DocumentCode :
2206882
Title :
Intelligent precision flexible manufacturing system through artificial neural networks and fuzzy modeling
Author :
Kuo, R.J.
Author_Institution :
Nat. Inst. of Technol. Kaohsiung, Tiawan, China
Volume :
1
fYear :
1998
fDate :
4-8 May 1998
Firstpage :
90
Abstract :
Online tool wear estimation plays a very critical role in industrial automation for higher productivity and product quality. In addition, appropriate and timely decision for tool change is required in machining systems. Thus, the paper describes the development of an estimation system through integration of two promising technologies, artificial neural networks (ANN) and fuzzy logic. The proposed system consists of five components: (1) data collection, (2) feature extraction, (3) pattern recognition, (4) multi-sensor integration, and (5) tool/work distance compensation. Physical experiments for a metal cutting process are implemented to evaluate the proposed system. The results showed that the proposed system can significantly increase the accuracy of the product profile
Keywords :
acoustic signal processing; computerised monitoring; cutting; feature extraction; fuzzy logic; fuzzy neural nets; machine tools; machining; process control; self-organising feature maps; sensor fusion; wear; artificial neural networks; data collection; estimation system; feature extraction; fuzzy logic; fuzzy modeling; higher productivity; intelligent precision flexible manufacturing system; machining systems; multi-sensor integration; online tool wear estimation; pattern recognition; product quality; tool change; tool/work distance compensation; Artificial neural networks; Feature extraction; Flexible manufacturing systems; Fuzzy logic; Machinery production industries; Machining; Manufacturing automation; Manufacturing industries; Paper technology; Productivity;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks Proceedings, 1998. IEEE World Congress on Computational Intelligence. The 1998 IEEE International Joint Conference on
Conference_Location :
Anchorage, AK
ISSN :
1098-7576
Print_ISBN :
0-7803-4859-1
Type :
conf
DOI :
10.1109/IJCNN.1998.682242
Filename :
682242
Link To Document :
بازگشت