A Nonlinear Error Compensator for FDM 3D Printed Part Dimensions Using a Hybrid Algorithm Based on GMDH Neural Network

Q4 Chemical Engineering

Applied and Computational Mechanics Pub Date : 2021-09-01 DOI:10.22059/JCAMECH.2021.325325.628

Hamid Haghshenas Gorgani, H. Korani, Reihaneh Jahedan, Sharif Shabani

{"title":"A Nonlinear Error Compensator for FDM 3D Printed Part Dimensions Using a Hybrid Algorithm Based on GMDH Neural Network","authors":"Hamid Haghshenas Gorgani, H. Korani, Reihaneh Jahedan, Sharif Shabani","doi":"10.22059/JCAMECH.2021.325325.628","DOIUrl":null,"url":null,"abstract":"Following the advances in Computer-Aided Design (CAD) and Additive Manufacturing (AM), with regards to the numerous benefits of the Fused Deposition Modeling (FDM) as a popular AM process, resolving its weaknesses has become increasingly important. A serious problem of the FDM is the dimensional error or size difference between the CAD model and the actual 3D printed part.In this study, the approach is compensating the error regardless of its source. At First, all parameters affecting the dimensional accuracy of FDM are comprehensively identified. Then, multi-input–single-output (MISO) data is prepared by designing experiments using the Taguchi method and obtaining the results from 3D printed samples. Next, a GMDH neural network is applied, which uses a simple nonlinear regression formula in each neuron but can create very complex neuron combinations. So, it is possible to analyze small or even noisy data. Regulatory parameters of the Neural Net have been optimized to increase efficiency. The case study shows a decrease in the RSME for the Nominal CAD Model from 0.377 to 0.033, displaying the compensator's efficiency.","PeriodicalId":37801,"journal":{"name":"Applied and Computational Mechanics","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Applied and Computational Mechanics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.22059/JCAMECH.2021.325325.628","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"Chemical Engineering","Score":null,"Total":0}

引用次数: 2

Abstract

Following the advances in Computer-Aided Design (CAD) and Additive Manufacturing (AM), with regards to the numerous benefits of the Fused Deposition Modeling (FDM) as a popular AM process, resolving its weaknesses has become increasingly important. A serious problem of the FDM is the dimensional error or size difference between the CAD model and the actual 3D printed part.In this study, the approach is compensating the error regardless of its source. At First, all parameters affecting the dimensional accuracy of FDM are comprehensively identified. Then, multi-input–single-output (MISO) data is prepared by designing experiments using the Taguchi method and obtaining the results from 3D printed samples. Next, a GMDH neural network is applied, which uses a simple nonlinear regression formula in each neuron but can create very complex neuron combinations. So, it is possible to analyze small or even noisy data. Regulatory parameters of the Neural Net have been optimized to increase efficiency. The case study shows a decrease in the RSME for the Nominal CAD Model from 0.377 to 0.033, displaying the compensator's efficiency.

查看原文本刊更多论文

基于GMDH神经网络的FDM三维打印零件尺寸非线性误差补偿器

随着计算机辅助设计(CAD)和增材制造(AM)技术的进步，随着熔融沉积建模(FDM)作为一种流行的增材制造工艺的众多优点，解决其缺点变得越来越重要。FDM的一个严重问题是CAD模型与实际3D打印部件之间的尺寸误差或尺寸差异。在本研究中，该方法是补偿误差，而不管其来源。首先，综合识别了影响FDM尺寸精度的所有参数;然后，采用田口法设计实验，并从3D打印样品中获取结果，得到多输入单输出(MISO)数据。接下来，应用GMDH神经网络，它在每个神经元中使用简单的非线性回归公式，但可以创建非常复杂的神经元组合。因此，可以分析小甚至有噪声的数据。对神经网络的调节参数进行了优化，提高了效率。案例研究表明，标称CAD模型的RSME从0.377降至0.033，显示了补偿器的效率。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Applied and Computational Mechanics Engineering-Computational Mechanics

CiteScore

0.80

自引率

0.00%

发文量

审稿时长

14 weeks

期刊介绍： The ACM journal covers a broad spectrum of topics in all fields of applied and computational mechanics with special emphasis on mathematical modelling and numerical simulations with experimental support, if relevant. Our audience is the international scientific community, academics as well as engineers interested in such disciplines. Original research papers falling into the following areas are considered for possible publication: solid mechanics, mechanics of materials, thermodynamics, biomechanics and mechanobiology, fluid-structure interaction, dynamics of multibody systems, mechatronics, vibrations and waves, reliability and durability of structures, structural damage and fracture mechanics, heterogenous media and multiscale problems, structural mechanics, experimental methods in mechanics. This list is neither exhaustive nor fixed.