engleski

Application of Vibration Signals in Medical Drill Wear Monitoring

Usage of worn drills in medical interventions has highly negative influence on the heat generation which can consequently result in thermal necrosis of bone tissue and prolonged postoperative healing process. Precise real time direct measurement of cutting tool wear level during machining process is not possible. Therefore, the main goal of this study was to identify wear level using indirect monitoring technique based on tool wear features extracted from vibration signals measured during drilling process. Experiment was based on fresh bovine bone samples which were drilled with standard surgical drill used for bone and joint surgery applications. Three drill wear levels in combination with the 12 different machining parameter sets were analyzed. Drill wear features were analyzed using Radial Basis Function Neural Network algorithm with Gaussian activation function. The best overall classification precision regarding all three wear levels was around 79%, while the third and the highest wear level analyzed in this study was exactly classified in 95% of all test samples.

Drilling ; Thermal osteonecrosis ; Vibrations ; Wear modelling

Rad je dobio nagradu "Certificate of Merit for The 2018 IAENG International Conference on Artificial Intelligence and Applications" (http://www.iaeng.org/IMECS2018/Best_paper_awards.html)