文献类型：期刊文献

英文题名：An Adaptive Gradient Neural Network to Solve Dynamic Linear Matrix Equations

作者：Liao, Shan[1];Liu, Jiayong[1];Qi, Yimeng[2];Huang, Haoen[3];Zheng, Rongfeng[4];Xiao, Xiuchun[3]

机构：[1]Sichuan Univ, Sch Cyber Sci & Engn, Chengdu 610065, Peoples R China;[2]Lanzhou Univ, Sch Informat Sci & Engn, Lanzhou 730000, Peoples R China;[3]Guangdong Ocean Univ, Sch Elect & Informat Engn, Zhanjiang 524025, Peoples R China;[4]Sichuan Univ, Coll Elect & Informat Engn, Chengdu 610065, Peoples R China

年份：2022

卷号：52

期号：9

起止页码：5913

外文期刊名：IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS

收录：SCI-EXPANDED(收录号：WOS:000732205100001)、、EI(收录号：20215111369158)、Scopus(收录号：2-s2.0-85121365179)、WOS

基金：This work was supported in part by the Frontier Science and Technology Innovation Projects of National Key Research and Development Program under Grant 2019QY1405; in part by the Key Research and Development Program of Sichuan Province under Grant 2020YFG0076; in part by the Sichuan Science and Technology Program under Grant 2021YFG0159; in part by the Key Research and Development Program of Sichuan Province under Grant 2021YFG0156; in part by the Fundamental Research Funds for the Central Universities; in part by the Guangdong Graduate Education Innovation Project, Graduate Academic Forum under Grant 2020XSLT27; in part by the Key Laboratory of Digital Signal and Image Processing of Guangdong Province under Grant 2019GDDSIPL-01; and in part by the Guangdong Basic and Applied Basic Research Foundation under Grant 2021A1515011847. This article was recommended by Associate Editor X. Zhao.

语种：英文

外文关键词：Mathematical models; Computational modeling; Heuristic algorithms; Adaptation models; Convergence; Numerical models; Load modeling; Adaptive gradient recurrent neural networks (AGRNNs); angle-of-arrival (AoA) localization; dynamic linear matrix equations; inversion-free; motion planning

外文摘要：In this article, the existing approaches, including numerical algorithms as well as neural networks to solve dynamic linear matrix equations, have been presented and reviewed. Specifically, the conventional gradient recurrent neural networks (CGRNNs) and the conventional zeroing neural networks (CZNNs) are successively provided to solve the dynamic problems and linear matrix equations, both of which manifest inherent limitations during the solving procedures. To remedy the drawbacks on convergence time, nonzero residual error, and large computational load of the traditional models, an adaptive gradient recurrent neural network (AGRNN) to solve dynamic linear matrix equations is proposed. This proposed inversion-free model possesses rapid convergence rate and accurate calculated solutions. Moreover, theoretical analyses guarantee the advantages of the AGRNN compared with the CGRNN and the CZNN to solve dynamic linear matrix equations. Finally, three numerical experiments, and applications to a PUMA 560 robot motion planning and a mobile subject localization based on angle-of-arrival technique are implemented to testify the advantages of the AGRNN.