In the actual structural health monitoring system of suspension bridges, only part of suspenders tension can be monitored, but not all the suspenders tension can be obtained. To solve this problem, a method for suspenders tension identification of bridges based on the spatio-temporal correlation between the girder strain and suspenders tension is proposed. By using actual monitoring data of vehicle loads, a spatio-temporal correlation model of the girder strain and tension forces of all suspenders is constructed based on the combined application of stacked denoising autoencoder and convolutional neural networks-long short-term memory model, so as to realize the preliminary identification of suspenders tension. On this basis, by using the actual monitoring data of suspenders tension and the strain monitoring data obtained through the distributed optical fiber sensors, the delicate identification of tension forces of all suspenders is realized based on the error interpolation of preliminary identification results. The results of the example bridge show that the method in this paper can effectively identify tension forces of all suspenders of the suspension bridge, and identification results are more accurate than the method using only the monitoring data of suspenders.

中文翻译：

---

基于梁应变与吊杆张力时空相关性的桥梁吊杆张力识别方法

在实际的悬索桥结构健康监测系统中，只能监测部分吊杆张力，而无法获取全部吊杆张力。针对这一问题，提出一种基于梁应变与吊杆张力时空相关性的桥梁吊杆张力识别方法。利用车辆荷载的实际监测数据，基于堆叠式去噪自编码器和卷积神经网络-长短期记忆模型的结合应用，构建了所有吊杆梁应变和拉力的时空相关模型，从而实现吊带张力的初步识别。在此基础上，利用吊杆张力的实际监测数据和分布式光纤传感器获得的应变监测数据，在初步识别结果的误差插值的基础上，实现了对所有吊杆拉力的精细识别。实例桥梁结果表明，本文方法能够有效识别悬索桥所有吊杆的拉力，且识别结果比仅利用吊杆监测数据的方法更加准确。