Measurement while drilling (MWD) data reflect the drilling rig–rock mass interaction; they are crucial for accurately classifying the rock mass ahead of the tunnel face. Although machine-learning methods can learn the relationship between MWD data and rock mechanics parameters to support rock classification, most current models do not consider the impact of the continuous drilling-sequence process, thereby leading to rock-classification errors, while small and unbalanced field datasets result in poor model performance. We propose a novel deep neural network model based on Bi-directional Long Short-Term Memory (BILSTM) to extract information-related sequences in MWD data and improve the accuracy of the rock-mass classification. Two optimization modules were designed to improve the model’s generalization performance. Stratified K-fold cross-validation was used for model optimization in small and unbalanced datasets. Model validation is based on the MWD dataset of a highway tunnel in Yunnan, China. Multiple metrics show that the prediction ability of the network is significantly better than those of a multilayer perceptron (MLP) and a support-vector machine (SVM), while the model exhibits an improved generalization performance. The accuracy of the network can reach 90%, which is 13% and 15% higher than the MLP and SVM, respectively.

Objective. To study the protective effect of trimetazidine on myocardial cells in rats with myocardial infarction and explore its effect on ERK signaling pathway. Methods. 40 SD rats were randomly divided into the sham operation group, model group, low‐dose group, and high‐dose group (intra‐abdominal injection of trimetazidine 5 mg/kg and 10 mg/kg, respectively), construction of rat myocardial infarction model by coronary artery left anterior descending artery ligation. 7 days after surgery, the survival rate and cardiac function of each group of rats were recorded. The myocardial infarct size was detected by TTC staining. The apoptosis level of rat cardiomyocytes was detected by TUNEL staining. The content of ROS in rat cardiomyocytes was detected by DCFH‐DA. Western‐blot was used to detection of Caspase‐3, Bcl‐2/Bax, and ERK signaling pathway‐related proteins in myocardial tissue. Results. Compared with the model group, the survival rate of the rats in the low‐dose group and the high‐dose group was significantly increased (P < 0.01), the cardiac function was significantly improved (P < 0.01), the myocardial infarct size was significantly decreased (P < 0.01), the level of apoptosis was significantly decreased (P < 0.01), the content of ROS in cardiomyocytes was significantly decreased (P < 0.01), the protein expression of Caspase‐3 and NF‐κB in cardiomyocytes was significantly decreased (P < 0.01), and the expression of Bcl‐2/Bax and p‐ERK were significantly increased (P < 0.01). Conclusion. Trimetazidine can activate ERK signaling pathway in cardiomyocytes of rats with myocardial infarction, increase the expression of p‐ERK, decrease the content of ROS in cardiomyocytes, decrease the expression of apoptotic proteins, reduce myocardial infarct size, improve cardiac function, and increase myocardial function.

Reliable geology prediction is of great importance in ensuring the stability and safety of tunnels and other underground engineering projects. This paper presents basic neural network and deep neural network models using a genetic algorithm (GA) to predict geological conditions for tunneling. Batch normalization and GA optimization approaches are employed in the deep neural network. A case study of the Jiudingshan Tunnel on the Chuxiong–Dali Highway in Yunnan, China, shows that the neural network method can predict geological conditions well, especially for rock types with voluminous data, for which predictive accuracy exceeds 90%. These results suggest that an appropriately trained neural network can reliably and accurately predict the geological conditions behind the tunnel face. The area under the curve (AUC) and confusion matrix evaluations show that the accuracy performance of the deep neural network exceeds that of the basic neural network. The feature importance of each drilling parameter was also analyzed; the results indicate that a neural network model for geology prediction can achieve predictive accuracy with few drilling parameters. The neural network geology prediction method provides reliable results for dynamic tunnel design.

A new definition of the factor of safety—the vector-sum factor of safety (VFOS) considering force-vector characteristics—is introduced and is defined as the ratio of projection of the resistance force to that of shear force in the potential sliding direction of the slope. This study develops a new analysis method for solving the VFOS of slope with a noncircular slip surface considering interslice forces based on slice method. The analysis method developed for slope stability is implemented in the spreadsheet software Microsoft Excel for efficient calculation. The proposed method is verified through comparison with the VFOS by the FEM and the rigorous limit-equilibrium method, and the significance of the proposed method is highlighted.