Hole Depth Prediction in a Femtosecond Laser Drilling Process Using Deep Learning

In high-aspect ratio laser drilling, many laser and optical parameters can be controlled, including the high-laser beam fluence and number of drilling process cycles. Measurement of the drilled hole depth is occasionally difficult or time consuming, especially during machining processes. This study...

Full description

Bibliographic Details
Main Authors: Dong-Wook Lim, Myeongjun Kim, Philgong Choi, Sung-June Yoon, Hyun-Taek Lee, Kyunghan Kim
Format: Article
Language:English
Published: MDPI AG 2023-03-01
Series:Micromachines
Subjects:
Online Access:https://www.mdpi.com/2072-666X/14/4/743
_version_ 1797604284351643648
author Dong-Wook Lim
Myeongjun Kim
Philgong Choi
Sung-June Yoon
Hyun-Taek Lee
Kyunghan Kim
author_facet Dong-Wook Lim
Myeongjun Kim
Philgong Choi
Sung-June Yoon
Hyun-Taek Lee
Kyunghan Kim
author_sort Dong-Wook Lim
collection DOAJ
description In high-aspect ratio laser drilling, many laser and optical parameters can be controlled, including the high-laser beam fluence and number of drilling process cycles. Measurement of the drilled hole depth is occasionally difficult or time consuming, especially during machining processes. This study aimed to estimate the drilled hole depth in high-aspect ratio laser drilling by using captured two-dimensional (2D) hole images. The measuring conditions included light brightness, light exposure time, and gamma value. In this study, a method for predicting the depth of a machined hole by using a deep learning methodology was devised. Adjusting the laser power and the number of processing cycles for blind hole generation and image analysis yielded optimal conditions. Furthermore, to forecast the form of the machined hole, we identified the best circumstances based on changes in the exposure duration and gamma value of the microscope, which is a 2D image measurement instrument. After extracting the data frame by detecting the contrast data of the hole by using an interferometer, the hole depth was predicted using a deep neural network with a precision of within 5 μm for a hole within 100 μm.
first_indexed 2024-03-11T04:44:15Z
format Article
id doaj.art-0696c5977bd6444fa68b3cb1ab0f41d2
institution Directory Open Access Journal
issn 2072-666X
language English
last_indexed 2024-03-11T04:44:15Z
publishDate 2023-03-01
publisher MDPI AG
record_format Article
series Micromachines
spelling doaj.art-0696c5977bd6444fa68b3cb1ab0f41d22023-11-17T20:28:43ZengMDPI AGMicromachines2072-666X2023-03-0114474310.3390/mi14040743Hole Depth Prediction in a Femtosecond Laser Drilling Process Using Deep LearningDong-Wook Lim0Myeongjun Kim1Philgong Choi2Sung-June Yoon3Hyun-Taek Lee4Kyunghan Kim5Department of Mechanical Engineering, Inha University, Incheon 22212, Republic of KoreaDepartment of Mechanical Engineering, Chungnam University, Daejeon 34134, Republic of KoreaDepartment of Laser and Electron Beam Application Group, Korea Institute of Machinery & Materials, Daejeon 34103, Republic of KoreaDepartment of Mechanical Engineering, Inha University, Incheon 22212, Republic of KoreaDepartment of Mechanical Engineering, Inha University, Incheon 22212, Republic of KoreaDepartment of Laser and Electron Beam Application Group, Korea Institute of Machinery & Materials, Daejeon 34103, Republic of KoreaIn high-aspect ratio laser drilling, many laser and optical parameters can be controlled, including the high-laser beam fluence and number of drilling process cycles. Measurement of the drilled hole depth is occasionally difficult or time consuming, especially during machining processes. This study aimed to estimate the drilled hole depth in high-aspect ratio laser drilling by using captured two-dimensional (2D) hole images. The measuring conditions included light brightness, light exposure time, and gamma value. In this study, a method for predicting the depth of a machined hole by using a deep learning methodology was devised. Adjusting the laser power and the number of processing cycles for blind hole generation and image analysis yielded optimal conditions. Furthermore, to forecast the form of the machined hole, we identified the best circumstances based on changes in the exposure duration and gamma value of the microscope, which is a 2D image measurement instrument. After extracting the data frame by detecting the contrast data of the hole by using an interferometer, the hole depth was predicted using a deep neural network with a precision of within 5 μm for a hole within 100 μm.https://www.mdpi.com/2072-666X/14/4/743laser micromachiningdeep learningfemtosecond lasersilicon nitrideblind hole
spellingShingle Dong-Wook Lim
Myeongjun Kim
Philgong Choi
Sung-June Yoon
Hyun-Taek Lee
Kyunghan Kim
Hole Depth Prediction in a Femtosecond Laser Drilling Process Using Deep Learning
Micromachines
laser micromachining
deep learning
femtosecond laser
silicon nitride
blind hole
title Hole Depth Prediction in a Femtosecond Laser Drilling Process Using Deep Learning
title_full Hole Depth Prediction in a Femtosecond Laser Drilling Process Using Deep Learning
title_fullStr Hole Depth Prediction in a Femtosecond Laser Drilling Process Using Deep Learning
title_full_unstemmed Hole Depth Prediction in a Femtosecond Laser Drilling Process Using Deep Learning
title_short Hole Depth Prediction in a Femtosecond Laser Drilling Process Using Deep Learning
title_sort hole depth prediction in a femtosecond laser drilling process using deep learning
topic laser micromachining
deep learning
femtosecond laser
silicon nitride
blind hole
url https://www.mdpi.com/2072-666X/14/4/743
work_keys_str_mv AT dongwooklim holedepthpredictioninafemtosecondlaserdrillingprocessusingdeeplearning
AT myeongjunkim holedepthpredictioninafemtosecondlaserdrillingprocessusingdeeplearning
AT philgongchoi holedepthpredictioninafemtosecondlaserdrillingprocessusingdeeplearning
AT sungjuneyoon holedepthpredictioninafemtosecondlaserdrillingprocessusingdeeplearning
AT hyuntaeklee holedepthpredictioninafemtosecondlaserdrillingprocessusingdeeplearning
AT kyunghankim holedepthpredictioninafemtosecondlaserdrillingprocessusingdeeplearning