Journal
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
Volume 68, Issue 10, Pages 9844-9854Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIE.2020.3029478
Keywords
Mathematical model; Computational modeling; Neural networks; Analytical models; Robots; Convergence; Kinematics; Computer simulations; robot experiments; saturation-allowed neural dynamics (SAND); theoretical analyses; time-dependent system of linear equations
Categories
Funding
- National Natural Science Foundation of China [61703189]
- National Key Research and Development Program of China [2017YFE0118900]
- Team Project of Natural Science Foundation of Qinghai Province, China [2020-ZJ-903]
- Key Laboratory of IoT of Qinghai [2020-ZJ-Y16]
- CAS Light of West China Program
- Natural Science Foundation of Chongqing (China) [cstc2020jcyj-zdxmX0028]
- Fundamental Research Funds for the Central Universities [lzujbky-2019-89, lzujbky-2020-it09]
Ask authors/readers for more resources
The study introduces a saturation-allowed neural dynamics model for solving perturbed time-dependent linear equations with noise-tolerance. The proposed model has been shown to have global convergence with zero theoretical error, and performs well under various additive noise conditions through theoretical analysis and experimental validation.
Neural networks as well as the related neural dynamics have been widely exploited to conduct online computing operations for solving various problems in recent years. This article makes progress along this direction by proposing a saturation-allowed neural dynamics (SAND) model for solving the perturbed time-dependent system of linear equations with noise-tolerant capacity. Specifically, by elaborately constructing a new general framework enhanced by the error-integration information and nonlinear projection functions (PFs), a SAND model is proposed and investigated under various additive noises. In addition, theoretical analyses reveal that the proposed SAND model is of global convergence with zero theoretical error. Moreover, when the value of PF is strictly limited by bounds, i.e., a saturation function, the upper bound of the residual errors of the proposed SAND model is subject to the noises and the bounds of PF. Computer simulation results, as well as robot experiments, verify the superior property of the proposed SAND model for solving the perturbed time-dependent system of linear equations, compared with the state of the prior art.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available