Abstract
In this paper, system identification problem in which input and output data are measured by using sensors with static nonlinearity, such as saturation, dead zone, and so on. A novel system identification method which estimates sensor erros due to its nonlinearity, as well as system parameters, is proposed. The key idea is to formulate the identification problem as a constrained optimization problem. Then the system parameters are estimated by using quasi-Newton method. The effectiveness of the proposed method is examined through numerical experiments.
