FEATURE Machine Vision
Achieving 100% with the help of artifi cial intelligence
Technologies based on AI are increasingly used to achieve comprehensive quality control, write Oliver Schnerr, Stephan Bellem and Ferenc Bögner from Kistler Group
A stamping cell with an integrated optical inspection method “shape from shading”
R
andom inspection of components, which is widely practiced in the production of stamped parts, is not only time
consuming but also far from delivering end-to-end traceability. Yet, there are solutions that can replace inspection based on random part sampling with an automated, comprehensive quality control. They offer traceable quality all the way to component level.
Optical inspection The optical inspection process “shape from shading” uses special illumination and imaging techniques. It separates the information about the texture of an inspected part from its topological characteristics and makes possible exact inspection of individual components in the stamping and punching industry. With this method even the tiniest anomalies in individual parts can be made visible that would remain undiscovered with other methods. During the inspection process the inspected part is illuminated from several angles and captured by a camera. The resulting images only show the dispersion of light and shadow. Based on these (real) single images, the software calculates different topographical images that only show the 3D information about the part’s surface. This makes quality inspection independent of changes in the surface of the inspected part that would otherwise show up in the texture
24 May 2023 | Automation
image and prevent stable evaluation. With the “shape from shading” process and conventional image processing techniques, even scratches, cracks and indentions with heights or depths of only a few micrometers can be reliably detected.
Due to the special LED illumination, the method works reliably even with dark or shiny surfaces. A sophisticated algorithm that compensates movement allows the process to be applied to moving objects, too.
Tackling complex textures with AI The AI-based process is used to inspect and evaluate the images taken. It is a special technique based on deep neural networks (DNN). Here, a convolutional autoencoder works in combination with differential image generation to visualise unusual or unexpected deviations in images of inspected parts. Neural networks are often the only option when it comes to variability among good parts and decision criteria between OK and NOK components that can’t be sufficiently described by mathematics. To use anomaly detection, the software needs to be taught first. The deep neural network is fed with images of OK parts and learns their characteristics and the skill to reconstruct them as precisely as possible. Provided that the anomaly is easily recognisable, users can train the neuronal network with coloured or monochrome images and with depth or
curvature images. In the anomaly-detection method, a
reconstruction of an inspected part will not include the anomaly but also look at a corresponding good part, establishing the differences between the two. The anomalies are then classified through further image-processing methods or even AI, which triggers the separation of the part when an anomaly is detected. After several production batches, users can feed the software with more pictures of OK parts that may have different characteristics than the parts in the first round, further refining the method.
A promising combination With the use of AI, manufacturers can vastly improve their quality assurance regarding unusual or only sporadically occurring defects. These defects are often not covered by the mathematical parameters used in conventional, rule- based inspection methods. Therefore, parts with these faults do neither get detected nor sorted out. Going forward, manufacturers will in all probability use a combination of conventional, rule-based and AI-based methods, because one can’t replace the other but they do complement each other for best results.
CONTACT:
Kistler
www.kistler.com
automationmagazine.co.uk
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66
