Diagnosis of tapping operations using an AI approach

Author

Liu, I. ; Ko, E.J. ; Sha, S.L.

Author_Institution

Dept. of Mech. Eng., California State Univ., Sacramento, CA, USA

fYear

1991

fDate

9-11 Apr 1991

Firstpage

1556

Abstract

An artificial neural network was utilized for the diagnosis of tapping operations. The input vector for the neural network is obtained by processing the signals of the thrust, torque, and lateral forces during the tapping operations. A total of ten indices was used in the input layer of the network. The output of the artificial neural network provides the tapping states. Five different tapping states were investigated: normal operation, tap wear, misalignment, oversize hole, and undersize hole. Experimental results showed that diagnosis of tapping operations through an artificial neural network can reach a success rate of over 95%

Keywords

computerised signal processing; fault location; mechanical engineering computing; neural nets; artificial intelligence; computerised signal processing; input vector; lateral forces; mechanical engineering computing; misalignment; neural network; oversize hole; tap wear; tapping operations diagnosis; thrust; torque; undersize hole; Artificial intelligence; Artificial neural networks; Biological neural networks; Feedforward neural networks; Manufacturing; Mechanical engineering; Neural networks; Signal processing; Torque; Yarn;

fLanguage

English

Publisher

ieee

Conference_Titel

Robotics and Automation, 1991. Proceedings., 1991 IEEE International Conference on

Conference_Location

Sacramento, CA

Print_ISBN

0-8186-2163-X

Type

conf

DOI

10.1109/ROBOT.1991.131838

Filename

131838