A new varying-parameter convergent-differential neural-network for solving time-varying convex QP problem constrained by linear-equality
A new varying-parameter convergent-differential neural-network for solving time-varying convex QP problem constrained by linear-equality
复制标题
求解线性等式约束的时变凸QP问题的新型变参数收敛微分神经网络
DOI：
10.1109/tac.2018.2810039
复制
发表时间：
2018
影响因子：
6.8
通讯作者：
Yuanqing Li
中科院分区：
文献类型：
--
作者：
Zhijun Zhang;Yeyun Lu;Lunan Zheng;Shuai Li;Zhuliang Yu;Yuanqing Li
为了解决时变线性等式约束的在线连续时变凸二次规划问题，提出并分析了一种新型变参数收敛微分神经网络（VP-CDNN）。与固定参数收敛微分神经网络（FP-CDNN）不同，例如基于梯度的循环神经网络、经典的张神经网络（ZNN）和有限时间ZNN（FT-ZNN），VP-CDNN基于单调递增的时变设计参数。理论分析证明，VP-CDNN具有超指数收敛性，即使在扰动情况下，VP-CDNN的残差也收敛为零，优于传统的FP-CDNN和FT-ZNN。基于不同激活函数的计算机仿真验证了所提出的 VP-CDNN 的超指数收敛性能和强鲁棒性特性。最后给出了一个机器人跟踪示例来验证所提出的 VP-CDNN 的有效性和可用性。
To solve online continuous time-varying convex quadratic-programming problems constrained by a time-varying linear-equality, a novel varying-parameter convergent-differential neural network (termed as VP-CDNN) is proposed and analyzed. Different from fixed-parameter convergent-differential neural network (FP-CDNN), such as the gradient-based recurrent neural network, the classic Zhang neural network (ZNN), and the finite-time ZNN (FT-ZNN), VP-CDNN is based on monotonically increasing time-varying design-parameters. Theoretical analysis proves that VP-CDNN has super exponential convergence and the residual errors of VP-CDNN converge to zero even under perturbation situations, which are both better than traditional FP-CDNN and FT-ZNN. Computer simulations based on different activation functions are illustrated to verify the super exponential convergence performance and strong robustness characteristics of the proposed VP-CDNN. A robot tracking example is finally presented to verify the effectiveness and availability of the proposed VP-CDNN.