中文版 | English
CSpace
RNN for Solving Perturbed Time-Varying Underdetermined Linear System With Double Bound Limits on Residual Errors and State Variables
Lu, Huiyan1,2; Jin, Long1,2; Luo, Xin3,4; Liao, Bolin5; Guo, Dongsheng6; Xiao, Lin7
2019-11-01
摘要Neural networks have been generally deemed as important tools to handle kinds of online computing problems in recent decades, which have plenty of applications in science and electronics fields. This paper proposes a novel recurrent neural network (RNN) to handle the perturbed time-varying underdetermined linear system with double bound limits on residual errors and state variables. Beyond that, the bound-limited underdetermined linear system is converted into a time-varying system that consists of linear and nonlinear formulas through constructing a nonnegative time-varying variable. Then, theoretical analyses are conducted to verify the superior convergence performance of the proposed RNN model. Furthermore, numerical experiment results and computer simulations demonstrate the superiority and effectiveness of the proposed RNN model for handling the time-varying underdetermined linear system with double bound limits. Finally, the proposed RNN model is applied to the physically limited PUMA560 robot to show its satisfactory applicabilities.
关键词Mathematical model Time-varying systems Linear systems Informatics Robots Recurrent neural networks Double bound limits recurrent neural network simulation results theoretical analyses time-varying underdetermined linear system
DOI10.1109/TII.2019.2909142
发表期刊IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
ISSN1551-3203
卷号15期号:11页码:5931-5942
通讯作者Jin, Long(longjin@ieee.org)
收录类别SCI
WOS记录号WOS:000498643600013
语种英语