通过构造合适的Lyapunov泛函,并根据It?公式沿该神经网络求Lyapunov泛函的随机导数,在Dirichlet边界条件下讨论一类具有Markov跳变参数、随机干扰和混合时滞的广义反应扩散神经网络的全局均方鲁棒渐进稳定性,得到依赖于时滞、扩散系数和扩散空间的稳定性判据。最后,通过数值模拟说明所得结论判据的有效性。 By constructing a suitable Lyapunov functional and finding random derivatives of the Lyapunov functional along the It neural network by the It? Formula, a class of generalized reaction-diffusing neural networks with Markov transition parameters, stochastic disturbances and mixing delays are discussed under Dirichlet boundary conditions The global asymptotic robust asymptotic stability of the network relies on stability criteria that depend on time delays, diffusion coefficients, and diffusion spaces. Finally, numerical simulation is used to show the validity of the conclusions obtained.