Compressive strength is an important mechanical property of high-strength concrete (HSC), but testing methods are usually uneconomical, time-consuming, and labor-intensive. To this end, in this paper, a long short-term memory (LSTM) model was proposed to predict the HSC compressive strength using 324 data sets with five input independent variables, namely water, cement, fine aggregate, coarse aggregate, and superplasticizer. The prediction results were compared with those of the conventional support vector regression (SVR) model using four metrics, root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and correlation coefficient (R2). The results showed that the prediction accuracy and reliability of LSTM were higher with R2 = 0.997, RMSE = 0.508, MAE = 0.08, and MAPE = 0.653 compared to the evaluation metrics R2 = 0.973, RMSE = 1.595, MAE = 0.312, MAPE = 2.469 of the SVR model. The LSTM model is recommended for the pre-estimation of HSC compressive strength under a given mix ratio before the laboratory compression test. Additionally, the Shapley additive explanations (SHAP)-based approach was performed to analyze the relative importance and contribution of the input variables to the output compressive strength.
It is time-consuming and uneconomical to estimate the strength properties of fly ash concrete using conventional compression experiments. For this reason, four machine learning models—extreme learning machine, random forest, original support vector regression (SVR), and the SVR model optimized by a grid search algorithm—were proposed to predict the compressive strength of fly ash concrete on 270 group datasets. The prediction results of the proposed model were compared using five evaluation indices, and the relative importance and effect of each input variable on the output compressive strength were analyzed. The results showed that the optimized hybrid model showed the best predictive behavior compared to the other three models, and can be used to forecast the compressive strength of fly ash concrete at a specific mix design ratio before conducting laboratory compression tests, which will save costs on the specimens and laboratory tests. Among the eight input variables listed, age and water were the two relatively most important features with superplasticizer and fly ash being of weaker relative importance.
The prediction of rate-dependent compressive strength of rocks in dynamic compression experiments is still a notable challenge. Four machine learning models were introduced and employed on a dataset of 164 experiments to achieve an accurate prediction of the rate-dependent compressive strength of rocks. Then, the relative importance of the seven input features was analyzed. The results showed that compared with the extreme learning machine (ELM), random forest (RF), and the original support vector regression (SVR) models, the correlation coefficient R2 of prediction results with the hybrid model that combines the particle swarm optimization (PSO) algorithm and SVR was highest in both the training set and the test set, both exceeding 0.98. The PSO-SVR model obtained a higher prediction accuracy and a smaller prediction error than the other three models in terms of evaluation metrics, which showed the possibility of the model as a rate-dependent compressive strength prediction tool. Additionally, besides the static compressive strength, the stress rate is the most important influence factor on the rate-dependent compressive strength of the rock among the listed input parameters. Moreover, the strain rate has a positive effect on the rock strength.
Axial bearing capacity is the key index of circular concrete-filled steel tubes (CCFST). A hybrid PSO-ANN model consisting of an artificial neural network (ANN) optimized with particle swarm algorithm (PSO) was proposed to reliably and accurately predict the axial bearing capacity in this paper. The predictive performance of the model was evaluated and compared with the EC4 code and original ANN based on a dataset of 227 experiments, and a graphical user interface (GUI) was developed to achieve the automatic output of the results. The influence of each design parameter on the bearing capacity was analyzed and quantified using the Shapley additive explanation (SHAP) method and sensitivity analysis. The results show that the prediction performance of the PSO-ANN model is superior, and can be recommended as a candidate for the prediction of axial compression bearing capacity of the CCFST column in terms of performance indices. Shapley additive explanation-based parameter analysis indicated that the diameter and thickness of the steel tube are the most two important parameters to the bearing capacity; in particular, the fluctuation of the diameter under the stochastic environment leads to the variation of the axial compression bearing capacity beyond the diameter itself.
Concrete crack detection in complex backgrounds remains challenging due to severe visual interference and limited computational resources on edge devices. To address these issues, this study proposes a lightweight crack segmentation network (LCNet) for accurate and efficient crack detection in real-world bridge inspection scenarios. LCNet adopts an asymmetric channel scaling strategy to improve computational resource allocation across network layers and introduces a bottleneck enhancement module to strengthen feature representation while maintaining low computational cost. Extensive experiments conducted on a self-constructed bridge crack dataset demonstrate that LCNet outperforms several state-of-the-art methods, including DeepLabV3+, UNet, UNet++, and Swin-Unet. Specifically, LCNet achieves an mIoU of 87.51% and a Dice coefficient of 89.67%, with only 9.01 M parameters and 19.03 GFLOPs, demonstrating a superior balance between accuracy and efficiency. Qualitative results further show that LCNet effectively suppresses pseudo-texture interference, preserves crack continuity, and accurately captures complex crack topology under challenging conditions. In addition, experiments on real bridge inspection images validate its robustness and practical applicability in engineering scenarios. Overall, LCNet achieves a favorable trade-off between segmentation accuracy and computational efficiency, demonstrating strong potential for UAV- and edge-device-based structural health monitoring applications.