Ship domain model correction method based on a generalized self-organizing neural network

A neural network technology in the field of ships, applied in the field of revision of ship field models, which can solve problems such as lack of physical meaning and difficulty in selection

Inactive Publication Date: 2013-07-10
DALIAN MARITIME UNIVERSITY
View PDF3 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] There are too many pre-set parameters in the dynamic fuzzy neural network (DFNN), and these parameters lack physical meaning, so it is difficult to choose these specific parameters

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
  • Ship domain model correction method based on a generalized self-organizing neural network
  • Ship domain model correction method based on a generalized self-organizing neural network
  • Ship domain model correction method based on a generalized self-organizing neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0058] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention are clearly and completely described below in conjunction with the drawings in the embodiments of the present invention:

[0059] Such as Figure 1-Figure 9 Shown: An identification method of ship domain model based on generalized online self-organizing neural network, which mainly includes the following steps:

[0060] First, select the ship safety area model, and determine the function, input variables and expected output values ​​of the model:

[0061] The ship area model adopted is the "cross-sectional area" model (can you provide the source?) (such as figure 2 ), where R bf , R ba and S b Represent the front and rear radius and cross-sectional radius of the area respectively, and the model is determined by the following formula:

[0062] ...

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 ship domain model identification method based on a generalized on-line self-organizing neural network. The ship domain model identification method based on the generalized on-line self-organizing neural network includes the following steps: a ship safe region model is selected, and a function, input variables and an expected output value of the ship safe region model are determined; a dynamic fuzzy neural network which comprises an input layer, a membership function layer, a T-norm layer and an output layer is established; a training dataset containing the input variables and the output value of the model is used, and the dynamic fuzzy neural network is subjected to training until the accuracy requirement is met; sailing parameters of two corresponding ships are used as the input variables and input to the ship safe region model after the training is finished, and then a ship safety region of the two ships is obtained. Due to the technical scheme, compared with a traditional ship domain model, the safe model after being corrected through the ship domain model identification method based on the generalized on-line self-organizing neural network has higher accuracy and higher security.

Description

technical field [0001] The invention relates to a method for correcting a domain model of a ship, in particular to a method for correcting a domain model of a ship based on a generalized self-organizing neural network. Background technique [0002] Maritime intelligent transportation, as an important part of my country's science and technology development strategy, has gradually become an emerging cross-research hotspot for the effective integration of ship transportation and information science. And it is particularly important to study the behavior of individual ships in the marine traffic system. In the 1960s and 1970s, Kato [1] of Japan proposed the concept of the field of ship navigation safety. It can be seen from the literature [2] [3] [4] [5] that researchers have proposed various shapes and sizes of ships. Navigation Safety Domain Model. It has a wide range of applications in the field of modern ships. However, it has not been possible to form a unified model. Th...

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): G08G3/02
Inventor 王宁刘刚健董诺孟凡超孙树蕾汪旭明
Owner DALIAN MARITIME UNIVERSITY
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