Intelligent design and evaluation of tunnel support structure systems

With the rapid development of artificial intelligence, intelligent algorithms for parameter nonlinear mapping provide a new design approach to address the long-term reliance on empirical design in tunnel engineering. This paper proposes an intelligent model for predicting support structure parameters based on tunnel background information. After comparing the characteristics of machine learning and deep learning algorithms applied in the intelligent design model, the generated model is validated using tunnel deformation indicators. The results show the overall accuracies of the machine learning CLS-PSO-SVM and deep learning HRNet algorithms used are 81.1 % and 88.5 %, respectively. Converting the maximum deformation as the only output indicator, the prediction accuracies of the vault and haunch deformations are 85.2 % and 82.8 %, respectively, verifying the reliability of the intelligent model. The research results can provide theoretical support for the intelligent design of tunnel engineering. Meanwhile, intelligent design models will develop towards finer prediction parameters in the future.