中国物理B ›› 2008, Vol. 17 ›› Issue (3): 878-882.doi: 10.1088/1674-1056/17/3/024

• • 上一篇    下一篇

Numeral eddy current sensor modelling based on genetic neural network

俞阿龙   

  1. Department of Electronic and Electrical Engineering, Huaiyin Teachers College, Huaian 223001, China
  • 收稿日期:2007-07-15 修回日期:2007-08-22 出版日期:2008-03-04 发布日期:2008-03-04
  • 基金资助:
    Project supported by the Natural Science Foundation of the Higher Education Institutions of Jiangsu Province, China and by the Foundation of Huaiyin Teachers College Professor, China (Grant Nos 07KJD510027 and 06HSJS020).

Numeral eddy current sensor modelling based on genetic neural network

Yu A-Long(俞阿龙)   

  1. Department of Electronic and Electrical Engineering, Huaiyin Teachers College, Huaian 223001, China
  • Received:2007-07-15 Revised:2007-08-22 Online:2008-03-04 Published:2008-03-04
  • Supported by:
    Project supported by the Natural Science Foundation of the Higher Education Institutions of Jiangsu Province, China and by the Foundation of Huaiyin Teachers College Professor, China (Grant Nos 07KJD510027 and 06HSJS020).

摘要: This paper presents a method used to the numeral eddy current sensor modelling based on the genetic neural network to settle its nonlinear problem. The principle and algorithms of genetic neural network are introduced. In this method, the nonlinear model parameters of the numeral eddy current sensor are optimized by genetic neural network (GNN) according to measurement data. So the method remains both the global searching ability of genetic algorithm and the good local searching ability of neural network. The nonlinear model has the advantages of strong robustness, on-line modelling and high precision. The maximum nonlinearity error can be reduced to 0.037{\%} by using GNN. However, the maximum nonlinearity error is 0.075$^{ }${\%} using the least square method.

关键词: modelling, numeral eddy current sensor, functional link neural network, genetic neural network

Abstract: This paper presents a method used to the numeral eddy current sensor modelling based on the genetic neural network to settle its nonlinear problem. The principle and algorithms of genetic neural network are introduced. In this method, the nonlinear model parameters of the numeral eddy current sensor are optimized by genetic neural network (GNN) according to measurement data. So the method remains both the global searching ability of genetic algorithm and the good local searching ability of neural network. The nonlinear model has the advantages of strong robustness, on-line modelling and high precision. The maximum nonlinearity error can be reduced to 0.037% by using GNN. However, the maximum nonlinearity error is 0.075% using the least square method.

Key words: modelling, numeral eddy current sensor, functional link neural network, genetic neural network

中图分类号:  (Sensors (chemical, optical, electrical, movement, gas, etc.); remote sensing)

  • 07.07.Df
07.05.Mh (Neural networks, fuzzy logic, artificial intelligence) 07.50.-e (Electrical and electronic instruments and components)