Wind turbine state evaluation and prediction method and system

The invention discloses a wind turbine state evaluation and prediction method and system. The method comprises the steps of obtaining data of health periods from history data of the same model of wind turbines, carrying out statistics to generate health value ranges of index parameters of different space time dimensions, providing a weight corresponding to the deviation degree between each parameter and each health value range, and establishing a health model; taking the change condition of the same parameter in the history data of the same model of wind turbines as a space domain, extracting change trends and ranges of the index parameters in space time with wind turbine faults, and establishing a fault model; and comparing wind turbine parameters which are monitored in real time with the health model and the fault model, evaluating and predicting current wind turbine states and outputting alarm in due time. According to the method and the system, the wind turbine health states can be monitored and evaluated