BP改进算法及其在电压稳定性评估中的应用

iming at the questions of BP algorithm,such as long training time and slow convergence speed，an improved BP algorithm is issued in this paper. According to this algorithm，different learning rates are applied to different connection weights and threshold values when a BP network is trained. A neural network model is setup to be used on voltage stability, the convergent performance of the improved BP algorithm is studied through the Matlab, The simulation results show that this improved algorithm is able to effectively improve the convergence speed and modeling precision.