Zeroing neural dynamics (ZND) can be seen as an effective controller to solve various challenging scientific and engineering problems. Computing Lyapunov equation is a kind of important issue in nonlinear systems for stability analysis in control. This paper presents a systematic and constructive procedure on using ZND to design control laws based on the efficient solution of dynamic Lyapunov equation. We particularly address three important aspects in the design: 1. the global stability of ZND, to guarantee the effectiveness of the solution; 2. the robustness against additive noises, to ensure the capability of ZND for using in harsh environments; 3. the finite-time convergence of ZND, to endow ZND for real-time solution of dynamical problems. To do so, a novel formula is first designed in a unified manner of ZND. Differing from the conventional formula appeared in ZND, the proposed formula simultaneously has finite-time convergence and noise robustness property. According to this novel formula, a novel control law (termed nonlinear neural dynamics, NND) is established to compute dynamic Lyapunov equation in the presence of various additive noises. Both theoretical and simulative results ensure the finite-time convergence and noise robustness property of the NND model for computing dynamic Lyapunov equation in the front of various additive noises. As compared to the conventional ZND model for computing dynamic Lyapunov, the superior property of the NND model is further demonstrated.

This article aims to solve the Moore-Penrose inverse of time-varying full-rank matrices in the presence of various noises in real time. For this purpose, two varying-parameter zeroing neural networks (VPZNNs) are proposed. Specifically, VPZNN-R and VPZNN-L models, which are based on a new design formula, are designed to solve the right and left Moore-Penrose inversion problems of time-varying full-rank matrices, respectively. The two VPZNN models are activated by two novel varying-parameter nonlinear activation functions. Detailed theoretical derivations are presented to show the desired finite-time convergence and outstanding robustness of the proposed VPZNN models under various kinds of noises. In addition, existing neural models, such as the original ZNN (OZNN) and the integration-enhanced ZNN (IEZNN), are compared with the VPZNN models. Simulation observations verify the advantages of the VPZNN models over the OZNN and IEZNN models in terms of convergence and robustness. The potential of the VPZNN models for robotic applications is then illustrated by an example of robot path tracking.