Abstract

The utilization of drones is expected to streamline the process of building inspection in Japan; however, no known drone utilization platform exists in the region‘s architectural sector. Therefore, in this study we pioneered the development of a drone platform based on an industry- government-academia collaboration within Japan‘s architectural field. We first investigated drone related trends, such as a utilization roadmap, flight rules, the drone market, new technologies and issues relating to the architecture field. Subsequently, we worked on solutions for drone utilization in the building sector, including methods for building inspection, determination of drone-flight risk factors relative to building inspection and the creation of a drone safety operation manual. Through field tests, we validated the effectiveness of the drone platform in building inspection, i.e., the determination of a cost-time relation during inspection, the merits of applying a high-resolution camera for inspection, the possibility of utilizing an infrared camera for exfoliation detection in exterior wall tiles and the development and efficiency of a built-in automatic inspection system. Furthermore, trial tests were conducted for the application of a drone-inspection system in disaster areas and a micro-drone in small building spaces. The findings of this study confirmed that the new drone platform achieved inspection- and disaster-related objectives within the architectural sector.

Abstract

Real-time monitoring of oil-gas wellbore temperature profiles provides important support for drilling strategy adjustment and model parameter calibration. MEMS-based micro-measurers can collect fullwellbore temperature data by flowing with drilling fluid circulation, but converting their time-series records to well depth relies on idealized steady-motion assumptions that neglect wall collisions, sticking, and local flow disturbances, introducing systematic positioning errors. In this study, a deep learning-based time-depth conversion method is proposed. A gated recurrent unit (GRU)-based temporal neural network is developed to extract motion-state features from six-axis dynamic signals, and a bounded velocity correction mechanism is introduced to compensate deviations from the idealized terminal velocity. The results show that: (1) The proposed model effectively learns motion-state deviations from dynamic response data and provides stable velocity correction under complex downhole conditions. (2) The corrected time-velocity curve exhibits transient fluctuations relative to the idealized terminal velocity, accurately capturing non-ideal behaviors while preserving directional stability. (3) During model training, the loss function decreases progressively and stabilizes, indicating good convergence and training stability. (4) Comparative analysis shows that the proposed GRU-Full method achieves a mean absolute anchor-point error of 1.23 m (0.24% of the well depth), outperforming the MLP and LSTM alternatives. Ablation experiments confirm that both the physical constraints and regularization terms contribute substantially to the model accuracy. This study enhances the spatial mapping accuracy of temperature data acquired by micro-measurers under complex downhole dynamic conditions. The established physically constrained deep learning framework provides a new technical pathway for refined wellbore thermal-field characterization and intelligent drilling decision-making.