Artificial Intelligence-based optimization of Variable Blank Holder Force to reduce residual stress and improve formability; Experimental and statistical analysis

Author:

Khaboushani Mohammad,Parvizi Ali,Aminzadeh Ahmad1,Karganroudi Sasan Sattarpanah

Affiliation:

1. University of Quebec in Rimouski: Universite du Quebec a Rimouski

Abstract

Abstract Many contributory factors can influence the quality of the deep drawing process, among which Blank Holder Force (BHF) plays a decisive role. Therefore, controlling the BHF during the deep drawing process can bring many advantages and act as a deterrent against process failures, including tearing, wrinkling, and fatigue due to excessive residual stress and cyclic loads. Variable Blank Holder Force (VBHF), in which the BHF varies along the punch stroke, has recently been a popular method for improving sheet metal quality in the deep drawing process. In this study, VBHF was optimized to improve the formability of the process and reduce the residual stress using two different methods of Artificial Intelligence (AI) and Response Surface Method (RSM). The main purpose of this research is to introduce a new approach based on AI for VBHF optimization and compare the result of which with that of previous methods (Statistical methods). To reach this aim, BHFs in seven different stages of punch stroke were considered as the inputs of the process, and drawn depth at the tearing moment in addition to residual stresses were considered as the outputs of this optimization process. The optimization was carried out in two forms, single and multi-objective optimization to yield the desired results. The deep drawing process was numerically simulated using Abaqus/Explicit Software, with heavy modeling calculations performed on the supercomputer, Simorgh, and the experimental studies were carried out to verify FEM simulation. Additionally, to optimize VBHF using AI methods, Artificial Neural Network (ANN) was used to define a correlation function between inputs and outputs, and a Genetic Algorithm (GA) was used to optimize the function trained by ANN. Optimization results demonstrated that although the trend of optimized VBHF using AI and RSM were considerably similar to each other, the AI results were better than that of RSM in both cases of residual stress reduction and draw ability improvement. The FEM model of deep drawing process was shown to be reliable due to its excellent agreement with experimental studies.

Publisher

Research Square Platform LLC

Reference42 articles.

1. Aminzadeh A, Parvizi A, Moradi M (2020) Multi-objective topology optimization of deep drawing dissimilar tailor laser welded blanks; experimental and finite element investigation. Optics & Laser Technology. May 1;125:106029

2. "Controlled strain path forming process with space variant blank holder force using RSM method;Wang L,2005

3. "Optimization of sheet metal forming processes by adaptive response surface based on intelligent sampling method;Hu W,2008

4. Determining the optimum variable blank-holder forces using adaptive response surface methodology (ARSM).;Chengzhi S,2005

5. Optimization sheet metal forming process – using hierarchy and response surface methodology;Jansson T,2006

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3