Rolling bearings are critical components of marine shafting power transmission systems, and accurate prediction of their vibration signal trends is essential for predictive maintenance. To address the limited adaptability of conventional time-series forecasting models under varying operating conditions and their insufficient ability to capture strong noise and abrupt changes, this study proposes a vibration signal prediction method that integrates particle swarm optimization (PSO) with an improved Informer model. PSO is used to adaptively optimize key Informer hyperparameters for different operating conditions, while a rolling time-window mechanism is introduced to enhance the capture of abrupt signal variations. In addition, a mixture of sparse attention (MoSA) encoder with a collaborative dense-head/sparse-head structure is designed to balance global temporal dependency modeling and local fault feature extraction. Experimental results on the Case Western Reserve University (CWRU) bearing fault dataset show that the proposed model outperforms Long Short-Term Memory (LSTM), Transformer, Informer, iTransformer, and Flowformer in terms of Mean Squared Error (MSE), Mean Absolute Error (MAE), and Root Mean Squared Erro (RMSE). The model achieves an MSE of 0.2015, which is 25.5% lower than that of the second-best iTransformer model. It also demonstrates robust performance under four different bearing operating states, confirming its adaptability to complex operating conditions. The proposed method provides a promising technical route for the predictive maintenance of rolling bearings in marine shafting systems.

This paper presents a genetic algorithm (GA) tuned Mamdani type fuzzy logic control (FLC) framework for trajectory tracking of a quadrotor unmanned aerial vehicle (UAV) using a nonlinear rigid body model. The proposed architecture adopts a cascaded structure in which an outer loop position controller generates attitude and thrust references $(\phi_{\mathrm{ref}},\theta_{\mathrm{ref}},T_{\mathrm{ref}})$, while an inner loop attitude controller generates body torques $(\tau_\phi,\tau_\theta,\tau_\psi)$. Both loops employ a shared Mamdani fuzzy inference system with normalized inputs (tracking error and error-rate) and a normalized control output. The GA automatically tunes scaling gains $(K_e,K_d,K_u)$ across all axes to minimize a robust objective that averages tracking error, control effort, and constraint violations over multiple scenarios with mass uncertainty and wind disturbances. Simulation results on a three dimensional figure eight trajectory indicate that GA tuning can reduce position and attitude errors while respecting actuator saturation and tilt safety limits, demonstrating a practical route to performance enhancement without requiring a high fidelity aerodynamic model. The methodology leverages the interpretability of fuzzy rules and the global search capabilities of evolutionary optimization within a UAV modeling framework consistent with established quadrotor dynamics literature.

The increasing complexity of modern urban traffic networks demands intelligent control strategies that can anticipate and adapt to dynamic traffic conditions. Model Predictive Control (MPC) is a framework that optimizes vehicle control by predicting future states and respecting real-time constraints, such as traffic signals at intersections. However, the computational complexity of MPC increases significantly with the number of decision variables and constraints, which is directly proportional to the length of the prediction horizon, creating a critical trade-off between control performance and computational efficiency. To address this challenge, this paper proposes an adaptive-horizon optimal driving (AHOD) bi-level optimization framework that incorporates a novel time-step discretization for real-time trajectory optimization and integrates it into a full traffic signal cycle. Unlike conventional MPC, which employs uniform time discretization leading to exponential growth in decision variables with horizon length, the proposed AHOD framework assigns finer time steps near signal phase transitions and coarser steps in the distant horizon, maintaining a fixed number of optimization nodes regardless of cycle length. The proposed framework comprises two controllers: the upper and lower controllers. The Upper controller employs finer resolution at critical times of signal change and coarser resolution in distant horizons, thereby reducing computational cost while maintaining prediction accuracy. The lower controller applies a practical MPC scheme to generate realtime control actions that are consistent with the long-term constraints of the upper controller. Simulation results demonstrate that the proposed framework achieves up to 17.6% fuel savings compared to traditional human driving and reduces computation time by approximately 61% compared to long-horizon MPC, while maintaining comparable control performance. The proposed framework enables real-time, cycle-aware predictive control for connected and automated vehicles (CAVs), and establishes a practical basis for embedding long-horizon prediction within an MPC-based trajectory-planning framework.