中文版 | English
CSpace
Modified Gradient Projection Neural Network for Multiset Constrained Optimization
Ying, Liufu1,2; Long, Jin2; Shuai, Li1
2023-09-01
摘要To solve nonlinear optimization problems under multiple set constraints, a modified gradient projection neural network (MGPNN) is proposed and investigated. Different from existing approaches specialized for linear constrained optimizations, such as the gradient-based recurrent neural network or dynamic-parameter zeroing neural network, the MGPNN is intrinsically designed from the perspective of the multiple set constrained optimization (MSCO), which is a more generalized form for the linear constrained optimization. The MGPNN is able to efficiently and conveniently provide a feasible solution to the MSCO problem. Ultimately, compared with existing solution methods, numerical simulations and applications to the control of an underactuated portal crane system are provided for verifications of the robust stability and preponderance of the proposed MGPNN model.
关键词Modified gradient projection neural network (MGPNN) multiset constrained optimization (MSCO) problem robust stability underactuated system
DOI10.1109/TII.2022.3228396
发表期刊IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
ISSN1551-3203
卷号19期号:9页码:9413-9423
通讯作者Long, Jin(longjin@ieee.org) ; Shuai, Li(lishuai@lzu.edu.cn)
收录类别SCI
WOS记录号WOS:001037910900015
语种英语