Real-time optimization method for desktop level 3D printing parameters based on deep learning

doi:10.3785/j.issn.1008-973X.2026.11.005

Journal of ZheJiang University (Engineering Science)

2026, Vol. 60

Issue (11): 2355-2363 DOI: 10.3785/j.issn.1008-973X.2026.11.005

Real-time optimization method for desktop level 3D printing parameters based on deep learning

Ming CAO1(

),Daokuan CHEN1,Pengfei YUAN2,Jinpeng ZHOU1,Kui ZHOU1,*(

)

1. School of Advanced Manufacturing, Nanchang University, Nanchang 330031, China
2. Process Equipment Research and Development Center, Jiangxi Hongdu Aviation Industry Group Co., Ltd., Nanchang 330001, China

Download:

HTML

PDF(4882KB) HTML
Export: BibTeX | EndNote (RIS)

Abstract

An intelligent online parameter adjustment method based on an improved YOLOv11 model was proposed to address poor print quality and the heavy reliance on manual expertise for parameter tuning in 3D printers. On the basis of a conventional 3D printing platform, a nozzle-targeted image acquisition system was incorporated, and a quantitative mapping model between printing parameters (such as speed and temperature) and print quality metrics (such as tensile strength and surface roughness) was established. The improved YOLOv11 model was employed to identify early visual signatures of various defects (such as stringing and under-extrusion) during the printing process, enabling real-time adjustment of key compensatory parameters. Experimental results demonstrate that, under preset defect parameters, activating the online adjustment method increases the tensile strength of printed parts by four times compared to the unadjusted state, while significantly reducing surface roughness from Ra100 to Ra50. The proposed method can automatically adjust parameters during use to improve print quality.

Key words： additive manufacturing technology deep learning image recognition defect detection dynamic optimization of printing parameter

Received: 20 September 2025 Published: 16 October 2026

CLC:

TP 393

Fund: 江西省重点研发计划资助项目（20232BBE50017）；江西省自然科学基金资助项目（20232BAB215016，20242BAB25358）；赣鄱俊才支持计划·青年科技人才托举项目（2024QT13）；江西省大学生创新创业训练计划项目（202510403037）.

Corresponding Authors: Kui ZHOU E-mail: caoming@ncu.edu.cn;zhoukui@ncu.edu.cn

	Service
	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Ming CAO
	Daokuan CHEN
	Pengfei YUAN
	Jinpeng ZHOU
	Kui ZHOU

Cite this article:

Ming CAO,Daokuan CHEN,Pengfei YUAN,Jinpeng ZHOU,Kui ZHOU. Real-time optimization method for desktop level 3D printing parameters based on deep learning. Journal of ZheJiang University (Engineering Science), 2026, 60(11): 2355-2363.

URL:

https://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2026.11.005 OR https://www.zjujournals.com/eng/Y2026/V60/I11/2355

基于深度学习的桌面级3D打印参数实时优化方法

3D打印机的参数调节依赖人工经验，且打印质量不稳定，为此提出基于改进YOLOv11模型的智能在线参数调节方法. 基于传统3D打印平台，增加指向喷嘴的图像采集系统，建立打印参数（如速度和温度）与打印质量（如拉伸强度和表面粗糙度）之间的定量映射模型. 通过改进YOLOv11模型，识别打印过程中出现的多种缺陷（如拉丝和欠挤出）的早期视觉特征，实时调整关键打印补偿参数. 实验结果表明，在预设缺陷参数下，启用在线调节方法后，打印件的拉伸强度相较于未调节状态提升了4倍，表面粗糙度从Ra100显著优化至Ra50. 所提方法能够在使用过程中自动化调整参数以提升打印质量.

关键词： 增材制造技术, 深度学习, 图像识别, 缺陷检测, 打印参数动态优化

Fig.1 Ender-5S 3D printer

Fig.2 Klipper architecture diagram

Fig.3 Structural diagram of vision system hardware component

Fig.4 Diagram of filament states under different extrusion flow rates

Fig.5 Diagram of filament extrusion states under different nozzle temperatures

Fig.6 Diagram of filament extrusion states under different nozzle travel speed conditions

Fig.7 Diagram of filament extrusion states under different Z-axis deviations

Tab.1 3D printer parameter state definition

Fig.8 Comparison of images before and after enhancement

Fig.9 YOLOv11 image classification architecture

Fig.10 Architecture diagram of convolutional block attention module

Fig.11 Image classification structure of YOLOv11-convolutional block attention module

Fig.12 Gradient-weighted class activation mapping feature heatmap

Fig.13 Printing process flow chart of real-time adjustment

Fig.14 Image recognition and adjustment process

Fig.15 Comparison of surface quality of standard parts under different parameter combinations

Tab.2 Tensile performance test results of standard parts under different parameter combinations

Fig.16 Comparison of surface quality of complex models under different parameter combinations


[1]	孟伟 3D打印技术及应用趋势分析[J]. 科技创新与应用, 2021, (11): 146- 148 MENG Wei Analysis of 3D printing technology and its application trends[J]. Technology Innovation and Application, 2021, (11): 146- 148

[2]	邓滨, 欧阳汉斌, 黄文华 3D打印在医学领域的应用进展[J]. 中国医学物理学杂志, 2016, 33 (4): 389- 392 DENG Bin, OUYANG Hanbin, HUANG Wenhua Application progress of three-dimensional printing in medical field[J]. Chinese Journal of Medical Physics, 2016, 33 (4): 389- 392

[3]	谭立忠, 方芳 3D打印技术及其在航空航天领域的应用[J]. 战术导弹技术, 2016, (4): 1- 7 TAN Lizhong, FANG Fang 3D printing technology and its application in aerospace industry[J]. Tactical Missile Technology, 2016, (4): 1- 7

[4]	谢文 3D打印技术在汽车机械制造领域的应用[J]. 汽车与驾驶维修, 2025, (6): 20- 22 XIE Wen Applications of 3D printing technology in automotive mechanical manufacturing[J]. Auto Driving and Service, 2025, (6): 20- 22

[5]	贾杭, 顾九毓, 庞扬扬 3D打印在建筑领域中的应用发展[J]. 土木工程, 2023, 12 (5): 604- 610 JIA Hang, GU Jiuyu, PANG Yangyang Application and development of 3D printing in the field of architecture[J]. Hans Journal of Civil Engineering, 2023, 12 (5): 604- 610 doi: 10.12677/HJCE.2023.125067

[6]	冯丹艳基于FDM技术3D打印典型零件的力学性能和质量研究[J]. 装备制造技术, 2022, (2): 50- 52 FENG Danyan Research on mechanical properties and quality of 3D printing typical parts based on FDM technology[J]. Equipment Manufacturing Technology, 2022, (2): 50- 52

[7]	余东满, 李晓静, 王笛熔融沉积快速成型工艺过程分析及应用[J]. 机械设计与制造, 2011, (8): 65- 67 YU Dongman, LI Xiaojing, WANG Di Process analysis and application for rapid prototyping based on fused deposition modeling[J]. Machinery Design and Manufacture, 2011, (8): 65- 67

[8]	刘秋平教育及生活用品3D打印的市场应用探索[J]. 科技风, 2024, (34): 4- 6 LIU Qiuping Exploration on the market application of 3D printing for educational and daily supplies[J]. Technology Wind, 2024, (34): 4- 6

[9]	马秀清, 劳志超, 李明谦, 等 3D打印工艺参数对PLA/PTW共混物力学性能影响的研究[J]. 中国塑料, 2024, 38 (2): 70- 75 MA Xiuqing, LAO Zhichao, LI Mingqian, et al Effect of 3D printing process parameters on mechanical properties of PLA/PTW blends[J]. China Plastics, 2024, 38 (2): 70- 75

[10]	SAMPEDRO G A R, AGRON D J S, AMAIZU G C, et al Design of an in-process quality monitoring strategy for FDM-type 3D printer using deep learning[J]. Applied Sciences, 2022, 12 (17): 8753 doi: 10.3390/app12178753

[11]	黄周林, 周敏, 李鑫炎, 等基于机器视觉的3D打印异常诊断方法[J]. 机床与液压, 2024, 52 (13): 212- 218 HUANG Zhoulin, ZHOU Min, LI Xinyan, et al Abnormal diagnosis method of 3D printing based on machine vision[J]. Machine Tool and Hydraulics, 2024, 52 (13): 212- 218

[12]	ROHIT J S, KUMAR N. Evaluation of additive manufacturing using Marlin firmware [M]// SINGH R, GEHLOT A. Intelligent circuits and systems. London: CRC Press, 2021: 342–350.

[13]	NAZARENKO V, OSTROUSHKO B Comparative research of 3D printer main control parameters and characteristics utilising Klipper firmware[J]. Machinery and Energetics, 2025, 16 (1): 81- 90 doi: 10.31548/machinery/1.2025.81

[14]	王世檩, 朱家威, 张鹏, 等基于FDM成型技术的打印强度和成型速率研究进展[J]. 中国塑料, 2025, 39 (1): 112- 117 WANG Shilin, ZHU Jiawei, ZHANG Peng, et al Research progress in printing strength and molding rate based on FDM molding technology[J]. China Plastics, 2025, 39 (1): 112- 117

[15]	HARUTA M, KIKKAWA J, KIMOTO K, et al Comparison of detection limits of direct-counting CMOS and CCD cameras in EELS experiments[J]. Ultramicroscopy, 2022, 240: 113577 doi: 10.1016/j.ultramic.2022.113577

[16]	RAI H, SINGH K R, NATARAJAN A, et al Advances in field effect transistor based electronic devices integrated with CMOS technology for biosensing[J]. Talanta Open, 2025, 11: 100394 doi: 10.1016/j.talo.2024.100394

[17]	GAO X, YAO T, GAO F, et al A new granule extrusion-based for 3D printing of POE: studying the effect of printing parameters on mechanical properties with “response surface methodology”[J]. Iranian Polymer Journal, 2025, 34 (5): 739- 750 doi: 10.1007/s13726-024-01405-7

[18]	LIU B, QIAN B, LIANG Y, et al Fast and accurate auto-disturbances-rejection temperature control system based on particle swarm optimized fuzzy control: applied for particle three-dimensional (3D) printing prosthetic orthotic plate[J]. Additive Manufacturing, 2025, 101: 104704 doi: 10.1016/j.addma.2025.104704

[19]	KUMAR L, KUMAR SATYARTHI M SurfaceVision: an automated module for surface fault detection in 3D printed products[J]. Tehnički Glasnik, 2025, 19 (2): 243- 251 doi: 10.31803/tg-20240925082150

[20]	韩定坤 FDM 3D打印工艺对轻质蜂巢结构机械性能的影响[J]. 机械工程与技术, 2024, (1): 44- 51 HAN Dingkun The influence of FDM 3D printing process on the mechanical properties of lightweight honeycomb structure[J]. Mechanical Engineering and Technology, 2024, (1): 44- 51

[21]	STEFENON S F, SEMAN L O, SINGH G, et al Enhanced insulator fault detection using optimized ensemble of deep learning models based on weighted boxes fusion[J]. International Journal of Electrical Power and Energy Systems, 2025, 168: 110682 doi: 10.1016/j.ijepes.2025.110682

[22]	顾海军, 陈胜一种基于深度学习的轮胎缺陷检测系统[J]. 计算机与数字工程, 2022, 50 (7): 1463- 1467 GU Haijun, CHEN Sheng A tire defect detection system based on deep learning[J]. Computer and Digital Engineering, 2022, 50 (7): 1463- 1467

[23]	吴京城, 施露露, 杜亚南, 等基于双重高斯滤波的细胞图像快速分割方法[J]. 激光与光电子学进展, 2022, 59 (2): 0210002 WU Jingcheng, SHI Lulu, DU Yanan, et al Fast segmentation method of cell image based on dual-Gaussian filtering[J]. Laser and Optoelectronics Progress, 2022, 59 (2): 0210002 doi: 10.3788/LOP202259.0210002

[24]	王靖, 姜文刚, 程耀, 等基于Lab颜色空间改进U—Net的稻田杂草分割方法[J]. 中国农机化学报, 2025, 46 (5): 148- 154 WANG Jing, JIANG Wengang, CHENG Yao, et al Improved U—Net based on Lab color space for weed segmentation method in rice fields[J]. Journal of Chinese Agricultural Mechanization, 2025, 46 (5): 148- 154

[25]	杨卫中, 徐银丽, 乔曦, 等基于对比度受限直方图均衡化的水下海参图像增强方法[J]. 农业工程学报, 2016, 32 (6): 197- 203 YANG Weizhong, XU Yinli, QIAO Xi, et al Method for image intensification of underwater sea cucumber based on contrast-limited adaptive histogram equalization[J]. Transactions of the Chinese Society of Agricultural Engineering, 2016, 32 (6): 197- 203

[26]	刘毛毛, 刘宗辉, 周东, 等基于改进双边滤波的GPR图像强振幅噪声压制算法[J]. 地球物理学进展, 2022, 37 (4): 1749- 1756 LIU Maomao, LIU Zonghui, ZHOU Dong, et al GPR image strong amplitude noise suppression algorithm based on improved bilateral filtering[J]. Progress in Geophysics, 2022, 37 (4): 1749- 1756

[27]	MOHAMMED A, KORA R A comprehensive review on ensemble deep learning: opportunities and challenges[J]. Journal of King Saud University Computer and Information Sciences, 2023, 35 (2): 757- 774 doi: 10.1016/j.jksuci.2023.01.014

[28]	马岽奡, 唐娉, 赵理君, 等深度学习图像数据增广方法研究综述[J]. 中国图象图形学报, 2021, 26 (3): 487- 502 MA Dongao, TANG Ping, ZHAO Lijun, et al Review of data augmentation for image in deep learning[J]. Journal of Image and Graphics, 2021, 26 (3): 487- 502

[29]	李浩宇, 曲丽颖, 华子杰, 等基于深度学习的荧光显微成像技术及应用[J]. 激光与光电子学进展, 2021, 58 (18): 1811007 LI Haoyu, QU Liying, HUA Zijie, et al Deep learning based fluorescence microscopy imaging technologies and applications[J]. Laser and Optoelectronics Progress, 2021, 58 (18): 1811007 doi: 10.3788/LOP202158.1811007

[30]	JIANG P, ERGU D, LIU F, et al A review of YOLO algorithm developments[J]. Procedia Computer Science, 2022, 199: 1066- 1073 doi: 10.1016/j.procs.2022.01.135

[31]	耿创, 宋品德, 曹立佳 YOLO算法在目标检测中的研究进展[J]. 兵器装备工程学报, 2022, 43 (9): 162- 173 GENG Chuang, SONG Pinde, CAO Lijia Research progress of YOLO algorithm in target detection[J]. Journal of Ordnance Equipment Engineering, 2022, 43 (9): 162- 173 doi: 10.11809/bqzbgcxb2022.09.023

[32]	李明, 来国红, 常晏鸣, 等深度学习算法中不同优化器的性能分析[J]. 信息技术与信息化, 2022, (3): 206- 209 LI Ming, LAI Guohong, CHANG Yanming, et al Performance analysis of different optimizers in deep learning algorithm[J]. Information Technology and Informatization, 2022, (3): 206- 209 doi: 10.3969/j.issn.1672-9528.2022.03.052

[1]	Heng YANG,Shaohan WANG,Qing DONG,Keyuan ZHAO,Mingliang YANG. Object pose estimation based on attention enhancement cross-modal multilayer fusion network[J]. Journal of ZheJiang University (Engineering Science), 2026, 60(9): 1872-1880.

[2]	Jian XIAO,Xiaoyuan YANG,Xinze HE,Lin CHEN,Xin HU. Lightweight rebar surface defect detection algorithm based on global information perception[J]. Journal of ZheJiang University (Engineering Science), 2026, 60(7): 1438-1451.

[3]	Hongbin LIN,Sijin LV,Chenyang WANG,Tianfang CAI,Pengwei LUO. Radial basis network based on residual/gradient Gaussian adaptive sampling[J]. Journal of ZheJiang University (Engineering Science), 2026, 60(5): 1119-1127.

[4]	Zixiang LI,Kecheng LU,Haibing CAI,Weishuai XIE,Guangdong ZHANG. Concrete crack detection in dark environments based on biomimetic tactile technology[J]. Journal of ZheJiang University (Engineering Science), 2026, 60(5): 915-925.

[5]	Jie WU,Beilin HAN,Yihang ZHANG,Chao ZOU,Lifeng XIN,Shiping HUANG. Method for augmenting crack image datasets via fine-tuning of stable diffusion models[J]. Journal of ZheJiang University (Engineering Science), 2026, 60(5): 926-934.

[6]	Wei TIAN,Linhong ZHOU,Xinyang LI,Jianming WANG,Yukang HUANG. 3D-printed concrete apparent defect detection method based on improved YOLOv8[J]. Journal of ZheJiang University (Engineering Science), 2026, 60(4): 833-843.

[7]	Xiaochun WU,Ning GUO. Lightweight detection method of water leakage in tunnel based on HMARU-net[J]. Journal of ZheJiang University (Engineering Science), 2026, 60(3): 468-477.

[8]	Leping LIN,Liang LI,Ning OUYANG. High spatio-temporal resolution precipitation forecast based on dual-polarization radar[J]. Journal of ZheJiang University (Engineering Science), 2026, 60(3): 574-584.

[9]	Minghui YANG,Muyuan SONG,Daxi FU,Yanwei GUO,Xianzhui LU,Wencong ZHANG,Weilong ZHENG. Prediction of shield tunneling-induced soil settlement based on multi-head self-attention-Bi-LSTM model[J]. Journal of ZheJiang University (Engineering Science), 2026, 60(2): 415-424.

[10]	Xin HU,Xiyue YAN,Yashu CHANG,Hongliang CHENG,Jian XIAO,Shiwei LUO,Liang MA. Context-enhanced multi-target semantic perception algorithm for power defect detection[J]. Journal of ZheJiang University (Engineering Science), 2026, 60(10): 2176-2185.

[11]	Yue SUN,Xinglan ZHANG. Targeted adversarial attack method based on dual guidance[J]. Journal of ZheJiang University (Engineering Science), 2026, 60(1): 81-89.

[12]	Zhihang ZHU,Yunfeng YAN,Donglian QI. Image generation for power personnel behaviors based on diffusion model with multimodal prompts[J]. Journal of ZheJiang University (Engineering Science), 2026, 60(1): 43-51.

[13]	Jizhong DUAN,Haiyuan LI. Multi-scale parallel magnetic resonance imaging reconstruction based on variational model and Transformer[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(9): 1826-1837.

[14]	Tao ZHOU,Pengfei WANG,Weijie GAO. Device defect detection based on intrinsic rotational symmetry[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(9): 1856-1863.

[15]	Fujian WANG,Zetian ZHANG,Xiqun CHEN,Dianhai WANG. Usage prediction of shared bike based on multi-channel graph aggregation attention mechanism[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(9): 1986-1995.

Viewed

Full text

Abstract

Cited

Shared

Discussed