Stability prediction of underground entry-type excavations based on particle swarm optimization and gradient boosting decision tree

The stability of underground entry-type excavations will directly affect the working environment and the safety of staff. Empirical critical span graphs and traditional statistics learning methods can not meet the requirements of high accuracy for stability assessment of entry-type excavations. Therefore, this study proposes a new prediction method based on machine learning to scientifically adjust the critical span graph. Accordingly, the particle swarm optimization (PSO) algorithm is used to optimize the core parameters of the gradient boosting decision tree (GBDT), abbreviated as PSO-GBDT. Moreover, the classification performance of eight other classifiers including GDBT, k-nearest neighbors (KNN), two kinds of support vector machines (SVM), Gaussian naive Bayes (GNB), logistic regression (LR) and linear discriminant analysis (LDA) are also applied to compare with the proposed model. Findings revealed that compared with the other eight models, the prediction performance of PSO-GBDT is undoubtedly the most reliable, and its classification accuracy is up to 0.93. Therefore, this model has great potential to provide a more scientific and accurate choice for the stability prediction of underground excavations. In addition, each classification model is used to predict the stability category of several grid points divided by the critical span graph, and the updated critical span graph of each model is discussed in combination with previous studies. The results show that the PSO-GBDT model has the advantages of being scientific, accurate and efficient in updating the critical span graph, and its output decision boundary has strict theoretical support, which can help mine operators make favorable economic decisions.