Dam safety monitoring has become an important topic and is critical for evaluating a dam's safety status. This study focuses on identifying the mechanical properties of a concrete dam from long-term viscoelastic deformation monitoring data. A novel inversion framework is proposed in which a surrogate model, instead of the finite element model, is placed inside the optimization loop. First, a multi-output surrogate model based on Gaussian process is trained by using data from a finite element simulation in the creep regime. In order to efficiently create a high-precision and reliable surrogate model, three test instances are conducted to investigate the impact of sample size, parameter range and output quantity on the performance of the surrogate model. Subsequently, a meta-heuristic optimization, multi-verse optimizer, is employed to identify the unknown viscoelastic parameters. The results illustrate that the identified properties allow predictions on dam displacement which are consistent with the monitoring data. Compared with the traditional inversion method based on finite element modelling, the proposed inversion method based on the multi-output surrogate model not only achieves accurate estimation of mechanical parameters but also greatly improves computational efficiency.@en

Usage of asphalt mixture with poor gradation will most likely lead to pavement deficiency. There is a growing need for rapid and non-destructive methods to extract pavement aggregate gradation. In this study, a deep learning-based method that utilizes point clouds data for gradation extraction was proposed. Firstly, a data enhancement algorithm along with three data format conversion methods (aligned point cloud, voxel, and depth image) were proposed to preprocess the original collected point clouds. Subsequently, different neural network models were designed for each data format to extract gradation. Finally, a multi-feature fusion network was developed, which using extraction network as the backbone and additional auxiliary information. In the case study, the MAE loss of multi-feature fusion networks with PointNet, Vox-ResNet34 and GoogLeNet-v4 as the backbone respectively achieved 0.202, 0.142 and 0.046 on the test set, which means an estimation accuracy of more than 95% for the pavement aggregate gradation.@en