Neural network based signal processing scheme for automatic tool wear recognition

Research output: A Conference proceeding or a Chapter in BookConference contribution

Abstract

Monitoring of components in the manufacturing plants involves the automatic detection and identification of failure events. One of the important machine monitoring problems is the monitoring of tool wear in automatic metal drilling systems. The purpose of tool wear detection systems is to actually track down the wearing process of the machining tool, allowing the estimation of the quality of parts being machined by tool and prediction of the useful life of tools. Conventional methods of detecting the tool wear from processing the sensor measured signals have led to tool wear detection systems which perform well for a given set of machining parameters, but are not capable of meeting performance requirements in real manufacturing operations, where the machining parameters are more varied. This paper reports a automatic tool wear recognition scheme based on neural network technology. This technology provides an improved tool wear recognition alternative because of potential of neural networks to operate in real time mode and to handle data that may be distorted and noisy.

Original languageEnglish
Title of host publicationFourth International Symposium on Signal Processing and its Applications
Place of PublicationBrisbane
Pages533-536
Number of pages4
Volume2
Publication statusPublished - 1996
Externally publishedYes
EventProceedings of the 1996 4th International Symposium on Signal Processing and its Applications, ISSPA'96. Part 2 (of 2) - Gold Coast, Aust
Duration: 25 Aug 199630 Aug 1996

Conference

ConferenceProceedings of the 1996 4th International Symposium on Signal Processing and its Applications, ISSPA'96. Part 2 (of 2)
CityGold Coast, Aust
Period25/08/9630/08/96

Fingerprint

Signal processing
Wear of materials
Neural networks
Machining
Monitoring
Drilling
Sensors
Processing
Metals

Cite this

Chetty, G. (1996). Neural network based signal processing scheme for automatic tool wear recognition. In Fourth International Symposium on Signal Processing and its Applications (Vol. 2, pp. 533-536). Brisbane.
Chetty, Girija. / Neural network based signal processing scheme for automatic tool wear recognition. Fourth International Symposium on Signal Processing and its Applications. Vol. 2 Brisbane, 1996. pp. 533-536
@inproceedings{515d565d9ff142f0b5f69b9130189efb,
title = "Neural network based signal processing scheme for automatic tool wear recognition",
abstract = "Monitoring of components in the manufacturing plants involves the automatic detection and identification of failure events. One of the important machine monitoring problems is the monitoring of tool wear in automatic metal drilling systems. The purpose of tool wear detection systems is to actually track down the wearing process of the machining tool, allowing the estimation of the quality of parts being machined by tool and prediction of the useful life of tools. Conventional methods of detecting the tool wear from processing the sensor measured signals have led to tool wear detection systems which perform well for a given set of machining parameters, but are not capable of meeting performance requirements in real manufacturing operations, where the machining parameters are more varied. This paper reports a automatic tool wear recognition scheme based on neural network technology. This technology provides an improved tool wear recognition alternative because of potential of neural networks to operate in real time mode and to handle data that may be distorted and noisy.",
keywords = "Neural Network",
author = "Girija Chetty",
year = "1996",
language = "English",
isbn = "1864352108",
volume = "2",
pages = "533--536",
booktitle = "Fourth International Symposium on Signal Processing and its Applications",

}

Chetty, G 1996, Neural network based signal processing scheme for automatic tool wear recognition. in Fourth International Symposium on Signal Processing and its Applications. vol. 2, Brisbane, pp. 533-536, Proceedings of the 1996 4th International Symposium on Signal Processing and its Applications, ISSPA'96. Part 2 (of 2), Gold Coast, Aust, 25/08/96.

Neural network based signal processing scheme for automatic tool wear recognition. / Chetty, Girija.

Fourth International Symposium on Signal Processing and its Applications. Vol. 2 Brisbane, 1996. p. 533-536.

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - Neural network based signal processing scheme for automatic tool wear recognition

AU - Chetty, Girija

PY - 1996

Y1 - 1996

N2 - Monitoring of components in the manufacturing plants involves the automatic detection and identification of failure events. One of the important machine monitoring problems is the monitoring of tool wear in automatic metal drilling systems. The purpose of tool wear detection systems is to actually track down the wearing process of the machining tool, allowing the estimation of the quality of parts being machined by tool and prediction of the useful life of tools. Conventional methods of detecting the tool wear from processing the sensor measured signals have led to tool wear detection systems which perform well for a given set of machining parameters, but are not capable of meeting performance requirements in real manufacturing operations, where the machining parameters are more varied. This paper reports a automatic tool wear recognition scheme based on neural network technology. This technology provides an improved tool wear recognition alternative because of potential of neural networks to operate in real time mode and to handle data that may be distorted and noisy.

AB - Monitoring of components in the manufacturing plants involves the automatic detection and identification of failure events. One of the important machine monitoring problems is the monitoring of tool wear in automatic metal drilling systems. The purpose of tool wear detection systems is to actually track down the wearing process of the machining tool, allowing the estimation of the quality of parts being machined by tool and prediction of the useful life of tools. Conventional methods of detecting the tool wear from processing the sensor measured signals have led to tool wear detection systems which perform well for a given set of machining parameters, but are not capable of meeting performance requirements in real manufacturing operations, where the machining parameters are more varied. This paper reports a automatic tool wear recognition scheme based on neural network technology. This technology provides an improved tool wear recognition alternative because of potential of neural networks to operate in real time mode and to handle data that may be distorted and noisy.

KW - Neural Network

UR - http://www.scopus.com/inward/record.url?scp=0030354325&partnerID=8YFLogxK

UR - https://trove.nla.gov.au/version/17237475

M3 - Conference contribution

SN - 1864352108

VL - 2

SP - 533

EP - 536

BT - Fourth International Symposium on Signal Processing and its Applications

CY - Brisbane

ER -

Chetty G. Neural network based signal processing scheme for automatic tool wear recognition. In Fourth International Symposium on Signal Processing and its Applications. Vol. 2. Brisbane. 1996. p. 533-536