@inproceedings{147a3f37cab1439c99b89ad97e9da7f3,
title = "Internal Reconstruction Gradient Blind Estimation Method for Hammerstien-like System",
abstract = "Most of the block-oriented nonlinear system identifications focus on the memoryless nonlinear sub-model, there exist relatively few researches on nonlinear submodel with memory. In this work, we study the blind identification of Hammerstein-like system with memory nonlinearity. By force of the half-substitution technology, the estimation model of the Hammerstein-like system is written as a compact form in which the bulk-parameters are escaped, the high time-consuming is avoided. To achieve the parameter estimation, the system order information is obtained using the determinant ratio scheme. For the presented algorithm, we applied an internal reconstruction idea to revise the multi-innovation gradient scheme in which the innovation length obstacle is addressed. For the unmeasurable variable, we use the reference model method to realize indirect measurability of unmeasurable variable. Finally, the effectiveness of the developed estimator is demonstrated based on the numerical example.",
keywords = "Hammerstein-like, System identification, backlash, blind estimation, multi-innovation method",
author = "Linwei Li and Xianglong Liu and Fengxian Wang and Xuemei Ren and Hangli Ren and Mo Zhou",
note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 10th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2021 ; Conference date: 14-05-2021 Through 16-05-2021",
year = "2021",
month = may,
day = "14",
doi = "10.1109/DDCLS52934.2021.9455365",
language = "English",
series = "Proceedings of 2021 IEEE 10th Data Driven Control and Learning Systems Conference, DDCLS 2021",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "184--189",
editor = "Mingxuan Sun and Huaguang Zhang",
booktitle = "Proceedings of 2021 IEEE 10th Data Driven Control and Learning Systems Conference, DDCLS 2021",
address = "United States",
}