CAJ | 학술논문

提出基于BP算法的小波神经网络改进算法.仿真结果表明它避免了BP神经网络结构设计的盲目性和局部最优等非线性优化问题,简化了训练,具有较强的函数学习能力和推广能力.该算法成功应用于桥梁损伤预测,具有广泛的应用前景.
제출기우BP산법적소파신경망락개진산법.방진결과표명타피면료BP신경망락결구설계적맹목성화국부최우등비선성우화문제,간화료훈련,구유교강적함수학습능력화추엄능력.해산법성공응용우교량손상예측,구유엄범적응용전경.
The improved algorithm of Wavelet Neural Networks(WNN) based on BP is proposed.Theoretical analysis and simulation result show it avoids both the blindness of framework designs for BP Neural Networks and the problem of nonlinear optimiza-tions,such as local optimization.So it can simplify the training of Neural Networks.It has better abilities in function learning and generalization.This algorithm is applied to the damage of bridge forecasting.Therefore it has wide application prospect.