Modeling, analysis, and optimization of dimensional accuracy of FDM-fabricated parts using definitive screening design and deep learning feedforward artificial neural network

作     者：Omar Ahmed Mohamed Syed Hasan Masood Jahar Lal Bhowmik Omar Ahmed Mohamed;Syed Hasan Masood;Jahar Lal Bhowmik

作者机构：School of EngineeringDeakin UniversityGeelongAustralia Department of Mechanical EngineeringHigher Institute of Engineering TechnologyBani WalidLibya Department of Mechanical and Product Design EngineeringSwinburne University of TechnologyHawthornVIC 3122Australia Department of Health Science and BiostatisticsSwinburne University of TechnologyHawthornVIC 3122Australia 

出 版 物：《Advances in Manufacturing》 (先进制造进展（英文版）)

年 卷 期：2021年第9卷第1期

页      面：115-129页

核心收录：

学科分类：07[理学] 0817[工学-化学工程与技术] 0807[工学-动力工程及工程热物理] 0805[工学-材料科学与工程（可授工学、理学学位）] 0802[工学-机械工程] 0811[工学-控制科学与工程] 0701[理学-数学] 0801[工学-力学（可授工学、理学学位）] 070101[理学-基础数学] 

主　　题：Artificial neural network(ANN) OptimizationDefinitive screening design(DSD) Analysis of variance(ANOVA) Fused deposition modeling(FDM) Dimensional accuracy 

摘      要：Additive manufacturing(AM)technologies such as fused deposition modeling(FDM)rely on the quality of manufactured products and the process ***,the dimensional accuracy and stability of any AM process is essential for ensuring that customer specifications are satisfied at the highest standard,and variations are controlled without significantly affecting the functioning of processes,machines,and product *** study aims to investigate the effects of FDM fabrication conditions on the dimensional accuracy of cylindrical *** this study,a new class of experimental design techniques for integrated second-order definitive screening design(DSD)and an artificial neural network(ANN)are proposed for designing experiments to evaluate and predict the effects of six important operating *** determining the optimum fabrication conditions to obtain better dimensional accuracies for cylindrical parts,the time consumption and number of complex experiments are reduced considerably in this *** optimum fabrication conditions generated through a second-order DSD are verified with experimental *** results indicate that the slice thickness,part print direction,and number of perimeters significantly affect the percentage of length difference,whereas the percentage of diameter difference is significantly affected by the raster-to-raster air gap,bead width,number of perimeters,and part print ***,the results demonstrate that a second-order DSD integrated with an ANN is a more attractive and promising methodology for AM applications.