The main focus of this project is the Condition Monitoring (CM) of Axial Piston Pumps (APPs), which, in contrast to other types of machinery, has received far less attention both in research and industry. Still, APPs are currently used in several critical industrial applications and comprise a very high investment. The harsh operational conditions and large loads make these structures very sensitive to damage. Hence, highly sensitive and responsive CM algorithms can result in significant operations and maintenance savings. While Machine Learning (ML)-driven CM methods can potentially provide high damage diagnosis performance, their performance is bound on the availability of sufficient training data. The main objective of this project is to develop high-fidelity Finite Element Models (FEMs) to form so-called “Digital Twins” of APPs, which can be used as synthetic data generators for various damage scenarios in the training of ML-driven CM algorithms. The project is funded by Innovation fund.
Digital Twins of Axial Piston Pumps (APPs) for Machine Learning-based Condition Monitoring
