Bhandari Prakash, Jang Shinae, Malla Ramesh B, Han Song
Department of Civil and Environmental Engineering, University of Connecticut, Storrs, CT 06269, USA.
Department of Computer Science and Engineering, University of Connecticut, Storrs, CT 06269, USA.
Sensors (Basel). 2024 Aug 19;24(16):5350. doi: 10.3390/s24165350.
Bridges are critical infrastructures that support our economic activities and daily lives. Aging bridges have been a major issue for decades, prompting researchers to improve resilience and performance through structural health monitoring. While most research focuses on superstructure damage, the majority of bridge failures are associated with support or joint damages, indicating the importance of bridge support. Indeed, bridge support affects the performance of both the substructure and superstructure by maintaining the load path and allowing certain movements to mitigate thermal and other stresses. The support deterioration leads to a change in fixity in the superstructure, compromising the bridge's integrity and safety. Hence, a reliable method to determine support fixity level is essential to detecting bearing health and enhancing the accuracy of the bridge health monitoring system. However, such research is lacking because of its complexity. In this study, we developed a support fixity quantification method based on thermal responses using an Artificial Neural Network (ANN) model. A finite element (FE) model of a representative highway bridge is used to derive thermal displacement data under different bearing stiffnesses, superstructure damage, and thermal loading. The thermal displacement behavior of the bridge under different support fixity conditions is presented, and the model is trained on the simulated response. The performance of the developed FE model and ANN was validated with field monitoring data collected from two in-service bridges in Connecticut using a real-time Wireless Sensor Network (WSN). Finally, the support stiffnesses of both bridges were predicted using the ANN model for validation.
桥梁是支撑我们经济活动和日常生活的关键基础设施。几十年来，桥梁老化一直是一个重大问题，促使研究人员通过结构健康监测来提高桥梁的恢复力和性能。虽然大多数研究集中在上部结构的损伤，但大多数桥梁故障与支座或节点损伤有关，这表明桥梁支座的重要性。事实上，桥梁支座通过维持荷载路径并允许一定的位移来减轻热应力和其他应力，从而影响下部结构和上部结构的性能。支座劣化会导致上部结构的固定性发生变化，危及桥梁的完整性和安全性。因此，一种可靠的确定支座固定性水平的方法对于检测支座健康状况和提高桥梁健康监测系统的准确性至关重要。然而，由于其复杂性，此类研究尚属缺乏。在本研究中，我们使用人工神经网络（ANN）模型开发了一种基于热响应的支座固定性量化方法。使用一座具有代表性的公路桥梁的有限元（FE）模型来获取不同支座刚度、上部结构损伤和热荷载作用下的热位移数据。给出了桥梁在不同支座固定性条件下的热位移行为，并在模拟响应上对模型进行训练。利用从康涅狄格州两座在用桥梁收集的现场监测数据，通过实时无线传感器网络（WSN）对所开发的有限元模型和人工神经网络的性能进行了验证。最后，使用人工神经网络模型预测了两座桥梁的支座刚度以进行验证。
