Combining Machine Learning and Operational Modal Analysis Approaches to Gain Insights in Wind Turbine Drivetrain Dynamic
Operational Modal Analysis (OMA) is one of the branches of experimental modal analysis which allows extracting modal parameters based on measuring only the responses of a structure under ambient or operational excitation which is not needed to be measured
- PDF / 1,188,464 Bytes
- 7 Pages / 595.516 x 790.987 pts Page_size
- 100 Downloads / 204 Views
Combining Machine Learning and Operational Modal Analysis Approaches to Gain Insights in Wind Turbine Drivetrain Dynamics N. Gioia, P. J. Daems, T. Verstraeten, P. Guillaume, and J. Helsen
Abstract Operational Modal Analysis (OMA) is one of the branches of experimental modal analysis which allows extracting modal parameters based on measuring only the responses of a structure under ambient or operational excitation which is not needed to be measured. This makes OMA extremely attractive to modal analysis of big structures such as wind turbines where providing measured excitation force is an extremely difficult task. One of the main OMA assumption concerning the excitation is that it is distributed randomly both temporally and spatially. Obviously, closer the real excitation is to the assumed one, better modal parameter estimation one can expect. Traditionally, wind excitation is considered as a perfect excitation obeying the OMA assumptions. However, the present study shows that the aeroelastic phenomena due to rotor rotation dramatically changes the character of aerodynamic excitation and sets limitations on the applicability of OMA to operational wind turbines. The main purpose of the study is to warn the experimentalists about these limitations and discuss possible ways of dealing with them. Keywords Automatic operational modal analysis · Wind turbine drivetrain · Harmonics · Machine learning · Noise vibration and harshness
30.1 Introduction The continuously increasing demand of wind energy production has led the interest of the wind industry towards the effort of reducing the cost of produced energy. This has caused the so called up-scaling trend in the last decades: bigger turbines with increased height are being produced and higher capacity models are being developed [1]. Moreover, offshore farms are becoming increasingly popular: at sea, the wind is generally more stable and stronger and there are less limitations on the size and on the produced noise of the turbine due to the lack of interaction with the human habitation. The increase of the loads acting on the different components caused by this up-scaling trend however makes a robust design harder. Moreover, the increased machine size increases significantly the challenge of installing offshore wind turbines. From a design point of view, a big challenge is that the loads acting on the different components of the machines are strongly dependent on the conditions at which the machines operate. Therefore, they are difficult to predict and simulate. A pressing issue in this context is that there is no complete understanding of the dynamics of the different machine components. For this reason, the design of machines solely based on simulated models cannot be considered adequate. Additional experimental tests must thus take place to have a better insight in the loads acting on the machines and to improve the design of the components. What is currently missing in the industrial design process is a continuous insight in the modal behavior of machines during thei
Data Loading...
