1
|
Wang D, Liu XW. A varying-parameter fixed-time gradient-based dynamic network for convex optimization. Neural Netw 2023; 167:798-809. [PMID: 37738715 DOI: 10.1016/j.neunet.2023.08.047] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/13/2023] [Revised: 07/05/2023] [Accepted: 08/28/2023] [Indexed: 09/24/2023]
Abstract
We focus on the fixed-time convergence and robustness of gradient-based dynamic networks for solving convex optimization. Most of the existing gradient-based dynamic networks with fixed-time convergence have limited ability to resist interferences of noises. To improve the convergence of the gradient-based dynamic networks, we design a new activation function and propose a gradient-based dynamic network with fixed-time convergence. The proposed dynamic network has a smaller upper bound of the convergence time than the existing dynamic networks with fixed-time convergence. A time-varying scaling parameter is employed to speed up the convergence. Our gradient-based dynamic network is proved to be robust against bounded noises and is able to resist the interference of unbounded noises. The numerical tests illustrate the effectiveness and superiority of the proposed network.
Collapse
Affiliation(s)
- Dan Wang
- School of Artificial Intelligence, Hebei University of Technology, Tianjin, 300401, China.
| | - Xin-Wei Liu
- Institute of Mathematics, Hebei University of Technology, Tianjin, 300401, China.
| |
Collapse
|
2
|
Optimal discrete-time sliding-mode control based on recurrent neural network: a singular value approach. Soft comput 2022. [DOI: 10.1007/s00500-022-07486-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/14/2022]
|
3
|
Wang D, Liu XW. A gradient-type noise-tolerant finite-time neural network for convex optimization. Neurocomputing 2022. [DOI: 10.1016/j.neucom.2022.01.018] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
|
4
|
Continuous and discrete zeroing neural network for a class of multilayer dynamic system. Neurocomputing 2022. [DOI: 10.1016/j.neucom.2022.04.056] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/21/2022]
|
5
|
Zhao X, Zong Q, Tian B, You M. Finite-Time Dynamic Allocation and Control in Multiagent Coordination for Target Tracking. IEEE TRANSACTIONS ON CYBERNETICS 2022; 52:1872-1880. [PMID: 32603302 DOI: 10.1109/tcyb.2020.2998152] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/11/2023]
Abstract
A new finite-time dynamic allocation and control scheme is developed in this article for multiple agents tracking a moving target. Based on a competitive manner, the dynamic allocation is achieved by k-winners-take-all (k-WTA), which can be realized by a novel finite-time dual neural network with the adaptive-gain activation function. Then, a finite-time disturbance compensation-based control law is proposed for agents to conduct capturing task or return to the specified point in vigilance. The finite-time stability of the system is guaranteed through Lyapunov analysis. Finally, the efficiency of the proposed scheme is illustrated by simulations in which the situation with higher target velocity than trackers is considered.
Collapse
|
6
|
Li W, Han L, Xiao X, Liao B, Peng C. A gradient-based neural network accelerated for vision-based control of an RCM-constrained surgical endoscope robot. Neural Comput Appl 2022. [DOI: 10.1007/s00521-021-06465-x] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
|
7
|
Double Accelerated Convergence ZNN with Noise-Suppression for Handling Dynamic Matrix Inversion. MATHEMATICS 2021. [DOI: 10.3390/math10010050] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/07/2023]
Abstract
Matrix inversion is commonly encountered in the field of mathematics. Therefore, many methods, including zeroing neural network (ZNN), are proposed to solve matrix inversion. Despite conventional fixed-parameter ZNN (FPZNN), which can successfully address the matrix inversion problem, it may focus on either convergence speed or robustness. So, to surmount this problem, a double accelerated convergence ZNN (DAZNN) with noise-suppression and arbitrary time convergence is proposed to settle the dynamic matrix inversion problem (DMIP). The double accelerated convergence of the DAZNN model is accomplished by specially designing exponential decay variable parameters and an exponential-type sign-bi-power activation function (AF). Additionally, two theory analyses verify the DAZNN model’s arbitrary time convergence and its robustness against additive bounded noise. A matrix inversion example is utilized to illustrate that the DAZNN model has better properties when it is devoted to handling DMIP, relative to conventional FPZNNs employing other six AFs. Lastly, a dynamic positioning example that employs the evolution formula of DAZNN model verifies its availability.
Collapse
|
8
|
Kong Y, Jiang Y, Han R, Wu H. A generalized varying-parameter recurrent neural network for super solution of quadratic programming problem. Neurocomputing 2021. [DOI: 10.1016/j.neucom.2021.01.084] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
|
9
|
Performance analysis of nonlinear activated zeroing neural networks for time-varying matrix pseudoinversion with application. Appl Soft Comput 2021. [DOI: 10.1016/j.asoc.2020.106735] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
|
10
|
Kong Y, Jiang Y, Zhou J, Wu H. A time controlling neural network for time‐varying QP solving with application to kinematics of mobile manipulators. INT J INTELL SYST 2021. [DOI: 10.1002/int.22304] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
Affiliation(s)
- Ying Kong
- Department of Information and Electronic Engineering Zhejiang University of Science and Technology Zhejiang China
| | - Yunliang Jiang
- Department of Information Engineering Huzhou University Huzhou China
| | - Junwen Zhou
- Department of Information and Electronic Engineering Zhejiang University of Science and Technology Zhejiang China
| | - Huifeng Wu
- Department of Intelligent and Software Technology Hangzhou Dianzi University Hangzhou China
| |
Collapse
|
11
|
Li W, Chiu PWY, Li Z. An Accelerated Finite-Time Convergent Neural Network for Visual Servoing of a Flexible Surgical Endoscope With Physical and RCM Constraints. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2020; 31:5272-5284. [PMID: 32011270 DOI: 10.1109/tnnls.2020.2965553] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/10/2023]
Abstract
This article designs and analyzes a recurrent neural network (RNN) for the visual servoing of a flexible surgical endoscope. The flexible surgical endoscope is based on a commercially available UR5 robot with a flexible endoscope attached as an end-effector. Most of the existing visual servo control frameworks of the robotic endoscopes or robot arms have not considered either the physical limits of the robot or the remote center of motion (RCM) constraints (i.e., the fulcrum effect). To tackle this issue, this article first conducts the kinematic modeling of the flexible robotic endoscope to achieve automation by visual servo control. The kinematic modeling results in a quadratic programming (QP) framework with physical limits and RCM constraints involved, making the UR5 robot applicable to surgical field. To solve the QP problem and accomplish the visual task, an RNN activated by a sign-bi-power activation function (AF) is proposed. The motivation of using the sign-bi-power AF is to enable the RNN to exhibit an accelerated finite-time convergence, which is more preferred in time-critical applications. Theoretically, the finite-time convergence of the RNN is rigorously proved using the Lyapunov theory. Compared with the previous AFs applied to the RNN, theoretical analysis shows that the RNN activated by the sign-bi-power AF delivers an accelerated convergence speed. Comparative validations are performed, showing that the proposed finite-time convergent neural network is effective to achieve visual servoing of the flexible endoscope with physical limits and RCM constraints handled simultaneously.
Collapse
|
12
|
Zhang D, Mittal K, Wilson J, Luh PB, Fan J, Gupta S. Efficiency and Reliability Joint Optimization of Chiller Plants Based on a Hybrid Model. IEEE Robot Autom Lett 2019. [DOI: 10.1109/lra.2019.2924126] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
|
13
|
Miao P, Wu D, Shen Y, Zhang Z. Discrete-time neural network with two classes of bias noises for solving time-variant matrix inversion and application to robot tracking. Neural Comput Appl 2019. [DOI: 10.1007/s00521-018-03986-w] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/27/2022]
|
14
|
Yu F, Liu L, Xiao L, Li K, Cai S. A robust and fixed-time zeroing neural dynamics for computing time-variant nonlinear equation using a novel nonlinear activation function. Neurocomputing 2019. [DOI: 10.1016/j.neucom.2019.03.053] [Citation(s) in RCA: 100] [Impact Index Per Article: 20.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
|
15
|
Improved Zhang neural network with finite-time convergence for time-varying linear system of equations solving. INFORM PROCESS LETT 2019. [DOI: 10.1016/j.ipl.2019.03.012] [Citation(s) in RCA: 13] [Impact Index Per Article: 2.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/23/2022]
|
16
|
Bounded Z-type neurodynamics with limited-time convergence and noise tolerance for calculating time-dependent Lyapunov equation. Neurocomputing 2019. [DOI: 10.1016/j.neucom.2018.10.031] [Citation(s) in RCA: 30] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/21/2022]
|
17
|
|
18
|
|
19
|
Ye Q, Lou X, Sheng L. Generalized predictive control of a class of MIMO models via a projection neural network. Neurocomputing 2017. [DOI: 10.1016/j.neucom.2016.12.067] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
|
20
|
Feng J, Qin S, Shi F, Zhao X. A recurrent neural network with finite-time convergence for convex quadratic bilevel programming problems. Neural Comput Appl 2017. [DOI: 10.1007/s00521-017-2926-7] [Citation(s) in RCA: 13] [Impact Index Per Article: 1.9] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
|
21
|
Qiu B, Zhang Y, Yang Z. Revisit and compare Ma equivalence and Zhang equivalence of minimum velocity norm (MVN) type. Adv Robot 2016. [DOI: 10.1080/01691864.2015.1120243] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/22/2022]
|
22
|
Duan K, Zhang H, Wang JJY. Joint learning of cross-modal classifier and factor analysis for multimedia data classification. Neural Comput Appl 2016. [DOI: 10.1007/s00521-015-1866-3] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
|
23
|
Miao P, Shen Y, Li Y, Bao L. Finite-time recurrent neural networks for solving nonlinear optimization problems and their application. Neurocomputing 2016. [DOI: 10.1016/j.neucom.2015.11.014] [Citation(s) in RCA: 40] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
|
24
|
Xiao L. A nonlinearly activated neural dynamics and its finite-time solution to time-varying nonlinear equation. Neurocomputing 2016. [DOI: 10.1016/j.neucom.2015.08.031] [Citation(s) in RCA: 73] [Impact Index Per Article: 9.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
|
25
|
Du X, Wang JJY. Support image set machine: Jointly learning representation and classifier for image set classification. Knowl Based Syst 2015. [DOI: 10.1016/j.knosys.2015.01.016] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
|
26
|
Miao P, Shen Y, Huang Y, Wang YW. Solving time-varying quadratic programs based on finite-time Zhang neural networks and their application to robot tracking. Neural Comput Appl 2014. [DOI: 10.1007/s00521-014-1744-4] [Citation(s) in RCA: 80] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
|