Training guidelines for neural networks to estimate stability regions

Resumen:: This paper presents new results on the use of neural networks to estimate stability regions for autonomous nonlinear systems. In contrast to model-based analytical methods, this approach uses empirical data from the system to train the neural network. A method is developed to generate confidence intervals for the regions identified by the trained neural network. The neural network results are compared with estimates obtained by previously proposed methods for a standard two-dimensional example.

Temas:: Neural networks
Power system stability
State estimation
Linear systems
Chemical reactors
Nonlinear systems