提出一种新颖的用于变形预测的基于扩展Kalman滤波的小波神经网络学习算法,与BP算法相比,该方法具有更好的收敛率和学习能力,并通过实例计算证明了该方法具有较高的精度和较快的计算速度。
A novel learning algorithm for wavelet neural network based on Extended Kalman Filter is proposed to predict the deformation of structure, In comparison with the BP algorithm, the EKF learning algorithm has improved convergence and can provide much more accuracy learning results. Experiments in forecasting the deformation of structure prove that the proposed algorithm has much more accuracy and faster speed.