524 papers
This paper proposes an embedded model-data interactive framework for power system dispatch that utilizes a U-Net GAN to map nodal sequences into image tensors and serve as a fast, physics-informed power flow surrogate, thereby overcoming the computational bottlenecks of traditional methods while ensuring operational reliability and safety.
This paper presents and validates an FPGA-in-the-Loop implementation of a Sequential Eliminative Lévy Flight-based MPPT controller that utilizes adaptive mode-switching and hardware-optimized algorithms to achieve high-efficiency global maximum power point tracking with rapid convergence under partial shading conditions.
This study introduces the "Digital Geophysical Eye," a proof-of-concept framework that combines a physics-based Magnetic Signature Database with a CNN model to achieve 90.7% accuracy in classifying archaeological magnetic anomalies, thereby establishing a reproducible foundation for future Explainable AI applications in geophysical archaeology.
This study demonstrates that a standardized, platform-agnostic robotic intraoperative ultrasound workflow using drop-in probes is technically feasible and reproducible across four distinct robotic surgical systems, thereby supporting cross-platform skill transfer and collaborative tele-guided surgery.
This paper proposes a composite fixed-time integral sliding mode control strategy for surface-mounted permanent magnet synchronous motors that integrates a radial basis function neural network and a super-twisting extended state observer to achieve robust speed regulation with guaranteed fixed-time convergence, effectively suppressing chattering and compensating for both internal uncertainties and external disturbances.
This paper presents the design, theoretical modeling, simulation, and experimental validation of a novel in-pipe inspection robot for DN1016 natural gas pipelines, demonstrating its ability to adapt to large diameters, successfully navigate 5D bends, and overcome circumferential weld obstacles up to 8.5 mm in height while maintaining stability at recommended speeds.
This study demonstrates that combining cross-linked biopolymers (xanthan gum and starch) with fiber reinforcement significantly enhances the compressive strength and ductility of sandy soil, outperforming conventional cement-treated soil while offering a more sustainable alternative.
This study develops the "Mobility C3" digital platform to assess motor vehicle CO₂ emissions, finding that the NEDC and WLTP testing procedures offer greater accuracy than the GHG Protocol for improving emission accounting and carbon market mechanisms.
This study demonstrates that adding titanium dioxide nanoparticles to a mango seed biodiesel-butanol-diesel ternary blend improves hydrocarbon emissions and thermal efficiency at specific concentrations, although it results in increased brake specific fuel consumption and nitrogen oxide emissions compared to conventional diesel.
This paper presents the design and preliminary validation of a novel dry laboratory apparatus that replicates real-time knee arthroscopic kinematics and tracking conditions to provide a reproducible, regulatory-informed framework for evaluating AI algorithms prior to clinical deployment, thereby bridging the gap between offline dataset benchmarking and cadaveric studies.