Paper Title:
Using Artificial Neural Networks in Investigations on the Effects of Ultrasonic Vibrations on the Extrusion Process
  Abstract

Neural Networks are powerful data modeling tools that are capable of capturing and representing complex input/output relationships. The motivation for the development of neural network technology stemmed from the desire to develop an artificial system that could perform "intelligent" tasks similar to those performed by the human brain. Using artificial neural network in approximating of complex data is one of easy way to save time and cost. Ultrasonic vibrations can be applied on the die during the extrusion process. Numerical and experimental analyses have been already performed in the literature on the application of ultrasonic vibrations on the wire drawing, deep drawing, upsetting and rolling processes. No attempts have been made to investigate on the effects of ultrasonic vibrations on the forward extrusion process, yet. A detailed analysis and understanding of the mechanism of improvement is not possible on the basis of conventional experimental observations because ultrasonic vibration processing phenomenon occur at high speeds. Hence, in order to progress the perceptive of the mechanism of ultrasonic vibration extrusion, the finite element analysis was performed by using the explicit analysis procedure. The proposed approach builds on a comprehensive Neuro-Finite Element simulation of the effects of ultrasonic vibration on the forward extrusion. Then use the resulting data to train a Multi-Layer Perceptron (MLP) Neural Network which would predict –accurately enough- those quantities throughout the speeds, vibration amplitudes and frequencies, friction factors and reductions body for any given input vector. The resulting neural simulator is intended to replace the computationally expensive cost-function evaluators that are traditionally used in numerical optimization algorithms. To demonstrate the applicability of the proposed approach, we examine data from FEM as from training with together ultrasonic vibration using the constructed neural simulator and present the results.

  Info
Periodical
Edited by
Zhou Mark
Pages
103-108
DOI
10.4028/www.scientific.net/AMM.52-54.103
Citation
K. Pazand, H. Feizi, "Using Artificial Neural Networks in Investigations on the Effects of Ultrasonic Vibrations on the Extrusion Process", Applied Mechanics and Materials, Vols. 52-54, pp. 103-108, 2011
Online since
March 2011
Export
Price
$32.00
Share

In order to see related information, you need to Login.

In order to see related information, you need to Login.

Authors: Jung Min Lee, Byung Min Kim, Chung Gil Kang
487
Authors: A. Krishnaiah, K. Kumaran, Chakkingal Uday
Abstract:Equal channel angular extrusion (ECAE) is a severe plastic deformation (SPD) method for obtaining bulk nanostructured materials. The ECAE die...
1574
Authors: Jin Biao Zhang, Jing Wen Wang, Zong Yin Duan
Abstract:More and more attention is being paid to extrusion with multi-hole die in the manufacturing industry because of its advantages of high...
1548
Authors: Lei Cheng, Shui Sheng Xie, You Feng He, Guo Jie Huang, Yao Fu
Modeling, Analysis and Simulation of Manufacturing Processes
Abstract:FEM simulation of aluminum profiles in porthole die extrusion process using Lagrange mesh description will inevitably bring mesh...
290
Authors: Sören Müller, Jerome Muehlhause, J. Maier, Pavel Hora
Abstract:Of the various boundary conditions that are relevant for the correct modeling of the extrusion process the realistic representation of the...
113