NEURAL-NET BASED CALCULATION OF VOLTAGE DIPS AT MAXIMUM ANGULAR SWING IN DIRECT TRANSIENT STABILITY ANALYSIS

In heavily stressed power systems, post-fault transient voltage dips can lead to undesired tripping of industrial drives and large induction motors. The lowest transient voltage dips occur when fault clearing times are less than critical ones. In this paper, we propose a new iterative analytical methodology to obtain more accurate estimates of voltage dips at maximum angular swing in direct transient stability analysis. We also propose and demonstrate the possibility of storing the results of these computations into the associative memory (AM) system, which exhibits remarkable generalization capabilities. Feature-based models stored in the AM can be utilized for fast and accurate prediction of the location, duration and the amount of worst voltage dips, thereby avoiding the need and cost for lengthy time-domain simulations. Numerical results obtained using the example of the New England power system are presented to illustrate our approach.