In this article, a Fault Detection and Diagnosis (FDD) strategy based on Set Membership Identification is proposed for the supervision of an electrostatic microactuator subject to failure modes in its structural components. Relying on the a priori knowledge of the bound of the noise corrupting the measurement data, the parametric uncertainty is assumed to be bounded and the SMI computes the parametric sets (ellip-soids, support-orthotopes), within which the nominal parameter vector resides. A fault is detected at the time instant that an empty parametric set is obtained. Prior to the fault isolation and identification procedure, a control reconfiguration scheme is used for prevention of catastrophic damages in the system, due to large parameter variations. Simulations studies are used to verify the efficiency of the suggested strategy.