A Health State Assessment Method for Wind Turbines Based on Spherical Fuzzy Sets and Cloud Model

With the rapid development of the global wind power industry, wind turbines operate for long periods in complex, variable, and often harsh environments, resulting in persistently high operation and maintenance costs. Therefore, accurate health state assessment is of great importance for improving turbine reliability and reducing maintenance costs. This paper proposes a wind turbine health state assessment method based on spherical fuzzy sets and cloud models. By integrating the SFS-AHP, an improved entropy weight method, and game theory, a combined weighting model is established to achieve an effective balance between subjective judgment and objective data. To address the fuzziness and uncertainty of health states, a cloud model-based fuzzy comprehensive evaluation method is adopted. The degradation degrees of various indicators are normalized to construct a membership matrix, which is then combined with a weighted average fuzzy operator to realize accurate health state classification. Simulation results demonstrate that the proposed method can effectively handle uncertainty in the assessment process and provide a reliable basis for refined operation and maintenance scheduling and active power optimization of wind turbines.