• Energy Research

This paper introduces a machine learning based control strategy for energy converter arrays designed to work under realistic conditions where the optimal control parameter can not be obtained analytically. The control strategy neither relies on a mathematical model, nor does it need a priori information about the energy medium. Therefore several identical energy converters are arranged so that they are affected simultaneously by the energy medium. Each device uses a different control strategy, of which at least one has to be the machine learning approach presented in this paper. During operation all energy converters record the absorbed power and control output; the machine learning device gets the data from the converter with the highest power absorption and so learns the best performing control strategy for each situation. Consequently, the overall network has a better overall performance than each individual strategy. This concept is evaluated for wave energy converters (WECs) with numerical simulations and experiments with physical scale models in a wave tank. In the first of two numerical simulations, the learnable WEC works in an array with four WECs applying a constant damping factor. In the second simulation, two learnable WECs were learning with each other. It showed that in the first test the WEC was able to absorb as much as the best constant damping WEC, while in the second run it could absorb even slightly more. During the physical model test, the ANN showed its ability to select the better of two possible damping coefficients based on real world input data.

A challenge while applying latching control on a wave energy converter (WEC) is to find a reliable and robust control strategy working in irregular waves and handling the non-ideal behavior of real WECs. In this paper, a robust and model-free collaborative learning approach for latchable WECs in an array is presented. A machine learning algorithm with a shallow artificial neural network (ANN) is used to find optimal latching times. The applied strategy is compared to a latching time that is linearly correlated with the mean wave period: It is remarkable that the ANN-based WEC achieved a similar power absorption as the WEC applying a linear latching time, by applying only two different latching times. The strategy was tested in a numerical simulation, where for some sea states it absorbed more than twice the power compared to the uncontrolled WEC and over 30% more power than a WEC with constant latching. In wave tank tests with a 1:10 physical scale model the advantage decreased to +3% compared to the best tested constant latching WEC, which is explained by the lower advantage of the latching strategy caused by the non-ideal latching of the physical power take-off model.

Abstract A submerged wave device generates energy from the relative motion of floating bodies. In WaveSub, three floats are joined to a reactor; each connected to a spring and generator. Electricity generated damps the orbital movements of the floats. The forces are non-linear and each float interacts with the others. Tuning to the wave climate is achieved by changing the line lengths, so there is a need to understand the performance trade-offs for a large number of configurations. This requires an efficient, large displacement, multidirectional, multi-body numerical scheme. Results from a 1/25 scale wave basin experiment are described. Here, we show that a time domain linear potential flow formulation (Nemoh, WEC-Sim) can match the tank testing provided that suitably tuned drag coefficients are employed. Inviscid linear potential models can match some wave device experiments; however, additional viscous terms generally provide better accuracy. Scale experiments are also prone to mechanical friction, and we estimate friction terms to improve the correlation further. The resulting error in mean power between numerical and physical models is approximately 10%. Predicted device movement shows a good match. Overall, drag terms in time domain wave energy modelling will improve simulation accuracy in wave renewable energy device design.

Abstract Physical modelling of floating offshore wind turbines (FOWTs) is challenging due to the complexities associated with simultaneous application of two different scaling laws, governing the hydrodynamic and aerodynamic loading on the structure. To avoid these issues, this paper presents a real-time hybrid testing strategy in which a feedback-loop, consisting of an on-board fan, and control algorithm, is utilised to emulate the aerodynamic forces acting on the FOWT system. Here, we apply this strategy to a 70th-scale IEA Wind 15MW reference wind turbine mounted on a version of the VolturnUS-S platform. Unlike other similar methods, which directly simulate the aerodynamic loads for the fan’s control using an aerodynamic code running in parallel with the experiment, this example utilises a surrogate model trained on numerical model data calculated in advance. This strategy enables high fidelity numerical model data, or even physical data, to be included in the aerodynamic emulation, by removing the requirement for real-time simulation, and, therefore, potentially enables more accurate loading predictions to be used in the experiments. This paper documents the development of the real-time hybrid testing system in the Coastal Ocean And Sediment Transport (COAST) Laboratory at the University of Plymouth in the U.K., including the hardware, software and instrumentation set-up, and demonstrates the power of the surrogate-based aerodynamic emulator based on numerical data calculated using OpenFAST.

An alternating rotatory generator using an eddy current break is developed as a physical scale model of a direct-driven floating point absorber power take-off (PTO) for wave tank tests. It is shown that this design is a simple and cost-effective way to get an accurate linear damping PTO. The device shows some beneficial characteristics, making it an interesting option for full scale devices: For similar weights the inertia can be significantly higher than for linear generators, allowing it to operate with natural frequencies close to typical wave frequencies. The influence of the higher inertia on the power absorption is tested using both a numerical simulation and physical wave tank tests. With the increased inertia the PTO is able to absorb more than double the energy of a comparable direct-driven linear generator in some sea states. Moreover, the alternating rotatory generator allows the absorption characteristic to be tuned by changing the inertia and the generator damping.