Jožef Stefan Institute

Streaming Machine Learning and Online Active Learning for Automated Visual Inspection

Nov 22, 2021 | Jože M. Rožanec, Elena Trajkova, Paulien Dam, Blaž Fortuna, Dunja Mladenić

Quality control is a key activity performed by manufacturing companies to verify product conformance to the requirements and specifications. Standardized quality control ensures that all the products are evaluated under the same criteria. The decreased cost of sensors and connectivity enabled an increasing digitalization of manufacturing and provided greater data availability. Such data availability has spurred the development of artificial intelligence models, which allow higher degrees of automation and reduced bias when inspecting the products. Furthermore, the increased speed of inspection reduces overall costs and time required for defect inspection. In this research, we compare five streaming machine learning algorithms applied to visual defect inspection with real world data provided by Philips Consumer Lifestyle BV. Furthermore, we compare them in a streaming active learning context, which reduces the data labeling effort in a real-world context. Our results show that active learning reduces the data labeling effort by almost 15% on average for the worst case, while keeping an acceptable classification performance. The use of machine learning models for automated visual inspection are expected to speed up the quality inspection up to 40%....

Inkjet-Printing-Derived Lead-Zirconate-Titanate-Based Thick Films For Printed Electronics

Jul 13, 2021 | Danjela Kuscer, Silvo Drnovšek, Franck Levassort

We have investigated the processing of lead-zirconate-titanate-based thick films by inkjet printing Pb (Zr0.53Ti0.47)0.98Nb0.02O3 with a 6 mol% excess of PbO nanosized powder dispersed in water. Differentwaveforms were employed to determine the optimum size and shape of the drops. A uniform, defect-free pattern with dimensions of 4 mm × 4 mm can be printed using 20 V and a drop spacing of 20 μm. The inkjet-printed films were heated to 400 °C to remove the organics and subsequently sintered at 750 and 850 °C. The correlations between the density, grain size and electromechanical properties of the thick films and bulk ceramics are qualitatively discussed. A thickness coupling factor of 46% was obtained for a 15-μm-thick film sintered at low temperature of 850 °C, which is comparable to the value of the bulk ceramic with an identical nominal chemical composition. Our results are important for the economic and environmental-benign printing of piezoelectric materials applicable in variety of electronic devices, such as sensors, actuators, transformers, piezoelectric energy harvesters and transducers....