Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o...
Transcript of Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o...
![Page 1: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/1.jpg)
Workshop AI in Photonics
Swissmem und Swissphotonics
Machine learning foroptical quality
inspection
Thomas Grünberger plasmo Industrietechnik GmbH
Vienna2019-09-03
![Page 2: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/2.jpg)
content
page02
o company presentationplasmo
o data is not information
o human intelligence
o artificial intelligence
o examples machinelearning
![Page 3: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/3.jpg)
companyplasmo
![Page 4: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/4.jpg)
global. focussed.independent.
page04
800more than 800 plasmo systems
in operation
100more than 100 global customers
using plasmo
![Page 5: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/5.jpg)
visualization
correlation
integration
sensors
plasmo quality suite
![Page 6: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/6.jpg)
basic technologies
page06
processobserver profileobserver
plasmoeye
![Page 7: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/7.jpg)
contact
page07
austriaplasmo Industrietechnik GmbH
Dresdner Str. 81-85
1200 Vienna
phone +43 1 236 26 07-0
www.plasmo.eu
germanyplasmo Industrietechnik GmbH
NL Deutschland
Leitzstr. 45
70469 Stuttgart
phone +49 711 49066-307
www.plasmo.eu
usaplasmo USA LLC
44160 Plymouth Oaks Blvd,
Plymouth, MI 48170
phone +1 734 414 7912
www.plasmo-us.com
chinaplasmo China
42F Wheelock Square
1717 Nanjing West Road
Shanghai 200040/P.R. China
phone +86 21 8028 6166
www.plasmo.cn
![Page 8: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/8.jpg)
data is notinformation
![Page 9: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/9.jpg)
how to extractinformation from data
page09
o data plausibility
o data analytics
o human intelligence
o artificial intelligence
o machine learning
o deep learning
![Page 10: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/10.jpg)
data analytics
page010
o data architect
o data engineer
o data scientist
o business analyst
o devops
o SQL/no SQL
o Docker
o Kybernets
o DFS
o cloud/edge/fog
o …
![Page 11: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/11.jpg)
human intelligence and graphical data analyticsaggregation seam and part level
page011
![Page 12: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/12.jpg)
human intelligence and graphical data analytics aggregation machine level
page012
![Page 13: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/13.jpg)
human intelligence and graphical data analytics aggregation site level
page013
![Page 14: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/14.jpg)
human intelligence and graphical data analytics root cause analysis
page014
![Page 15: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/15.jpg)
human intelligence and graphical data analytics process optimization
page015
o statistical analysis of
o defect positionso defect typeso date/timeo material/vendoro maintenance planningo …
o finding correlations,trends
![Page 16: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/16.jpg)
artificialintelligence
![Page 17: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/17.jpg)
artificial intelligencedefinitions
page017
o AI Artificial Intelligence
o tries to model human intelligenceo cybernetics, …
o statistics
o tries to define what happenedo DM and ML came from statistics
o DM Data Mining
o tries to explain why somethinghappens (e.g. root cause)
o ML Machine Learning
o tries to explain what will happen in future and how to optimize oravoid certain situations
o ML is a first step for modelhuman intelligence and can beseen as part if AI
![Page 18: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/18.jpg)
machine learningtechniques
page018
o supervised learning
o target is knowno develop model based on
input and output data
o unsupervised learning
o group and interpretdata based only on input data
![Page 19: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/19.jpg)
examples
![Page 20: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/20.jpg)
diode based process monitoringwelding of thin sheets
page020
o 2 sensors are used (different wavelengths), 710 test runs (index), onemeasurement consists of 2050 measurement values.
o information is expected in the characteristics mean value and standard deviationfor one complete seam (4 dimensions)
![Page 21: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/21.jpg)
diode based process monitoringunsupervised learning
page021
o are there clusters in the data?
manifold learningk-means
![Page 22: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/22.jpg)
diode based process monitoringsupervised learning
page022
o OKNOK and defect types were analysed via DT and NDT techniques
classification logistic regressionOKNOK distribution
![Page 23: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/23.jpg)
diode based process monitoringsupervised learning
page023
o comparison of different modelling techniques for OKNOK, ANN and random forestyields in optimal results (comparison based on confusion matrix)
logistic regression random forest artificial neural network
![Page 24: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/24.jpg)
diode based process monitoringsupervised learning
page024
o 3D visualisation of the task (OK runs type 1 and 3 defect types (-3, -2, -1)
![Page 25: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/25.jpg)
diode based process monitoringsummary
page025
o at least 3 different characteristics and at least 2 different diode signals needed
o unsupervised learning shows 4 different clusters correlating with the 4 defect types
o supervised learning using machine learningtechniques enables correctclassification
![Page 26: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/26.jpg)
camera based weld seam monitoring
page026
o camera based weld seam monitoring enables the detection of visible defects
o used in addition to process monitoring systems detecting defects defects likelack of fusion, porosity, no full penetration, …, which can‘t be seen at the top ofthe seam
o gray value or color images useable
o example welding of C shaped seams
![Page 27: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/27.jpg)
camera based weld seam monitoringsupervised training, deep learning
page027
o deep learning are available the last few years due to computational power(e.g. GPU processing)
o artificial neural networks are used typically using many neurons
o different approaches available including pretrained nets for specific tasks
o unsupervised deep learning also usable
o supervised learning using training, test and validation data set
o check for inter- and extrapolation capabilities (e.g. overtraining)
![Page 28: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/28.jpg)
camera based weld seam monitoringsupervised training, deep learning
page028
o trainings data setclassified correct
![Page 29: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/29.jpg)
camera based weld seam monitoringsupervised training, deep learning
page029
o test data set1 false positive and1 false negative
![Page 30: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/30.jpg)
camera based weld seam monitoringsupervised training, deep learning
page030
o trainings data setclassified correct
![Page 31: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/31.jpg)
camera based weld seam monitoringsupervised training, deep learning
page031
o test data setclassified correct
![Page 32: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/32.jpg)
camera based weld seam monitoringsummary
page032
o deep learning gives better results compared to manual inspection
o unsupervised approach also applicable (presentation of OK seams and detectionof anomalies)
o models can be trained once or retrained online
o result depends on input data and correct classifications (supervised)
![Page 33: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/33.jpg)
machine learning at plasmosummary
page033
o dashboard based analysis of production and sensor data (SPC)o correlationso trend analysis
o modelling OKNOK for different sensors for quality inspection of differentjoining techniques (laser, TIG, plasma, FSW, …)
o unsupervised clustering of sensor data for all applications
o genetic algorithms for supervised or unsupervised automatic parameterisationof quality inspection systems
![Page 34: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/34.jpg)
machine learning at plasmosummary
page034
o deep learning for image based analysis
o analysis of powder bed images (AM) and classification of different defect types
o unsupervised analysis of image staples (layer by layer) in additive manufacturing
example3D visualisation of 50 layersbuilding a bridge (1mm height)
-> up to 10.000 layers (images) has to be analysed for a real job
![Page 35: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/35.jpg)
machine learning at plasmosummary
page035
o some tips from our experience
o don‘t learn existing knowledge
o keep it as simple as possible
o 80percent rule: 80% is data preparation, 20% is data analysis
![Page 36: Machine learning for optical quality inspection · 2019. 9. 13. · o business analyst o devops o SQL/no SQL ... o supervised learning using training, test and validation data set](https://reader035.fdocuments.in/reader035/viewer/2022071008/5fc668bc1f7ea91662688282/html5/thumbnails/36.jpg)
summary
page036