Paper Info
Title
An Improved Multi-Gene Genetic Programming Approach for the Evolution of Generalized Model in Modelling of Rapid Prototyping Process.
Abstract
The Rapid prototyping (RP) processes are widely used for the fabrication of complex shaped functional prototypes from the 3-D design. Among the various RP processes, fused deposition modeling (FDM) is widely known among researchers. The working mechanism behind the FDM process is governed by multiple input and output variables, which makes this process complex and its implementation costly. Therefore, the highly generalized mathematical models are an alternative for the practical realization of the process. Artificial intelligence methods such as multi-gene genetic programming (MGGP), artificial neural network and support vector regression can be used. Among these methods, MGGP evolves explicit models and its coefficients automatically. Since MGGP uses a multiple sets of genes for the formulation of model and is population based, it suffers from the problem of over-fitting. Over-fitting is caused due to inappropriate procedure of formation of MGGP model and the difficulty in model selection. To counter over-fitting, the present paper proposes an improved MGGP (I-MGGP) approach by embedding the statistical and classification algorithms in the paradigm of MGGP. The proposed I-MGGP approach is tested on the wear strength data obtained from the FDM process and results show that the I-MGGP has performed better than the standard MGGP approach. Thus, the I-MGGP model can be deployed by experts for understanding the physical aspects as well as optimizing the performance of the process.
Year
DOI
Venue
2014
10.1007/978-3-319-07455-9_23
Lecture Notes in Computer Science
Keywords
Field
DocType
Wear strength prediction,over-fitting,FDM,Rapid prototyping modeling,FDM modeling
Data mining,Population,Computer science,Support vector machine,Model selection,Input/output,Genetic programming,Artificial intelligence,Overfitting,Statistical classification,Artificial neural network,Machine learning
Conference
Volume
ISSN
Citations 
8481
0302-9743
0
PageRank 
References 
Authors
0.34
8
2
Name
Order
Citations
PageRank
Akhil Garg1214.21
K. Tai217722.25