1690 papers
This paper proposes a novel finite-time barrier function-based sliding mode control strategy that ensures rapid, safe, and accurate trajectory tracking for autonomous sailboats by guaranteeing finite-time convergence and explicitly constraining system states within predefined bounds despite nonlinear dynamics and environmental disturbances.
This paper proposes and validates a flow-balance feedforward fuzzy-PID control method for the pump set of a pile-bottom sediment cleaning robot, demonstrating through simulations that it significantly reduces pressure difference peak deviations and settling times compared to traditional PID and fuzzy-PID controllers under various inflow and flow disturbances.
This study demonstrates through 75 laboratory experiments that the longitudinal length of debris accumulation upstream of trash screens significantly increases upstream water levels and reduces downstream hydraulic efficiency, highlighting the need to incorporate accumulation length into the design and maintenance of open channel systems.
This paper proposes an improved voltage regulation controller for V2G bidirectional interleaved converters that utilizes a cascaded extended state observer with a two-layer third-order nested architecture and cross-layer feedforward mechanism to effectively balance noise suppression and steady-state accuracy while outperforming traditional control methods in dynamic tracking and disturbance rejection.
This paper presents a learning-driven autonomy pipeline for horizontal wellbore geosteering that integrates ridge regression for geometry-based true-vertical-thickness prediction with a residual sparse-attention conditional variational autoencoder to provide probabilistic lithologic corrections, uncertainty quantification, and actionable steering guidance.
This quasi-experimental study demonstrates that an AI-supported, learning analytics-driven system significantly improves secondary school physical education outcomes by delivering personalized exercise prescriptions and actionable feedback, with the greatest benefits observed among students with lower baseline fitness levels.
This study employs multi-objective metaheuristic optimization to identify cutting parameters that balance operator safety (minimizing heart rate and perceived risk) with productivity (maximizing material removal rate) in milling operations, revealing that the Genetic Algorithm offers the best trade-off while feed rate is the primary driver of operator stress.
This paper introduces a novel, scalable parameter estimation framework for pipeline networks that utilizes a wave-propagation-path strategy and probabilistic methods to efficiently estimate wave speeds and friction factors by focusing on coarse pressure signal features, thereby avoiding complex nonlinear equations and demonstrating robustness in both theoretical and realistic urban water distribution systems.
This study introduces Aquivo, an open-source, interactive Python-based decision-support tool that utilizes multi-objective optimization and the TOPSIS method to generate empirically grounded, ranked water allocation strategies balancing economic, environmental, and social objectives.
This research introduces the XAI-AMBR framework, an explainable AI system combining LSTM, SHAP, and reinforcement learning that enables real-time, multi-contaminant adaptive control in full-scale Membrane Bioreactors, achieving superior micropollutant removal while significantly reducing energy consumption.