Predictive Visualisation of Fibre Laser Machining via Deep Learning

undefined
Predictive Visualisation of Fibre
Laser Machining via Deep Learning
Alexander F. Courtier
1
, Michael McDonnell
1
, Matt Praeger
1
, James
A. Grant-Jacob
1
, Christophe Codemard
1,2
, Paul Harrison
2
, Ben
Mills
1
, Michalis Zervas
1
1
 Optoelectronics Research Centre, University of Southampton, University
Road, Southampton, SO17 1BJ, United Kingdom
2
 TRUMPF Laser UK, 6 Wellington Park, Toolbar Way, Hedge End,
Southampton, SO30 2QU, United Kingdom
2
 
Outline
Motivation
Introduction to 
laser cutting
Introduction to 
deep learning
Imaging of 
laser cutting
Using 
deep learning 
to model 
laser cutting defects
Conclusions
3
 
Motivation
Laser cutting enables fast, precise, contact-free cutting of materials.
However, modelling of light-matter interactions can be challenging.
Can Deep Learning model and predict laser cutting defects based on
laser parameters?
Fibre Laser Cutting
Continuous wave laser
cutting is achieved by
irradiating and locally
melting the workpiece,
and removing the
molten material with an
assist gas.
Fast, precise, and
contact-free.
However, 
defects
 can
be formed at the edge of
the cut, negatively
impacting cut quality.
4
Deep Learning
Deep Learning is a subset
of machine learning
using deep Neural
Networks (NNs).
NNs can act as universal
function approximators,
and therefore can be
used to model any
complex system.
Used for tasks such as
classification, regression,
and image generation.
5
Deep Learning
Deep Learning is a subset
of machine learning
using deep Neural
Networks (NNs).
NNs can act as universal
function approximators,
and therefore can be
used to model any
complex system.
Used for tasks such as
classification, regression,
and image generation.
6
Convolutional Neural Networks
Extracts features
from datasets using
convolutional filters
Can be used to
transform images
into a numerical
label
Highly suitable for
image analysis
7
Generative Adversarial Networks (GAN)
Formed of a generator network and a discriminator network
working in opposition
The generator predicts an output, if a labelled input is used they
are called Conditional GANs (CGANs)
The discriminator determines if an output is experimental or
predicted
8
Imaging of Laser Cutting
2mm thick stainless steel
sheets were cut by fibre
laser a 2kW, 1075nm at
ten cutting speeds, 15
m/min to  24 m/min.
Imaged after machining
using 5x optical
microscope
Experimental image of
laser cut edge
A)
15 m/min
B)
16 m/min
C)
17 m/min
D)
18 m/min
E)
19 m/min
F)
20 m/min
G)
21 m/min
H)
22 m/min
I)
23 m/min
J)
24 m/min
Experimental
Identification of Laser Cutting Speed
11
11
A CNN identifies the
cutting speed using images
of the laser cut.
99.9% accuracy.
Trained for 10 epochs on
~90000 images and tested
on ~10000 images.
Demonstrates that each
cutting speed produces
unique defects.
Parameter to Image Visualisation
Successfully reproduces
defects from parameters
Speed shown: 
15 m/min
Reproduces 
angle of
striations (22.5±2.2⁰
experimentally, and
26.8±2.2⁰ predicted)
12
12
Parameter to Image Visualisation
13
13
Experimental
Predicted
Successfully reproduces
defects from parameters
Speed shown: 
15 m/min
Reproduces 
angle of
striations (22.5±2.2⁰
experimentally, and
26.8±2.2⁰ predicted)
Parameter to Image Visualisation
14
14
Successfully reproduces
defects from parameters
Speed shown: 
20 m/min
Reproduces 
angle of
striations (32.7±3.0⁰
experimentally, and
36.9 ±3.6⁰ predicted)
Parameter to Image Visualisation
15
15
Experimental
Predicted
Successfully reproduces
defects from parameters
Speed shown: 
20 m/min
Reproduces 
angle of
striations (32.7±3.0⁰
experimentally, and
36.9 ±3.6⁰ predicted)
Adjacent Image Visualisation
16
16
Successfully predicts
defects from adjacent
images
Can use a predicted image
as an input
Can be chained to predict
subsequent predicted
images
Speed shown: 
15 m/min
Adjacent Image Visualisation
17
17
Successfully predicts
defects from adjacent
images
Can use a predicted image
as an input
Can be chained to predict
subsequent predicted
images
Speed shown: 
15 m/min
Experimental
Predicted
Adjacent Image Visualisation
18
18
Successfully predicts
defects from adjacent
images
Can use a predicted image
as an input
Can be chained to predict
subsequent predicted
images
Speed shown: 
20 m/min
Adjacent Image Visualisation
19
19
Successfully predicts
defects from adjacent
images
Can use a predicted image
as an input
Can be chained to predict
subsequent predicted
images
Speed shown: 
20 m/min
Experimental
Predicted
Conclusions
CNNs can distinguish laser cutting defects by cutting speed
with 
99.9% accuracy.
CGANs can accurately visualise laser cutting defects 
from
laser cutting parameters and adjacent images.
May have applications in real-time monitoring and real-
time predictions of laser cutting defects, to optimise the
laser cutting process.
 This work was supported under EPSRC (grant numbers EP/N03368X/1 and EP/N509747/1)
Slide Note
Embed
Share

Laser cutting is a fast and precise method, but predicting defects can be challenging. This study explores using Deep Learning to model and forecast laser cutting defects based on parameters. Topics include introduction to laser cutting, deep learning, imaging, and conclusions.


Uploaded on Sep 11, 2024 | 2 Views


Download Presentation

Please find below an Image/Link to download the presentation.

The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. Download presentation by click this link. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.

E N D

Presentation Transcript


  1. Predictive Visualisation of Fibre Laser Machining via Deep Learning Alexander F. Courtier1, Michael McDonnell1, Matt Praeger1, James A. Grant-Jacob1, Christophe Codemard1,2, Paul Harrison2, Ben Mills1, Michalis Zervas1 1 Optoelectronics Research Centre, University of Southampton, University Road, Southampton, SO17 1BJ, United Kingdom 2 TRUMPF Laser UK, 6 Wellington Park, Toolbar Way, Hedge End, Southampton, SO30 2QU, United Kingdom

  2. Outline Motivation Introduction to laser cutting Introduction to deep learning Imaging of laser cutting Using deep learning to model laser cutting defects Conclusions 2

  3. Motivation Laser cutting enables fast, precise, contact-free cutting of materials. However, modelling of light-matter interactions can be challenging. Can Deep Learning model and predict laser cutting defects based on laser parameters? 3

  4. Fibre Laser Cutting Continuous wave laser cutting is achieved by irradiating and locally melting the workpiece, and removing the molten material with an assist gas. Fast, precise, and contact-free. However, defects can be formed at the edge of the cut, negatively impacting cut quality. 4

  5. Deep Learning Deep Learning is a subset of machine learning using deep Neural Networks (NNs). NNs can act as universal function approximators, and therefore can be used to model any complex system. Used for tasks such as classification, regression, and image generation. 5

  6. Deep Learning Deep Learning is a subset of machine learning using deep Neural Networks (NNs). NNs can act as universal function approximators, and therefore can be used to model any complex system. Used for tasks such as classification, regression, and image generation. 6

  7. Convolutional Neural Networks Extracts features from datasets using convolutional filters Can be used to transform images into a numerical label Highly suitable for image analysis 7

  8. Generative Adversarial Networks (GAN) Formed of a generator network and a discriminator network working in opposition The generator predicts an output, if a labelled input is used they are called Conditional GANs (CGANs) The discriminator determines if an output is experimental or predicted 8

  9. Imaging of Laser Cutting 2mm thick stainless steel sheets were cut by fibre laser a 2kW, 1075nm at ten cutting speeds, 15 m/min to 24 m/min. Imaged after machining using 5x optical microscope Experimental image of laser cut edge

  10. Experimental A) 15 m/min B) 16 m/min C) 17 m/min D) 18 m/min E) 19 m/min F) 20 m/min G) 21 m/min H) 22 m/min I) 23 m/min J) 24 m/min

  11. Identification of Laser Cutting Speed A CNN identifies the cutting speed using images of the laser cut. 99.9% accuracy. Trained for 10 epochs on ~90000 images and tested on ~10000 images. Demonstrates that each cutting speed produces unique defects. 11 11

  12. Parameter to Image Visualisation Successfully reproduces defects from parameters Speed shown: 15 m/min Reproduces angle of striations (22.5 2.2 experimentally, and 26.8 2.2 predicted) 12 12

  13. Parameter to Image Visualisation Successfully reproduces defects from parameters Speed shown: 15 m/min Reproduces angle of striations (22.5 2.2 experimentally, and 26.8 2.2 predicted) Predicted Experimental 13 13

  14. Parameter to Image Visualisation Successfully reproduces defects from parameters Speed shown: 20 m/min Reproduces angle of striations (32.7 3.0 experimentally, and 36.9 3.6 predicted) 14 14

  15. Parameter to Image Visualisation Successfully reproduces defects from parameters Speed shown: 20 m/min Reproduces angle of striations (32.7 3.0 experimentally, and 36.9 3.6 predicted) Experimental Predicted 15 15

  16. Adjacent Image Visualisation Successfully predicts defects from adjacent images Can use a predicted image as an input Can be chained to predict subsequent predicted images Speed shown: 15 m/min 16 16

  17. Adjacent Image Visualisation Successfully predicts defects from adjacent images Can use a predicted image as an input Can be chained to predict subsequent predicted images Speed shown: 15 m/min Experimental Predicted 17 17

  18. Adjacent Image Visualisation Successfully predicts defects from adjacent images Can use a predicted image as an input Can be chained to predict subsequent predicted images Speed shown: 20 m/min 18 18

  19. Adjacent Image Visualisation Successfully predicts defects from adjacent images Can use a predicted image as an input Can be chained to predict subsequent predicted images Speed shown: 20 m/min Experimental Predicted 19 19

  20. Conclusions CNNs can distinguish laser cutting defects by cutting speed with 99.9% accuracy. CGANs can accurately visualise laser cutting defects from laser cutting parameters and adjacent images. May have applications in real-time monitoring and real- time predictions of laser cutting defects, to optimise the laser cutting process. This work was supported under EPSRC (grant numbers EP/N03368X/1 and EP/N509747/1)

Related


More Related Content

giItT1WQy@!-/#giItT1WQy@!-/#giItT1WQy@!-/#giItT1WQy@!-/#