An intelligent process parameters optimization approach for directed energy deposition of nickel-based alloys using deep reinforcement learning

doi:10.1016/j.jmapro.2024.05.001

IMR OpenIR

	An intelligent process parameters optimization approach for directed energy deposition of nickel-based alloys using deep reinforcement learning
	Shi, Shuai 1; Liu, Xuewen 1; Wang, Zhongan 1; Chang, Hai 1; Wu, Yingna 1; Yang, Rui 1,2; Zhai, Zirong 1
通讯作者	Zhai, Zirong()
	2024-06-30
发表期刊	JOURNAL OF MANUFACTURING PROCESSES
ISSN	1526-6125
卷号	120 页码:1130-1140
摘要	Directed Energy Deposition (DED) is crucial in the ongoing industrial revolution, providing a unique ability to fabricate high-quality components with complex shapes. However, the determination of key process parameters, such as scan sequence, laser power, and scanning speed, often relies on offline trial-and-error or heuristic methods. These methods are not only suboptimal but also lack generalizability. A major challenge is the nonuniform temperature distribution during manufacturing, which affects the uniformity of the mechanical properties. To overcome these challenges, we have developed a framework based on Deep Reinforcement Learning (DRL). This framework dynamically adjusts process parameters to achieve an optimal control policy. Additionally, we introduce a cost-effective temperature simulation model of the deposition process. This model is particularly useful for researchers testing the proximal policy optimization algorithm. The experimental results demonstrate that DRL policies substantially improve temperature uniformity in Inconel 718, enhancing hardness variability with improvements of 31.8 % and 27.1 % in horizontal and vertical building directions, respectively. This research marks an important step toward achieving a highly intelligent and automated optimization of process parameters. It also proves to be robust and computationally efficient for future online implementation.
关键词	Directed energy deposition Temperature simulator Deep reinforcement learning Proximal policy optimization Vickers hardness measurement
资助者	Double First -Class Initiative Fund ; ShanghaiTech University ; CAS Interdisciplinary Innovation Team Project
DOI	10.1016/j.jmapro.2024.05.001
收录类别	SCI
语种	英语
资助项目	Double First -Class Initiative Fund ; ShanghaiTech University ; CAS Interdisciplinary Innovation Team Project[JCTD- 2020-10]
WOS研究方向	Engineering
WOS类目	Engineering, Manufacturing
WOS记录号	WOS:001242384800001
出版者	ELSEVIER SCI LTD
引用统计	被引频次：4[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.imr.ac.cn/handle/321006/186986
专题	中国科学院金属研究所
通讯作者	Zhai, Zirong
作者单位	1.ShanghaiTech Univ, Ctr Adapt Syst Engn, 393 Huaxia Middle Rd, Shanghai 201210, Peoples R China 2.Chinese Acad Sci, Inst Met Res, 72 Wenhua Rd, Shenyang 110016, Peoples R China
推荐引用方式 GB/T 7714	Shi, Shuai,Liu, Xuewen,Wang, Zhongan,et al. An intelligent process parameters optimization approach for directed energy deposition of nickel-based alloys using deep reinforcement learning[J]. JOURNAL OF MANUFACTURING PROCESSES,2024,120:1130-1140.
APA	Shi, Shuai.,Liu, Xuewen.,Wang, Zhongan.,Chang, Hai.,Wu, Yingna.,...&Zhai, Zirong.(2024).An intelligent process parameters optimization approach for directed energy deposition of nickel-based alloys using deep reinforcement learning.JOURNAL OF MANUFACTURING PROCESSES,120,1130-1140.
MLA	Shi, Shuai,et al."An intelligent process parameters optimization approach for directed energy deposition of nickel-based alloys using deep reinforcement learning".JOURNAL OF MANUFACTURING PROCESSES 120(2024):1130-1140.