摘要
移动荷载识别可作为桥梁损伤机理研究的基础,同时为交通规划提供可靠的车载信息。提出了一种基于BP神经网络的桥上移动荷载的分阶段识别新方法。建立了桥梁有限元模型和2自由度5参数车辆模型,模拟生成了神经网络训练样本。采用分阶段识别技术,分步识别了桥上车辆的位置、速度和荷载。在神经网络设计中,利用正交设计法选择训练样本集,采用正则化方法对误差性能函数进行修正,并采用遗传算法对初始权进行了优化。数值仿真了一简支梁桥的移动车辆荷载识别,并通过模型试验进行了验证。结果表明:所提出的方法能够在线、实时地识别桥上移动车辆荷载,识别精度高、收敛速度快,且具有较强的鲁棒性和抗噪能力。
Identification of moving loads on bridges may be required in the study of the fatigue or damage mechanism of bridges, and it provides reliable data for traffic planning. A novel BP neural network-based stage identification method for moving loads on bridge is proposed. To develop this method, a finite element model of a bridge and a vehicle model with two degrees of freedom and five parameters are built, and the training samples of the neural network are numerically simulated. The position, velocity and weight of vehicles on bridge are identified step by step using the stage identification technique. In the design of neural network, the training sample set is selected using the orthogonal design method, the error performance function is modified by regularization, and the initial weights are optimized by employing the genetic algorithm. The identification for moving vehicle load on a simply supported girder is numerically simulated and verified through a model test. The results show that the proposed method may identify the moving loads on bridge on-line and real-time with high accuracy and rapid convergence, and has powerful robustness and noise-immunity.
出处
《工程力学》
EI
CSCD
北大核心
2008年第9期85-92,共8页
Engineering Mechanics
基金
国家杰出青年科学基金项目(50425824)
关键词
桥梁
移动荷载识别
BP神经网络
分阶段识别
正交设计
正则化
遗传算法
bridge
moving loads identification
BP neural network
stage identification
orthogonal design
regularization
genetic algorithm
作者简介
李忠献（1961-），男，安徽枞阳人，长江学者特聘教授，博士，博导，从事工程结构抗震抗爆、减灾控制与健康监测研究（E—mail：zxli@tju．edu。cn）；
陈锋（1977-），男，河北定州人，博士，从事桥梁设计理论与健康监测研究（E-mail：chenfeng7707@163．com）：
王波（1979-），女，河北南皮人，硕士，从事桥梁设计与研究工作（E-mail：wangbo_xuan@163．com）
