The optimal torque (OT) method is a common method to realize the maximum power point tracking (MPPT) of wind turbines. By modifying the torque curve gain, the wind energy capture efficiency of wind turbine operating in MPPT mode under turbulent conditions can be improved. However, there is a precondition that the torque curve gain should be reasonably designed comprehensively considering the influence of turbulence characteristics. The existing researches construct the optimal parameter model describing the relationship between optimal torque curve gain and turbulence characteristics offline, then, based on the model, realize the dynamic optimization of torque curve gain according to the time-varying turbulence characteristics online. Nevertheless, because there is a complex three-dimensional nonlinear function relation between the optimal torque curve gain and turbulence characteristic indexes including average wind speed, turbulence intensity and turbulence frequency, it is necessary to traverse search the corresponding optimal torque gain based on a large number of turbulent wind speed series with different characteristics, so as to obtain sufficient samples for constructing the optimal parameter model. The corresponding huge amount of dynamic simulation calculation is very time-consuming and difficult to be applied in batch engineering. It was found in this paper that the wind energy capture efficiency corresponding to the OT method (PfavgOT ) can reflect the comprehensive effect of multiple factors affecting the MPPT of wind turbine. And the results based on Spearman rank correlation analysis show that the correlation coefficient between PfavgOT and the optimal torque curve gain is greater than 0.9, which is a very strong correlation. By comparison, the Spearman correlation coefficient between optimal torque curve gain and three turbulence characteristics is about 0.5, indicates that the degree of correlation is only moderate. Therefore, it was proposed to use PfavgOT as a single-valued characterization index to construct a quantitative relationship with the optimal torque gain, which can reduce the dimension of the optimal parameter model based on three variables to a single variable. On this basis, an MPPT control method was proposed to optimize the torque curve gain online according to PfavgOT and the optimal parameter model. Since the actual wind turbine adopts an improved MPPT control method with dynamic adjustment of torque curve gain, this paper constructed a digital twin of wind turbine using the OT method in programmable logic controller (PLC), and made it run synchronously with the actual wind turbine to realize the acquisition of PfavgOT . Simulation results based on FAST software developed by National Renewable Energy Laboratory show that, the proposed method reduces the time required to construct the optimal parameter model from 112.7 days to 2.3 days, not only retains the comprehensive consideration of turbulence characteristics so as to maintain high wind energy capture efficiency, but also significantly reduces the computing capacity demand and time cost, which is convenient for batch customization and rapid deployment. At the same time, based on the Beckhoff CX5130 PLC commonly used by the current batch wind turbine products, the engineering feasibility of synchronous operation of the wind turbine digital twin and actual wind turbine was tested and verified. It should be noted that, when the wind turbine model parameters used to construct the optimal parameter model and the wind turbine digital twin do not match the actual wind turbine parameters, the application effect of this method will be decreased. Therefore, how to calibrate the wind turbine model parameters based on operating data, and update the optimal parameter model and wind turbine digital twin in a timely manner remains to be further studied. © 2023 Chinese Machine Press. All rights reserved.
