A systematic approach to model and optimize wear behaviour of castings produced by squeeze casting process

Manjunath Patel G C, Arun Kumar Shettigar, Mahesh B. Parappagoudar

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

The present work is an attempt to produce squeeze cast component with excellent wear resistance property. The material wear rate in squeeze casting depends on appropriate selection of pressure duration, squeeze pressure, die temperature and pouring temperature. Experiments are conducted and data is collected as per central composite and box-behnken design approaches. The input-output relationship developed by utilizing central composite design is found to be statistically adequate and yielded better prediction accuracy. Recurrent and back propagation neural networks are trained by using data generated from best response model. The huge training data in batch mode helps to capture fully the dynamics of squeeze casting process. The recurrent neural network outperformed both, the back propagation neural network and central composite design. Genetic algorithm, desirability function approach, and particle swarm optimization are used to determine best set of squeeze casting conditions that locate the extreme values and will result in minimum wear rate. Particle swarm optimization and genetic algorithm outperformed desirability function approach, as the former carried out search in many directions at multi dimensional space, simultaneously. The results of non-linear regression, neural network based models, the performance of different optimization techniques are compared and some concluding remarks are made.

Original languageEnglish
Pages (from-to)199-212
Number of pages14
JournalJournal of Manufacturing Processes
Volume32
DOIs
Publication statusPublished - 01-04-2018

Fingerprint

Squeeze casting
Wear of materials
Neural networks
Backpropagation
Particle swarm optimization (PSO)
Composite materials
Genetic algorithms
Recurrent neural networks
Wear resistance
Temperature
Castings
Experiments
Particle swarm optimization
Genetic algorithm
Back-propagation neural network

All Science Journal Classification (ASJC) codes

  • Strategy and Management
  • Management Science and Operations Research
  • Industrial and Manufacturing Engineering

Cite this

@article{1a206c1f77b546c1b723ae9ddabf31d0,
title = "A systematic approach to model and optimize wear behaviour of castings produced by squeeze casting process",
abstract = "The present work is an attempt to produce squeeze cast component with excellent wear resistance property. The material wear rate in squeeze casting depends on appropriate selection of pressure duration, squeeze pressure, die temperature and pouring temperature. Experiments are conducted and data is collected as per central composite and box-behnken design approaches. The input-output relationship developed by utilizing central composite design is found to be statistically adequate and yielded better prediction accuracy. Recurrent and back propagation neural networks are trained by using data generated from best response model. The huge training data in batch mode helps to capture fully the dynamics of squeeze casting process. The recurrent neural network outperformed both, the back propagation neural network and central composite design. Genetic algorithm, desirability function approach, and particle swarm optimization are used to determine best set of squeeze casting conditions that locate the extreme values and will result in minimum wear rate. Particle swarm optimization and genetic algorithm outperformed desirability function approach, as the former carried out search in many directions at multi dimensional space, simultaneously. The results of non-linear regression, neural network based models, the performance of different optimization techniques are compared and some concluding remarks are made.",
author = "{Patel G C}, Manjunath and Shettigar, {Arun Kumar} and Parappagoudar, {Mahesh B.}",
year = "2018",
month = "4",
day = "1",
doi = "10.1016/j.jmapro.2018.02.004",
language = "English",
volume = "32",
pages = "199--212",
journal = "Journal of Manufacturing Processes",
issn = "1526-6125",
publisher = "Elsevier BV",

}

A systematic approach to model and optimize wear behaviour of castings produced by squeeze casting process. / Patel G C, Manjunath; Shettigar, Arun Kumar; Parappagoudar, Mahesh B.

In: Journal of Manufacturing Processes, Vol. 32, 01.04.2018, p. 199-212.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A systematic approach to model and optimize wear behaviour of castings produced by squeeze casting process

AU - Patel G C, Manjunath

AU - Shettigar, Arun Kumar

AU - Parappagoudar, Mahesh B.

PY - 2018/4/1

Y1 - 2018/4/1

N2 - The present work is an attempt to produce squeeze cast component with excellent wear resistance property. The material wear rate in squeeze casting depends on appropriate selection of pressure duration, squeeze pressure, die temperature and pouring temperature. Experiments are conducted and data is collected as per central composite and box-behnken design approaches. The input-output relationship developed by utilizing central composite design is found to be statistically adequate and yielded better prediction accuracy. Recurrent and back propagation neural networks are trained by using data generated from best response model. The huge training data in batch mode helps to capture fully the dynamics of squeeze casting process. The recurrent neural network outperformed both, the back propagation neural network and central composite design. Genetic algorithm, desirability function approach, and particle swarm optimization are used to determine best set of squeeze casting conditions that locate the extreme values and will result in minimum wear rate. Particle swarm optimization and genetic algorithm outperformed desirability function approach, as the former carried out search in many directions at multi dimensional space, simultaneously. The results of non-linear regression, neural network based models, the performance of different optimization techniques are compared and some concluding remarks are made.

AB - The present work is an attempt to produce squeeze cast component with excellent wear resistance property. The material wear rate in squeeze casting depends on appropriate selection of pressure duration, squeeze pressure, die temperature and pouring temperature. Experiments are conducted and data is collected as per central composite and box-behnken design approaches. The input-output relationship developed by utilizing central composite design is found to be statistically adequate and yielded better prediction accuracy. Recurrent and back propagation neural networks are trained by using data generated from best response model. The huge training data in batch mode helps to capture fully the dynamics of squeeze casting process. The recurrent neural network outperformed both, the back propagation neural network and central composite design. Genetic algorithm, desirability function approach, and particle swarm optimization are used to determine best set of squeeze casting conditions that locate the extreme values and will result in minimum wear rate. Particle swarm optimization and genetic algorithm outperformed desirability function approach, as the former carried out search in many directions at multi dimensional space, simultaneously. The results of non-linear regression, neural network based models, the performance of different optimization techniques are compared and some concluding remarks are made.

UR - http://www.scopus.com/inward/record.url?scp=85042182551&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85042182551&partnerID=8YFLogxK

U2 - 10.1016/j.jmapro.2018.02.004

DO - 10.1016/j.jmapro.2018.02.004

M3 - Article

VL - 32

SP - 199

EP - 212

JO - Journal of Manufacturing Processes

JF - Journal of Manufacturing Processes

SN - 1526-6125

ER -