改进Q学习的薄壁结构3D打印路径规划

doi:10.3778/j.issn.1002-8331.2012-0438

摘要/Abstract

摘要： 3D打印是一项先进的制造技术，通过优化其中路径规划方案可以提高效率或成型质量。由于用于3D打印路径规划的传统方法在打印复杂薄壁结构时效果不佳，该文结合强化学习的智能性，提出了一种适用于复杂薄壁结构的路径规划方法。基于3D打印中的路径规划是填充任务，将强化学习中的路径规划任务转换为全遍历问题。为提高打印效率和成型质量，以最小化打印总成本为优化目标，根据优化目标设计强化学习中的约束条件，即最小化打印头的启停和转弯次数。建立单层切片的仿真环境，采用带有上述约束条件的Q-learning算法，通过计算总成本的值来引导学习，寻找最优路径方案。实验结果表明，该方法在打印复杂薄壁结构上的表现优于用于3D打印路径规划的传统方法。

关键词: 3D打印, 强化学习, 路径规划, Q-学习

Abstract: 3D printing is an advanced manufacturing technology, the optimized path planning method of 3D printing can improve efficiency or molding quality. For the traditional path planning methods are short of handling complex thin-walled structures, an reinforcement learning-based path planning method named Q-path is proposed for complex thin-walled structures. First of all, based on the path planning in 3D printing is a filling task, the path planning task in reinforcement learning is converted to a traversal problem. In order to improve printing efficiency and molding quality, the optimization goal is to minimize the total cost of printing, and the constraint conditions in the reinforcement learning are designed according to the optimization goal, that is, to minimize the number of start, stop and turns of the print head. This paper establishes a simulation environment of a slice, uses the Q-learning algorithm with the above constraints, learning is guided by calculating the value of the total cost to find the optimal path plan. Experimental results show that this method is better than the traditional method for 3D printing path planning in printing complex thin-walled structures.

Key words: 3D printing, reinforcement learning, path planning, Q-learning

王祎, 葛静怡, 薛昕惟, 王胜法, 李凤岐. 改进Q学习的薄壁结构3D打印路径规划[J]. 计算机工程与应用, 2022, 58(12): 299-303.

WANG Yi, GE Jingyi, XUE Xinwei, WANG Shengfa, LI Fengqi. Path Planning for Complex Thin-Walled Structures in 3D Printing：Improved Q-Learning Method[J]. Computer Engineering and Applications, 2022, 58(12): 299-303.

参考文献

[1] JIN Y，DU J，MA Z，et al.An optimization approach for path planning of high-quality and uniform additive manufacturing[J].The International Journal of Advanced Manufacturing Technology，2017，92（1/4）：651-662.
[2] LOU Q，WU R X.Integrated printing stereo antenna with dual materials 3D printing technology[J].Electronics Letters，2017，54（3）：118-120.
[3] ZAHARIA C，GABOR A G，GAVRILOVICI A，et al.Digital dentistry—3D printing applications[J].Journal of Interdisciplinary Medicine，2017，2（1）：50-53.
[4] 侯章浩，乌日开西·艾依提.3D打印的路径规划研究综述[J].机床与液压，2016，44（5）：179-182.
HOU Z H，AIYITI W R K X.Review of studies on path planning of 3D printing[J].Machine Tool & Hydraulics，2016，44（5）：179-182.
[5] ASIABANPOUR B，KHOSHNEVIS B.Machine path generation for the SIS process[J].Robotics & Computer Integrated Manufacturing，2004，20（3）：167-175.
[6] EL-MIDANY T T，ELKERAN A，TAWFIK H.Toolpath pattern comparison：contour-parallel with direction-parallel[C]//Geometric Modeling and Imaging New Trends（GMAI’06），2006：77-82.
[7] 王腾飞.3D打印技术中分层与路径规划算法的研究及实现[D].天津：河北工业大学，2015.
WANG T F.The research and implement of slicing and path planing algorithm in 3D printing technology[D].Tianjin：Hebei University of Technology，2015.
[8] 程艳阶.选择性激光烧结激光扫描路径的研究与开发[D].武汉：华中科技大学，2004.
CHENG Y J.The research and development of laser scan path of selective laser sintering process[D].Wuhan：Huazhong University of Science and Technology，2004.
[9] ZHAO H，GU F，HUANG Q X，et al.Connected fermat spirals for layered fabrication[J].ACM Transactions on Graphics，2016，35（4）：1-10.
[10] LENSGRAF S，METTU R R.An improved toolpath generation algorithm for fused filament fabrication[C]//2017 IEEE International Conference on Robotics and Automation（ICRA），2017：1181-1187.
[11] PANCHAGNULA J S，SIMHAMBHATLA S.Manufacture of complex thin-walled metallic objects using weld-deposition based additive manufacturing[J].Robotics & Computer Integrated Manufacturing，2018，49：194-203.
[12] JIN Y，HE Y，DU J.A novel path planning methodology for extrusion-based additive manufacturing of thin-walled parts[J].International Journal of Computer Integrated Manufacturing，2017，30（12）：1301-1315.
[13] DINH H Q，GELMAN F，LEFEBVRE S，et al.Modeling and toolpath generation for consumer-level 3d printing[C]//ACM SIGGRAPH 2015 Courses，2015：1-273.
[14] ZHANG R，ISHIKAWA A，WANG W，et al.Using reinforcement learning with partial vehicle detection for intelligent traffic signal control[J].arXiv：1807.01628，2018.
[15] 夏新海.交互协调强化学习下的城市交通信号配时决策[J].计算机工程与应用，2018，54（11）：265-270.
XIA X H.Research on urban traffic signal timing decision based on reinforcement learning with interaction coordination mechanism[J].Computer Engineering and Applications，2018，54（11）：265-270.
[16] 赵发君，李龙澍.基于多Agent Q学习的RoboCup局部配合策略[J].计算机工程与应用，2014，50（23）：127-130.
ZHAO F J，LI L S.RoboCup regional cooperative strategy based on multi-Agent Q-learning[J].Computer Engineering and Applications，2014，50（23）：127-130.
[17] 侯艳丽.基于支持向量机和Q学习的移动机器人导航[J].计算机工程与应用，2011，47（23）：242-244.
HOU Y L.Mobile robot navigation based on support vector machine and Q-learning[J].Computer Engineering and Applications，2011，47（23）：242-244.