基于ANN和动应变的梁桥移动荷载识别及试验

为了实现桥梁上车载参数的快速识别,基于欧拉梁动力解析解分析桥梁挠度和应变对移动荷载的敏感性,选择敏感性更强的应变作为输入参数,研究将人工神经网络(artificial neural networks,简称ANN)用于识别梁桥移动车载的理论和方法。对简支梁桥在移动车载作用下的动应变响应进行理论分析及数值模拟,选取不同工况下的模拟数据对网络进行训练,分析激活函数组合和训练方法对网络精度的影响及噪声水平对动荷载工况下正确识别率的影响。通过车-桥模型动力试验验证该方法的合理性和可用性。结果表明,不同激活函数组合对识别结果影响较小,而不同的训练算法对识别结果影响较大,在应用神经网络识别桥梁移动荷载时,可以通过桥梁的动应变,对车辆的位置、速度和动荷载进行识别。

Moving Load Identification and Experimental Verification of Beam Bridge Based on Dynamic Strain and ANN

In order to quickly identify loads of vehicle on a bridge, the effects of moving loads on the bridge strain and deflection are analyzed based on the Euler beam model. The artificial neural network (ANN) is used in bridge moving loads identification. The moving loads are identified on a 30-width simply-supported bridge. The influences of different activation function combinations and algorithm on the network are discussed. The identification results of different load conditions are analyzed and the effect of noise is considered. Finally, the rationality of the method is verified by experiments. The results show that transfer function has little influence on the recognition result, but training algorithm has a great influence on the recognition result. By selecting the appropriate network structure and training methods, the BP neural network can identify the location, speed and dynamic loads of the vehicle according to the strain response of the bridge.