Distributed simultaneous state and parameter estimation of nonlinear systems

In this paper, we consider distributed simultaneous state and parameter estimation for a class of nonlinear systems, which the augmented model comprising both states parameters is only partially observable. Specifically, first illustrate how sensitivity analysis (SA) can select variables estimation. Then, community structure detection (CSD) based process decomposition method proposed dividing entire system into interconnected subsystems as basis Next, develop local moving horizon estimators on configured subsystem models, communicate with each other to exchange their estimates. Finally, an SA CSD (DMHE) mechanism proposed. The effectiveness approach illustrated using chemical consisting four connected reactors.