This paper addresses the challenges faced by icebreakers in polar environments, particularly the difficulty in sensing underwater ice formations when navigating through thick ice layers, which often results in suboptimal icebreaking effectiveness. To overcome these challenges, this paper introduces a novel underwater robot equipped with both sensing and icebreaking capabilities. We propose a path-planning method for icebreaking that leverages the synergistic capabilities of the genetic algorithm and safe particle swarm optimization (GA-SPSO). The GA-SPSO algorithm integrates the global search prowess of the particle swarm optimization with the local optimization strength of the genetic algorithm, enabling efficient and adaptive path planning in complex ice environments. The unmanned underwater vehicles (UUV)-assisted icebreaking approach developed here utilizes the UUV’s flexibility and high-precision environmental sensing to provide real-time optimization suggestions for icebreaker navigation paths. Simulation results demonstrate that the GA-SPSO algorithm not only effectively circumvents hazardous areas but also significantly reduces the energy consumption and operational time of icebreakers, thereby enhancing the safety and stability of navigation. When compared to the conventional safe particle swarm optimization (SPSO), our approach shows marked improvements in path length, convergence speed, and obstacle avoidance capabilities, significantly enhancing the success and efficiency of polar navigation missions.

The traditional robotic arm control method has strong dependence on the application scenario. To improve the reliability of the mobile robotic arm control when the scene is disturbed, this paper proposes a control method based on an improved proximal policy optimization algorithm. This study researches mobile robotic arms for opening doors. At first, the door handle position is obtained through an image-recognition method based on YOLOv5. Second, the simulation platform CoppeliaSim is used to realize the interaction between the robotic arm and the environment. Third, a control strategy based on a reward function is designed to train the robotic arm and applied to the opening-door task in the real environment. The experimental results show that the proposed method can accelerate the convergence of the training process. Besides, our method can effectively reduce the jitter of the robotic arm and improve the stability of control.

Addressing the issue of significant speed fluctuations in permanent magnet synchronous motors (PMSM) under load, this paper proposes an active disturbance rejection control strategy based on an improved particle swarm optimization (PSO) algorithm. Initially, the speed of the PMSM is considered as the comprehensive optimization objective, and an active disturbance rejection control (ADRC) model for the PMSM is established by integrating the ADRC with vector control. Subsequently, an adaptive PSO algorithm incorporating genetic algorithms is proposed. This algorithm uses chaotic initialization for uniform particle distribution, introduces adaptive inertia weight and dynamic cognitive factors to enhance search efficiency, and integrates the crossover and mutation modules from genetic algorithms, optimizing mutations using a Gaussian probability function. Simulation results demonstrated that: (1) under identical external load conditions, the proposed ADRC strategy ensured smaller speed fluctuations and a smoother waveform for the PMSM, and (2) compared to the traditional PSO algorithm, the proposed method reduced the speed fluctuation after external load by approximately 26%.

With the continuous progress of intelligent power system technology, in order to meet the needs of substation operation and maintenance, a target detection algorithm is applied to identify the status of equipment switches. YOLOv7, as the latest achievement of YOLO (You Only Look Once) series algorithms, has good speed and accuracy in target detection tasks. However, when the generalized network is applied in a specific scenario, its advantages are not obvious due to its high weight and poor portability. In this paper, an improved GF-YOLOv7 network model is proposed to apply in the recognition of the status of bounce locks in a substation. The MobileViT module is used to improve the feature extraction ability of the backbone network. Referring to the CBAM feature attention mechanism, the channel attention module and the spatial attention module are used to design a more lightweight feature fusion network. The experimental results in the test set show that the proposed network can significantly reduce the network weight and improve the detection accuracy on the basis of a small reduction in the detection speed, and the accuracy reaches 97.8%, which can meet the needs of the detection task of substation bounce locks.

This paper addresses the challenges faced by icebreakers in polar environments, particularly the difficulty in sensing underwater ice formations when navigating through thick ice layers, which often results in suboptimal icebreaking effectiveness. To overcome these challenges, this paper introduces a novel underwater robot equipped with both sensing and ice-breaking capabilities. We propose a path planning method for icebreaking that leverages the synergistic capabilities of the Safe Particle Swarm Optimization and Genetic Algorithm (GA-SPSO). The GA-SPSO algorithm integrates the global search prowess of the particle swarm optimization with the local optimization strength of the genetic algorithm, enabling efficient and adaptive path planning in complex ice environments. The underwater unmanned vehicle (UUV)-assisted icebreaking approach developed here utilizes the UUV's flexibility and high-precision environmental sensing to provide real-time optimization suggestions for icebreaker navigation paths. Simulation results demonstrate that the GA-SPSO algorithm not only effectively circumvents hazardous areas but also significantly reduces the energy consumption and operational time of icebreakers, thereby enhancing the safety and stability of navigation. When compared to the conventional Safe Particle Swarm Optimization (SPSO), our approach shows marked improvements in path length, convergence speed, and obstacle avoidance capabilities, significantly enhancing the success and efficiency of polar navigation missions.

To address the challenge of multimodal anomaly data governance in ship maintenance-cost prediction, this study proposes a three-stage hybrid data-cleansing framework integrating physical constraints and intelligent optimization. First, we construct a multi-dimensional engineering physical constraints rule base to identify contradiction-type anomalies through ship hydrodynamics validation and business logic verification. Second, we develop a Feature-Weighted Isolation Forest Algorithm (W-iForest) algorithm that dynamically optimizes feature selection strategies by incorporating rule triggering frequency and expert knowledge, thereby enhancing detection efficiency for discrete-type anomalies. Finally, we create a Genetic Algorithm-Ant Colony Optimization Collaborative Random Forest (GA-ACO-RF) to resolve local optima issues in high-dimensional missing data imputation. Experimental results demonstrate that the proposed method achieves a physical compliance rate of 88.2% on ship-maintenance datasets, with a 25% reduction in RMSE compared to conventional prediction methods, validating its superior data governance capability and prediction accuracy under complex operating conditions. This research establishes a reliable data preprocessing paradigm for maritime operational assurance, exhibiting substantial engineering applicability in real-world maintenance scenarios.