Sensor-assisted method for on-line flank wear estimation in turning processes

Sagar V. Kamarthi; Soundar R.T. Kumara; Paul H. Cohen

Sensor-assisted method for on-line flank wear estimation in turning processes

Sagar V. Kamarthi, Soundar R.T. Kumara, Paul H. Cohen

Research output: Contribution to conference › Paper › peer-review

Abstract

This paper describes a sensor-assisted method for on-line flank wear estimation in turning processes. This method, unlike most of the existing ones, predicts continually the gradually increasing flank wear on a cutting tool. This method is tested on individual as well as different combinations of force, vibration, and acoustic emission sensors. The performance of the flank wear estimation method is studied by conducting extensive turning experiments on AISI 6150 steel workpiece and K68 (C2) grade uncoated carbide inserts. The average percent flank wear estimation error for different sensor combinations, for the range of operating conditions that were used during neural network training, is between -0.91% and 12.97%. The results indicate that the proposed estimation method provides flank wear estimates good enough for most real-world turning processes.

Original language	English (US)
Pages	461-466
Number of pages	6
State	Published - 1997
Event	Proceedings of the 1997 6th Annual Industrial Engineering Research Conference, IERC - Miami Beach, FL, USA Duration: May 17 1997 → May 18 1997

Other

Other	Proceedings of the 1997 6th Annual Industrial Engineering Research Conference, IERC
City	Miami Beach, FL, USA
Period	5/17/97 → 5/18/97

All Science Journal Classification (ASJC) codes

Industrial and Manufacturing Engineering

Cite this

@conference{d2fb156c6416437a9b430f7cd941a3ab,

title = "Sensor-assisted method for on-line flank wear estimation in turning processes",

abstract = "This paper describes a sensor-assisted method for on-line flank wear estimation in turning processes. This method, unlike most of the existing ones, predicts continually the gradually increasing flank wear on a cutting tool. This method is tested on individual as well as different combinations of force, vibration, and acoustic emission sensors. The performance of the flank wear estimation method is studied by conducting extensive turning experiments on AISI 6150 steel workpiece and K68 (C2) grade uncoated carbide inserts. The average percent flank wear estimation error for different sensor combinations, for the range of operating conditions that were used during neural network training, is between -0.91% and 12.97%. The results indicate that the proposed estimation method provides flank wear estimates good enough for most real-world turning processes.",

author = "Kamarthi, {Sagar V.} and Kumara, {Soundar R.T.} and Cohen, {Paul H.}",

year = "1997",

language = "English (US)",

pages = "461--466",

note = "Proceedings of the 1997 6th Annual Industrial Engineering Research Conference, IERC ; Conference date: 17-05-1997 Through 18-05-1997",

}

TY - CONF

T1 - Sensor-assisted method for on-line flank wear estimation in turning processes

AU - Kamarthi, Sagar V.

AU - Kumara, Soundar R.T.

AU - Cohen, Paul H.

PY - 1997

Y1 - 1997

N2 - This paper describes a sensor-assisted method for on-line flank wear estimation in turning processes. This method, unlike most of the existing ones, predicts continually the gradually increasing flank wear on a cutting tool. This method is tested on individual as well as different combinations of force, vibration, and acoustic emission sensors. The performance of the flank wear estimation method is studied by conducting extensive turning experiments on AISI 6150 steel workpiece and K68 (C2) grade uncoated carbide inserts. The average percent flank wear estimation error for different sensor combinations, for the range of operating conditions that were used during neural network training, is between -0.91% and 12.97%. The results indicate that the proposed estimation method provides flank wear estimates good enough for most real-world turning processes.

AB - This paper describes a sensor-assisted method for on-line flank wear estimation in turning processes. This method, unlike most of the existing ones, predicts continually the gradually increasing flank wear on a cutting tool. This method is tested on individual as well as different combinations of force, vibration, and acoustic emission sensors. The performance of the flank wear estimation method is studied by conducting extensive turning experiments on AISI 6150 steel workpiece and K68 (C2) grade uncoated carbide inserts. The average percent flank wear estimation error for different sensor combinations, for the range of operating conditions that were used during neural network training, is between -0.91% and 12.97%. The results indicate that the proposed estimation method provides flank wear estimates good enough for most real-world turning processes.

UR - http://www.scopus.com/inward/record.url?scp=0031367994&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031367994&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0031367994

SP - 461

EP - 466

T2 - Proceedings of the 1997 6th Annual Industrial Engineering Research Conference, IERC

Y2 - 17 May 1997 through 18 May 1997

ER -

Sensor-assisted method for on-line flank wear estimation in turning processes

Abstract

Other

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this