A double-level intelligent improvement approach for overhangs on side loss

doi:10.3785/j.issn.1008-9497.2023.06.013

Journal of Zhejiang University (Science Edition)

2023, Vol. 50

Issue (6): 781-794 DOI: 10.3785/j.issn.1008-9497.2023.06.013

CSIAM-GDC 2023

A double-level intelligent improvement approach for overhangs on side loss

Xinjing LI¹,Wanbin PAN^1,^2,³(

),Ye YANG¹,Yigang WANG¹,Cheng LIN¹

^1.School of Media and Design，Hangzhou Dianzi University，Hangzhou 310018，China
^2.State Key Laboratory of Virtual Reality Technology and Systems，Beihang University，Beijing 100191，China
^3.State Key Laboratory of CAD&CG，Zhejiang University，Hangzhou 310058，China

Download:

HTML( 0 )

PDF(4681KB)
Export: BibTeX | EndNote (RIS)

Abstract

Overhangs are usually inevitable when fabricating a part of complex shape in 3D printing. Meanwhile, the geometric error on the side surface of an overhang (i.e. the side loss) after fabricating is often significant, which seriously affects the accuracy of the overhang as well as its container (i.e. a part). To solve the above problem, a double-level intelligent improvement approach for overhangs on side loss (i.e. process parameter optimization and geometry pre-compensation) is proposed in this paper. Firstly, a series of experiments with different values concerning the critical design parameter and process parameters are designed based on the Taguchi method. Then, a deliberate measurement method is designed to get the side loss data from the fabricated inverted 'L'-shaped parts. Secondly, two types of side loss prediction networks are respectively constructed for the two sides (that is the overhang side and the non-overhang side) of each inverted 'L'-shaped part. They are mainly designed according to the requirements of support structures on an overhang. Aided with these networks, the geometric error of both sides of an overhang on an inverted 'L'-shaped part (with various values of the critical design parameter) can be predicted accurately. Thirdly, aiming at minimizing the side losses on both sides of an overhang, a single-objective and multiple-variables nonlinear programming problem is formulated. Hereby, the corresponding optimized side losses as well as their counterpart values of key process parameters can be determined. Finally, we compensate the geometries on the two sides of an overhang based on the above-optimized side losses by conducting an inverse modification first and then fabricate the overhang adopting the above-optimized values of key process parameters. Based on fused deposition modeling, experiments were implemented on various inverted 'L'-shaped parts except the ones used in constructing prediction networks, which verified the effectiveness of the proposed approach. Meanwhile, comparative analyses with state-of-the-art works were also carried out. The results show that our method is suitable for overhangs and has great potential to significantly improve their side losses.

Key words： overhang area side loss process parameters geometric pre-compensation 3D printing

Received: 12 June 2023 Published: 30 November 2023

CLC:

TP 391.41

Corresponding Authors: Wanbin PAN E-mail: panwanbin@hdu.edu.cn

	Service
	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Xinjing LI
	Wanbin PAN
	Ye YANG
	Yigang WANG
	Cheng LIN

Cite this article:

Xinjing LI,Wanbin PAN,Ye YANG,Yigang WANG,Cheng LIN. A double-level intelligent improvement approach for overhangs on side loss. Journal of Zhejiang University (Science Edition), 2023, 50(6): 781-794.

URL:

https://www.zjujournals.com/sci/EN/Y2023/V50/I6/781

悬空区域侧损失双层次智能改善方法

形状复杂的零件采用3D打印时通常存在悬空区域，悬空区域侧面成型后几何误差，即侧损失，往往非常明显，严重影响悬空区域及其零件的成型精度。为此，提出一种悬空区域侧损失双层次智能改善方法。首先，基于田口法设计了取不同关键设计参数和打印参数的一系列实验，并用所设计的测量方法测取打印的倒“L”形零件的侧损失样本数据。其次，针对倒“L”形零件悬空区域支撑结构迥异的两侧（即悬空侧和非悬空侧）构造了两类侧损失预测网络，可准确预测各尺寸下倒“L”形零件悬空区域两侧成型后的几何误差。再次，以悬空区域两侧的侧损失最小为目标，构造了单目标多变量非线性规划问题，得到优化的侧损失预测值及对应的工艺参数值。最后，依据侧损失预测值对悬空区域两侧实施反向几何偏移补偿，并用优化的工艺参数值进行打印，实现了对悬空区域侧损失的双层次智能改善。基于熔融沉积技术，用训练集以外的倒“L”形零件进行实验，验证了所提方法的有效性。结果表明，所提方法适用于悬空区域且具有显著改善悬空区域侧损失的巨大潜力。

关键词： 悬空区域, 侧损失, 工艺参数, 几何预补偿, 3D打印

Fig.1 The illustration of the side loss

Fig.2 Flow chart

Fig.3 Design drawing of the benchmark model

Fig.4 A set of geometric features related to the contour of the benchmark model

Fig.5 The measurement of the side loss

Fig.6 Sensitivity analysis of the artificial neural network model

Fig.7 Network structure of the side loss prediction based on ANN

Fig.8 Improved particle swarm optimization algorithm

Table 1 Value range of the benchmark model parameters

Table 2 Factor level value of main process parameters

Table 3 Factor level value of main design parameters

Fig.9 The illustration of the measurement

Table 4 Normalized results of the collected data

Fig.10 The comparison of the actual measured side losses with predicted side losses

Fig.11 The illustration of the geometric pre-compensation on both sides of the overhang

Fig.12 Printed results of the benchmark model one before and after compensating

Fig.13 Printed results of the benchmark model two before and after compensating

Fig.14 Printed results of the benchmark model three before and after compensating

Table 5 Comparison of relevant literature methods

Table 6 Comparison of efficiency and effectiveness


[1]	NATH P， OLSON J D， MAHADEVAN S， et al. Optimization of fused filament fabrication process parameters under uncertainty to maximize part geometry accuracy［J］. Additive Manufacturing，2020， 35： 101331. DOI：10.1016/j.addma.2020. 101331 doi: 10.1016/j.addma.2020. 101331

[2]	TOUNSI R， VIGNAT F. New concept of support structures in electron beam melting manufacturing to reduce geometric defects［C］// Proceedings of 15e Colloque National AIP-Primeca. Plagne Montalbert： AIP-PRIMECA， 2017： 1-6.

[3]	JIANG J C， XU X， STRINGER J. Support structures for additive manufacturing： A review［J］. Journal of Manufacturing and Materials Processing， 2018， 2（4）： 64-86. DOI：10.3390/jmmp2040064 doi: 10.3390/jmmp2040064

[4]	PELLENS J， LOMBAERT G， MICHIELS M， et al. Topology optimization of support structure layout in metal-based additive manufacturing accounting for thermal deformations［J］. Structural and Multidisciplinary Optimization， 2020， 61： 2291-2303. DOI：10.1007/s00158-020-02512-8 doi: 10.1007/s00158-020-02512-8

[5]	SCHMUTZLER C， BAYERLEIN F， JANSON S， et al. Pre-compensation of warpage for additive manufacturing［J］. Journal of Mechanics Engineering and Automation， 2016， 6（8）： 392-399. DOI：10.17265/2159-5275/2016.08.002 doi: 10.17265/2159-5275/2016.08.002

[6]	GHAOUI S， LEDOUX Y， VIGNAT F， et al. Analysis of geometrical defects in overhang fabrications in electron beam melting based on thermomechanical simulations and experimental validations［J］. Additive Manufacturing， 2020， 36： 101557. DOI：10.1016/j.addma.2020.101557 doi: 10.1016/j.addma.2020.101557

[7]	DONG G Y， WIJAYA G， TANG Y， et al. Optimizing process parameters of fused deposition modeling by Taguchi method for the fabrication of lattice structures［J］. Additive Manufacturing， 2018， 19（11）： 62-72. DOI：10.1016/j.addma.2017.11.004 doi: 10.1016/j.addma.2017.11.004

[8]	王继东，庞明勇. 基于深度剥离的三维打印模型朝向优化算法［J］. 计算机辅助设计与图形学学报， 2018， 30（9）： 1741-1747. DOI：10.3724/sp.j.1089.2018. 16877 WANG J D， PANG M Y. A depth peeling based algorithm to optimize model orientation for 3D printing［J］. Journal of Computer-Aided Design & Computer Graphics， 2018， 30（9）： 1741-1747. DOI：10.3724/sp.j.1089.2018.16877 doi: 10.3724/sp.j.1089.2018.16877

[9]	BINTARA R D， LUBIS D Z， PRADANA Y R A. The effect of layer height on the surface roughness in 3D printed polylactic acid （PLA） using FDM 3D printing［C］// Proceedings of the IOP Conference Series （Materials Science and Engineering）. Bristol： IOP Publishing， 2021： 012096. doi:10.1088/1757-899x/1034/1/012096 doi: 10.1088/1757-899x/1034/1/012096

[10]	KUO C C， WU Y R， LI M H， et al. Minimizing warpage of ABS prototypes built with low-cost fused deposition modeling machine using developed closed-chamber and optimal process parameters［J］. The International Journal of Advanced Manufacturing Technology， 2019， 101（1-4）： 593-602. DOI：10. 1007/s00170-018-2969-7 doi: 10. 1007/s00170-018-2969-7

[11]	WANG W M， SHAO H L， LIU X P， et al. Printing direction optimization through slice number and support minimization［J］. IEEE Access，2020， 8（3）： 75646-75655. DOI：10.1109/access.2020.2980282 doi: 10.1109/access.2020.2980282

[12]	CHINCHANIKAR S， SHINDE S， GAIKWAD V， et al. ANN modelling of surface roughness of FDM parts considering the effect of hidden layers， neurons， and process parameters［J］. Advances in Materials and Processing Technologies， 2022： 1-11. DOI：10. 1080/2374068X.2022.2091085 doi: 10. 1080/2374068X.2022.2091085

[13]	LEE B H， ABDULLAH J， KHAN Z A. Optimization of rapid prototyping parameters for production of flexible ABS object［J］. Journal of Materials Processing Technology， 2005， 169（1）： 54-61. DOI：10.1016/j.jmatprotec.2005.02.259 doi: 10.1016/j.jmatprotec.2005.02.259

[14]	QIN J， HU F， LIU Y， et al. Research and application of machine learning for additive manufacturing［J］. Additive Manufacturing， 2022， 52： 102691. DOI：10.1016/j.addma.2022.102691 doi: 10.1016/j.addma.2022.102691

[15]	ZHU Z W， ANWER N， MATHIEU L. Geometric deviation modeling with statistical shape analysis in design for additive manufacturing［J］. Procedia CIRP， 2019， 84： 496-501. DOI：10.1016/j.procir.2019. 04.251 doi: 10.1016/j.procir.2019. 04.251

[16]	XU S Z， LIU J K， MA Y S. Residual stress constrained self-support topology optimization for metal additive manufacturing［J］. Computer Methods in Applied Mechanics and Engineering， 2022， 389： 114380. DOI：10.1016/j.cma.2021.114380 doi: 10.1016/j.cma.2021.114380

[17]	WANG W M， VAN K F， WU J. Fabrication sequence optimization for minimizing distortion in multi-axis additive manufacturing［J］. Computer Methods in Applied Mechanics and Engineering， 2023， 406： 115899. DOI：10.1016/j.cma.2023.115899 doi: 10.1016/j.cma.2023.115899

[18]	DECKER N. Machine Learning-Driven Deformation Prediction and Compensation for Additive Manufacturing［D］. Los Angeles： University of Southern California， 2022.

[19]	HONG R C， ZHANG L， LIFTON J， et al. Artificial neural network-based geometry compensation to improve the printing accuracy of selective laser melting fabricated sub-millimetre overhang trusses［J］. Additive Manufacturing，2021， 37： 101594. DOI：10.1016/j.addma.2020.101594 doi: 10.1016/j.addma.2020.101594

[20]	CHOWDHURY S， ANAND S. Artificial neural network based geometric compensation for thermal deformation in additive manufacturing processes［C］// Proceedings of the International Manufacturing Science and Engineering Conference. Virginia： American Society of Mechanical Engineers， 2016： 1-10. doi:10.1115/msec2016-8784 doi: 10.1115/msec2016-8784

[21]	SHAMASS R， FERREIRA F P V， LIMBACHIYA V， et al. Web-post buckling prediction resistance of steel beams with elliptically-based web openings using artificial neural networks （ANN）［J］. Thin-Walled Structures， 2022， 180： 109959. DOI：10.1016/j.tws. 2022.109959 doi: 10.1016/j.tws. 2022.109959

[22]	JAFARI D， VANEKER T H J， GIBSON I. Wire and arc additive manufacturing： Opportunities and challenges to control the quality and accuracy of manufactured parts［J］. Materials & Design，2021， 202： 109471. DOI：10.1016/j.matdes.2021.109471 doi: 10.1016/j.matdes.2021.109471

[23]	SINGH S， SINGH G， PRAKASH C， et al. Current status and future directions of fused filament fabrication［J］. Journal of Manufacturing Processes，2020， 55： 288-306. DOI：10.1016/j.jmapro.2020. 04.049 doi: 10.1016/j.jmapro.2020. 04.049

[24]	CHOWDHURY S， MHAPSEKAR K， ANAND S. Part build orientation optimization and neural network-based geometry compensation for additive manufacturing process［J］. Journal of Manufacturing Science and Engineering， 2018， 140（3）： 031009. DOI：10.1115/1.4038293 doi: 10.1115/1.4038293

[25]	HARTMANN C， LECHNER P， HIMMEL B， et al. Compensation for geometrical deviations in additive manufacturing［J］. Technologies， 2019， 7（4）： 83-95. DOI：10.3390/technologies7040083 doi: 10.3390/technologies7040083

[26]	YANG L P， LI S J， LI Y， et al. Experimental investigations for optimizing the extrusion parameters on FDM PLA printed parts［J］. Journal of Materials Engineering and Performance， 2019， 28（1）： 169-182. DOI：10.1007/s11665-018-3784-x doi: 10.1007/s11665-018-3784-x

[27]	MOHAMED O A， MASOOD S H， BHOWMIK J L. Modeling， analysis， and optimization of dimensional accuracy of FDM-fabricated parts using definitive screening design and deep learning feedforward artificial neural network［J］. Advances in Manufacturing， 2021， 9（1）： 115-129. DOI：10. 1007/s40436-020-00336-9 doi: 10. 1007/s40436-020-00336-9

[28]	VIKAS B， HUSSAIN M， REDDY C. Optimization of 3D printing process parameters of poly lactic acid materials by fused deposition modeling process［J］. International Journal of Engineering Development and Research， 2019， 7（3）： 189-196.

[29]	TONG K， LEHTIHET E A， JOSHI S. Software compensation of rapid prototyping machines［J］. Precision Engineering， 2004， 28（3）： 280-292. DOI：10.1016/j.precisioneng.2003.11.003 doi: 10.1016/j.precisioneng.2003.11.003

[30]	TONG K， JOSHI S， LEHTIHET E A. Error compensation for fused deposition modeling （FDM） machine by correcting slice files［J］. Rapid Prototyping Journal， 2008， 14（1）： 4-14. DOI：10. 1108/13552540810841517 doi: 10. 1108/13552540810841517

[31]	HUANG Q， ZHANG J Z， SABBAGHI A， et al. Optimal offline compensation of shape shrinkage for three-dimensional printing processes［J］. IIE Transactions， 2015， 47（5）： 431-441. DOI：10.1080/0740817x.2014.955599 doi: 10.1080/0740817x.2014.955599

[32]	HUANG Q， NOURI H， XU K， et al. Statistical predictive modeling and compensation of geometric deviations of three-dimensional printed products［J］. Journal of Manufacturing Science and Engineering，2014， 136（6）： 061008. DOI：10.1115/1.4028510 doi: 10.1115/1.4028510

[33]	LUAN H， HUANG Q. Prescriptive modeling and compensation of in-plane shape deformation for 3D printed freeform products［J］. IEEE Transactions on Automation Science and Engineering， 2016， 14（1）： 73-82. DOI：10.1109/TASE.2016.2608955 doi: 10.1109/TASE.2016.2608955

[34]	MCCONAHA M， ANAND S. Additive manufacturing distortion compensation based on scan data of built geometry［J］. Journal of Manufacturing Science and Engineering， 2020， 142（6）： 061001. DOI：10.1115/1.4046505 doi: 10.1115/1.4046505

[35]	LEDOUX Y， GHAOUI S， VO T H， et al. Geometrical defect analysis of overhang geometry produced by electron beam melting： Experimental and statistical investigations［J］. The International Journal of Advanced Manufacturing Technology， 2022， 122（3/4）： 2059-2075. DOI：10.1007/s00170-022-10040-6 doi: 10.1007/s00170-022-10040-6

[36]	HORNIK K. Approximation capabilities of multilayer feedforward networks［J］. Neural Networks， 1991， 4（2）： 251-257. DOI：10.1016/0893-6080（91）90009-T doi: 10.1016/0893-6080（91）90009-T

[37]	BOUSSAïD I， LEPAGNOT J， SIARRY P. A survey on optimization metaheuristics［J］. Information Sciences， 2013， 237： 82-117. DOI：10.1016/j.ins. 2013.02.041 doi: 10.1016/j.ins. 2013.02.041

[38]	PEDREGOSA F， VAROQUAUX G， GRAMFORT A， et al. Scikit-learn： Machine hon［J］. Journal of Machine Learning Research， 2011， 12： 2825-2830.

[39]	QUAN Z Z， WU A， KEEFE M， et al. Additive manufacturing of multi-directional preforms for composites： Opportunities and challenges［J］. Materials Today， 2015， 18（9）： 503-512. DOI：10.1016/j.mattod.2015.05.001 doi: 10.1016/j.mattod.2015.05.001

[1]	WANG Kang, WU Wenming, LIU Ligang. 3D maze design and modeling[J]. Journal of Zhejiang University (Science Edition), 2017, 44(2): 127-133.

Viewed

Full text

Abstract

Cited

Shared

Discussed