Transfer Learning For Predictive Quality In Laser-Induced Plasma Micro-Machining

IF 1 Q4 ENGINEERING, MANUFACTURING
Mengfei Chen, Rajiv Malhotra, Weihong (Grace) Guo
{"title":"Transfer Learning For Predictive Quality In Laser-Induced Plasma Micro-Machining","authors":"Mengfei Chen, Rajiv Malhotra, Weihong (Grace) Guo","doi":"10.1115/1.4064010","DOIUrl":null,"url":null,"abstract":"Abstract In laser-induced plasma micro-machining (LIPMM), a focused, ultrashort pulsed laser beam creates a highly localized plasma zone within a transparent liquid dielectric. When the beam intensity is greater than the breakdown threshold in the dielectric media, plasma is formed which is then used to ablate the workpiece. This paper aims to facilitate in-situ process monitoring and quality prediction for LIPMM by developing a deep learning model to (1) understand the relationship between acoustic emission data and quality of micro-machining with LIPMM, (2) transfer such understanding across different process parameters, and (3) predict quality accurately by fine-tuning models with a smaller dataset. Experiments and results show that the relationship learned from one process parameter can be transferred to other parameters, requiring lesser data and lesser computational time for training the model. We investigate the feasibility of transfer learning and compare the performance of various transfer learning models: different input features, different CNN structures, and the same structure with different fine-tuned layers. The findings provide insights into how to design effective transfer learning models for manufacturing applications.","PeriodicalId":45459,"journal":{"name":"Journal of Micro and Nano-Manufacturing","volume":null,"pages":null},"PeriodicalIF":1.0000,"publicationDate":"2023-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Micro and Nano-Manufacturing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1115/1.4064010","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENGINEERING, MANUFACTURING","Score":null,"Total":0}
引用次数: 0

Abstract

Abstract In laser-induced plasma micro-machining (LIPMM), a focused, ultrashort pulsed laser beam creates a highly localized plasma zone within a transparent liquid dielectric. When the beam intensity is greater than the breakdown threshold in the dielectric media, plasma is formed which is then used to ablate the workpiece. This paper aims to facilitate in-situ process monitoring and quality prediction for LIPMM by developing a deep learning model to (1) understand the relationship between acoustic emission data and quality of micro-machining with LIPMM, (2) transfer such understanding across different process parameters, and (3) predict quality accurately by fine-tuning models with a smaller dataset. Experiments and results show that the relationship learned from one process parameter can be transferred to other parameters, requiring lesser data and lesser computational time for training the model. We investigate the feasibility of transfer learning and compare the performance of various transfer learning models: different input features, different CNN structures, and the same structure with different fine-tuned layers. The findings provide insights into how to design effective transfer learning models for manufacturing applications.
激光诱导等离子体微加工中预测质量的迁移学习
在激光诱导等离子体微加工(LIPMM)中,聚焦的超短脉冲激光束在透明液体介质内产生高度局部化的等离子体区。当光束强度大于介电介质中的击穿阈值时,形成等离子体,然后用于烧蚀工件。本文旨在通过开发深度学习模型来促进LIPMM的现场过程监测和质量预测,以(1)了解声发射数据与LIPMM微加工质量之间的关系,(2)跨不同工艺参数传递这种理解,以及(3)使用较小的数据集通过微调模型准确预测质量。实验和结果表明,从一个过程参数中学习到的关系可以转移到其他参数中,从而减少了训练模型所需的数据量和计算时间。我们研究了迁移学习的可行性,并比较了各种迁移学习模型的性能:不同的输入特征,不同的CNN结构,以及具有不同微调层的相同结构。研究结果为如何为制造应用设计有效的迁移学习模型提供了见解。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Journal of Micro and Nano-Manufacturing
Journal of Micro and Nano-Manufacturing ENGINEERING, MANUFACTURING-
CiteScore
2.70
自引率
0.00%
发文量
12
期刊介绍: The Journal of Micro and Nano-Manufacturing provides a forum for the rapid dissemination of original theoretical and applied research in the areas of micro- and nano-manufacturing that are related to process innovation, accuracy, and precision, throughput enhancement, material utilization, compact equipment development, environmental and life-cycle analysis, and predictive modeling of manufacturing processes with feature sizes less than one hundred micrometers. Papers addressing special needs in emerging areas, such as biomedical devices, drug manufacturing, water and energy, are also encouraged. Areas of interest including, but not limited to: Unit micro- and nano-manufacturing processes; Hybrid manufacturing processes combining bottom-up and top-down processes; Hybrid manufacturing processes utilizing various energy sources (optical, mechanical, electrical, solar, etc.) to achieve multi-scale features and resolution; High-throughput micro- and nano-manufacturing processes; Equipment development; Predictive modeling and simulation of materials and/or systems enabling point-of-need or scaled-up micro- and nano-manufacturing; Metrology at the micro- and nano-scales over large areas; Sensors and sensor integration; Design algorithms for multi-scale manufacturing; Life cycle analysis; Logistics and material handling related to micro- and nano-manufacturing.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信