An accurate cavitation prediction thruster model based on Gaussian process regression - Details

author：

Indexed by：

EI Scopus

Abstract：

Cavitation　effect　generates　when　the　propeller　of　the　thruster　revolves　close　to　the　free　surface　which　can　lead　to　thrust　attenuation　and　high　noise.　In　this　paper,　a　Gaussian　process　regression　based　thruster　model　which　considers　cavitation　effect　is　presented.　The　conventional　thruster　model　is　introduced　at　first.　Afterwards,　the　error　of　the　conventional　thruster　model　caused　by　cavitation　effect　is　analyzed　and　the　cavitation　prediction　thruster　model　based　on　Gaussian　process　regression　is　proposed.　The　effectiveness　of　the　proposed　model　is　validated　via　proof-of-concept　experiments.　The　experimental　results　demonstrate　the　accuracy　of　the　proposed　model　with　the　error　less　than　the　conventional　model.　©　2017　IEEE.

Keyword：

Biomimetics Cavitation Gaussian distribution Gaussian noise (electronic) Regression analysis Robotics

Community：

[ 1 ] [Luo, Yang]Dept. of Mechanical Engineering, Harbin Institute of Technology, Harbin, China
[ 2 ] [Tao, Jianguo]Dept. of Mechanical Engineering, Harbin Institute of Technology, Harbin, China
[ 3 ] [Li, Zhandong]Dept. of Mechanical Engineering, Harbin Institute of Technology, Harbin, China
[ 4 ] [Ding, Liang]Dept. of Mechanical Engineering, Harbin Institute of Technology, Harbin, China
[ 5 ] [Deng, Zongquan]Dept. of Mechanical Engineering, Harbin Institute of Technology, Harbin, China
[ 6 ] [Sun, Hao]School of Mechanical Engineering and Automation, Fuzhou University, Fuzhou, China
[ 7 ] [Song, Xingguo]Dept. of Mechanical Engineering, Southwest Jiaotong University, Chengdu, China