Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Robotic fish path tracking method and device fusing with BP-RBF neural network

A BP-RBF and BP neural network technology, applied in the field of bionic fish, can solve problems such as difficulty in suppressing chattering and overshoot, lack of high-quality tracking control effect in robotic fish, etc., to achieve good control quality, reduce external interference, and control accuracy. improved effect

Pending Publication Date: 2021-12-31
湖南工商大学
View PDF10 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Active disturbance rejection control (active disturbance rejection control, ADRC) is currently an algorithm with excellent anti-disturbance in the path-following control method of robotic fish. It has good dynamic and static characteristics for path-following control of robotic fish. There are generally various flaws in the setting
[0004] Therefore, there is a need for a robotic fish path tracking method and device that integrates the BP-RBF neural network to solve the problem of the lack of high-quality tracking control effects of robotic fish underwater, and the difficulty in suppressing chattering and overshooting caused by external interference. The problem of phenomena

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
  • Robotic fish path tracking method and device fusing with BP-RBF neural network
  • Robotic fish path tracking method and device fusing with BP-RBF neural network
  • Robotic fish path tracking method and device fusing with BP-RBF neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0076] Such as figure 1 As shown, the present embodiment is a robotic fish path tracking method for merging BP-RBF neural network, comprising the following steps:

[0077] Step 1, given the initial position, expected velocity V(t), and expected path S of the robotic fish to be tracked; then input the initial position, expected velocity V(t), and expected path S into the control information generation module; the control information generation module receives The collected actual speed and actual control quantity are used to generate error information through the expected speed V(t) and the expected path S, and the error information includes the tangential error , normal error and attitude tracking error (yaw angle error) Ψ; then generate the corresponding expected speed control rate v according to the error information 0 (t), desired path control rate r d ; Then put the desired speed control rate v 0 (t), desired path control rate r d Input ADRC control module;

[007...

Embodiment 2

[0116] Such as image 3 and Figure 4 As shown, the difference between this embodiment and Embodiment 1 is that the ADRC control module includes a speed ADRC control module and a steering ADRC control module.

[0117] Such as Figure 5 ,Such as Figure 6 As shown, the speed ADRC control module receives the desired speed control rate v 0 (t) and control the robotic fish, which includes a first tracking differentiator, a first nonlinear combination and a first extended state observer;

[0118] The steering ADRC control module receives the desired path control rate r d And control the robotic fish, which includes a second tracking differentiator, a second nonlinear combination and a second extended state observer.

[0119] combine Figure 6 , Figure 7 and Figure 8 As shown, the steps of speed control in step 1, step 2 and step 3 specifically include:

[0120] Set the desired speed control rate v 0 (t) Input speed ADRC control module, the first tracking differentiator co...

Embodiment 3

[0124] Such as figure 2 As shown, the present embodiment adopts the robotic fish path tracking device of the fusion BP-RBF neural network of the method in embodiment 1 and embodiment 2, which includes:

[0125] Control information generation module, which is used to generate error information, desired speed control rate v 0 (t), desired path control rate r d ;

[0126] ADRC control module, which includes tracking differentiator (TD), nonlinear combination (NF), extended state observer (ESO);

[0127] A parameter optimization module, which includes a BP neural network and an RFC neural network, the BP neural network optimizes the extended state observer, and the RFC neural network optimizes a nonlinear combination;

[0128] The trajectory generation module is used to generate the real-time position of the robotic fish and form a trajectory.

[0129] The ADRC control module includes a speed ADRC control module and a steering ADRC control module,

[0130] The speed ADRC con...

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 relates to the technical field of bionic fishes, in particular to a robotic fish path tracking method and device fused with a BP-RBF neural network. The method comprises the following steps: giving an initial position to be tracked, an expected speed and an expected path of a robotic fish, inputting the initial position, the expected speed and the expected path into a control information generation module, generating error information, an expected speed control rate and an expected path control rate, and inputting the error information, the expected speed control rate and the expected path control rate into an ADRC control module; optimizing the ADRC control module by using a BP neural network and an RBF neural network in a parameter optimization module; judging whether the deviation meets performance indexes or not, if yes, conducting corresponding adjustment according to the deviation, and then outputting the final control quantity to the robotic fish again; generating a trajectory of the robotic fish using a trajectory generation module. According to the invention, the robotic fish has a high-quality tracking control effect underwater, the phenomena of buffeting, overshoot and the like caused by external interference can be well inhibited, and a target tracking task is completed.

Description

technical field [0001] The invention relates to the technical field of bionic fish, in particular to a path tracking method and device for a robotic fish fused with a BP-RBF neural network. Background technique [0002] Because rivers, lakes and seas are rich in biological and mineral resources, target detection and path tracking have great application value in the monitoring and development of resources. In order to detect these precious resources, the bionic robot fish can detect in the underwater depth and breadth that humans cannot reach, and has the advantages of small size, high mobility, low cost, small resistance, low noise, etc. , water quality monitoring and reconnaissance demining and other civilian and military fields have been widely used. With the gradual deepening of human understanding and development of the underwater environment, the intelligent path control technology of the bionic robot fish is also facing innovation. [0003] In the complex water envir...

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): G05B13/04
CPCG05B13/042
Inventor 易国栋易淑婷鲁晓海陈萍萍熊婷刘利枚
Owner 湖南工商大学
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products