Dynamic Positioning Control of Surge−Pitch Coupled Motion for Small-Waterplane-Area Marine Structures

For general dynamic positioning systems,controllers are mainly based on the feedback of motions only in the horizontal plane.However,for marine structures with a small water plane area and low metacentric height,undesirable surge and pitch oscillations may be induced by the thruster actions.In this paper,three control laws are investigated to suppress the induced pitch motion by adding pitch rate,pitch angle or pitch acceleration into the feedback control loop.Extensive numerical simulations are conducted with a semi-submersible platform for each control law.The influences of additional terms on surge−pitch coupled motions are analyzed in both frequency and time domain.The mechanical constraints of the thrust allocation and the frequency characters of external forces are simultaneously considered.It is concluded that adding pitch angle or pitch acceleration into the feedback loop changes the natural frequency in pitch,and its performance is highly dependent on the frequency distribution of external forces,while adding pitch rate into the feedback loop is always effective in mitigating surge−pitch coupled motions.

Deep reinforcement learning based active surge control for aeroengine compressors

This study proposes an active surge control method based on deep reinforcement learning to ensure the stability of compressors when adhering to the pressure rise command across the wide operating range of an aeroengine.Initially,the study establishes the compressor dynamic model with uncertainties,disturbances,and Close-Coupled Valve(CCV)actuator delay.Building upon this foundation,a Partially Observable Markov Decision Process(POMDP)is defined to facilitate active surge control.To address the issue of unobservability,a nonlinear state observer is designed using a finite-time high-order sliding mode.Furthermore,an Improved Soft Actor-Critic(ISAC)algorithm is developed,incorporating prioritized experience replay and adaptive temperature parameter techniques,to strike a balance between exploration and convergence during training.In addition,reasonable observation variables,error-segmented reward functions,and random initialization of model parameters are employed to enhance the robustness and generalization capability.Finally,to assess the effectiveness of the proposed method,numerical simulations are conducted,and it is compared with the fuzzy adaptive backstepping method and Second-Order Sliding Mode Control(SOSMC)method.The simulation results demonstrate that the deep reinforcement learning based controller outperforms other methods in both tracking accuracy and robustness.Consequently,the proposed active surge controller can effectively ensure stable operation of compressors in the high-pressure-ratio and high-efficiency region.

INVESTIGATING MULTISTAGE AXIAL FLOW COMPRESSOR INSTABILITIES

A numerical methodology for investigating compressor instabilities in a multistage environment is presented. The method is based on a stage-by-stage dynamic compression model and considers air compressibility explicitly throughout the compressor. It involves discretizing the compression system into distinct elements and a use of the local elemental characteristic of mean performance. The models are presented in both nonlinear and linearized forms. The linearised form permits well surge condition prediction for multistage axial compressors, while the non-linear form is able to investigate the growth of local flow disturbances, and helps to develop practical control strategy. Validations were carried out using the data from several aircraft engine compressors. A good experiment-model consistency is achieved.