Scholarlink

Abstract <p>This study develops an Artificial Neural Network (ANN)-based prediction model to optimise Incremental Sheet Forming (ISF) parameters for AA6061-T6 aluminium alloy, focusing on surface roughness, geometric accuracy, and sheet thinning. A Central Composite Design (CCD) was used to vary input parameters systematically, and a Multi-Objective Genetic Algorithm (MOGA) was employed for optimisation. Experimental validation confirmed that the optimised parameters (step depth = 0.2 mm, feed rate = 750&#xa0;mm/min, spindle speed = 750 RPM) reduced surface roughness by 80% (from 0.9 to 0.18−0.2 <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="12008_2025_2292_Article_IEq1.gif" Format="GIF" Height="12" Rendition="HTML" Resolution="72" Type="Linedraw" Width="15" /> </InlineMediaObject> <EquationSource Format="TEX">\(\mu \)</EquationSource> <EquationSource Format="MATHML"><math> <mi>μ</mi> </math></EquationSource> </InlineEquation>m) and improved geometric accuracy by 48% (from 3.191 to 1.67 mm). However, sheet thinning remained unimproved at 8%. The ANN model, trained on experimental data, demonstrated superior predictive accuracy (MSE = 0.0153, <InlineEquation ID="IEq2"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="12008_2025_2292_Article_IEq2.gif" Format="GIF" Height="14" Rendition="HTML" Resolution="72" Type="Linedraw" Width="66" /> </InlineMediaObject> <EquationSource Format="TEX">\(R &gt; 0.99\)</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mi>R</mi> <mo>&gt;</mo> <mn>0.99</mn> </mrow> </math></EquationSource> </InlineEquation>), outperforming traditional CCD models in capturing non-linear parameter-response relationships. These findings highlight the effectiveness of ANN and MOGA in optimising ISF process parameters, leading to significant improvements in forming quality while identifying key trade-offs in material thinning.</p> Graphical abstract <p></p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Investigation and prediction of forming quality influenced by ISF process parameters for AA6061 T6 using artificial neural network

  • 期刊论文

  • 发表日期：

    2025年5月5日

查看全文
  • Viren Mevada,
  • Harit Raval

摘要

Abstract

This study develops an Artificial Neural Network (ANN)-based prediction model to optimise Incremental Sheet Forming (ISF) parameters for AA6061-T6 aluminium alloy, focusing on surface roughness, geometric accuracy, and sheet thinning. A Central Composite Design (CCD) was used to vary input parameters systematically, and a Multi-Objective Genetic Algorithm (MOGA) was employed for optimisation. Experimental validation confirmed that the optimised parameters (step depth = 0.2 mm, feed rate = 750 mm/min, spindle speed = 750 RPM) reduced surface roughness by 80% (from 0.9 to 0.18−0.2 \(\mu \) μ m) and improved geometric accuracy by 48% (from 3.191 to 1.67 mm). However, sheet thinning remained unimproved at 8%. The ANN model, trained on experimental data, demonstrated superior predictive accuracy (MSE = 0.0153, \(R > 0.99\) R > 0.99 ), outperforming traditional CCD models in capturing non-linear parameter-response relationships. These findings highlight the effectiveness of ANN and MOGA in optimising ISF process parameters, leading to significant improvements in forming quality while identifying key trade-offs in material thinning.

Graphical abstract