Detecting chatter and estimating wear from the torque of end milling signals by using Index Based Reasoner (IBR)

Tansel, BÜLENT; Li, M.; Demetgul, M.; Bickraj, K.; Kaya, B.; Ozcelik, B.

doi:10.1007/s00170-010-2838-5

Detecting chatter and estimating wear from the torque of end milling signals by using Index Based Reasoner (IBR)

Atıf İçin Kopyala

Tansel I. N., Li M., Demetgul M., Bickraj K., Kaya B., Ozcelik B.

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, cilt.58, ss.109-118, 2012 (SCI-Expanded)

Yayın Türü: Makale / Tam Makale
Cilt numarası: 58
Basım Tarihi: 2012
Doi Numarası: 10.1007/s00170-010-2838-5
Dergi Adı: INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
Sayfa Sayıları: ss.109-118
Erciyes Üniversitesi Adresli: Hayır

Özet

Index Based Reasoning (IBR) is proposed for chatter detection and tool wear estimation by using the torque signal data of rotary dynamometers during the end milling operation. The IBR is a simple reasoner which classifies the incoming signals with the help of lookup table after the most descriptive features are identified with pre-processing. Easy implementation, selection of programming or self-learning modes depending on the characteristics of the application, and capability of distributing the smart nodes to physically separated locations make the IBR a good candidate for diagnostic of manufacturing processes either at the tool, machine, and work cell level. For chatter detection, programming mode was used for preparation of the lookup table. For wear estimation, lookup table was automatically generated from very limited training cases (only three) by detecting the trend. The IBR performed well on the experimentally collected data.