ILSE

Goal of the project is the development of technologies for
- automatic detection of unusual operating conditions in district heating systems with self-learning
systems, using the example of district heating substations
- verification and validation of intelligent learning systems in energy networks by parallel training of
application- and test-system
- adaptive learning systems that adapt continuously to a changing environment

The focus is on Deep Learning methods using neuronal networks, the area of application is operation and maintenance of district heating systems, in particular district heating substations. We will develop new methods for predictive maintenance of district heating systems, which go beyond the prevailing statistical methods. We expect new insights regarding the system-behavior when detecting unusual operating conditions. New technologies for semi-supervised learning will be developed, enabling the learning system to adapt itself continuously to changes in the district heating system during operation. In addition, we will look into new methods for verification and validation of software in data-driven development, based on parallel automatic training of core- and test-system.