Intermittent fault is an important factor causing built-in test(BIT) false alarm. Diagnosing intermittent fault is an important approach to restrain BIT false alarms. This paper proposes a intermittent faults diagnostic methods based on empirical mode decomposition (EMD) and multiple support vector machine (MSVM). Firstly, the EMD method is used to decompose the original signal into a number of intrinsic mode function (IMF), the auto-regressive (AR) model of each IMF component is established. The AR model parameters and the variance of remnant are regarded as the feature vectors, are input to MSVM classifier, so the working conditions and faults are classified. The experimental results show that the BIT false alarm caused by intermittent fault can be effectively reduced by this proposed method.