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

Distributed multi-unmanned ship adaptive neural network formation control method considering input quantization

A neural network and control method technology, applied in the field of distributed multi-unmanned ship adaptive neural network formation control, can solve the problem of not considering control input quantization and other problems

Pending Publication Date: 2021-12-24
DALIAN MARITIME UNIVERSITY
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Current formation studies have not considered control input quantification issues

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
  • Distributed multi-unmanned ship adaptive neural network formation control method considering input quantization
  • Distributed multi-unmanned ship adaptive neural network formation control method considering input quantization
  • Distributed multi-unmanned ship adaptive neural network formation control method considering input quantization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0214] In order to verify the effectiveness of the method of the present invention, the following simulation experiments have been carried out. In this embodiment, they are all underactuated unmanned ships, and the trajectory parameters of the pilot ship are as follows:

[0215] p 0 (t)=[0.2t,2*sin(0.1*t)-3] T ,

[0216] m iu =25.8kg,

[0217] m iv =33.8kg,

[0218] m ir =2.76kg·m 2 ,

[0219] f iu (·)=-5.87u 3 -1.33|u|u-0.72u+m iv vr+1.0948r 2 ,

[0220] f iv (·)=-36.5|v|v-0.8896v-0.805v|r|-m iu ur,

[0221] f ir (·)=-0.75|r|r-1.90r+0.08v|r|+(m iu -m iv )uv-1.0948ur;

[0222] The initial status of the five ships is as follows:

[0223] p 1 =[0,0] T ;p 2 =[-7,7] T ;p 3 =[-7,-7] T ;p 4 =[-14,14] T ;p 5 =[-14,-14] T ;

[0224] The desired formation state is as follows:

[0225] p 1d =[0,0] T ;p 2d =[-7,7] T ;p 3d =[-7,-7] T ;p 4d =[-14,14] T ;p 5d =[-14,-14] T

[0226] The controller parameters are as follows:

[0227] c iu = c ir =1...

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 provides a distributed multi-unmanned ship adaptive neural network formation control method considering input quantization. The method comprises the following steps of: constructing an unmanned ship kinematic model; considering a quantitative input problem, and constructing an unmanned ship dynamics model; designing a kinematics controller; based on the kinematics controller, designing a distributed formation control law, and designing a dynamics controller; and designing a dynamics control law based on the dynamics controller. In the kinematics subsystem, a distributed guidance law is designed based on an extended state observer, a time-varying trajectory is tracked, and an unknown state of an adjacent ship is estimated by using the observer; in a dynamics subsystem, a linear time-varying model is used to describe a quantization process, a radial basis function neural network is used to identify unmodeled dynamic and system uncertain items, and a quantizer-free parameter information adaptive neural network quantization control law is designed; and an unknown dynamics problem caused by external ocean disturbance and internal model uncertainty is considered, and effective control of the distributed multi-unmanned ship formation considering an input quantization problem is realized.

Description

technical field [0001] The invention belongs to the cooperative control technology of unmanned ships in the field of ships and ocean engineering, and in particular relates to a distributed multi-unmanned ships adaptive neural network formation control method considering input quantization. Background technique [0002] Due to the changeable marine climate, harsh environment and complex and diverse ship tasks, a single surface ship can no longer meet the needs of actual ocean engineering. Therefore, multi-vessel collaboration has become a development trend in marine engineering. It can not only improve the efficiency of ships, but also ensure the safety of personnel and ships, such as laying optical cables on the seabed, exploring marine resources, mapping seabed topography, marine rescue and formation cruising, etc. . Under the new situation of the development of marine science and technology, compared with the higher demand, complex environment, task diversity and the part...

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): G05D1/02
CPCG05D1/0206
Inventor 宁君陈汉民李铁山彭周华刘陆陈俊龙
Owner DALIAN MARITIME UNIVERSITY
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com