Set membership estimation of state and parameters in quantity models of water supply and distribution systems

The concept of joint state and parameter estimation for water supply systems under bounded uncertainty is presented in this paper. A recursive scheme to tackle dynamic estimation problems is proposed. The nonlinear non-convex estimation problem is transformed into a separable programming problem, which is formulated as a sparse mixed integer linear programming problem by piecewise linear approximation in order to guarantee the global optima. A real water system is extensively studied using the algorithm presented in this paper