Interacting multiple model algorithm with maximum likelihood estimation for FDI

In this paper we propose an approach to detect, identify and estimate failures, including partial failures, in a dynamic system. The approach (IM/sup 3/L) uses the interacting multiple model (IMM) estimators to detect and identify total and partial failures and the maximum likelihood estimator (MLE) to estimate the extent of failure. It provides an effective and integrated framework for fault detection, identification and state estimation. The hierarchical structure of the fault model set for FDI is further addressed and a two-level hierarchical IMM (HIMM) is implemented. By using an aircraft example, the proposed IM/sup 3/L approach is evaluated and its performance is compared with those of the HIMM and autonomous MM (AMM). The robustness of IM/sup 3/L is analyzed in the presence of the uncertain noise statistics. The results show that the proposed approach provides not only fast detection and proper identification but also good estimation of the failure extent as well as robust state estimation.