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

Evolutionary algorithm for sensor position optimization during space-time modeling of distributed parameter system based on two codes

A technology of distributed parameters and evolutionary algorithms, applied in genetic models, genetic laws, design optimization/simulation, etc., can solve problems such as a large number of feasible solutions and time-consuming

Pending Publication Date: 2021-05-28
CENT SOUTH UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The number of feasible solutions to the sensor optimization problem is huge. At this time, the traditional evolutionary algorithm is generally too time-consuming to solve the problem.

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
  • Evolutionary algorithm for sensor position optimization during space-time modeling of distributed parameter system based on two codes
  • Evolutionary algorithm for sensor position optimization during space-time modeling of distributed parameter system based on two codes
  • Evolutionary algorithm for sensor position optimization during space-time modeling of distributed parameter system based on two codes

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0013] A kind of sensor position optimization evolution method with two kinds of encoding mechanisms designed by the present invention with minimum spatio-temporal modeling error is as follows:

[0014] Step 1: Set the parameters of the algorithm, the maximum number of iterations genMax, the number of global search iterations Nt, and the number of local search iterations Ns.

[0015] Step 2: Using the first encoding method, an individual conducts a global search for a sensor layout: search for a set of sensor placement locations in the current entire distributed parameter system space, randomly select several groups of locations as an initial sensor layout population, and judge each group Whether the sensor layout position is feasible, it is feasible to adjust the position of the infeasible sensor. Then construct the error size and differential evolution algorithm calculated by using the initial population layout, and generate a new layout group called offspring. If the offspr...

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 an evolutionary algorithm for sensor position optimization during space-time modeling of a distributed parameter system based on two codes, and belongs to the field of intelligent systems and mode recognition. The sensor layout scheme is effectively combined and optimized by mixing two coding mechanisms provided by the invention, and the optimal sensor layout scheme can be determined to minimize the space-time modeling error of the distribution parameter system. The invention comprises the following steps: initializing the initial position layout of each sensor, selecting the temperature data of the position according to the layout of the sensor to carry out distribution system space-time modeling, namely decomposing a distribution parameter system into a time function and a space function according to KLD, carrying out rbf neural network fitting on the time function, and finally estimating the error of a combined model, performing global search and local search by using two coding modes and a differential evolution algorithm, continuously adjusting the positions of the sensors to obtain different calculation errors, and finally placing the sensors with a limited number according to the layout with the minimum error. The space-time modeling error is minimized, the stable operation of the distributed parameter system is maintained, and the robustness of predicting and monitoring the distributed parameter system is improved.

Description

technical field [0001] The invention relates to a sensor position optimization method for time-space modeling of a distributed parameter system based on two types of codes, which can be applied to sensor layout position optimization and belongs to the field of intelligent systems and pattern recognition. Background technique [0002] Advanced technological demands in semiconductor manufacturing, nanotechnology, biotechnology, materials engineering, and chemical engineering drive the control of material microstructure, fluid flow, spatial distribution (e.g., temperature field), and product size distribution. Whereas physical, chemical or biological processes lead to systems with distributed parameters, where inputs, outputs and even parameters may vary in time and space. Typical examples include thermal processes, fluid processes, convection-diffusion-reaction processes. With the development of sensors, actuators, and computing technologies, the study of distributed parametr...

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): G06F30/18G06F30/27G06N3/04G06N3/08G06N3/12G06F119/08G06F119/12
CPCG06N3/049G06N3/086G06N3/126G06F30/18G06F30/27G06F2119/08G06F2119/12
Inventor 何诗慧王勇
Owner CENT SOUTH UNIV
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