This paper proposes a method based on the artificial neural network model to evaluate health state of wind turbine by using SCADA data. In this study, the core idea is to analysis the health condition of wind turbine by BP-ANN model, a kind of supervised learning technique is used in this proposed model, by selecting standard data as baseline data and compare with current testing data can realize the evaluation the state of wind turbines. By verifying the validation of the model through real SCADA data, and by visualization method and BP neural network to realize health assessment. This article focuses on the health status of the wind turbines, and provide a method to assess performance. Experimental results show that this method as an effective tool that can achieve the health assessment of wind turbines.