Modeling of spring-back in V-die bending process by using fuzzy learning back-propagation algorithm

► Spring-back is one of the most sensitive features of sheet metal forming processes. ► Process parameters are sheet thickness, sheet orientation and punch tip radius. ► A new fuzzy learning back-propagation (FLBP) algorithm developed to predict the spring-back using the data generated based on expe...

Full description

Saved in:
Bibliographic Details
Published in:Expert systems with applications 2011-07, Vol.38 (7), p.8894-8900
Main Authors: Baseri, H., Bakhshi-Jooybari, M., Rahmani, B.
Format: Article
Language:English
Subjects:
Algorithms
Back propagation
Elastic recovery
Fuzzy
Fuzzy learning
Fuzzy logic
Fuzzy set theory
Learning
Mathematical models
Neural network
Spring-back
V-die bending
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:► Spring-back is one of the most sensitive features of sheet metal forming processes. ► Process parameters are sheet thickness, sheet orientation and punch tip radius. ► A new fuzzy learning back-propagation (FLBP) algorithm developed to predict the spring-back using the data generated based on experimental observations. ► Performance of the FLBP compared with those of the constant learning rate back-propagation (CLBP) and the variable learning rate back-propagation (VLBP) algorithms. ► Results indicated that the FLBP algorithm has a best performance with respect to the other algorithms. Spring-back is one of the most sensitive features of sheet metal forming processes, which is due to the elastic recovery during unloading and leads to some geometric changes in the product. Three parameters which are most influential on spring-back in V-die bending process are sheet thickness, sheet orientation and punch tip radius. In this research, a new fuzzy learning back-propagation (FLBP) algorithm is proposed to predict the spring-back using the data generated based on experimental observations. The performance of the model in training and testing is compared with those of the constant learning rate back-propagation (CLBP) and the variable learning rate back-propagation (VLBP) algorithms. Then the best model with the minimum mean absolute error (MAE) is selected to predict the spring-back. The results indicated that the proposed FLBP algorithm has best performance in prediction of the spring-back with respect to the other algorithms.
ISSN:0957-4174
1873-6793
DOI:10.1016/j.eswa.2011.01.102