Hao Zhu's research while affiliated with Key Technology and other places

The accuracy of instructions for the extraction of large open caissons directly affects the construction quality and safety. This study is focused on developing a smart construction methodology for predicting open caisson excavation instructions. The proposed approach aims to reduce the errors in excavation instructions attributable to the subjective and varying experiences of decision-makers. The multilabel classification task of predicting the instructions of large open caisson excavation is accomplished through the problem analysis. The study conducted a comparative analysis of a multilayer perceptron model, a classifier chain model, and a multilabel K-nearest neighbor model (MLKNN) based on Hamming loss and accuracy. The results revealed that MLKNN exhibits significant differences from the other models and is most suitable for predicting open caisson excavation instructions. Furthermore, the traditional MLKNN model was improved by refining the normalization and distance measurement methods for the open caisson scenario. The prediction accuracy of the improved MLKNN model is 89.04% for the excavation instructions and 98.63% for the nonexcavation decisions. The successful prediction of excavation instructions for a large open caisson can compensate for the lack of data mining capability of the existing monitoring system. This can reduce construction risks. Finally, this study discussed the robustness of the improved MLKNN in a real project, highlighting the model’s high accuracy during the midstage of open caisson construction.

In the process of bridge foundation construction, the height of poured concrete cannot be measured automatically, which depends on manual operation and construction interruption. This paper proposes an automatic detection technology of the height of poured concrete via fiber-optic temperature sensing, which use the small temperature difference between concrete and air medium in the process of concrete pouring. The median filtering method is used to process the temperature position curve to obtain a signal curve similar to a step signal. The step functions with different periods are constructed, and the correlation coefficient curve is obtained by cross-correlation operation between the obtained temperature curve and the step functions with different periods. The variable step size search method is used to improve computational efficiency. Finally, the correlation coefficient curve is processed by peak seeking to realize the automatic discrimination of concrete level elevation. This technology has been successfully applied to the diaphragm wall project of Zhang-Jing-Gao Yangtze River Bridge. Limited by the spatial resolution of the temperature measurement system, the resolution of the liquid level elevation is ± 0.5m, and the automatic judgment of the liquid level elevation is consistent with the actual measurement results judged by the temperature nephogram, indicating that the algorithm has good accuracy, and the results of 30 operations at the same time are consistent, indicating that the algorithm has good stability.

Currently, there is no automatic method available to measure the height of poured concrete during concreting of underground diaphragm walls (UDWs), and the conventional manual method interrupts the operation. To address this issue, a distributed fiber-optic sensing-based method for measuring the height of poured concrete during the concreting of UDWs was developed and successfully applied to the real-time measurement of the height of poured concrete. The proposed method was verified by performing a scale mode test, wherein an acrylic circular tube was used to simulate a UDW steel cage and a temperature-sensing fiber-optic cable was laid spirally to increase the spatial resolution of measurement to 0.1 m. The temperature distribution in the tube and real-time measurements of the height of the poured concrete during concreting were obtained. The proposed method was applied to the construction of a real UDW. A total of 3360 data points representing the spatiotemporal temperature distribution in the UDW steel cage were obtained. The results indicated that the temperature of the mud in the steel cage was approximately 25–26 °C when no concreting operation was performed and that the temperature of the concrete layer increased to approximately 28–31 °C during concreting. The height of the poured concrete was the boundary representing the transition from the temperature of the mud to that of the concrete, and the measurement precision reached ±0.5 m. The measurement results obtained via the proposed method were consistent with those obtained manually using a plumb bob, thus confirming the effectiveness of the proposed method for high-precision, real-time measurement of the height of poured concrete during the concreting of UDWs.

The soil pressure on the bottom surface of the foot blades is an important monitoring point during the sinking process of large underwater caissons. Complex soil-structure interactions occur during the sinking process, making it difficult to accurately predict the soil pressure of foot blades. Accurate construction processes often rely on data from the soil pressure of foot blades in the field. In this study, a data-driven approach is used to establish the relationship between the amount of sinking of the caisson and the soil pressure of foot blades. Furthermore, by improving the splitting method of the original Classification and Regression Tree (CART) algorithm, a single model’s numerical prediction of 80-foot blades soil pressures is realized. The improved CART model, multilayer perceptron (MLP), long short-term memory (LSTM), and a linear regression model are compared through a comprehensive multiparameter evaluation method. Finally, this article discusses the deployment scheme of the model by comparing and analyzing the data in the time period of 10 : 00 on July 29, 2020, and 23 : 00 on August 7, 2020. The experimental results can satisfy the engineering demands and provide a basis for further data-driven intelligent control of large caisson sinking.