Prediction of Workpiece Surface Roughness Using Soft Computing

B. Samanta; W. Erevelles; Y. Omurtag

doi:10.1016/B978-008045157-2/50063-8

Prediction of Workpiece Surface Roughness Using Soft Computing

B. Samanta, W. Erevelles, Y. Omurtag

Manufacturing Engineering

Research output: Contribution to book or proceeding › Chapter › peer-review

4 Scopus citations

Abstract

Surface roughness is widely used as an index of product quality in finish machining processes. This chapter presents a study to model surface roughness in end milling using adaptive neuro-fuzzy inference system (ANFIS).The machining parameters, namely, the spindle speed, feed rate, and depth of cut are used as inputs to model the workpiece surface roughness. The parameters of membership functions (MFs) are tuned using the training data in ANFIS maximizing the modeling accuracy. The trained ANFIS are tested using the set of validation data. The effects of different machining parameters and number of MFs on the prediction accuracy are then studied. The procedure is illustrated using the experimental data of end-milling 6061 aluminum alloy. Finally, results are compared with artificial neural network (ANN) and previously published results. These results show the effectiveness of the proposed approach in modeling the surface roughness. © 2006

Original language	English
Title of host publication	Intelligent Production Machines and Systems - 2nd I*PROMS Virtual International Conference 3-14 July 2006
Publisher	Elsevier Ltd
Pages	344-349
Number of pages	6
ISBN (Print)	9780080451572
DOIs	https://doi.org/10.1016/B978-008045157-2/50063-8
State	Published - 2006

Access to Document

10.1016/B978-008045157-2/50063-8

Cite this

@inbook{6974cb3abf954710a30c42267dd46782,

title = "Prediction of Workpiece Surface Roughness Using Soft Computing",

abstract = "Surface roughness is widely used as an index of product quality in finish machining processes. This chapter presents a study to model surface roughness in end milling using adaptive neuro-fuzzy inference system (ANFIS).The machining parameters, namely, the spindle speed, feed rate, and depth of cut are used as inputs to model the workpiece surface roughness. The parameters of membership functions (MFs) are tuned using the training data in ANFIS maximizing the modeling accuracy. The trained ANFIS are tested using the set of validation data. The effects of different machining parameters and number of MFs on the prediction accuracy are then studied. The procedure is illustrated using the experimental data of end-milling 6061 aluminum alloy. Finally, results are compared with artificial neural network (ANN) and previously published results. These results show the effectiveness of the proposed approach in modeling the surface roughness. {\textcopyright} 2006",

author = "B. Samanta and W. Erevelles and Y. Omurtag",

year = "2006",

doi = "10.1016/B978-008045157-2/50063-8",

language = "English",

isbn = "9780080451572",

pages = "344--349",

booktitle = "Intelligent Production Machines and Systems - 2nd I*PROMS Virtual International Conference 3-14 July 2006",

publisher = "Elsevier Ltd",

address = "United Kingdom",

}

TY - CHAP

T1 - Prediction of Workpiece Surface Roughness Using Soft Computing

AU - Samanta, B.

AU - Erevelles, W.

AU - Omurtag, Y.

PY - 2006

Y1 - 2006

N2 - Surface roughness is widely used as an index of product quality in finish machining processes. This chapter presents a study to model surface roughness in end milling using adaptive neuro-fuzzy inference system (ANFIS).The machining parameters, namely, the spindle speed, feed rate, and depth of cut are used as inputs to model the workpiece surface roughness. The parameters of membership functions (MFs) are tuned using the training data in ANFIS maximizing the modeling accuracy. The trained ANFIS are tested using the set of validation data. The effects of different machining parameters and number of MFs on the prediction accuracy are then studied. The procedure is illustrated using the experimental data of end-milling 6061 aluminum alloy. Finally, results are compared with artificial neural network (ANN) and previously published results. These results show the effectiveness of the proposed approach in modeling the surface roughness. © 2006

AB - Surface roughness is widely used as an index of product quality in finish machining processes. This chapter presents a study to model surface roughness in end milling using adaptive neuro-fuzzy inference system (ANFIS).The machining parameters, namely, the spindle speed, feed rate, and depth of cut are used as inputs to model the workpiece surface roughness. The parameters of membership functions (MFs) are tuned using the training data in ANFIS maximizing the modeling accuracy. The trained ANFIS are tested using the set of validation data. The effects of different machining parameters and number of MFs on the prediction accuracy are then studied. The procedure is illustrated using the experimental data of end-milling 6061 aluminum alloy. Finally, results are compared with artificial neural network (ANN) and previously published results. These results show the effectiveness of the proposed approach in modeling the surface roughness. © 2006

UR - http://www.scopus.com/inward/record.url?scp=56149094553&partnerID=8YFLogxK

U2 - 10.1016/B978-008045157-2/50063-8

DO - 10.1016/B978-008045157-2/50063-8

M3 - Chapter

AN - SCOPUS:56149094553

SN - 9780080451572

SP - 344

EP - 349

BT - Intelligent Production Machines and Systems - 2nd I*PROMS Virtual International Conference 3-14 July 2006

PB - Elsevier Ltd

ER -

Prediction of Workpiece Surface Roughness Using Soft Computing

Abstract

Access to Document

Other files and links

Fingerprint

Cite this