Mode-free altitude control for airship based on Q-learning and CMAC network

Nie, Chunyu; Zhu, Ming; Zheng, Zewei; Wu, Zhe

doi:10.1109/cgncc.2016.7829104

Cited by 1 publication

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [11], the auxiliary air bursas charge or deflation and elevator combination control was employed to adjust the airship altitude for suspension, and the control law was designed based on fuzzy self-tuning control. The Q-learning and cerebella model articulation controller (CMAC) were utilized to realize the airship altitude reinforcement learning control based on the Markov decision process [12]. It should be noted that all these mentioned control algorithms are complicated in form with many parameters to tune, which are difficult to implement in practice.…”

Section: Introductionmentioning

confidence: 99%

Coordinated Symmetrical Altitude Position and Attitude Control for Stratospheric Airship Subject to Strong Aerodynamic Uncertainties

et al. 2023

View full text Add to dashboard Cite

The stratospheric airship has important value in both commercial and military use. The altitude position control is very crucial for the airship to conduct specific missions, which is also a challenge because of both the severe relative aerodynamic mismatches and the large lag due to the quite low speed of the airship within 15 m/s. In this paper, a coordinated altitude and attitude control method was proposed to realize satisfactory altitude position control while maintaining the attitude stability by properly employing the two actuators, the propeller thrust and the elevator, in a consistent manner. In this process, the references for the vertical speed and the pitch were specified in a straightforward way of proportionating them by considering their physical characteristics and the inherent symmetrical relationship between them, which can be obtained through the kinematics. An extended disturbance observer was used to eliminate the severe aerodynamic uncertainties to symmetrically distribute the two actuator outputs by dynamically decoupling the vertical speed and the pitch angular rate loops into the two independent integrators. As a result, the explicit proportional controllers were sufficient to realize efficient command tracking. Rigorous theoretical investigation was provided to symmetrically prove the quantitative bounded property of the estimation and tracking errors. The simulation results demonstrated the effectiveness of the proposed approach, which can realize a 500-m altitude difference tracking within 200 s with less than 0.5 deg/s pitch angular rate.

show abstract

Section: Introductionmentioning

confidence: 99%