Search

Kicks can lead to well control risks during petroleum drilling, and even more serious kicks may lead to serious casualties, which is the biggest threat factor affecting the safety in the process of petroleum drilling. Therefore, how to detect kicks early and efficiently has become a focus practical problem. Traditional machine learning models require a large amount of labeled data, such kicked sample, and it is difficult to label data, which requires a lot of labor and time. To address the above issues, the deep forest is extended to a transfer learning model to improve the generalization ability. In this paper, a transfer learning model is built to detect kicks early. The source domain model adopts the deep forest model. Deep forest is an ensemble learning model with a hierarchical structure similar to deep learning. Each layer contains a variety of random forests. It is an integration of the model in depth and breadth. In the case of a small sample size (20–60 min), kick can be identified 10 min in advance. The deep forest model is established as the source domaining model, and a cascade forest is added at the last layer according to the transfer learning algorithm to form the classification model of this paper. The experimental results show that the kick prediction accuracy of the model is 80.13% by a confusion matrix. In the target domain, the proposed model performs better than other ensemble learning algorithms, and the accuracy is 5% lower than other SOTA transfer learning algorithms. [ABSTRACT FROM AUTHOR]

The occurrence of rockburst can cause significant disasters in underground rock engineering. It is crucial to predict and prevent rockburst in deep tunnels and mines. In this paper, the deficiencies of ensemble learning algorithms in rockburst prediction were investigated. Aiming at these shortages, a novel machine learning model, deep forest, was proposed to predict rockburst risk. The deep forest combines the characteristics of deep learning and ensemble models, which can solve complex problems. To develop the deep forest model for rockburst prediction, 329 real rockburst cases were collected to build a comprehensive database for intelligent analysis. Bayesian optimization was proposed to tune the hyperparameters of the deep forest. As a result, the deep forest model achieved 100% training accuracy and 92.4% testing accuracy, and it has more outstanding capability to forecast rockburst disasters compared to other widely used models (i.e., random forest, boosting tree models, neural network, support vector machine, etc.). The results of sensitivity analysis revealed the impact of variables on rockburst levels and the applicability of deep forest with a few input parameters. Eventually, real cases of rockburst in two gold mines, China, were used for validation purposes while the needed data sets were prepared by field observations and laboratory tests. The promoting results of the developed model during the validation phase confirm that it can be used with a high level of accuracy by practicing engineers for predicting rockburst occurrences. [ABSTRACT FROM AUTHOR]

Rock mass conditions are extremely sensitive to tunnel boring machine (TBM) tunneling. Therefore, establishing a surrounding rock excavatability (SRE) classification system applicable to TBM tunnels. Accurately and intelligently identifying excavatability grades can also facilitate efficient TBM tunneling and intelligent construction. Specific excavation and penetration rates were used to evaluate SRE. Their correlations with geological and tunneling parameters were explored using the field data from two water conveyance tunnels in China with different lithologies. A high-precision empirical SRE classification system was constructed using TOPSIS for multi-objective decision-making, and it was verified using engineering cases. An intelligent identification model for SRE grades in the stable phase of a TBM excavation cycle was established using 12,382 TBM rock-breaking datasets and deep forest models. Ten characteristic parameters, e.g., total thrust, were selected as model input features. Hyperparameter optimization was achieved using the grid search method. Deep forest was compared with decision tree, random forest, support vector classifier, and deep neural network. The contribution of the model's features was measured using random forest. The main conclusions are as follows: the proposed SRE classification method is feasible and matches well with the actual excavation. In the intelligent identification of SRE classification, the accuracy and F1 scores when using deep forest were 96.33% and 0.9581, respectively. Deep forest exhibited better grade identification performance than the four models. Among the ten input features, penetration is the most important feature for the model's input, while the top shield cylinder rod's chamber pressure is the least important. The findings can provide some references for SRE classification and prediction and intelligent TBM control. [ABSTRACT FROM AUTHOR]