Improving an Inverse Model of Sheet Metal Forming by Neural Network Based Regression
Y. Frayman, B. Rolfe, und G. Webb. Proceedings of the Design Engineering Technical Conferences and Computer and Information in Engineering Conference (DETC'02/ASME 2002), Seite 1-8. New York, ASME Press, (2002)
Zusammenfassung
The inverse model for a sheet metal forming process aims to determine the initial parameter levels required to form the final formed shape. This is a difficult problem that is usually approached by traditional methods such a finite element analysis. Formulating the problem as a classification problem makes is possible to use a well established classification algorithms such as decision trees. The classification is, however, generally based on a winner-takes-all approach when associating the output value with the corresponding class. On the other hand when formulating the problem as a regression task, all the output values are combined to produce the corresponding class value. For a multi-class problem, this may result in very different associations between the output of the model and the corresponding class. Such formulation makes it possible to use a well known regression algorithms such as neural networks.In this paper, we develop a neural network based inverse model of a sheet forming process, and compare its performance with that of a linear model. Both models are used in two modes: classification mode and a function estimation mode to investigate the advantage of re-formulating the problem as function estimation. This results in large improvements in the recognition rate of set-up parameters of a sheet metal forming process for both models, with a neural network model achieving much more accurate parameters recognition than a linear model
%0 Conference Paper
%1 FraymanRolfeWebb02b
%A Frayman, Y
%A Rolfe, B.
%A Webb, G. I.
%B Proceedings of the Design Engineering Technical Conferences and Computer and Information in Engineering Conference (DETC'02/ASME 2002)
%C New York
%D 2002
%I ASME Press
%K Applications Engineering
%P 1-8
%T Improving an Inverse Model of Sheet Metal Forming by Neural Network Based Regression
%X The inverse model for a sheet metal forming process aims to determine the initial parameter levels required to form the final formed shape. This is a difficult problem that is usually approached by traditional methods such a finite element analysis. Formulating the problem as a classification problem makes is possible to use a well established classification algorithms such as decision trees. The classification is, however, generally based on a winner-takes-all approach when associating the output value with the corresponding class. On the other hand when formulating the problem as a regression task, all the output values are combined to produce the corresponding class value. For a multi-class problem, this may result in very different associations between the output of the model and the corresponding class. Such formulation makes it possible to use a well known regression algorithms such as neural networks.In this paper, we develop a neural network based inverse model of a sheet forming process, and compare its performance with that of a linear model. Both models are used in two modes: classification mode and a function estimation mode to investigate the advantage of re-formulating the problem as function estimation. This results in large improvements in the recognition rate of set-up parameters of a sheet metal forming process for both models, with a neural network model achieving much more accurate parameters recognition than a linear model
@inproceedings{FraymanRolfeWebb02b,
abstract = {The inverse model for a sheet metal forming process aims to determine the initial parameter levels required to form the final formed shape. This is a difficult problem that is usually approached by traditional methods such a finite element analysis. Formulating the problem as a classification problem makes is possible to use a well established classification algorithms such as decision trees. The classification is, however, generally based on a winner-takes-all approach when associating the output value with the corresponding class. On the other hand when formulating the problem as a regression task, all the output values are combined to produce the corresponding class value. For a multi-class problem, this may result in very different associations between the output of the model and the corresponding class. Such formulation makes it possible to use a well known regression algorithms such as neural networks.In this paper, we develop a neural network based inverse model of a sheet forming process, and compare its performance with that of a linear model. Both models are used in two modes: classification mode and a function estimation mode to investigate the advantage of re-formulating the problem as function estimation. This results in large improvements in the recognition rate of set-up parameters of a sheet metal forming process for both models, with a neural network model achieving much more accurate parameters recognition than a linear model},
added-at = {2016-03-20T05:42:04.000+0100},
address = {New York},
audit-trail = {*},
author = {Frayman, Y and Rolfe, B. and Webb, G. I.},
biburl = {https://www.bibsonomy.org/bibtex/2076932ab6e403683bb95c49fbc4eb479/giwebb},
booktitle = {Proceedings of the Design Engineering Technical Conferences and Computer and Information in Engineering Conference (DETC'02/ASME 2002)},
interhash = {621af354982f30785d4935dfe3a2cbe0},
intrahash = {076932ab6e403683bb95c49fbc4eb479},
keywords = {Applications Engineering},
pages = {1-8},
publisher = {ASME Press},
timestamp = {2016-03-20T05:42:04.000+0100},
title = {Improving an Inverse Model of Sheet Metal Forming by Neural Network Based Regression},
year = 2002
}