.
The areas along transportation routes constructed in mountainous terrain often harbor significant landslide hazards. Ensemble learning techniques have proven their effectiveness in improving landslide susceptibility prediction performance. In this study, novel ensemble models (Bagging (B), Cascade Generalization (CG), and Dagging (D)) based on the Dual Perturb and Combine for Tree-based (DPCT) approach were employed to predict landslide susceptibility along the Ha Long-Van Don highway. The dataset comprised 77 landslide locations (3263 points), non-landslide locations (1:1 ratio with landslide points), and 14 conditional factors, including topography characteristics, geology, rainfall, and land use/land cover (LULC), which were input parameters for the models (B-DPCT, CG-DPCT, D-DPCT, and DPCT). Evaluation criteria for model prediction outcomes included the area under the receiver operating characteristic curve (AUC), parameters derived from the confusion matrix, the Kappa statistic, and the root mean square error (RMSE). The results demonstrate that the integration of higher-resolution datasets with hybrid machine-learning models leads to a significant improvement in predictive performance and accuracy for landslide susceptibility mapping compared to previous studies. Accordingly, landslide susceptibility maps predicted based on the B-DPCT model exhibited optimal evaluation results on the validation dataset (AUC = 0.948, accuracy ACC = 83.6, Kappa statistic = 0.67, and RMSE = 0.37), suggesting their recommended use for construction planning and mitigation efforts along the Ha Long-Van Don highway to minimize landslide-induced damages.
Vehicle rollover instability becomes critical during sharp steering at high speeds. While Sliding Mode Control (SMC) is widely adopted for its robustness, its inherent chattering significantly deteriorates control smoothness and actuator durability. This article proposes a novel integrated control strategy that combines Disturbance Rejection Control (DRC) with a smooth SMC law shaped by a fuzzy-tuned expanded sigmoid function to enhance the performance of electric stabilizer bars. Unlike conventional SMC- or ESO-based approaches, the proposed method provides several significant advantages: (i) suppresses chattering through an adaptive sigmoid function whose slope is dynamically tuned by a fuzzy mechanism, (ii) improves disturbance estimation accuracy via an LESO integrated in the DRC framework, and (iii) enhances adaptability under varying driving conditions without relying on fixed control gains. Simulation results demonstrate clear performance improvements: the maximum roll angle is reduced from 8.110 degrees (without bars) to 5.975 degrees using the proposed control, and the minimum vertical tire force increases from 327.436 to 2937.274 N. Chattering amplitude in the control input is reduced by approximately 98% (Root Mean Square value) compared with conventional SMC, effectively eliminating high-frequency oscillations. These findings confirm that the proposed control provides a more stable, smoother, and disturbance-resilient anti-roll control solution suitable for practical implementation.
Adverse climatic and environmental conditions have compromised the durability and structural integrity of concrete in construction projects. Environmentally friendly composite material systems that are lightweight and enhance the erosion resistance, water impermeability, and mechanical performance of concrete surfaces, thereby mitigating the reduction. In this study, biochar obtained from the anaerobic pyrolysis of pineapple leaf fibers (PALF) was used as a reinforcing agent in epoxy/PALF composites at 2%, 4%, and 6% by weight. Electron microscopy (SEM), energy-dispersive X-ray spectroscopy (EDX), and Fourier transform infrared spectroscopy (FTIR) methods were used to characterize the morphological, chemical composition, and surface functionality of the biochar. The addition of biochar reduces porosity, strengthens interlayer bonding, and improves the mechanical strength of the epoxy/PALF material, resulting in tensile strength of 45 MPa, compressive strength of 52 MPa, impact toughness with the addition of 2% biochar, and flexural strength of 68 MPa with the addition of 4% biochar. The biochar-infused coating increases the compressive strength of M300 concrete by up to 46% and significantly improves adhesion compared to epoxy/PALF materials. The research results show that the biochar/epoxy/PALF system provides a durable, high-performance, UV-resistant coating that protects concrete structures for the long term.
Sizing optimization of nonlinear inelastic steel truss structures poses significant challenges due to computational intensity from repeated nonlinear analyses and limitations of existing metaheuristic algorithms in handling high-dimensional problems with geometric and material nonlinearities. This paper proposes LEpDE, an enhanced differential evolution algorithm tailored for this task. LEpDE integrates: (1) a pbest mutation scheme balancing local and global searches, (2) a linear population size reduction (LPSR) transitioning from large to small populations for improved initial diversity and final convergence, (3) novel formulas for scale factor (F) and crossover (CR), and (4) an earlier constraint evaluation stop (ECES) to efficiently reduce unnecessary structural analyses. LEpDE's performance was evaluated on three examples (planar 10-bar truss, 47-bar power line truss, and planar 39-bar truss) against EpDE, Rao, a success-history-based parameter adaptation for DE (SHADE), and a LPSR application for SHADE (LSHADE). LEpDE consistently achieved superior best, worst, average, and standard deviation results, with statistical significance confirmed by Student's t-test. Despite a modest 7-10% increase in computation time over EpDE, the substantial gains in solution quality justify this trade-off. These findings establish LEpDE as a robust and efficient tool for nonlinear structural optimization with broad engineering applications.
Active stabilizer bars are widely used in modern vehicles to enhance roll stability during high-speed cornering. However, most existing studies focus on hydraulic stabilizer bars, whereas the control of electric stabilizer bars, whose dynamics are more nonlinear and sensitive to disturbances, has received far less attention. This paper proposes a novel integrated robust control framework that combines Nonlinear Active Disturbance Rejection Control (NADRC) with Finite-Time Sliding Mode Control (FTSMC), in which the switching gain of the FTSMC law is adaptively adjusted using a fuzzy logic system. The proposed method introduces three key innovations: (i) a fuzzy-based FTSMC strategy that effectively suppresses chattering while preserving fast convergence; (ii) an enhanced disturbance rejection mechanism using an Nonlinear Extended State Observer (NESO) to estimate parameter uncertainties, external disturbances, and the lifting torque; and (iii) refined nonlinear vehicle and stabilizer bar dynamic models to compute the desired control torque. To validate the approach, simulations are performed under multiple high-speed steering conditions, including J-turn and sinusoidal steering inputs, and compared with conventional controllers. The results demonstrate that the proposed controller significantly reduces fluctuations in roll angle, roll rate, and vertical tire force. It also achieves a maximum current tracking error of less than 0.08 A and an RMS error of approximately 0.02 A, while maintaining an observation error of around 0.2
