Intelligent Techniques in Condition Monitoring of Electromechanical Energy Conversion Systems (I-Tech)

Electromechanical energy conversion systems, such as electric vehicles, wind turbines, or hydraulic power units, are ubiquitous in industry. A failure in any part of the system can incur considerable economical losses or might endanger the safety of the humans and environment. To minimize these risks, the condition of these systems is continuously monitored for prognosis and diagnosis.

I-Tech research project develops novel machine learning methods to automate the condition monitoring of these systems. We investigate high-dimensional non-linear models such as artificial deep neural networks, random forests or networked exponential families. We develop modern AI-based methods for condition monitoring of electromechanical energy conversion systems, or powertrains. In order to ensure the safe and efficient functioning of these powertrains we will predict their incipient faults at an early stage.

The I-Tech research project aims at developing modern machine learning methods (ML) to monitor the health of powertrains and accurately diagnoses and prognoses their incipient faulty operations.

The condition monitoring systems can be easily deployed in different sectors of industry and thus provide it with a mean for economic growth. Furthermore, it impacts the well-being through secure use of the energy conversion systems and electric vehicles as well as reduced need for scheduled maintenance, e.g. in offshore wind farms, which is very risky for the personnel. The developed simulations methods will make it possible to design robust, efficient and affordable powertrains.

Academy of Finland

Aalto University