Abstract
As global demand for offshore wind energy continues to rise, the imperative to enhance the profitability of wind power projects and reduce their operational costs becomes increasingly urgent. This study proposes an innovative approach to optimize the inspection routes of offshore wind farms, which integrates the K-means clustering algorithm and genetic algorithm (GA). In this paper, the inspection route planning problem is formulated as a multiple traveling salesman problem (mTSP), and the advantages of the K-means clustering algorithm in distance similarity are utilized to effectively group the positions of wind turbines, thereby optimizing the inspection schedule for vessels. Subsequently, by harnessing the powerful optimization capability and robustness of genetic algorithms, further refinement is conducted to search for the optimal inspection routes, aiming to achieve cost reduction objectives. The results of simulation experiments demonstrate the effectiveness of this integrated approach. Compared to traditional genetic algorithms, the inspection route length has been significantly reduced, from 93 kilometers to 79.36 kilometers. Simultaneously, operational costs have also experienced a notable decrease, dropping from 141,500 Chinese Yuan to 125,600 Chinese Yuan.