This study addresses the limitations of buoyancy factor and compensation capacity in pressure hulls for full-ocean-depth underwater gliders operating in extreme deep-sea conditions. A novel lightweight multifunctional composite structure pressure hull (CSPH) is proposed, utilizing a carbon fiber cylindrical shell as the primary load-bearing structure and silicone oil as the buoyancy compensation medium. A mechanical model of the carbon fiber cylindrical shell under hydrostatic pressure was developed based on three-dimensional elastic mechanics theory. Furthermore, a comprehensive performance evaluation model for the CSPH was created, incorporating both the buoyancy factor (B_f) and buoyancy fluctuation coefficient (f_B). The NSGA-II optimization algorithm was employed to simultaneously minimize B_f and f_B by co-optimizing the carbon fiber ply parameters and the silicone oil volume (V_C). This optimization resulted in a Pareto optimal solution balancing buoyancy and compensation performance. The accuracy of the mechanical model and optimization results was validated through finite element analysis and pressure testing. The results show that, compared to traditional metallic pressure hull designs, the CSPH reduces the buoyancy factor by 48% and enhances buoyancy compensation performance by 2.5 times. The developed CSPH has been successfully deployed on the “Sea-Wing 11000” full-ocean-depth underwater glider, significantly improving its endurance and motion stability for long-term deep-sea observation missions.

The efficient and stable application of periodic forcing for drag-reduction can help underwater vehicles operate at high speed for long durations and improve their energy-utilization efficiency. This study considers flow control around a body-of-revolution model subjected to periodic blowing or suction through annular slots. The focus is on the boundary-layer structure, properties, and drag of the control fluid under a wide range of body variables (size, free-flow velocity, slot area, and blowing/suction velocity) and control parameters (normalized periodic-forcing amplitude and relative slot sizes). Body variables differ in their effects on the drag-reduction rate, with the surface pressure pushing the model vehicle when S and v are higher than S₀ and v₀. In particular, the lowest pressure drag was −26.4 N with v increasing, and the maximum drag-reduction rate of total drag exceeded 135%. At a fixed Reynolds number, increasing the values of the control parameters leads to larger-scale unstable vortex rings downstream from the slots; the surface-velocity gradient is reduced, effectively lowering the drag. A simple model relating the periodic fluctuation of pressure drag to the body variables is developed through quantitative analysis and used to determine navigational stability.

Underwater dynamic target detection, classification, localization, and tracking (DCLT) is central to maritime surveillance and monitoring and increasingly relies on distributed AUV-based robotic sonar networks operating in passive listening and, when required, cooperative multistatic modes. Achieving a robust performance in realistic oceans remains challenging, because sensor placement must adapt to time-varying acoustic conditions and target priors while preserving acoustic communication connectivity, and because frequent reconfiguration under dynamic currents makes classical large-scale planning computationally expensive. This paper presents an integrated deep reinforcement learning (DRL)-based framework for passive-stage sonar placement and dynamic reconfiguration in distributed AUV networks. First, we cast placement as a constructive finite-horizon Markov decision process (MDP) and train a Proximal Policy Optimization (PPO) agent to sequentially build a collision-free layout on a discretized surveillance grid. The terminal reward is formulated to jointly optimize the environment-aware detection performance, computed from BELLHOP-based transmission loss models, and global network connectivity, quantified using algebraic connectivity. Second, to enable time-critical reconfiguration, we estimate flow-aware motion costs for all AUV–destination pairs using a PPO with a Long Short-Term Memory (LSTM) trajectory policy trained for partial observability. The learned policy can be deployed onboard, allowing each AUV to refine its path online using locally sensed currents, improving robustness to ocean-model uncertainty. The resulting cost matrix is solved via an efficient zero-element assignment method to obtain the optimal one-to-one reassignment. In the reported simulation studies, the proposed Sequential PPO placement method achieves a final reward 16–21% higher than Particle Swarm Optimization (PSO) and 2–3.7% higher than the Genetic Algorithm (GA), while the proposed PPO + LSTM planner reduces average travel time by 30.44% compared with A*. The proposed closed-loop architecture supports frequent re-optimization, scalable fleet operation, and a seamless transition to communication-supported cooperative multistatic tracking after detection, enabling efficient, adaptive DCLT in dynamic marine environments.