WSEAS Transactions on Circuits and Systems
Print ISSN: 1109-2734, E-ISSN: 2224-266X
Volume 12, 2013
A Fault Detection Method Based on Dynamic Peak-valley Limit under the Non-Steady Conditions
Authors: , , ,
Abstract: The multivariate statistical methods are commonly used to fault detection through a straight limit line given by the HotellingT2. However, the traditional straight limit line is difficult to detect the fault effectively under the non-steady conditions, and the rate of false alarm and missing alarm is high. For these problems above, a fault detection method based on dynamic peak-valley limit is proposed in this paper. The proposed method introduces relative principal component analysis (RPCA) to carry out data dimension reduction, extract principal component (PCs) and calculate T2 statistics, then adopts moving least squares (MLS) to preprocess T2 statistics to obtain the fitting curve which is called peak-valley curve, and finally connects peak and valley points in the curve to construct another control limit, by introducing a weight combined with the traditional straight limit line to construct the dynamic peak-valley limit. At the end, it is applied to wind power generation system, and the results could verify the effectiveness of the method.