论文部分内容阅读
利用动态学习率改进ＢＰ算法，建立基于混合神经网络的计算力学理论，为结构分析提供一种新的算法。数值模拟结果表明，该方法具有良好的应用前景。
The dynamic learning rate is used to improve the BP algorithm and a computational mechanics theory based on hybrid neural network is established to provide a new algorithm for structural analysis. The numerical simulation results show that this method has a good application prospect.