A fast decision-making method for process planning with dynamic machining resources via deep reinforcement learning

强化学习 过程(计算) 启发式 计算机科学 机械加工 工业工程 工程类 人工智能 机械工程 操作系统
作者
Wenbo Wu,Zijun Wu,Jiani Zeng,Kuan Fan
出处
期刊:Journal of Manufacturing Systems [Elsevier BV]
卷期号:58: 392-411 被引量:35
标识
DOI:10.1016/j.jmsy.2020.12.015
摘要

Mass customized production brings great uncertainty to the computer-aided process planning (CAPP). Current CAPP methods based on heuristic optimization assume in advance that manufacturing resources are static and make a deterministic plan that cannot cope with the uncertainty of the manufacture environment. As a promising method in solving complex and dynamic decision-making problems, deep reinforcement learning is employed in this paper for process planning, aiming at promoting the response speed by exploiting the reusability and expandability of past decision-making experiences. To simplify the decision procedure, two different types of decisions, operation sequencing and resource selection, are fused into one by integrating environment states and agent behaviors in a matrix manner. Then, a masking algorithm is developed to screen out currently inexecutable machining operations at each decision step and process planning datasets are generated for training and testing according to the actual processing logic. Next, the Monte Carlo method and the deep learning algorithm are utilized to evaluate and improve the process policy, respectively. Finally, the searching capability of the proposed method for both static and dynamic manufacturing resources are tested in case studies, and the results are discussed. It is shown that the proposed approach can solve the planning problem more efficiently compared with current optimization-based approaches.

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
推石头的玛卡巴卡完成签到,获得积分10
刚刚
刚刚
刚刚
楼宸发布了新的文献求助50
1秒前
勿明驳回了Whim应助
1秒前
星辰大海应助92567采纳,获得10
1秒前
1秒前
欧阳振应助留白留白采纳,获得10
2秒前
xiaowang发布了新的文献求助10
2秒前
李健应助闪闪问安采纳,获得10
3秒前
小蘑菇应助liuqun采纳,获得10
3秒前
自信友桃完成签到,获得积分10
3秒前
3秒前
扥会完成签到,获得积分20
3秒前
奋斗瑶发布了新的文献求助10
4秒前
积极从蕾应助若俗人采纳,获得10
4秒前
若风完成签到,获得积分10
4秒前
4秒前
5秒前
小二郎应助小白采纳,获得10
5秒前
思源应助kk采纳,获得10
5秒前
称心的猪完成签到,获得积分10
6秒前
6秒前
隐形曼青应助羊青丝采纳,获得10
6秒前
Nanocapsule完成签到,获得积分10
6秒前
7秒前
xiaoxiao发布了新的文献求助10
8秒前
IDHNAPHO完成签到,获得积分10
8秒前
一个美女完成签到,获得积分10
8秒前
自觉的元芹完成签到,获得积分10
9秒前
小包发布了新的文献求助10
9秒前
希望天下0贩的0应助HEIHEI采纳,获得10
9秒前
EvenCai应助奋斗瑶采纳,获得10
10秒前
负责冰烟发布了新的文献求助10
10秒前
科研八戒完成签到,获得积分10
10秒前
斯文败类应助buding采纳,获得10
10秒前
Yy完成签到,获得积分10
10秒前
bourne78发布了新的文献求助200
10秒前
文南犬完成签到 ,获得积分10
10秒前
灰灰发布了新的文献求助10
11秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
A new approach to the extrapolation of accelerated life test data 1000
徐淮辽南地区新元古代叠层石及生物地层 500
Coking simulation aids on-stream time 450
康复物理因子治疗 400
北师大毕业论文 基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 390
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 4016703
求助须知:如何正确求助?哪些是违规求助? 3556823
关于积分的说明 11322708
捐赠科研通 3289505
什么是DOI,文献DOI怎么找? 1812495
邀请新用户注册赠送积分活动 888064
科研通“疑难数据库(出版商)”最低求助积分说明 812086