Search

Low-permeability sandstone reservoirs with low clay content are prone to water-sensitive damage during the fracturing process. In field applications, serious formation damage occurred with the conventional fracturing fluid system using KCl clay stabilizer. The introduction of SP clay stabilizer into the fracturing fluid formulation system significantly reduced the water-sensitive damage during fracturing and improved the reservoir transformation and production enhancement effect. In this paper, the clay stabilization mechanism of two substances, inorganic clay stabilizer KCl and organic ammonium salts with low molar weight SP, is studied by tests of swelling inhibition, ζ-potential test, and scanning electron microscope test to compare. On this basis, the adsorption behavior of SP on the surface of clay minerals is also studied in depth by isothermal adsorption and desorption experiments to explain mechanistically the difference of two different clay stabilizers on the fracturing effect, which helps to solve the formation damage problem in the fracturing and production enhancement process of low-permeability sandstone reservoirs with low clay content. [ABSTRACT FROM AUTHOR]

Motivated by the strengths of unmanned aerial vehicle (UAV), the UAV–human collaboration route planning (UHCRP) for intelligent infrastructure inspection is a problem worthy of discussion to help reduce human costs and minimize the risk of noninspected infrastructures under limited resources. To facilitate UHCRP, this paper proposes a novel deep reinforcement learning (DRL)‐based approach to well handle multi‐source uncertain features and constraints at a fast speed. To begin with, UHCRP is mathematically described and reformulated as a dual interdependent deep reinforcement learning (diDRL) framework to reflect real‐world scenarios. Afterward, a novel policy network named the attention‐based deep neural network (A‐DNN) is introduced to learn the route planning decisions for the combinatorial optimization problem. In particular, A‐DNN is made up of an encoder and a dual decoder for UAV and human inspection, where the multi‐head attention mechanism is incorporated to generate richer representations for model performance improvement. Performance of the proposed dual multi‐head attention model (DAM) has been tested in simulations and a real‐world case study regarding wind farm inspection. Results indicate that DAM under the sampling decoding strategy can deliver a high‐quality path plan and show better generalizability for larger scale problem sizes compared to single‐head attention model (SAM), multi‐head attention model (AM), and two baseline models, namely OR‐Tools and genetic algorithm. Moreover, DAM trained by randomly generated data can be directly employed to solve the practical problem with standardization of inputs. Overall, DRL integrates decision‐making for inspection method selection and inspected infrastructure selection, providing adaptive and intelligent inspection path planning for UAV and human in complex and dynamic engineering environments. [ABSTRACT FROM AUTHOR]

Engineering practices indicate that stratum hydraulic conductivity (SHC) has a significant influence on deep excavations. However, this influence has been ignored in previous studies with undrained analyses. In this study, a numerical model, combined with the verified hydromechanical coupled method, is established to investigate the effect of SHCs on the performances of deep excavations. Excavation deformation, pore-water pressure, lateral pressure, and the stress evolution process are presented, respectively, to illustrate these influences. In addition, the model of a beam on an elastic foundation is employed to interpret the influential mechanism of SHCs on excavation deformations. Analysis results indicate that excavation deformations increase significantly with the increase in SHCs from 1 × 10−7 to 1 × 10−5 cm/s (i.e., the range of SHCs of soil containing silt). The influence of SHCs on excavation deformations is mainly attributed to the variation of effective stress levels on the excavated side. As SHC increases, the change in the resultant force of the total stress acting on the retained side of the wall, as loads, can be ignored, while the resultant force of the effective stress acting on the excavated side of the wall, as resistances, decreases dramatically. These findings emphasize the importance of accurate determination of the SHC of strata containing silt. Engineering practices indicate that stratum hydraulic conductivity (SHC) significantly affects the performances of deep excavations in Shanghai soft deposits. Constructions in the first aquitard (AdI) have been involved in the many deep excavations in Shanghai, China, and therefore, identifying the effects of the SHC of AdI on deep excavations can further ensure the safety of constructions. In this study, it is found that excavation deformations increase significantly as the SHC of AdI increases from 1 × 10−7 to 1 × 10−5 cm/s (i.e., the SHCs in soil containing silt). This finding indicates that valuing the SHC of AdI containing silt requires utmost caution, and adopting appropriate methods such as dewatering can significantly decrease excavation deformations. [ABSTRACT FROM AUTHOR]

During a deep excavation project, monitoring the structural health of the adjacent buildings is crucial to ensure safety. Therefore, this study proposes a novel probabilistic deep reinforcement learning (PDRL) framework to optimize the monitoring plan to minimize the cost and excavation‐induced risk. First, a Bayesian‐bi‐directional general regression neural network is built as a probabilistic model to describe the relationship between the ground settlement of the foundation pit and the safety state of the adjacent building, along with the actions in a dynamic manner. Subsequently, a double deep Q‐network method, which can capture the realistic features of the excavation management problem, is trained to form a closed decision loop for continuous learning of monitoring strategies. Finally, the proposed PDRL approach is applied to a real‐world deep excavation case in No. 14 Shanghai Metro. This approach can estimate the time‐variant probability of damage occurrence and maintenance actions and update the state of the adjacent building. According to the strategy proposed via PDRL, monitoring of the adjacent buildings begins in the middle stage rather than on the first day of the excavation project if there is full confidence in the quality of the monitoring data. When the uncertainty level of data rises, the starting day might shift to an earlier date. It is worth noting that the proposed PDRL method is adequately robust to address the uncertainties embedded in the environment and model, thus contributing to optimizing the monitoring plan for achieving cost‐effectiveness and risk mitigation. [ABSTRACT FROM AUTHOR]

Ascertaining failure mechanism is a prerequisite of the derivation for earth pressure against retaining structures. Retaining structures constructed adjacent to existing structures and excavation with narrow backfill have become common in practical engineering. The backfill width has a significant effect on the failure mechanism, requiring further study. In this study, a series of discrete element analyses are conducted to investigate the shear localization in soil mass behind retaining structures with narrow backfill in the active and passive limit states at the grain scale. Furthermore, the distribution characteristic of failure surfaces in soil mass is discussed from three aspects: the development of the failure surface, the state of soil mass behind retaining structures, and the shape of the failure surface. Based on the typical nonlinear failure mechanisms observed in particle rotation contours with various backfill widths and interface friction angles, the failure mechanisms behind retaining structures with narrow spacing are categorized into three types according to the backfill widths. According to the stress characteristics of interfaces under different failure mechanisms, the variational method and Mohr stress circle analysis are adapted to analytically obtain the failure surfaces behind the retaining structure with narrow backfill. Comparisons with results obtained by the discrete element simulation show a reasonable agreement. In addition, a series of parameter studies are conducted to investigate the effect of backfill widths and interface friction angles on the failure mechanism. [ABSTRACT FROM AUTHOR]

Axial forces can be artificially adjusted in deep excavations braced with servo struts to reduce excavation-induced deformations. The interactions among the servo strut, retaining wall, and retained soil must be considered to predict the excavation-induced deformations and axial force adjustment. According to the beam–spring model, this study advances a simplified method to calculate the wall deflections generated by excavation with adjustable axial forces in struts. The proposed method incorporates the coupling relationship between the alterations in the earth pressure and wall displacement to consider soil–wall interactions. A mixed boundary, including force boundary and spring boundary, is introduced in the equilibrium equation to simulate the adjustable forces in the servo struts. The recommended method accounts for the soil–wall–strut interactions. Two real excavation cases supported by traditional and servo steel struts, respectively, validate this study's findings. Comparisons between the predictions and measurements demonstrate the effectiveness of the proposed method. Projections and measurements indicate that the servo struts reduce the maximum wall deflection, which decreases significantly with the increased axial force. Importantly, the retaining wall moves outside the excavation if excessive axial forces are applied in the servo struts. [ABSTRACT FROM AUTHOR]

A novel semianalytical method is proposed to estimate the earth pressure exerted on rigid retaining walls supporting a narrow granular backfill in this study, which is based on the assumption of a log-spiral failure surface. This study adopts the differential element limit equilibrium method, coupled with the stress analysis considering the deflection of principal stress trajectory, to obtain the stress distribution against retaining walls. The resultant earth pressure, the point of application, and earth pressure distribution can be obtained by the finite-difference method. The method proposed in this study is verified via comparisons with model test results, centrifuge test results, and discrete-element method results. Furthermore, a series of extensive parameter studies are conducted to investigate the effect of backfill width and interface friction on resultant earth pressure, the point of application, and earth pressure distribution for further studies. [ABSTRACT FROM AUTHOR]