This paper proposes an improved method for car motion planning aimed at addressing the limitations of traditional path planning and obstacle avoidance algorithms in complex environments. The study utilizes Bi-RRT* and polynomial fitting for path planning, incorporating an environment-adaptive polynomial fitting technique based on obstacle density to enhance path precision in areas with high obstacle density. In the local planning phase, intelligent switching of the car’s obstacle avoidance strategies is implemented, allowing the car to use reverse motion or lateral avoidance in high-density regions to prevent stalling. Furthermore, problem decomposition and approximation methods are applied to large-scale quadratic programming (QP) problems in path tracking, improving the efficiency of the MPC algorithm. Experimental results demonstrate that the proposed method significantly enhances the car’s motion performance and stability in complex environments.
Rice husk ash concrete (RHAC) shows promise as a beneficial supplementary material in concrete. However, determining mechanical properties such as compressive strength (CS) and splitting tensile strength (STS) of RHAC through conventional lab-scale methods is laborious and time-consuming. In this research, seven important variables were selected as inputs to predict CS and STS using machine learning (ML) models, including Gaussian Process Regression (GPR), Random Forest Regression (RFR), and Decision Tree Regression (DTR) with grid search optimization. The result presented revealed that selected machine learning models provide well accuracy for CS and STS estimates. Among these, the DTR model demonstrated superior performance, with CS prediction R2, RMSE, MAE, and MAPE values of 0.964, 3.314, 2.225, and 5.068, at the testing stage respectively. For STS at the testing stage, DTR achieved R2 of 0.969, RMSE of 0.177, MAE of 0.1322, and MAPE of 3.413. GPR and RFR models also performed well, with R2 values of 0.9434 and 0.9530 for CS prediction. The partial dependence plot (PDP) analysis revealed the optimal mix design parameters for achieving the desired strength. These results offer valuable insights for sustainable construction, allowing engineers to efficiently predict and optimize material performance, reducing the reliance on time-consuming lab methods.
The deep mixing method (DMM) has become a leading ground improvement technique in Japan over 60 years. However, recent cases of construction defects suggest not only environmental factors but also human errors, such as poorly constructed improved columns. Engineers may struggle to visualize soil behavior from geotechnical borehole survey data from structural viewpoint. This study focuses on the unconfined compression characteristics, sensitivity, and compressibility of clayey soil samples collected from the Kyushu region of Japan. Statistical data, such as the mean values of state variables including failure strain (εf), normalized deformation modulus (E50/su), liquidity index (IL), and compression index ratio (Cc1/Cc2) were calculated. By incorporating soil structure considerations into the comparative analysis of these variables, the study aimed to identify thresholds that indicate the "compatibility" or "incompatibility" of clayey soils. Clayey soils with εf < 2.8%, E50/su ≥ 110, IL ≥ 1.11, and Cc1/Cc2 ≥ 1.43 were classified as “compatible” with a bulky structure, while those with εf ≥ 2.8%, E50/su < 110, IL < 1.11, and Cc1/Cc2 < 1.43 were “incompatible” with a dense structure. The findings provide a structural framework for engineers to interpret soil data, improving DMM quality, risk management, and sustainable construction.
Faults and fractured zones are common geological hazards in tunnel construction, especially in seismic regions where tunnels are highly vulnerable to fault movements. This study uses Urumqi Metro Line 2 as a case, establishes a new damage assessment system for tunnels crossing multiple slip surface faults. Three-dimensional nonlinear finite element models are used to analyze the effects of fault displacement magnitudes, distances between adjacent slip surfaces, and fault dip angles on tunnel lining damage. The study identifies the damage characteristics and evolution of tunnel linings under multiple fault movements, filling gaps in existing research. Lining damage is quantitatively assessed using two indicators: the damage state of the tunnel lining and the overall lining damage index. The proposed model has been verified through two methods. Results show that as fault displacement increases, lining damage progresses from the invert to the crown and sidewalls, longitudinal damage mainly occurs near the slip surface and fault-rock interface. Once the fault displacement exceeds 0.5 m, the overall lining damage index hardly changes anymore. Fault movements along narrow slip surfaces result in a cumulative effect on the lining; however, when the gap between slip surfaces exceeds 21.0 m, slight damage occurs in the central tunnel region. Tensile damage to the lining is highly sensitive to fault dip angle, with a 20.7% variation as the dip angle changes. Additionally, tunnels in the moving block experience more tensile damage than those in the fixed block. Overall, the numerical results of this study provide a better understanding of the response of tunnels under the movement of multiple slip surface faults.