Modulating function-based identification for fractional order systems

详细信息    查看全文

• 作者：Yi DaiAuthor Vitae ; Yiheng WeiAuthor Vitae ; Yangsheng HuAuthor Vitae ; Yong Wang ; ^{yongwang@ustc.edu.cn" class="auth_mail" title="E-mail the corresponding author} ; ^{ydai@mail.ustc.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae
• 关键词：Fractional order system ; Modulating function ; Modulation ; System identification ; Recursive least squares
• 刊名：Neurocomputing
• 出版年：2016
• 出版时间：15 January 2016
• 年：2016
• 卷：173
• 期：part_P3
• 页码：1959-1966
• 全文大小：663 K

文摘

This article deals with the identification of fractional order systems. A new algorithm based on modulating function is presented providing recursive parameter estimation of fractional order models. The article utilizes the property of modulating function and integration by parts, and handles the fractional order derivatives with modulating windows and numerical approximation. The algorithm achieves modulation integral on fractional order system equation, and formulates an identification model. Then the recursive least squares estimation is adopted to obtain parameters of the original fractional model with noise. It is shown that the proposed approach can arrive at a precise estimation of the parameters. Finally, numerical simulation examples are given to demonstrate the effectiveness of the proposed algorithm.