The study focuses on the fault signals of rolling bearings, which are characterized by nonlinearity, periodic impact, and low signal-to-noise ratio. The advantages of entropy calculation in analyzing time series data were combined with the high calculation accuracy of Multiscale Fuzzy Entropy (MFE) and the strong noise resistance of Multiscale Permutation Entropy (MPE), a multivariate coarse-grained form was introduced, and the coarse-grained process was improved. The Composite Multivariate Multiscale Permutation Fuzzy Entropy (CMvMPFE) method was proposed to solve the problems of low accuracy, large entropy perturbation, and information loss in the calculation process of fault feature parameters. This method extracts the fault characteristics of rolling bearings more comprehensively and accurately. The CMvMPFE method was used to calculate the entropy value of the rolling bearing experimental fault data, and Support Vector Machine (SVM) was used for fault diagnosis analysis. By comparing with MPFE, the Composite Multiscale Permutation Fuzzy Entropy (CMPFE) and the Multivariate Multiscale Permutation Fuzzy Entropy (MvMPFE) methods, the results of the calculations show that the CMvMPFE method can extract rolling bearing fault characteristics more comprehensively and accurately, and it also has good robustness.

The strong coupling between the ship’s sway and yaw motion increases the complexity of identifying hydrodynamic derivatives in mathematical models and reduces accuracy. To solve this problem, this paper proposes an identification method Alpha Evolution Multi-output Support Vector Regression (AE-MSVR) based on MSVR combined with AE. This method approaches the yaw and sway motion equations as a multi-input and multi-output (MIMO) problem, utilizing MSVR for modeling and optimizing hyperparameters with AE. It reduces parameter drift by restructuring the regression model’s input–output. Identification data is obtained via zigzag test simulation. The AE-MSVR method successfully identifies linear and nonlinear hydrodynamic derivatives in the 3 degree of freedom (DOF) Abkowitz model. Using clean simulation data, the results show promising agreement with experimental values from planar motion mechanism (PMM) tests and achieve improved accuracy compared with the standard SVR identification method. To assess robustness, simulated noise is introduced at different levels; maneuvering characteristics are evaluated using turning circle tests. Results demonstrate that AE-MSVR achieves promising accuracy in identifying ship hydrodynamic derivatives and shows encouraging robustness against noise. The method provides potential support for ship motion prediction and maneuverability forecasting.

With the continuous advancement of intelligent, integrated, and sophisticated modern marine equipment, bearing fault diagnosis faces increasingly severe technical challenges. Compared with traditional industrial environments, marine propulsion systems are characterized by multi-bearing coupled vibrations and complex operating conditions. To address these characteristics, this paper proposes a fault diagnosis method that combines a least squares support vector machine (LSSVM) with multi-domain feature extraction based on an improved hippopotamus optimization algorithm (LCM-HO). This method directly extracts time, spectral, and time-frequency domain features from the raw signal, effectively avoiding complex preprocessing and enhancing its potential for field engineering applications. Experimental verification using the Paderborn bearing dataset and a self-built marine bearing test bench demonstrates that the LCM-HO-LSSVM method achieves diagnostic accuracy rates of 99.11% and 98.00%, respectively, demonstrating significant performance improvements. This research provides a reliable, efficient, and robust technical solution for bearing fault diagnosis in complex marine environments.

Ship route planning in complex marine environments is essential for enhancing navigation safety and reducing energy consumption. Conventional algorithms often lack environmental awareness, exhibit limited multi-objective optimization, and are prone to premature convergence. This study proposes an Environment-Aware Adaptive Multi-Objective Ant Colony Optimization (EA-MOACO) algorithm under coupled wind–wave–current conditions.,A marine environmental model using ERA5 reanalysis data and a ship energy-consumption model accounting for current-induced speed correction, wind, and wave resistance are established. An environmental complexity assessment and adaptive parameter adjustment strategy dynamically balance global exploration and local exploitation. A dynamic multi-objective optimization framework integrating route length and energy consumption is implemented using Pareto dominance and ideal-point decision-making.,Experiments show that EA-MOACO outperforms ACO, PSO, MOPSO, NSGA-II, PSO-ACO, and DL-DACO in path length, energy consumption, HV, and IGD. The method provides an efficient, practical framework for intelligent ship route planning in complex marine environments.

Ship fuel consumption prediction is critical for green shipping, energy-efficiency management, and intelligent operational decision-making. However, real ship operational data exhibit multiple operating regimes, transitional states, and strong variable coupling, making it difficult for a single global model to achieve both high accuracy and interpretability. To address this challenge, this study proposes a physics-guided operating-regime-aware mixture-of-experts framework for ship fuel consumption prediction. An empirical propulsion-power proxy derived from the speed–power relationship is first introduced into a Gaussian mixture model through a latent physical power representation, consistency loss, and monotonicity loss, enabling physically meaningful operating-regime identification. Based on posterior responsibilities, confidence thresholds, and physical-load ranking, ship states are further categorized into stable, transitional, and complex regimes with clear engineering semantics. The identified regime information and statistical features of input sequences are then incorporated into a gating network to adaptively combine two BiLSTM-Attention experts. Experiments on real LPG-VLGC operational data collected from 2017 to 2019 demonstrate superior performance (MAE = 0.98, RMSE = 2.17, R² = 0.97) compared with XGBoost, GRU, CNN, single-expert models, and a standard GMM-MoE baseline. Results show that the proposed framework improves both prediction accuracy and engineering interpretability.