Predictive modelling of surface roughness and kerf widths in abrasive water jet cutting of Kevlar composites using neural network

M. Shukla, P.B. Tambe

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Abrasive water jet cutting (AWJC) is one of the important non-traditional machining processes used for cutting of difficult-to-cut materials and intricate profiles. Cutting of Kevlar fibre reinforced polymer composites is a complex process, making it difficult to model, predict and improve the cut surface quality. This paper presents a detailed approach of the usage and effectiveness of a back-propagation neural network (NN) for modelling and prediction of three cut surface characteristics namely top kerf width, bottom kerf width and surface roughness (Ra) in AWJC of aerospace grade Kevlar-epoxy composites. Statistically designed full factorial experiments based on three process parameters [water jet pressure (WJP), abrasive flow rate (AFR) and quality level (QL)] at three levels each were conducted to generate the NN training database. The results demonstrate that the NN model was able to successfully model and predict the two kerf widths and surface roughness closely matching the experimental results. Copyright © 2010 Inderscience Enterprises Ltd.
Original languageEnglish
Pages (from-to)226-246
Number of pages21
JournalInternational Journal of Machining and Machinability of Materials
Volume8
Issue number1-2
DOIs
Publication statusPublished - 2010
Externally publishedYes

Fingerprint

Abrasives
Surface roughness
Neural networks
Composite materials
Water
Backpropagation
Surface properties
Machining
Flow rate
Fibers
Polymers
Experiments

Bibliographical note

cited By 5

Keywords

  • Abrasive waterjet cutting
  • ANN
  • Artificial Neural Network
  • Epoxy composite
  • Kerf width, Abrasive cutting
  • Abrasives
  • Design of experiments
  • Forecasting
  • Jets
  • Machining
  • Metal analysis
  • Surface properties
  • Surface roughness, Neural networks

Cite this

@article{41472c6c2d5f44ada39715d091d85dd3,
title = "Predictive modelling of surface roughness and kerf widths in abrasive water jet cutting of Kevlar composites using neural network",
abstract = "Abrasive water jet cutting (AWJC) is one of the important non-traditional machining processes used for cutting of difficult-to-cut materials and intricate profiles. Cutting of Kevlar fibre reinforced polymer composites is a complex process, making it difficult to model, predict and improve the cut surface quality. This paper presents a detailed approach of the usage and effectiveness of a back-propagation neural network (NN) for modelling and prediction of three cut surface characteristics namely top kerf width, bottom kerf width and surface roughness (Ra) in AWJC of aerospace grade Kevlar-epoxy composites. Statistically designed full factorial experiments based on three process parameters [water jet pressure (WJP), abrasive flow rate (AFR) and quality level (QL)] at three levels each were conducted to generate the NN training database. The results demonstrate that the NN model was able to successfully model and predict the two kerf widths and surface roughness closely matching the experimental results. Copyright {\circledC} 2010 Inderscience Enterprises Ltd.",
keywords = "Abrasive waterjet cutting, ANN, Artificial Neural Network, Epoxy composite, Kerf width, Abrasive cutting, Abrasives, Design of experiments, Forecasting, Jets, Machining, Metal analysis, Surface properties, Surface roughness, Neural networks",
author = "M. Shukla and P.B. Tambe",
note = "cited By 5",
year = "2010",
doi = "10.1504/IJMMM.2010.034498",
language = "English",
volume = "8",
pages = "226--246",
journal = "International Journal of Machining and Machinability of Materials",
issn = "1748-5711",
publisher = "Inderscience Enterprises Ltd.",
number = "1-2",

}

TY - JOUR

T1 - Predictive modelling of surface roughness and kerf widths in abrasive water jet cutting of Kevlar composites using neural network

AU - Shukla, M.

AU - Tambe, P.B.

N1 - cited By 5

PY - 2010

Y1 - 2010

N2 - Abrasive water jet cutting (AWJC) is one of the important non-traditional machining processes used for cutting of difficult-to-cut materials and intricate profiles. Cutting of Kevlar fibre reinforced polymer composites is a complex process, making it difficult to model, predict and improve the cut surface quality. This paper presents a detailed approach of the usage and effectiveness of a back-propagation neural network (NN) for modelling and prediction of three cut surface characteristics namely top kerf width, bottom kerf width and surface roughness (Ra) in AWJC of aerospace grade Kevlar-epoxy composites. Statistically designed full factorial experiments based on three process parameters [water jet pressure (WJP), abrasive flow rate (AFR) and quality level (QL)] at three levels each were conducted to generate the NN training database. The results demonstrate that the NN model was able to successfully model and predict the two kerf widths and surface roughness closely matching the experimental results. Copyright © 2010 Inderscience Enterprises Ltd.

AB - Abrasive water jet cutting (AWJC) is one of the important non-traditional machining processes used for cutting of difficult-to-cut materials and intricate profiles. Cutting of Kevlar fibre reinforced polymer composites is a complex process, making it difficult to model, predict and improve the cut surface quality. This paper presents a detailed approach of the usage and effectiveness of a back-propagation neural network (NN) for modelling and prediction of three cut surface characteristics namely top kerf width, bottom kerf width and surface roughness (Ra) in AWJC of aerospace grade Kevlar-epoxy composites. Statistically designed full factorial experiments based on three process parameters [water jet pressure (WJP), abrasive flow rate (AFR) and quality level (QL)] at three levels each were conducted to generate the NN training database. The results demonstrate that the NN model was able to successfully model and predict the two kerf widths and surface roughness closely matching the experimental results. Copyright © 2010 Inderscience Enterprises Ltd.

KW - Abrasive waterjet cutting

KW - ANN

KW - Artificial Neural Network

KW - Epoxy composite

KW - Kerf width, Abrasive cutting

KW - Abrasives

KW - Design of experiments

KW - Forecasting

KW - Jets

KW - Machining

KW - Metal analysis

KW - Surface properties

KW - Surface roughness, Neural networks

U2 - 10.1504/IJMMM.2010.034498

DO - 10.1504/IJMMM.2010.034498

M3 - Article

VL - 8

SP - 226

EP - 246

JO - International Journal of Machining and Machinability of Materials

JF - International Journal of Machining and Machinability of Materials

SN - 1748-5711

IS - 1-2

ER -