Back propagation genetic and recurrent neural network applications in modelling and analysis of squeeze casting process

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

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Today, in competitive manufacturing environment reducing casting defects with improved mechanical properties is of industrial relevance. This led the present work to deal with developing the input-output relationship in squeeze casting process utilizing the neural network based forward and reverse mapping. Forward mapping is aimed to predict the casting quality (such as density, hardness and secondary dendrite arm spacing) for the known combination of casting variables (that is, squeeze pressure, pressure duration, die and pouring temperature). Conversely, attempt is also made to determine the appropriate set of casting variables for the required casting quality (that is, reverse mapping). Forward and reverse mapping tasks are carried out utilizing back propagation, recurrent and genetic algorithm tuned neural networks. Parameter study has been conducted to adjust and optimize the neural network parameters utilizing the batch mode of training. Since, batch mode of training requires huge data, the training data is generated artificially using response equations. Furthermore, neural network prediction performances are compared among themselves (reverse mapping) and with those of statistical regression models (forward mapping) with the help of test cases. The results shown all developed neural network models in both forward and reverse mappings are capable of making effective predictions. The results obtained will help the foundry personnel to automate and précised control of squeeze casting process.

Original languageEnglish
Pages (from-to)418-437
Number of pages20
JournalApplied Soft Computing Journal
Volume59
DOIs
Publication statusPublished - 01-10-2017

Fingerprint

Squeeze casting
Recurrent neural networks
Backpropagation
Casting
Neural networks
Foundries
Genetic algorithms
Hardness
Personnel
Mechanical properties
Defects

All Science Journal Classification (ASJC) codes

  • Software

Cite this

@article{6cc812e7b49b46a9957c7bef9176e70d,
title = "Back propagation genetic and recurrent neural network applications in modelling and analysis of squeeze casting process",
abstract = "Today, in competitive manufacturing environment reducing casting defects with improved mechanical properties is of industrial relevance. This led the present work to deal with developing the input-output relationship in squeeze casting process utilizing the neural network based forward and reverse mapping. Forward mapping is aimed to predict the casting quality (such as density, hardness and secondary dendrite arm spacing) for the known combination of casting variables (that is, squeeze pressure, pressure duration, die and pouring temperature). Conversely, attempt is also made to determine the appropriate set of casting variables for the required casting quality (that is, reverse mapping). Forward and reverse mapping tasks are carried out utilizing back propagation, recurrent and genetic algorithm tuned neural networks. Parameter study has been conducted to adjust and optimize the neural network parameters utilizing the batch mode of training. Since, batch mode of training requires huge data, the training data is generated artificially using response equations. Furthermore, neural network prediction performances are compared among themselves (reverse mapping) and with those of statistical regression models (forward mapping) with the help of test cases. The results shown all developed neural network models in both forward and reverse mappings are capable of making effective predictions. The results obtained will help the foundry personnel to automate and pr{\'e}cised control of squeeze casting process.",
author = "{Patel G.C}, Manjunath and Shettigar, {Arun Kumar} and Prasad Krishna and Parappagoudar, {Mahesh B.}",
year = "2017",
month = "10",
day = "1",
doi = "10.1016/j.asoc.2017.06.018",
language = "English",
volume = "59",
pages = "418--437",
journal = "Applied Soft Computing",
issn = "1568-4946",
publisher = "Elsevier BV",

}

Back propagation genetic and recurrent neural network applications in modelling and analysis of squeeze casting process. / Patel G.C, Manjunath; Shettigar, Arun Kumar; Krishna, Prasad; Parappagoudar, Mahesh B.

In: Applied Soft Computing Journal, Vol. 59, 01.10.2017, p. 418-437.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Back propagation genetic and recurrent neural network applications in modelling and analysis of squeeze casting process

AU - Patel G.C, Manjunath

AU - Shettigar, Arun Kumar

AU - Krishna, Prasad

AU - Parappagoudar, Mahesh B.

PY - 2017/10/1

Y1 - 2017/10/1

N2 - Today, in competitive manufacturing environment reducing casting defects with improved mechanical properties is of industrial relevance. This led the present work to deal with developing the input-output relationship in squeeze casting process utilizing the neural network based forward and reverse mapping. Forward mapping is aimed to predict the casting quality (such as density, hardness and secondary dendrite arm spacing) for the known combination of casting variables (that is, squeeze pressure, pressure duration, die and pouring temperature). Conversely, attempt is also made to determine the appropriate set of casting variables for the required casting quality (that is, reverse mapping). Forward and reverse mapping tasks are carried out utilizing back propagation, recurrent and genetic algorithm tuned neural networks. Parameter study has been conducted to adjust and optimize the neural network parameters utilizing the batch mode of training. Since, batch mode of training requires huge data, the training data is generated artificially using response equations. Furthermore, neural network prediction performances are compared among themselves (reverse mapping) and with those of statistical regression models (forward mapping) with the help of test cases. The results shown all developed neural network models in both forward and reverse mappings are capable of making effective predictions. The results obtained will help the foundry personnel to automate and précised control of squeeze casting process.

AB - Today, in competitive manufacturing environment reducing casting defects with improved mechanical properties is of industrial relevance. This led the present work to deal with developing the input-output relationship in squeeze casting process utilizing the neural network based forward and reverse mapping. Forward mapping is aimed to predict the casting quality (such as density, hardness and secondary dendrite arm spacing) for the known combination of casting variables (that is, squeeze pressure, pressure duration, die and pouring temperature). Conversely, attempt is also made to determine the appropriate set of casting variables for the required casting quality (that is, reverse mapping). Forward and reverse mapping tasks are carried out utilizing back propagation, recurrent and genetic algorithm tuned neural networks. Parameter study has been conducted to adjust and optimize the neural network parameters utilizing the batch mode of training. Since, batch mode of training requires huge data, the training data is generated artificially using response equations. Furthermore, neural network prediction performances are compared among themselves (reverse mapping) and with those of statistical regression models (forward mapping) with the help of test cases. The results shown all developed neural network models in both forward and reverse mappings are capable of making effective predictions. The results obtained will help the foundry personnel to automate and précised control of squeeze casting process.

UR - http://www.scopus.com/inward/record.url?scp=85020881605&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85020881605&partnerID=8YFLogxK

U2 - 10.1016/j.asoc.2017.06.018

DO - 10.1016/j.asoc.2017.06.018

M3 - Article

VL - 59

SP - 418

EP - 437

JO - Applied Soft Computing

JF - Applied Soft Computing

SN - 1568-4946

ER -