optimizing CNC cutting processes and reducing operational costs through enhanced tool wear prediction.