This paper studies the parameter identification problem of hammerstein output-error systems with two-segmentnonlinearities. New switching sequences are proposed to reduce the number of parameters to be estimated. A s...
详细信息
This paper studies the parameter identification problem of hammerstein output-error systems with two-segmentnonlinearities. New switching sequences are proposed to reduce the number of parameters to be estimated. A stochastic gradient identification algorithm together with the convergence analysis is further developed. A varying forgetting factor scheme is used to make a tradeoff between the convergence rate and estimation accuracy. Both numerical simulation results and applications to distillation columns are provided to show the effectiveness of the proposed method.
暂无评论