Search

Traditional path planning is mainly utilized for path planning in discrete action space, which results in incomplete ship navigation power propulsion strategies during the path search process. Moreover, reinforcement learning experiences low success rates due to its unbalanced sample collection and unreasonable design of reward function. In this paper, an environment framework is designed, which is constructed using the Box2D physics engine and employs a reward function, with the distance between the agent and arrival point as the main, and the potential field superimposed by boundary control, obstacles, and arrival point as the supplement. We also employ the state-of-the-art PPO (Proximal Policy Optimization) algorithm as a baseline for global path planning to address the issue of incomplete ship navigation power propulsion strategy. Additionally, a Beta policy-based distributed sample collection PPO algorithm is proposed to overcome the problem of unbalanced sample collection in path planning by dividing sub-regions to achieve distributed sample collection. The experimental results show the following: (1) The distributed sample collection training policy exhibits stronger robustness in the PPO algorithm; (2) The introduced Beta policy for action sampling results in a higher path planning success rate and reward accumulation than the Gaussian policy at the same training time; (3) When planning a path of the same length, the proposed Beta policy-based distributed sample collection PPO algorithm generates a smoother path than traditional path planning algorithms, such as A*, IDA*, and Dijkstra.

In view of the multi-objective optimization design of the squirrel cage fan for the range hood, a blade parameterization method based on the quadratic non-uniform B-spline (NUBS) determined by four control points was proposed to control the outlet angle, chord length and maximum camber of the blade. Morris-Mitchell criteria were used to obtain the optimal Latin hypercube sample based on the evolutionary operation, and different subsets of sample numbers were created to study the influence of sample numbers on the multi-objective optimization results. The Kriging model, which can accurately reflect the response relationship between design variables and optimization objectives, was established. The second-generation Non-dominated Sorting Genetic algorithm (NSGA-II) was used to optimize the volume flow rate at the best efficiency point (BEP) and the maximum volume flow rate point (MVP). The results show that the design parameters corresponding to the optimization results under different sample numbers are not the same, and the fluctuation range of the optimal design parameters is related to the influence of the design parameters on the optimization objectives. Compared with the prototype, the optimized impeller increases the radial velocity of the impeller outlet, reduces the flow loss in the volute, and increases the diffusion capacity, which improves the volume flow rate, and efficiency of the range hood system under multiple working conditions.

Cross-flow fans are widely used in heating, wind-curtains, and air-conditionings, as well as other ventilation systems. A single or double arc is generally used as the camber line of cross-flow fans, but this design leads to constraints in the geometry of the blade profiles. In this study, the camber line of a cross-flow fan blade was parameterized by five parameters based on the fourth-order Bezier curve. A two-dimensional computational fluid dynamics (CFD) simulation was conducted to predict the aerodynamic characteristics and the internal flow field. It is necessary in multi-condition optimization, to evaluate the relative importance of the performance parameters under different working conditions and determine their weight factors. Here, a novel maximum entropy method (MEM) was proposed to quantify of volume flow rate, because the method avoids the subjectivity in the selection of the weights. Subsequently, a multi-island genetic algorithm (MIGA), combined with numerical simulation, was used to search the global optimum in the given design space. The results indicated that the optimum combination of the structural parameters reduced the blade channel vortex in a particular location of the impeller and changed the position and size of the eccentric vortex. The volume flow rate of the optimized impeller was 4.28% higher at the minimum rotation speeds and 12.87% higher at the maximum rotation speeds.

In this study, the unique reverse-flow around the inlet nozzle of a squirrel-cage fan was numerically studied by computational fluid dynamics (CFD), and a non-axisymmetric D-type inlet nozzle was proposed to inhibit it. It is shown that serious back flow develops at the volute tongue when the fan operates at a low flow coefficient that is lower than the best efficiency point. The airflow passing the blade passages in reverse further crosses the impeller, mixing the clearance leakage airflow, and finally blows into the intake chamber near the circumferential position of $ 150^{\circ } $ . By installing the inlet nozzle along this direction, D-type inlet nozzle schemes with different blockage extent were calculated by CFD. The scheme with a cut distance of 70% of its exit-section radius was chosen as the best design by comprehensively comparing the back flow ratio and fan performance of different working conditions. CFD results illustrated that reverse blowing at the fan entrance was significantly constrained by this D-type inlet nozzle, and the vortex in the inlet chamber correspondingly disappeared. Experimental data illustrated that the new nozzle increased the fan pressure rise under low-flow conditions by about 6% and barely reduced performance at other working points.

The chaotic state of microfluidic devices such as electroosmotic micromixers has received extensive attention. Its unsteady flow and multi-physics mask low-dimensional structure and potential attractors. Based on the dynamic mode decomposition and the sparse identification of nonlinear dynamics, this study aims to construct a manifold equation with the minimum degree of freedom, reveal the mixing mechanism of micromixers, and discover the evolution of chaotic states. The attenuation degree of freedom was introduced to force the modal coefficients to be pure oscillations. The six, four, and two-dimensional minimum reduced-order models (ROMs) were constructed under different mixing conditions. The nonlinear dynamics evolves on attractors resembling a six-petal structure based on the amplitude-phase method. The attractor periodicity and decay map the evolution of the periodic oscillation and limit cycle of the active modes and are related to the appearance of the low-energy dominant non-axisymmetric modes. These results emphasize the significance of ROM technology in revealing the low-dimensional structure and attractor of the electroosmotic micromixer.

In this study, the blade shape of the squirrel-cage fan system inside the range hood was optimized using the surrogate model to improve the maximum volume flow rate. The influence of computational fluid dynamics (CFD) noise was concerned. The regression Kriging model (RKM) was used as a surrogate model to reflect the relationship between the design parameters of the blade and the volume flow rate. The parallel filling criterion after re-interpolation was used to improve the optimization efficiency further and ensure global optimization. Through experimental verification, we found that the relative error between the volume flow rate of the optimal sample of RKM and the experiment was only 0.4%. Compared with the prototype, the maximum volume flow rate of the optimal sample of RKM was increased by 2.9%, and the efficiency under the corresponding working conditions was increased by 2%. RKM was used to predict the velocity field of the volute and impeller exit section to explore the feasibility of the RKM in the flow field prediction. Research shows that the RKM cannot accurately predict the velocity of each grid on the cross-section. Still, it can accurately predict the changing trend of the velocity.

The cut volute profile is far and widely used in the squirrel cage fan to meet the space limitation of range hood systems. The cut volute profile often causes unreasonable impeller–volute interference and the aerodynamic performance of the fan to drop. A numerical model combined with the neural network and the genetic algorithm of a squirrel cage fan volute for a range hood is presented in this paper. The secondary non-uniform B-spline curve represents the volute profile variation law, and its control points are used as design variables to meet space constraints. The goal of global optimization is to maximize the efficiency and volume flow rate. As a result of the optimization, the internal flow loss of the fan is reduced compared with the prototype. The volume flow rate and efficiency are increased by over 4.4% in case of optimized volute than the original configuration of the volute.

The performance of low-pressure axial flow fans is directly affected by the three-dimensional bending and twisting of the blades. A new blade design method is adopted in this work, where the radial distribution of blade angle and blade bending angle is composed of standard-form rational quadratic Bézier curves. Dendrite Net is then trained to predict the pneumatic performance of the fan. A non dominated sorting genetic algorithm is employed to solve the global optimization problem of the total pressure coefficient and efficiency. The simulation results show that the optimal blade load distribution along the radial direction becomes uniform, and the suction surface separation vortex and passage vortex are restrained. On the other hand, the tip leakage vortex is enhanced and moves toward the blade leading edge. According to the experimental results, the maximum efficiency increases by 5.44%, and the maximum total pressure coefficient increases by 2.47% after optimization.

Riblets with an appropriate size can effectively restrain turbulent boundary layer thickness and reduce viscous drag, but the effects of riblets strongly depend on the appearance of the fabric that is to be applied and its operating conditions. In this study, in order to improve the aerodynamic performance of a low-pressure fan by using riblet technology, sawtooth riblets on NACA4412 airfoil are examined at the low Reynolds number of 1 × 105, and the airfoil is operated at angles of attack (AOAs) ranging from approximately 0° to 12°. The numerical simulation is carried out by employing the SST k–ω turbulence model through the Ansys Fluent, and the effects of the riblets’ length and height on aerodynamic performance and flow characteristics of the airfoil are investigated. The results indicate that the amount of drag reduction varies greatly with riblet length and height and the AOA of airfoil flow. By contrast, the riblets are detrimental to the airfoil in some cases. The most effective riblet length is found to be a length of 0.8 chord, which increases the lift and reduces the drag under whole AOA conditions, and the maximum improvements in both are 17.46% and 15.04%, respectively. The most effective height for the riblet with the length of 0.5 chord is 0.6 mm. This also improves the aerodynamic performance and achieves a change rate of 12.67% and 14.8% in the lift and drag coefficients, respectively. In addition, the riblets facilitate a greater improvement in airfoil at larger AOAs. The flow fields demonstrate that the riblets with a drag reduction effect form “the antifriction-bearing” structure near the airfoil surface and effectively restrain the trailing separation vortex. The ultimate cause of the riblet drag reduction effect is the velocity gradient at the bottom of the boundary layers being increased by the riblets, which results in a decrease in boundary thickness and energy loss.