索力振动法测量神经网络赋泛研究

索的受力状态关系着索体系桥梁的安全,索力值是衡量索力学状态的重要指标.目前,索的边界条件难以判别是影响索力识别结果准确性的重要因素.为此,利用ANSYS对拉索振动进行数值模拟,并借助已有索力计算公式对建模方式的可靠性进行验证,并生成模拟数据;然后,以索长、线密度、抗弯刚度、1阶频率、2阶频率、3阶频率为输入参数,以索力...

Research on Neural Network Generalization of Cable Force Vibration Measurement

The stress state of the cable is related to the safety of the cable system bridge, and the cable force value is an important index to measure the mechanical state of the cable. At present, the difficulty of determining the cable boundary conditions is an important factor affecting the accuracy of the cable force identification results. In this study, ANSYS is used to numerically simulate the cable vibration, and the reliability of the modeling method is verified by the existing cable force calculation formula and the simulation data is generated. Then taken cable length, line density, bending stiffness, first-order frequency, second-order frequency, and third-order frequency as input parameters, and used cable force as output parameter combined with vibration simulation data to establish BP neural network and generalized regression neural network cable force prediction model, and the two neural network cable force prediction models and the existing cable force calculation formula are applied to actual projects for comparison and verification. The results showed that the neural network structure of the BP neural network cable force prediction model is 6-13-13-1, the activation functions between the input layer and the hidden layer 1, the hidden layer 1 and the hidden layer 2, the hidden layer 2 and the output layer are tansig, tansig, purelin, the training algorithm is the L-M optimization algorithm trainlm, the learning rate is 0.1, the number of network iterations is 1000, the display interval is 100, the mean square error is 0.001, the prediction effect of the cable force prediction model is good, but there is room for further optimization. The best spread value of the generalized regression neural network cable force prediction model is 0.00215, the prediction effect of the cable force prediction model is better than the BP neural network and the existing cable force calculation formula, and the forecast error is basically controlled within 5%. Using generalized regression neural network to predict the cable force of the bridge can avoid the influence of the judgment error of the cable boundary condition on the accuracy of the cable force recognition result, and improve the accuracy of the cable force recognition, it has good engineering application value.