A physics informed convolution neural network for spatiotemporal temperature analysis of concrete dams

Abstract

Structural health monitoring is indispensable throughout the life cycle of dams, and the loading conditions determines the reliability of the assessment. Among them, temperature plays an important role on the behavior of arch dams, which are sparsely monitored in practice. How to use these sparsely measured data to obtain the accurate spatiotemporal temperature field becomes a critical problem. This study proposes a physics informed convolutional neural network for spatiotemporal temperature field of arch dams. A dual thread convolutional neural network considers the effects of spatiotemporal and temporal variables distinctively. The proposed model is validated using measured data from an existing arch dam. Compared with applied convolutional neural network, the proposed model improves the accuracy of temperature field reconstruction by 18 % and reduces reliance on measured data. Benefit of consideration of the continuity and heat transfer, the spatial distribution of the temperature field is more reasonable in continuity, and can retain accuracy even with limited monitoring data. The proposed model can provide the actual spatiotemporal non-uniform temperature field of the arch dam, providing basic data for the analysis and safety evaluation of arch dams throughout their life-cycle.