Intelligent control method for horizontal trajectory of stratospheric airship

Abstract

The invention discloses an intelligent control method for a horizontal trajectory of a stratospheric airship. In order to solve a problem of horizontal trajectory control of a stratospheric airship ina wind field environment, the method establishes an observation model and a Markov decision process model of the airship. With consideration of the characteristic object of the airship, an element interval in an action space is limited; on the basis of a known wind field model, neural network learning is carried out on the action input and state output of the airship by using an included angle probability of each wind direction incoming flow relative to the airship as an action selection basis; and according to a learning result, a Q-learning process is entered, a control law is obtained according to an optimal action strategy, an executing mechanism of the airship is controlled, so that tracking of expected horizontal movement is achieved. Therefore, adverse effects on stratospheric airship horizontal movement control caused by factors such as kinetic model parameter uncertainty and environmental wind field interference are effectively eliminated.

Description

technical field [0001] The invention relates to a method for intelligently controlling the horizontal trajectory of a stratospheric airship in a wind field, in particular to a method for controlling the horizontal trajectory of a stratospheric airship in a wind field based on Q-learning algorithm and CMAC neural network learning. Background technique [0002] The adjacent space is between the highest flight altitude of conventional aircraft and the lowest orbital altitude of spacecraft, and is an emerging strategic space that bridges aviation and aerospace. Countries are making full use of their potential value by developing near-space vehicles. Stratospheric airships, high-altitude balloons, and solar-powered drones are all current research hotspots. The stratospheric airship is a typical low-speed near-space aircraft, which can stay in the stratosphere area for a long time to realize high-resolution observation of the earth's surface, theater reconnaissance, communication ...

AI Technical Summary

Problems solved by technology

In addition, there are no reports on the application of reinforcement learning algorithms and neural network learning to the horizontal trajectory control of stratospheric airships.

Images