DocumentCode
394447
Title
Neural network based on-line detection of drill breakage in micro drilling process
Author
Fu, Lianyu ; Ling, Shih-Fu
Author_Institution
Sch. of Mech. & Production Eng., Nanyang Technol. Univ., Singapore
Volume
4
fYear
2002
fDate
18-22 Nov. 2002
Firstpage
2054
Abstract
The breakage of drill bit often occurs in micro drilling process because of the very small drill diameter. So on-line detection of drill breakage plays an important role in micro drilling process. In this paper, a method for the on-line detection of the drill breakage in micro drilling process based on neural network is presented. The characteristic of the drilling torque during the drilling process is studied first. Five features extracted from the drilling torque signal and the drilling conditions are input to a neural network for the detection of the drill breakage. A three-layer backpropagation neural network with five input nodes, ten hidden nodes and one output node is applied here. The results show that the presented neural network based method can effectively detect the drill breakage in micro drilling process.
Keywords
backpropagation; feature extraction; micromachining; multilayer perceptrons; neural nets; online operation; pattern recognition; drill bit breakage; feature extraction; micro drilling process; microdrilling process; online drill breakage detection; three-layer backpropagation neural network; Drilling; Force measurement; Intelligent networks; Machining; Monitoring; Neural networks; Signal detection; Signal processing; Torque measurement; Vibration measurement;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Information Processing, 2002. ICONIP '02. Proceedings of the 9th International Conference on
Print_ISBN
981-04-7524-1
Type
conf
DOI
10.1109/ICONIP.2002.1199036
Filename
1199036
Link To Document