Events

Tutorial:
Machine Learning for Industrial Condition Monitoring – how to?

Condition monitoring (CM) of components and processes using machine learning (ML) is one of the central promises of Industry 4.0. Many successful examples have been demonstrated under laboratory conditions. However, the transfer to actual industrial application is proving difficult. The main challenge remaining is the data quality required for developing a meaningful and robust ML model: in industrial applications, most data represent the “good” condition, while samples for different fault scenarios are typically scarce. Furthermore, comprehensive training data are required covering all relevant circumstances to allow successful CM under changing environmental conditions and other causes of domain shift. Even if extensive data are available, most effort is spent on their organization to delete outliers, ensure correct labeling etc.

The tutorial will address these issues with two main approaches. The first is a checklist to guide users through the complete process of an ML project, starting with project, measurement, and data planning proceeding to data acquisition, checking and pre-processing up to finally building and validating the ML model. This checklist specifically supports users with little experience in ML to be successful. The second approach is classical process optimization based on insights gained using explainable machine learning methods.

Presenters:

Tizian Schneider, Centre for Mechatronics and Automation Technology

Andreas Schütze, Lab for Measurement Technology, Saarland University

Prof. Andreas Schütze has been invited to give a keynote presentation at

The International Symposium on Olfaction and Electronic Nose (ISOEN) is the world’s premiere technical conference in artificial chemoreception, olfaction and taste.
ISOEN 2024 provides a forum for scientists, engineers and practitioners to share their latest findings, innovations and products in the area of artificial chemoreception.

ISOEN 2024 will be held in Grapevine, Texas, a town right next to the Dallas Forth-Worth (DFW) International Airport, Texas, USA.

The Call for Papers is open until January 15, 2024.
Topics of interest:

• Odor sampling: headspace analysis, dynamic sampling, pre-concentration and storage
• New detection principles and materials for sensors for gases, odors and liquids
• Sensors with multiple responses (known as multivariable or multiparameter sensors, virtual sensor arrays)
• Odor and taste analysis devices, including Electronic Noses, Electronic Tongues
• New data analytics (machine learning) for immunity to interferences, improved stability of baseline and sensitivity
• Applications: medical, industrial, environmental, air quality, and food safety
• IoT and robotic systems with chemical and biological sensors
• Odor and gustatory perception and olfactory display
• Bioengineering: cell-based olfactory sensors, receptor-based sensors, bioinspired algorithms

Environmental pollution is still one of the greatest challenges for Europe and worldwide. While outdoor air quality is frequently discussed in terms of NOx or ozone levels, indoor pollution is often overlooked. However, as many people spend most of their time indoors and because of increased building insulation and reduced air exchange, indoor pollution levels can be significantly higher and actually contribute similarly to the overall burden of disease.

The tutorial introduced the “why, what and how” of monitoring indoor pollution with special emphasis on volatile organic compounds (VOC). These are major contributors to both short (headaches, dizziness) and long term (asthma, cardiovascular diseases, cancer) health effects. The tutorial focussed on the new standard VDI/VDE 3518 part 4 defining standardized test instructions and test gases for VOC detectors for indoor air quality measurement. Target audience were engineers in sensors and sensor systems R&D, quality control and calibration as well as in building management.

Many thanks to Dr. Richard Fix of Bosch Sensortec for the excellent collaboration both in getting the standard finalized and in presenting the new approach duuring this tutorial.

Am 20. März 2023 hat Dr.-Ing. Tobias Baur seine Dissertation im Rahmen seines öffentlichen Promotionskolloquiums vorgestellt und verteidigt - herzlichen Glückwunsch vom gesamten LMT-Team!

Herzlichen Dank an die Prüfungskommission mit (von rechts): Prof. Max Fleischer (externer Gutachter, Siemens Energy), Prof. Uwe Hartmann (Vorsitz), PD Tilman Sauerwald (Gutachter), Dr.-Ing. Sarah Fischer (akad. Beisitzerin), Prof. Kathrin Flaßkamp (Gutachterin) und Prof. Schütze.

Titel / title:

Dynamic operation, efficient calibration, and advanced data analysis of gas sensors: from modelling to real-world operation

This thesis demonstrates the use of dynamic operation, efficient calibration and advanced data analysis using metal oxide semiconductor (MOS) gas sensors as an example – from modeling to real-world operation. The necessary steps for an application-specific, selective indoor volatile organic compound (VOC) measurement system are addressed, analyzed and improved. Selective measurements of VOCs in the laboratory and in the field are successfully demonstrated. The calibrated models are compared with analytical measurements using release tests. The excellent agreement of the results is unique in current research.

Offizieller Aushang / official announcement