Neural-net based critical clearing time prediction in power system transient stability analysis

Results obtained using an artificial neural network to predict critical clearing times for a specific fault and clearing mode in power system transient stability analysis are presented in this paper. The fault is applied at a bus distant from generators. The prefault active and reactive powers of all generators and loads are used as ANN inputs. For a 5-machine 14-bus system, it was found that for most testing examples the CCT was predicted with good accuracy. However, large errors still occurred in predicting some examples.<
>