idw – Informationsdienst Wissenschaft
Nachrichten, Termine, Experten
Nachrichten, Termine, Experten
Electric motors are getting smaller, lighter and more powerful – and that makes overheating a growing risk. A research team led by Professor Matthias Nienhaus at Saarland University has developed an AI-assisted method of determining the temperature distribution inside a running electric motor in real time – and without the need for additional hardware. The team will be showcasing the technology at the Hannover Messe (20–24 April) and is looking for industry partners to transfer it into practical and commercial applications. Hall 11, Stand D41
As manufacturers strive to reduce material use and keep their devices compact, any electric motors they contain must also become smaller and lighter – while still delivering high performance. But when motors generate high power within a tight motor housing, they heat up. Crucially, the temperature inside a motor does not rise uniformly. Different components reach different temperatures, and hotspots accelerate ageing, shortening service life and reducing performance.
‘The ability to operate an electric drive safely and, in particular, to control it efficiently depends on power losses and thermal processes within the motor,’ explains Matthias Nienhaus, professor of drive systems engineering at Saarland University. Ideally, the temperature inside the motor should be monitored continuously so that it can run as efficiently as possible without reaching critical limits. However, integrating temperature sensors into an electric motor is far from straightforward. The smaller the drive, the less space there is for additional measurement hardware. Moreover, the most relevant readings are needed when the motor is running under high load and at high speeds – conditions that make sensor deployment even more challenging. ‘Conventional methods for measuring temperature inside the motor tend to be complex and expensive, particularly when trying to assess the temperature of motor parts that are moving at high speeds. So, in practice, these methods are often not used,’ says Matthias Nienhaus.
Nienhaus and his team on Saarland University’s Saarbrücken campus are developing a method that addresses exactly this challenge: deriving temperature information from electric motors without requiring extensive additional instrumentation. Using only a small set of signals already available from the motor, the team is able to continuously determine the temperatures of key components while the motor is running. ‘We’re developing a monitoring and control system that shows us how temperatures inside the motor change during operation, and this enables precise and efficient power regulation,’ explains Matthias Nienhaus. The benefit is twofold. The system could warn of thermal overload and reduce power early enough to prevent overheating. Conversely, if the temperatures are within their permissible limits, the system could safely increase motor power – helping to get the best out of these compact drives.
AI-supported temperature diagnostics – the motor becomes its own sensor
Nienhaus’s research group specializes in using the motor itself as a sensor by extracting motor-condition data directly from the drive’s electromagnetic fields. With their new approach, they are able to determine motor temperatures during operation – including the temperatures of rotating components. ‘We estimate the temperatures in real time using artificial intelligence methods,’ says Saeed Farzami, a doctoral researcher in Nienhaus’s team. To do this, he had to collect vast amounts of electrical, mechanical and thermal data on a test bench he designed himself. The data was gathered from sensors that Farzami placed at those critical points inside the motor where temperature matters: at various locations in the windings, in the rotor and on the housing.
He recorded signals from the motor across a wide range of operating scenarios – from low to high rotational speeds – and then used the resulting dataset to train a neural network. Artificial neural networks are inspired by the human brain: they learn from ‘experience’ – in this case, from exposure to vast quantities of training data. And much like its biological counterpart, an AI model can be trained to recognize and evaluate complex patterns by processing large datasets and iteratively correcting errors. ‘With our thermal AI models, we’re now able to estimate the temperature distribution across the various motor components using only a few measurement values,’ explains Saeed Farzami.
At the Hannover Messe, Matthias Nienhaus’s research team will be showcasing the new technology on an electric-motor test bench. The group is seeking industrial partners to further develop their AI-assisted monitoring and control system for real-time temperature estimation in electric drives and to translate this technology into practical and commercial applications.
Joint stand ‘Germany’s Saarland’, Hall 11, Stand D41.
Professor Matthias Nienhaus (Drive Systems Engineering, Saarland University): Tel.: +49 681 302-71681; Email: info@lat.uni-saarland.de
Saeed Farzami Sarcheshmeh: Tel.: +49 681 302- 71690; Email: farzami@lat.uni-saarland.de
https://www.uni-saarland.de/en/news/hannover-messe-motor-heat-45091.html - Further press photographs
To estimate the temperature distribution in an electric motor in real time using AI methods, PhD stu ...
Source: Credit: Oliver Dietze
Copyright: Saarland University
Professor Matthias Nienhaus’s research team is developing AI-based methods of determining the temper ...
Source: Credit: Oliver Dietze
Copyright: Saarland University
Criteria of this press release:
Business and commerce, Journalists, Scientists and scholars
Electrical engineering, Information technology, Mechanical engineering
transregional, national
Research projects, Transfer of Science or Research
English
To estimate the temperature distribution in an electric motor in real time using AI methods, PhD stu ...
Source: Credit: Oliver Dietze
Copyright: Saarland University
Professor Matthias Nienhaus’s research team is developing AI-based methods of determining the temper ...
Source: Credit: Oliver Dietze
Copyright: Saarland University
You can combine search terms with and, or and/or not, e.g. Philo not logy.
You can use brackets to separate combinations from each other, e.g. (Philo not logy) or (Psycho and logy).
Coherent groups of words will be located as complete phrases if you put them into quotation marks, e.g. “Federal Republic of Germany”.
You can also use the advanced search without entering search terms. It will then follow the criteria you have selected (e.g. country or subject area).
If you have not selected any criteria in a given category, the entire category will be searched (e.g. all subject areas or all countries).
