Self-adaptive neural network automatic berthing control method and equipment for underactuated ship and medium

A neural network and control method technology, applied in the field of underactuated ship adaptive neural network automatic berthing control, can solve the problems of actuator time-varying gain, model dynamic uncertainty and unknown disturbance, etc.

Active Publication Date: 2018-09-21
SHANDONG JIAOTONG UNIV
View PDF4 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In berthing practice, the ship is affected by time-varying shallow water, low speed, quay wall effect, relatively enhanced wind current, etc., which

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
  • Self-adaptive neural network automatic berthing control method and equipment for underactuated ship and medium
  • Self-adaptive neural network automatic berthing control method and equipment for underactuated ship and medium
  • Self-adaptive neural network automatic berthing control method and equipment for underactuated ship and medium

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0185] Example 1: In the model parameter m u 、m v 、m r , f u (υ) and f r (υ) are unknown, the design parameter k u =diag([k 1 ,k 2 ]) = diag([5,6]), k r =k 3 =25, δ 1 =4×10 -5 ,δ 2 =2×10 -4 、a 1 =0.01, a 2 =0.01,b 1 =0.02,b 2 =0.001, and Dynamic surface parameter e=0.01, additional control coordinate conversion parameter ω 1 =0.1, ω 2 = 0.25.

[0186] Such as figure 1 As shown, the lateral position of the ship reaches the predetermined berth x(d)=0 in 26s, but at this time, the longitudinal position has not yet reached the target value y(d)=0, and it needs to be fine-tuned by reversing the propeller, and it reaches the predetermined berth in 50s. berth point. In order to further verify the stability of the controller, the simulation time is 300s. The heading angle ψ curve shows that during the time period of 0s-90s, the heading gradually stabilizes from 0° to 180°.

[0187] Such as figure 2 As shown, the change curve of the center position of the sh...

example 2

[0191] Example 2: On the basis of the previous section, in order to further verify the anti-disturbance ability of the control law, the bounded disturbance vector selected in this section includes two parts: constant value disturbance and sinusoidal function time-varying disturbance, and the disturbance vector is selected:

[0192]

[0193] For convenience of comparison, the settings are the same as those in Example 1. That is, the initial conditions such as the initial position and velocity of the ship and the design parameters of the control law remain unchanged, and the simulation results are as follows: Figure 6-Figure 10 shown.

[0194] Figure 6 It is given that the lateral position of the ship reaches the predetermined berth x(d)=0 at 58s, and at this time, the longitudinal position has not yet reached the target value y(d)=0, and needs to be fine-tuned by reversing the propeller, and finally reaches the predetermined berth in 210s. berth point. The heading angle...

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 self-adaptive neural network automatic berthing control method for an underactuated ship. According to the method, an additional control method is adopted for solving the difficulty of design of an underactuated controller; uncertain ship model dynamic parameters and unknown disturbance vectors are reconstructed by utilizing a neutral network self-adaptive method of navigation dynamic depth information, the neutral network weight, approximate error and disturbance quantity are taken as complex uncertain parameters to be estimated on line, the problem that since disturbance and approximate error are separated to be processed, the unknown disturbance input cannot directly approach and the coupling property to the system is neglected is solved, the uncertain couplingproperty is considered, also the design conservatism is reduced, and also the system computation load is reduced; the input saturation of rudder and paddle executors are considered in the controller,and dynamic technology and minimum study parameter methods are introduced, so that the provided control method is more convenient, and the engineer is easy to realize.

Description

technical field [0001] The invention relates to the technical field of ship control, in particular to an automatic berthing control method of an underactuated ship based on the dynamic depth information of the navigation. Background technique [0002] With the development of large-scale, automatic and intelligent ships, intelligent ships have become the mainstream direction of the development of marine transportation today. According to the "Smart Ship Specifications" compiled by China Classification Society (CCS), which came into effect on March 1, 2016, smart ships are divided into six functional modules: smart navigation, smart hull, smart engine room, smart energy efficiency management, smart cargo management and Intelligent integrated platform, among them, the intelligent navigation module not only has basic navigation functions, but also needs to have auxiliary intelligent functions such as automatic berthing. Compared with ship unberthing from the perspective of naut...

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
IPC IPC(8): G05B13/04
CPCG05B13/042
Inventor 张强张显库刘洋许世波张燕江娜孙昱浩杨仁明华莱士杰克逊
Owner SHANDONG JIAOTONG UNIV
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap