The thermal insulation integrity of liquefied natural gas storage tanks is essential for their life-cycle safety. However, perlite settlement (insulation material) can result in thermal leaks and lead to engineering risks. The direct measurement of perlite settlement is difficult due to the enclosed structure of these tanks. To address this challenge, this study presents a data-driven approach based on machine learning and real-time monitoring data. This study proposes a multi-fidelity machine learning framework to enhance generalizability and leverage multi-fidelity data effectively. Low-fidelity data are readily available but contain systematic errors, while high-fidelity data are accurate but limited in accessibility. By combining both types of data, this framework enhances the generalisability and prediction accuracy of trained models. The results of the data experiments demonstrate that the multi-fidelity framework outperforms models trained solely on low- or high-fidelity data, achieving a coefficient of determination of 0.980 and a root mean square error of 0.078 m. Three machine learning algorithms—Multilayer Perceptron, Random Forest, and Extreme Gradient Boosting—were evaluated to determine the optimal implementation. This approach provides a reliable method for the real-time monitoring of thermal insulation integrity in liquefied natural gas storage tanks, contributing to improved industrial safety and operational efficiency.

Deformation characteristics of exiting tunnel induced by tunnel under-crossing is crucial for the safety of existing tunnel. A combination of manual low-frequency monitoring and wireless sensing high-frequency monitoring was used for an under-crossing case. The case is existing three-line tunnels under-crossed by new three-line mechanized tunnels and there is a connected aisle between two existing tunnels. The monitoring measured settlement and deformation of existing tunnels. Settlement monitoring results show that the settlement of existing tunnel during under-crossing experienced 2 stages: (i) heave, (ii) subsidence. The settlement profiles of the existing tunnels induced by the second tunnel under-crossing were found to be asymmetric with respect to the second tunnel line and the location of maximum settlement point deviated toward the center of the first under-crossing tunnel and the second under-crossing tunnel. For the third tunnel under-crossing, the situation is similar but the offset is not as much. Besides, the connected aisle also caused a longitudinal asymmetric distribution of deformation. Rotational deformation monitoring results show that the deformation of existing tunnel is more complex. When the cutter of tunnel boring machine (TBM) is right below the existing tunnel, the existing tunnel heaved during TBM advancing and subsided during TBM halting. When the shield tail is 0.4D in front and behind the existing tunnel in horizontal direction where D is the diameter of TBM, the existing tunnel heaved at most of time while subsided if the grouting volume is insufficient. <!----> <!----> <!----> <!---->