A new super-predefined-time convergence and noise-tolerant RNN for solving time-variant linear matrix-vector inequality in noisy environment and its application to robot arm
文献类型:期刊论文
作者 | Zheng, Boyu1; Yue, Chong1; Wang, Qianqian1; Li, Chunquan1; Zhang, Zhijun2; Yu, Junzhi3,4; Liu, Peter X.5 |
刊名 | NEURAL COMPUTING & APPLICATIONS |
出版日期 | 2023-12-20 |
页码 | 17 |
ISSN号 | 0941-0643 |
关键词 | Linear matrix-vector inequality Recurrent neural network Robustness Time-variant problem Convergence |
DOI | 10.1007/s00521-023-09264-8 |
通讯作者 | Li, Chunquan(lichunquan@ncu.edu.cn) |
英文摘要 | Recurrent neural networks (RNNs) are excellent solvers for time-variant linear matrix-vector inequality (TVLMVI). However, it is difficult for traditional RNNs to track the theoretical solution of TVLMVI under non-ideal conditions [e.g., noisy environment]. Therefore, by introducing a novel nonlinear activation function (NNAF) and time-variant-gain, a new super-predefined-time convergence and noise-tolerant RNN (SPCNT-RNN) is proposed to acquire an online solution to TVLMVI in noisy environment. The difference between SPCNT-RNN and traditional fixed-parameter RNNs (FP-RNNs) is that the error function equation of SPCNT-RNN has NNAF and time-variant-gain coefficient. Due to this difference, the SPCNT-RNN can achieve super-predefined-time convergence in both noise-free and noisy environments, which is superior to that of existing RNNs. The stability, super-predefined-time convergence, and robustness of SPCNT-RNN are theoretically demonstrated. Moreover, the simulation results between various existing RNNs and SPCNT-RNN verify the feasibility, validity, robustness and rapid convergence effect of the proposed SPCNT-RNN. |
WOS关键词 | RECURRENT NEURAL-NETWORK ; NONLINEAR OPTIMIZATION ; ZNN MODEL ; DESIGN ; EQUALITY |
资助项目 | National Natural Science Foundation of China |
WOS研究方向 | Computer Science |
语种 | 英语 |
出版者 | SPRINGER LONDON LTD |
WOS记录号 | WOS:001127132800002 |
资助机构 | National Natural Science Foundation of China |
源URL | [http://ir.ia.ac.cn/handle/173211/54862] |
专题 | 复杂系统认知与决策实验室 |
通讯作者 | Li, Chunquan |
作者单位 | 1.Nanchang Univ, Sch Informat Engn, Nanchang 330031, Peoples R China 2.South China Univ Technol, Sch Automat Sci & Engn, Guangzhou 510640, Peoples R China 3.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing, Peoples R China 4.Peking Univ, Coll Engn, Dept Mech & Engn Sci, State Key Lab Turbulence & Complex Syst,BIC ESAT, Beijing, Peoples R China 5.Carleton Univ, Dept Syst & Comp Engn, Ottawa, ON K1S 5B6, Canada |
推荐引用方式 GB/T 7714 | Zheng, Boyu,Yue, Chong,Wang, Qianqian,et al. A new super-predefined-time convergence and noise-tolerant RNN for solving time-variant linear matrix-vector inequality in noisy environment and its application to robot arm[J]. NEURAL COMPUTING & APPLICATIONS,2023:17. |
APA | Zheng, Boyu.,Yue, Chong.,Wang, Qianqian.,Li, Chunquan.,Zhang, Zhijun.,...&Liu, Peter X..(2023).A new super-predefined-time convergence and noise-tolerant RNN for solving time-variant linear matrix-vector inequality in noisy environment and its application to robot arm.NEURAL COMPUTING & APPLICATIONS,17. |
MLA | Zheng, Boyu,et al."A new super-predefined-time convergence and noise-tolerant RNN for solving time-variant linear matrix-vector inequality in noisy environment and its application to robot arm".NEURAL COMPUTING & APPLICATIONS (2023):17. |
入库方式: OAI收割
来源:自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。