GA and RBFNN based PID for altitude-depth control of the multirotor Hybrid Aerial Underwater Vehicles

• Published in: Journal of physics. Conference series Vol. 2239; no. 1; pp. 12005 - 12011
• Main Authors: Zongcheng, Ma, Xianyong, Jing, Zhuoran, Zhang, Shuchen, Xiao, Tian, Zhao, Guoshuai, Li
• Format: Journal Article
• Language: English
• Published: Bristol IOP Publishing 01.04.2022
• Subjects: Controllers; Domains; Genetic algorithms; Parameters; Physics; Proportional integral derivative; Radial basis function; Underwater vehicles
• ISSN: 1742-6588; 1742-6596
• DOI: 10.1088/1742-6596/2239/1/012005

Abstract Multirotor Hybrid aerial underwater vehicle (HAUV) is the vehicle which could operate both in air and underwater powered by multi-rotors. The water-air trans-domain process is very changeling for the change of the floatage and added mass and ‘ground effect’. This paper researched on the effect of the intelligent algorithms on the trans-media control. And the genetic algorithm (GA) based and radial basis function (RBFNN) based proportional-integral-derivative (PID) controllers are developed for the trans-domain process. Then simulations and conclusions are made for these two controllers. It shows that the GA based PID controller is suitable for the trans-domain process. The RBFNN based PID controller could even do better work with the repeated optimized PID parameters value of GA. But one must pay attention to that the RBFNN-PID is very sensitive with the initial PID values. The initial values of PID parameters must be repeated optimized with GA to guarantee the better effect of the RBFNN-PID.