Ship reactor shielding design optimization method based on neural network and genetic algorithm

A neural network and genetic algorithm technology, applied in the field of shielding design optimization of marine reactors, can solve problems such as low efficiency, simple calculation model, and long computer simulation time, and achieve the effect of reducing fitting ability, reducing programming difficulty, and intuitive design work.

Active Publication Date: 2015-09-23
NANHUA UNIV
View PDF5 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] For the optimization of marine reactor shielding design, the numerical calculation method mainly has the disadvantages of simple calculation model, low precision and complex calculation; the Monte Carlo program has the disadvantages of long time-consuming computer simulation and low efficiency

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 reactor shielding design optimization method based on neural network and genetic algorithm
  • Ship reactor shielding design optimization method based on neural network and genetic algorithm
  • Ship reactor shielding design optimization method based on neural network and genetic algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0072] In this example, optimization calculations are performed for four reactor shields with different thicknesses. It is assumed that the four shielding materials are water, iron, lead and polyethylene in sequence and the thickness range of each material is 0-15cm. First, through modeling, the optimization problem of shielding design for marine reactors is transformed into the optimization problem of various shielding layer thicknesses; then, the MCNP program is used to calculate the dose after shielding of a series of different shielding layer thicknesses; further, the neural network is used to train the above samples and reach 97 % or more prediction accuracy; finally, genetic algorithm is used for optimization to search for the best shielding layer thickness scheme.

[0073] The target scheme of this example limits the shielding dose of the reactor under the condition of 1e-7, and finds the shielding scheme with the lightest weight. The thickness of the optimal shielding...

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 ship reactor shielding design optimization method based on a neural network and a genetic algorithm. A Monte Carlo method is used for simulating and calculating the reactor neutron and photon transport process; an MCNP (Monte Carlo N Particle Transport Code) program is used for carrying out simulation and calculation on a ship reactor layered shielding model; a neutron and photon flux after the reactor shielding is obtained; the total equivalent dose is worked out; a topological structure of a BP (Back Propagation) neural network is determined according to the input parameter number n1 and the output parameter number n2 of a sample; an adaptation degree function of the genetic algorithm is determined according to a reactor shielding problem objective; the recommended adaptation degree function is selected; and the strong optimization capacity of the genetic algorithm is used and is mutually coupled with the neural network to find the optimum shielding parameter. The ship reactor shielding design optimization method has the advantages that the high fitting capability of the neural network is used; the time consumption of the MCNP program in the particle transport process is reduced; the good optimization capacity of the genetic algorithm is used; and the optimum shielding parameter can be found in few iteration steps.

Description

technical field [0001] The invention belongs to the technical field of nuclear engineering, and relates to an optimization method for shielding design of a marine reactor based on a neural network and a genetic algorithm. Background technique [0002] The main task of shielding design optimization for marine reactors is to find a shielding scheme with small size, light weight and good shielding effect under the condition of ensuring dose safety. In the actual engineering in the past, the shielding design of marine reactors is to calculate many schemes and then select from them, which will take a lot of machine time and work preparation time, but this often cannot meet the needs of radiation safety, economy and material characteristics. factor optimal shielding scheme. Therefore, the optimal design of shielding for marine reactors has always been a hot spot and challenge in the nuclear engineering field. [0003] Internationally, there are three main categories of shielding...

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): G06F17/50
Inventor 宋英明赵云彪李鑫祥罗迪雯张淮超
Owner NANHUA 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