Long-term Missing Wind Data Recovery for Bridge Health Monitoring Using Deep Learning

As the performance of the electronic equipment for bridge SHM system deteriorates, wind data often suffer from long-term data missing, which creates barriers for safety monitoring of the bridge structures. Therefore, we proposed a framework for long-term missing wind data recovery based on a deep neural network (DNN) utilizing a free access database (ECMWF). This framework consisted of one regression task (Task 1) and one temporal super-resolution task (Task 2). In Task 1, the hourly wind data provided by ECMWF were learned to the hourly ones of the SHM system. In Task 2, the low-resolution wind data were upsampled to high-resolution ones (10-min averages). The U-net architecture provided the basis for the DNNs in both tasks. The proposed framework's feasibility was verified through a case study of Sutong Bridge. The proposed methodology provides a new perspective for recovering long-term continuous missing SHM data.