Application of fuzzy neural network to laser bending process of sheet metal
Authors: Chen, D.-J.; Xiang, Y.-B.; Wu, S.-C.; Li, M.-Q.
Source: Materials Science and Technology, Volume 18, Number 6, June 2002 , pp. 677-680(4)
Publisher: Maney Publishing
Abstract:The optimisation and selection of process plans is very important for laser bending of sheet metal to achieve the anticipated bending deformation. In this paper, an adaptive fuzzy neural network has been proposed to predict the bending deformation. This network integrates the learning power of neural networks with fuzzy inference systems. During the establishing process of the energy density (composed of three process parameters: laser power, scanning velocity, and spot diameter), width, thickness of sheet, and scanning path curvature were taken as four input variables of the network. The gradient descent learning algorithm was applied to optimally adjust the weight coefficients of the neural network and the parameters of the fuzzy membership functions. Then, the trained network was used to predict the laser bending deformation. Good correlation was found between the predictive and experimental results.
Document Type: Research Article
Publication date: 2002-06-01
- Materials Science and Technology is Journal of the Month in November. This means free online access to all of the last 3 years of content, including the most recently published 2013 articles! Find out more here
In 1985 Metal Science was incorporated into Material Science and Technology: See issues of Metal Science from 1985 to present. The archive also includes the complete run of Metals Technology (1974–84): Click here to see these issues.
- Editorial Board
- Information for Authors
- Subscribe to this Title
- Terms & Conditions
- Online submission site
- ingentaconnect is not responsible for the content or availability of external websites