【摘要】 为了解决模型更新混合试验中BP神经网络算法泛化能力较差的问题,引入了一种新方法——AdaBoost回归树算法作为混合试验中的模型更新算法.在学习阶段,选择回归树作为弱回归模型进行训练,然后将多个弱回归模型集成为一个强回归模型,最后对训练结果进行表决输出.利用在线AdaBoost回归树算法和BP神经网络算法作为模型更新算法,对一个二自由度非线性结构进行了数值模拟.结果表明,在线AdaBoost回归树算法的预测精度比神经网络高48.3%,证实了AdaBoost回归树算法比BP神经网络算法具有更好的泛化能力,并且有效消除了权重初始化的影响,提高了混合试验中恢复力的预测精度.更多还原

【Abstract】 In order to solve the poor generalization ability of the back-propagation(BP) neural network in the model updating hybrid test, a novel method called the AdaBoost regression tree algorithm is introduced into the model updating procedure in hybrid tests. During the learning phase, the regression tree is selected as a weak regression model to be trained, and then multiple trained weak regression models are integrated into a strong regression model. Finally, the training results are generated through voting by all the selected regression models. A 2-DOF nonlinear structure was numerically simulated by utilizing the online AdaBoost regression tree algorithm and the BP neural network algorithm as a contrast. The results show that the prediction accuracy of the online AdaBoost regression algorithm is 48.3% higher than that of the BP neural network algorithm, which verifies that the online AdaBoost regression tree algorithm has better generalization ability compared to the BP neural network algorithm. Furthermore, it can effectively eliminate the influence of weight initialization and improve the prediction accuracy of the restoring force in hybrid tests.更多还原