Forward and reverse mappings in green sand mould system using neural networks

2008 ◽  
Vol 8 (1) ◽  
pp. 239-260 ◽  
Author(s):  
Mahesh B. Parappagoudar ◽  
D.K. Pratihar ◽  
G.L. Datta
Keyword(s):  
Neural Networks ◽  
Green Sand ◽  
Sand Mould ◽  
Green Sand Mould System

scholarly journals Estimation of Permeability of Green Sand Mould by Performing Sensitivity Analysis on Neural Networks Model

2014 ◽  
Vol 34 (3) ◽  
pp. 107-111 ◽  
Author(s):  
N. Subba Reddy ◽  
Yong-Hyun Baek ◽  
Seong-Gyeong Kim ◽  
Bo Young Hur
Keyword(s):  
Neural Networks ◽  
Sensitivity Analysis ◽  
Green Sand ◽  
Sand Mould

Reverse Modeling of Green Sand Mould System Using Fuzzy Logic-Based Approaches

2012 ◽  
Vol 12 (1) ◽  
pp. 1-16
Author(s):  
B. Surekha ◽  
Pandu R. Vundavilli ◽  
M. B. Parappagoudar
Keyword(s):  
Fuzzy Logic ◽  
Real Time Control ◽  
Green Sand ◽  
Time Control ◽  
System A ◽  
Sand Mould ◽  
Input Variables ◽  
Green Sand Mould System ◽  
Reverse Mapping

AbstractIn the present study, reverse mapping problems of green sand mould system have been solved using Fuzzy Logic (FL)-based approaches. It is a complicated process, in which the quality of the castings is influenced by the mould properties (that is, green compression strength, permeability, hardness and others). In forward modeling, the outputs are expressed as the functions of input variables, whereas in reverse modeling, the later are represented as the functions of the former. The main advantage of reverse modeling lies in the fact that it helps in effective real-time control of the process. This paper proposes three different FL-based approaches for the reverse modeling of the green sand mould system. A binary-coded Genetic Algorithm (GA) has been used to optimize the knowledge base of the FL-based approaches, off-line. The developed approaches are found to solve the above problem effectively, and the performances of the developed approaches are compared among themselves. It has been observed that the approach “Automatic design of FL system using GA” yielded much better results in predicting a set of input variables from the set of known set of output.

Sign in / Sign up

Export Citation Format

Share Document