A novel robust fault diagnosis scheme,which possesses fault estimate capability as well as fault diagnosis property,is proposed.The scheme is developed based on a suitable combination of the adaptive multiple model (AMM) and unknown input observer (UIO).The main idea of the proposed scheme stems from the fact that the actuator Lock-in-Place fault is unknown (when and where the actuator gets locked are unknown),and multiple models are used to describe different fault scenarios,then a bank of unknown input observers are designed to implement the disturbance de-coupling.According to Lyapunov theory,proof of the robustness of the newly developed scheme in the presence of faults and disturbances is derived.Numerical simulation results on an aircraft example show satisfactory performance of the proposed algorithm.