Based on The Recursive Identifier of Different Innovation Lengths On-off Detection Strategy of Slow-switching Hammerstein System

For the slow-switching Hammerstein system in an impulsive noise environment, multiple identifiers are used to work together to detect the switching point quickly and accurately, and at the same time obtain the parameter estimates of the sub-model. Recursive identification of multiple innovations can improve the accuracy of the identification results and increase the robustness of the identification algorithm. Recursive identification of short innovations is more sensitive to changes in the system environment. Compare the identification results of the two identification algorithms to determine whether subsystem switching occurs and can resist the interference of impulse noise. During the switching process of the subsystem, the initial identification value generated during the switching process is confirmed to improve the convergence speed and speed up the switching process. Finally, simulation experiments prove the superiority of the proposed switching scheme.