Pregled bibliografske jedinice broj: 712254
Medical Drill Wear Classification Using Servomotor Drive Signals and Neural Networks
Medical Drill Wear Classification Using Servomotor Drive Signals and Neural Networks // Proceedings of the World Congress on Engineering 2014 Vol I / S. I. Ao, Len Gelman, David WL Hukins, Andrew Hunter and A. M. Korsunsky (ur.).
Hong Kong: Newswood Limited, 2014. (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 712254 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Medical Drill Wear Classification Using Servomotor Drive Signals and Neural Networks
Autori
Staroveški, Tomislav ; Brezak, Danko ; Grđan, Vinko ; Baček, Tomislav
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Proceedings of the World Congress on Engineering 2014 Vol I
/ S. I. Ao, Len Gelman, David WL Hukins, Andrew Hunter and A. M. Korsunsky - Hong Kong : Newswood Limited, 2014
ISBN
978-988-19252-7-5
Skup
World Congress on Engineering - WCE 2014
Mjesto i datum
London, Ujedinjeno Kraljevstvo, 02.07.2014. - 04.07.2014
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
medical drill; wear; thermal osteonecrosis; neural networks; modeling
Sažetak
Medical drills are subject to intensive wear due to the influence of different mechanical, chemical and thermal factors characteristic for drilling and sterilization process. Wear progress increases friction in the cutting zone, which consequently leads to higher temperatures and cutting forces, i.e., possible thermal and mechanical damages of the bone tissue. Therefore, the presented study aimed to analyze the possibility of drill wear monitoring using electric servomotor drive signals and neural network algorithm. Experimental work has been performed with adequately designed testbed machining system and using prepared bovine bone samples. Drill wear features were extracted from time and frequency domain of the process signals, and then analyzed separately and in combinations.
Izvorni jezik
Engleski
Znanstvena područja
Strojarstvo, Kliničke medicinske znanosti
POVEZANOST RADA
Ustanove:
Fakultet strojarstva i brodogradnje, Zagreb