Bionic fish hydrodynamic prediction method based on CFD and MLP

A prediction method, bionic fish technology, applied in the field of marine engineering and bionic robots, can solve the problems of not fully reflecting the swimming posture of fish, affecting the hydrodynamic performance and efficiency of bionic fish, and not showing, so as to improve operational efficiency and convenience, avoid grid negative volume, enhance the effect of confidence

Pending Publication Date: 2022-02-18
OCEAN UNIV OF CHINA
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The traveling wave model is a classic fish swimming mode, but in the traditional model, the head of the bionic fish is rigid and has no fluctuations, while the actual fish swims with a small fluctuation in the head, the improved traveling wave model Motion is transformed into a motion function of the tail relative to the head, but it does not show the process from rest to acceleration and then to stability
At present, the traditional model cannot fully reflect the swimming posture of the fish realistically, and the research and prediction of its movement mode has a certain deviation from the actual situation, and the parameters in the model affect the hydrodynamic performance and efficiency of the bionic fish, so Finding a way to optimize motion models and parameters and perform hydrodynamic predictions is critical

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Bionic fish hydrodynamic prediction method based on CFD and MLP
  • Bionic fish hydrodynamic prediction method based on CFD and MLP
  • Bionic fish hydrodynamic prediction method based on CFD and MLP

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0058] In order to understand the above-mentioned purpose, features and advantages of the present invention more clearly, the present invention will be further described below in conjunction with the accompanying drawings and embodiments. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the invention, but the invention may also be practiced otherwise than as described herein. Accordingly, the present invention is not limited to the specific examples disclosed below.

[0059] The present invention is realized by adopting the following technical solutions: a bionic fish hydrodynamic prediction method based on computational fluid dynamics (Computational Fluid Dynamics, CFD) and multilayer perceptron (Multilayer Perceptron, MLP), comprising the following steps:

[0060] Step A. Establish an improved self-propelled motion model: Based on Matlab, conduct research on the classic traveling wave model, compare the dif...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a bionic fish hydrodynamic prediction method based on CFD and MLP. The bionic fish hydrodynamic prediction method comprises the following steps: establishing an improved self-propelled motion model; constructing a bionic fish two-dimensional swimming geometric model by using a specific airfoil profile; carrying out grid division on the two-dimensional geometric model by adopting an overlapping grid method, and carrying out grid independence verification; determining input and output parameters, fusing the two-dimensional geometric model and the self-propelled motion model based on UDF, and taking a two-dimensional incompressible unsteady Navier-Stokes equation as a control equation; determining variables, setting boundary conditions, carrying out numerical simulation on the hydrodynamic force of the self-propelled model, and studying the influence of parameters on the motion performance of the bionic fish; according to a numerical simulation result, establishing a hydrodynamic prediction model based on MLP; optimizing parameters through a multi-target genetic algorithm, carrying out hydrodynamic prediction on the optimized parameters through CFD, MLP and RSM methods. The accuracy of an MLP prediction model is verified, and the effects that starting can be fast, and the quasi-steady-state swimming speed and movement efficiency can be improved are achieved.

Description

technical field [0001] The invention belongs to the field of ocean engineering and bionic robots, and in particular relates to a hydrodynamic prediction method for bionic fish based on CFD and MLP, which is applicable to the motion pattern and hydrodynamic optimization prediction problems of underwater bionic robotic fish. Background technique [0002] Because of its intelligence, convenience, and high efficiency, underwater robots are playing an increasingly important role in the process of understanding, developing, and managing the ocean. In addition to broad application prospects in the civilian field, underwater robots also have strong application potential in national defense construction and military fields. In particular, bionic underwater robots have become the focus of attention of researchers due to their unique flexibility and concealment. [0003] For the parameter optimization of underwater robots, the invention patent with the authorized announcement number C...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F30/28G06F30/23G06F30/15
CPCG06F30/28G06F30/15G06F30/23Y02T90/00
Inventor 刘继鑫于菲何波严天宏
Owner OCEAN UNIV OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products