Abstract
Systematic measuring of hydraulic machine’s performance data at hydraulic model test-rigs involves comprehensive expert knowledge of the test-rig-engineer and is time consuming, as the multi-dimensional operation space must be explored manually. Expertise is needed for taking into account specific performance limits of test-rig equipment, model turbine, storage pumps or pump-turbines as well as some hysteresis of the setup due to flow separation and dealing with quite operation point dependent gains between controlled parameters and measured quantities. In order to free valuable manpower from the burden of shiftwork, the measurement procedure is subject to automation. But testing new automation concepts involves safety critical or expensive tests and consumes valuable time at test-rig too.
To develop and validate new automation concepts offline, we present a hybrid data-driven modelling approach to create a digital twin of the combined setup of a hydraulic turbine on a hydraulic test-rig. Special attention is paid that the modelling approach is consistent with existing mathematical relations governed by either physical models or norms. The presented approach allows separation of test-rig and hydraulic model machine under test and by this enables offline-validation of automation concepts on different combinations of test-rigs and hydraulic model machines. The modelling approach is demonstrated performing cross-validation using recorded measurement data.
