Reducing overfitting in manufacturing process modeling using a backward elimination based genetic programming

Genetic programming (GP) has demonstrated as an effective approach in polynomial modeling of manufacturing processes. However, polynomial models with redundant terms generated by GP may depict overfitting, while the developed models have good accuracy on trained data sets but relatively poor accurac...

Full description

Bibliographic Details
Main Authors: Chan, Kit Yan, Kwong, C., Dillon, Tharam S., Tsim, Y.
Format: Journal Article
Published: Elsevier 2010
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/10336
_version_ 1848746204946497536
author Chan, Kit Yan
Kwong, C.
Dillon, Tharam S.
Tsim, Y.
author_facet Chan, Kit Yan
Kwong, C.
Dillon, Tharam S.
Tsim, Y.
author_sort Chan, Kit Yan
building Curtin Institutional Repository
collection Online Access
description Genetic programming (GP) has demonstrated as an effective approach in polynomial modeling of manufacturing processes. However, polynomial models with redundant terms generated by GP may depict overfitting, while the developed models have good accuracy on trained data sets but relatively poor accuracy on testing data sets. In the literature, approaches of avoiding overfitting in GP are handled by limiting the number of terms in polynomial models. However, those approaches cannot guarantee terms in polynomial models produced by GP are statistically significant to manufacturing processes. In this paper, a statistical method, backward elimination (BE), is proposed to incorporate with GP, in order to eliminate insignificant terms in polynomial models. The performance of the proposed GP has been evaluated by modeling three real-world manufacturing processes, epoxy dispenser for electronic packaging, solder paste dispenser for electronic manufacturing, and punch press system for leadframe downset in IC packaging. Empirical results show that insignificant terms in the polynomial models can be eliminated by the proposed GP and also the polynomial models generated by the proposed GP can achieve results with better predictions than the other commonly used existent methods, which are commonly used in GP for avoiding overfitting in polynomial modeling.
first_indexed 2025-11-14T06:29:33Z
format Journal Article
id curtin-20.500.11937-10336
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T06:29:33Z
publishDate 2010
publisher Elsevier
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-103362018-03-29T09:05:56Z Reducing overfitting in manufacturing process modeling using a backward elimination based genetic programming Chan, Kit Yan Kwong, C. Dillon, Tharam S. Tsim, Y. Genetic programming Polynomial modeling Overfitting Process modeling Genetic programming (GP) has demonstrated as an effective approach in polynomial modeling of manufacturing processes. However, polynomial models with redundant terms generated by GP may depict overfitting, while the developed models have good accuracy on trained data sets but relatively poor accuracy on testing data sets. In the literature, approaches of avoiding overfitting in GP are handled by limiting the number of terms in polynomial models. However, those approaches cannot guarantee terms in polynomial models produced by GP are statistically significant to manufacturing processes. In this paper, a statistical method, backward elimination (BE), is proposed to incorporate with GP, in order to eliminate insignificant terms in polynomial models. The performance of the proposed GP has been evaluated by modeling three real-world manufacturing processes, epoxy dispenser for electronic packaging, solder paste dispenser for electronic manufacturing, and punch press system for leadframe downset in IC packaging. Empirical results show that insignificant terms in the polynomial models can be eliminated by the proposed GP and also the polynomial models generated by the proposed GP can achieve results with better predictions than the other commonly used existent methods, which are commonly used in GP for avoiding overfitting in polynomial modeling. 2010 Journal Article http://hdl.handle.net/20.500.11937/10336 10.1016/j.asoc.2010.04.022 Elsevier restricted
spellingShingle Genetic programming
Polynomial modeling
Overfitting
Process modeling
Chan, Kit Yan
Kwong, C.
Dillon, Tharam S.
Tsim, Y.
Reducing overfitting in manufacturing process modeling using a backward elimination based genetic programming
title Reducing overfitting in manufacturing process modeling using a backward elimination based genetic programming
title_full Reducing overfitting in manufacturing process modeling using a backward elimination based genetic programming
title_fullStr Reducing overfitting in manufacturing process modeling using a backward elimination based genetic programming
title_full_unstemmed Reducing overfitting in manufacturing process modeling using a backward elimination based genetic programming
title_short Reducing overfitting in manufacturing process modeling using a backward elimination based genetic programming
title_sort reducing overfitting in manufacturing process modeling using a backward elimination based genetic programming
topic Genetic programming
Polynomial modeling
Overfitting
Process modeling
url http://hdl.handle.net/20.500.11937/10336