Drill core lithology is an important indicator reflecting the geological conditions of the drilling area. Traditional lithology identification usually relies on manual visual inspection, which is time-consuming and professionally demanding. In recent years, the rapid development of convolutional neural networks has provided an innovative way for the automatic prediction of drill core images. In this work, a core dataset containing a total of 10 common lithology categories in underground engineering was constructed. ResNeSt-50 we adopted uses a strategy of combining channel-wise attention and multi-path network to achieve cross-channel feature correlations, which significantly improves the model accuracy without high model complexity. Transfer learning was used to initialize the model parameters, to extract the feature of core images more efficiently. The model achieved superior performance on testing images compared with other discussed CNN models, the average value of its Precision, Recall, F_1−score for each category of lithology is 99.62%, 99.62%, and 99.59%, respectively, and the prediction accuracy is 99.60%. The test results show that the proposed method is optimal and effective for automatic lithology classification of borehole cores.

Crack is the early form of most pavement defects and has a great negative effect on road service life. Timely detection and maintenance of cracks may minimize the loss caused by it. In this paper, we propose a lightweight crack segmentation model based on a bilateral segmentation network, which achieves a good balance between inference speed and segmentation performance. The model contains two parts: context path and spatial path. The network used in context path is inspired by Xception, which is used to rapidly down-sample the feature map. Spatial path employs three convolutional layers to encode sufficient spatial information. The F1_score and IoU achieved by our model on the Crack500 dataset are 0.8270 and 0.7379, respectively. The proposed model gains superior performance in FPS compared to other four models. In addition, the model is able to process images at 1,024 × 512 pixels in real-time (31.3 FPS). Through the comparison of training time, our model can save 54.04% of the time.

Affected by various complex factors, dam deformation monitoring data usually reflect volatility and non-linear characteristics, and traditional prediction models are difficult to accurately capture the complex laws of dam deformation. A multi-scale deformation prediction model based on Variational Modal Decomposition (VMD) signal decomposition technology is proposed in this study. The method first decomposes the original deformation sequence into a series of sub-sequences with different frequencies, then the decomposed sub-sequences are modeled and predicted by Long Short-Term Memory neural network (LSTM) and Random Forest (RF) according to different frequencies. Finally, the prediction results of all sub-sequences are reconstructed to obtain the final deformation prediction results. In this process, it is proposed to use the instantaneous frequency mean method to determine the decomposition modulus of VMD. The innovation of this paper is to decompose the monitoring data with high volatility, and use LSTM and RF prediction, respectively, according to the frequency of the monitoring data, so as to realize the more accurate capture of volatility data during the prediction process. The case analysis results show that the proposed model can effectively solve the negative impact of the original data volatility on the prediction results, and is superior to the traditional prediction models in terms of stability and generalization ability, which has an important reference value for accurately predicting dam deformation and has far-reaching engineering significance.

Magnetorheological (MR) dampers, as an intelligent vibration damping device, can quickly change the damping size of the material in milliseconds. The traditional semiactive control strategy cannot give full play to the ability of the MR dampers to consume energy and reduce vibration under different currents, and it is difficult to control the MR dampers accurately. In this paper, a semiactive control strategy based on reinforcement learning (RL) is proposed, which is based on “exploring” to learn the optimal value of the MR dampers at each step of the operation, the applied current value. During damping control, the learned optimal action value for each step is input into the MR dampers so that they provide the optimal damping force to the structure. Applying this strategy to a two‐layer frame structure was found to provide more accurate control of the MR dampers, significantly improving the damping effect of the MR dampers.

The polygonal scaled boundary finite element method (PSBFEM) is a novel method integrating the standard scaled boundary finite element method (SBFEM) and the polygonal mesh technique. This work discusses developing a PSBFEM framework within the commercial finite element software Abaqus. The PSBFEM is implemented by the User Element Subroutine (UEL) feature of the software. The details on the main procedures to interact with Abaqus, defining the UEL element, and solving the stiffness matrix by the eigenvalue decomposition are present. Moreover, we also develop the preprocessing module and the postprocessing module using the Python script to generate meshes automatically and visualize results. Several benchmark problems from two-dimensional linear elastostatics are solved to validate the proposed implementation. The results show that PSBFEM-UEL has significantly better than FEM convergence and accuracy rate with mesh refinement. The implementation of PSBFEM-UEL can conveniently use arbitrary polygon elements by the polygon/quadtree discretizations in the Abaqus. The developed UEL and the associated input files can be downloaded from https://github.com/hhupde/PSBFEM-Abaqus.