An optimal sub-structure for a TLP-type wind turbine based on neuro-response surface method

Renewable energy is of global interest due to the exhaustion of fossil energy and environmental pollution. Wind energy in particular has attracted worldwide attention. In recent years, offshore wind turbines have been increasingly popular for addressing the problems of onshore wind turbine. The major objective in this research is to establish an optimal design process for the sub-structure of floating-type offshore wind turbines in the initial design stage. For this purpose, we proposed a framework for optimal design based on the neuro-response surface method (NRSM). The constructed framework is composed of three parts: the definition of the geometry, the generation of the design space, and an optimization process. To reduce the time for performance analysis and minimize the prediction errors, the approximate design space is generated using the back-propagation neural network which is considered as the NRSM. The optimization process is done for the generated design space by non-dominated sorting genetic algorithm-II (NSGA-II). Through case study on a side constraint optimization of the 5 MW TLP-type wind turbine, we have confirmed the usefulness of the constructed framework in view of hydrodynamic performances. In future research, we will handle further optimization problems in naval architectural and ocean engineering using the constructed framework.