The normalization PCA model and its application in fault detection of wind power generation system

The principal component analysis method is usually used for fault detection under the steady conditions, however, when system works under the non-steady conditions, the false alarm rate and the missing alarm rate, tested by the T² control limit, are so high. The main reason for this situation is that the sampled data is accord with normal distribution under the steady conditions, whereas the data does not satisfy normal distribution under the non-steady conditions, but T² control limit can only detect fault effectively for the data conforming to normal distribution. So this paper firstly analyzes the characteristics of the periodic non-steady conditions and then puts forward a normalization PCA (NPCA) model according to the precondition of effective detection under the T² control limit. This model deals with the measured data for normalization data based on the longitudinal standardization, and then uses T² control limit to detect fault. At the end, it is applied to wind power generation system, and the results verify the effectiveness of the model.