ObjectiveThis paper aims to investigate the multi-objective optimization problem of typical container ship structures. Method First, a ship structural component library to discretize the optimization variables was established. Next, an improved particle swarm optimization-simulated annealing (IPSO-SA) algorithm with dynamically adjusted optimization parameters was proposed. This method facilitates the rapid identification of the global optimal solution for single-objective optimization problems. Then, by introducing Pareto dominance, an MOPSO-SA algorithm for multi-objective optimization was developed. Results Taking the parallel middle body structure optimization of a container ship as an example, the parametric model of the structural components was constructed using the established component library, and the proposed optimization algorithm was applied. The IPSO-SA resulted in a 26.05% reduction in weight, while the MOPSO-SA approach resulted in a 14.11% decrease in structural weight, and a 12.95% reduction in the vertical center of gravity.ConclusionThe research not only improved the economic efficiency of the original design but also significantly enhanced the stability of the container ship.
ObjectiveTo address the limitations of the dung beetle optimization (DBO) algorithm in shipboard power system fault reconfiguration, including its susceptibility to local optima, slow convergence, and inability to directly handle discrete variables, an improved DBO (IDBO) algorithm-based fault reconfiguration method is proposed. MethodFirst, the initial population is optimized by introducing the Tent chaotic mapping, and the adjustment mechanism of the convergence factor R is improved to avoid the risk of the algorithm falling into local optima. Then, the migration strategy of the beluga whale optimization (BWO) algorithm is incorporated and a mutation mechanism is introduced to accelerate convergence and enhance global search capability. Finally, a discrete encoding strategy is introduced to map the continuous algorithm onto the discrete decision space of the shipboard power system.ResultsSimulation results demonstrate that, compared with the DBO algorithm, particle swarm optimization, genetic algorithm, adjustable space operator discrete state transition algorithm, and multifactorial evolutionary algorithm, the IDBO algorithm exhibits superior performance in both branch fault and generator fault scenarios, providing more accurate shipboard power system reconfiguration solutions with faster convergence. For single generator fault scenarios, the optimal solution is obtained by IDBO within only 4 iterations, while for branch fault scenarios, the optimal solution is obtained within just 3 iterations.ConclusionThe system reconfiguration scheme is rapidly and effectively generated by IDBO, significantly enhancing the safety and stability of the shipboard power system.
ObjectiveTraditional multi-channel automatic identification system (AIS) blind signal separation algorithms often suffer from unstable performance under low signal-to-noise ratio (SNR) conditions. Additionally, in real-world communication scenarios, the number of source signals is frequently unknown. To address these challenges, this paper proposes an improved joint approximate diagonalization of eigenmatrices (JADE) algorithm with preprocessing steps aimed at enhancing robustness and stability. Method First, the received signal is preprocessed using the singular spectrum analysis (SSA) algorithm to reduce noise. This is done by decomposing and reconstructing the trajectory matrix of the time series, effectively suppressing Gaussian white noise while preserving key features of the signal. Next, the minimum description length (MDL) algorithm is employed to estimate the number of source signals in the processed mixed matrix. By analyzing the eigenvalue distribution of the covariance matrix, we overcome the limitation of traditional algorithms that assume the number of source signals is known, thus enabling the adaptive identification of unknown source numbers. Finally, to address the issue of imprecise diagonalization measurement in the objective function of the traditional JADE algorithm, we propose an improved JADE optimization algorithm for separating AIS mixed signals. This method reconstructs an optimized objective function with scaling invariance and incorporates a column-cyclic iteration strategy, enhancing the accuracy of the joint diagonalization process while reducing computational redundancy. ResultsBy simulating the improved JADE algorithm, its performance was compared with that of the traditional JADE algorithm, the fast independent component analysis (FastICA) algorithm, the robust independent component analysis (RobustICA) algorithm, and the Information Maximization (Informax) algorithm. The results show that, when separating 2-, 3-, and 4-channel AIS observation signals, the improved JADE algorithm achieves the highest correlation coefficient, indicating the strongest correlation between the separated signal and the source signal. This coefficient exceeds 0.8015 across all SNR ranges from 0 to 20 dB. Additionally, in terms of crosstalk interference suppression, this method demonstrates superior performance, with suppression values consistently below 0.164 across all SNR ranges from −10 to 20 dB. Furthermore, the algorithm's running time is reduced by 30.38% compared to the traditional JADE, meeting the real-time requirements of satellite-based systems. ConclusionThe improved JADE optimization algorithm offers significant advantages in terms of separation accuracy, algorithm reliability, and computational stability. The research findings provide a theoretical basis and technical guidance for enhancing the separation performance and real-time capabilities of AIS receivers, as well as optimizing the design of maritime communication systems in practical engineering applications.
ObjectiveThe discontinuities in the large opening design and the non-uniform distribution of high-density cargo in the cargo hold section of large ore carriers pose significant challenges to hull structural safety. Therefore, it is essential to enhance the structural health monitoring system's ability to perceive and adapt to the structural safety status of ore carriers. MethodA real-time reconstruction method for the hull stress field under the combined action of global and local loads was proposed. A refined finite element model of the cargo hold section of a large ore carrier was selected as the research object, ensuring that the structural characteristics of the hull were represented comprehensively. The combined action of global-local and time-varying-static loads was comprehensively considered, and complex load conditions that closely mimicked the actual ship navigation environment were constructed. Based on the load forms and hull structural response characteristics, a monitoring point layout scheme and a unit load basis with various forms were designed. Monitoring points were positioned on the side shell plates, main decks, bottom girders and longitudinal bulkheads. Using the multi-source load superposition principle and limited measurement data, the real-time reconstruction of the structural stress field in the cargo hold section of the large ore carrier was achieved. Furthermore, the influence of dynamic load amplitude and periodic characteristics on the accuracy of stress reconstruction was analyzed. ResultsThe results showed that the method exhibited good prediction accuracy under typical wave conditions, with the prediction results accurately reflecting the spatiotemporal inhomogeneity of the hull's structural response. Over 97% of the reconstructed data points had a relative error rate within 5%, and the maximum relative error rate was approximately 10%. The reconstruction error increased with the load amplitude but remained highly accurate within the standard design value range, with the error always less than 1.0 MPa. The variation in load period had a more significant impact on the reconstruction results: the reconstruction error increased as the load period decreased. Within the common wave period range, the maximum absolute error of this method did not exceed 6 MPa, which could meet the practical engineering requirements to a certain extent.ConclusionThe proposed methodology demonstrates strong engineering applicability for the structural stress field reconstruction of large ore carriers. It can effectively support hull structural health monitoring and residual life assessment.
In ship design, the spatial layout of compartments is crucial not only for enhancing navigational safety and operational efficiency but also for ensuring crew comfort and overall ship performance. This paper aims to establish a multi-dimensional evaluation system for compartment layout optimization, systematically review relevant optimization algorithms, analyze current technical bottlenecks, and propose future research directions, thereby providing theoretical and technical support for the intelligent ship compartment design. First, a multi-dimensional evaluation system for optimizing ship compartment spatial layout is summarized and proposed. This system comprehensively accounts for factors such as functional correlation, absolute position, human activities, environmental conditions, and weight distribution, offering clear objectives and guidance for the selection and implementation of subsequent optimization algorithms. Taking into account the differences in functional requirements and design priorities among various ship types, as well as the availability of practical data, users can flexibly select applicable indicator combinations from this evaluation system to conduct targeted scientific assessments for specific scenarios. Next, a systematic review is presented of the major algorithms developed in recent years for ship compartment layout optimization. These include, but are not limited to, genetic algorithm, improved tabu search algorithm, gravitational search algorithm, integer programming method, and group motion simulation-driven method. The research achievements of these optimization algorithms in producing high-quality spatial layouts are systematically summarized and organized. A support relationship table between optimization methods and evaluation indicators is then constructed. The mainstream optimization methods are reviewed and compared across multiple dimensions, including algorithm principles, solution efficiency, multi-objective processing capability, and engineering applicability, to assess their suitability for ship compartment layout optimization tasks. For complex multi-deck scenarios, the study compares the differences between single-deck and multi-deck spatial layout optimization, summarizes examples of multi-deck spatial layout optimization, and identifies existing limitations. Furthermore, the rationality and scientific validity of the proposed evaluation system are verified through case studies of multi-deck configurations. The findings indicate that although significant progress has been made in ship compartment spatial layout optimization, several challenges remain, such as limited consideration of micro-execution-level issues and difficulties in efficiently modeling multi-deck layouts. Finally, this paper outlines future research directions from multiple perspectives, including the development of high-quality ship compartment layout datasets, the exploration of novel intelligent optimization algorithms, and the integration of human-in-the-loop deep reinforcement learning frameworks.
