The shield machine attitude (SMA) is the most important parameter in the process of tunnel construction. To prevent the shield machine from deviating from the design axis (DTA) of the tunnel, it is of great significance to accurately predict the dynamic characteristics of SMA. We establish eight SMA prediction models based on the data of five earth pressure balance (EPB) shield machines. The algorithms adopted in the models are four machine learning (ML) algorithms (KNN, SVR, RF, AdaBoost) and four deep learning (DL) algorithms (BPNN, CNN, LSTM, GRU). This paper obtains the hyperparameters of the models by utilizing grid search and K-fold cross-validation techniques and uses EVS and RMSE to verify and evaluate the prediction performances of the models. The prediction results reveal that the two best algorithms are the LSTM and GRU with EVS > 0.98 and RMSE < 1.5. Then, integrating ML algorithms and DL algorithms, we design a warning predictor for SMA. Through the historical 5-cycle data, the predictor can give a warning in advance if the SMA deviates significantly from DTA. This study indicates that AI technologies have considerable promise in the field of SMA dynamic prediction.

Serratia marcescens is a common opportunistic pathogen that causes infections in clinical patients. The aim of this study was to investigate the inhibitory efficiency of carvone on the production of virulence factors and evaluated the susceptibility of antibiotics against biofilms of S. marcescens in combination with carvone. Carvone treatment notably inhibited the production of lipase, prodigiosin, extracellular polysaccharides (EPS), and swimming and swarming motilities. Carvone exposure also reduced the formation of biofilms in S. marcescens NJ01. When exposed to antibiotics in combination with carvone, the inhibitory impact was notably improved. In addition, the expressions of genes glp and katG involved in the synthesis of glutathione peroxidase and catalase, respectively, were significantly suppressed after treatment with carvone. The suppression of antioxidant enzymes resulted in the improvement of reactive oxygen species (ROS) and H₂O₂, enhanced the permeability of membrane, and eventually increased the susceptibility of biofilms or planktonic cells to antibiotics. The data mentioned above indicated that carvone is expected to play an important role in the control and treatment of S. marcescns infection.

Perception of rock condition (RC) is a challenge in tunnel boring machine (TBM) construction due to lack of space and time to observe and detect RC. To overcome this problem, this study aims to extract a new rock fragmentation index (RFI) that can reflect RC from real-time rock fragmentation data of the TBM. First, a comprehensive review of existing rock fragmentation models is conducted, which leads to some candidate RFIs that can reflect RC. Next, these candidate RFIs are investigated using data from 12,237 samples from a well-monitored tunnel boring process of the TBM in a 20,198 m tunnel. Further, a new RFI system is recommended as the parameter involving the optimal models. Finally, a preliminary study of the relationship between these RFIs and RC is carried out, and it is shown that these RFIs can reflect RC to a large extent. In the TBM boring process, these RFIs can be extracted from real-time TBM fragmentation data and used to predict the RC in the field. Therefore, the challenge of RC perception is solved with this new RFI system. The new RFI system offers significant potential for the real-time rock classification, prediction of the surrounding rock collapse potential, and selection of control parameters or support measures during TBM construction. This will be the key to improving TBM construction performance.

In tunnel boring machine (TBM) construction, the presence of collapsible rock mass (CRM) can lead to accidents such as collapse and jamming. This study presents a novel CRM early warning strategy based on real-time TBM rock fragmentation data to improve safety and efficiency in CRM conditions. The strategy includes a qualitative classification model and a quantitative probability model for CRM identification. The results indicate that the distribution dissimilarity index β effectively reflect the significance of variables across CRM and non-CRM datasets. Various parameters, including TPI, FPI, WR, and AF, show discriminatory ability between CRM and non-CRM samples. In particular, the CRM-weighted index, which combines the strengths of the individual indices, achieves a distributional dissimilarity index of 1.05, significantly higher than any of the individual indices. The qualitative classification model proves effective in identifying samples from collapse areas, demonstrating ability to identify samples located in adverse geological condition. The quantitative model shows that the probability of CRM is generally higher in adverse geological area samples, particularly in zones where collapse has occurred, with a CRM probability is approaching 1. The proposed strategy provides accurate early warnings to prevent collapse accidents and represents a practical approach to improving the safety and efficiency.