作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2013, Vol. 39 ›› Issue (6): 247-250. doi: 10.3969/j.issn.1000-3428.2013.06.055

• 人工智能及识别技术 • 上一篇    下一篇

蚁群算法优化神经网络的零点误差非线性校正

吴文铁,宋曰聪,李 敏   

  1. (绵阳师范学院数学与计算机科学学院,四川 绵阳 621000)
  • 收稿日期:2012-06-20 出版日期:2013-06-15 发布日期:2013-06-14
  • 作者简介:吴文铁(1977-),男,讲师、硕士,主研方向:人工智能;宋曰聪,教授;李 敏,讲师、博士研究生
  • 基金资助:
    四川省教育厅基金资助项目(11ZA166);绵阳师范学院2011校级学科群建设基金资助项目(2011C05)

Zero Error Nonlinear Correction of Neural Network Optimized by Ant Colony Optimization Algorithm

WU Wen-tie, SONG Yue-cong, LI Min   

  1. (School of Mathematics and Computer Science, Mianyang Normal University, Mianyang 621000, China)
  • Received:2012-06-20 Online:2013-06-15 Published:2013-06-14

摘要: 为解决电流互感器的零点误差非线性校正问题,提出一种蚁群算法优化径向基函数(RBF)的零点误差非线性校正方法(ACO-RBF)。利用蚁群算法对RBF神经网络参数进行优化,并采用优化后的RBF神经网络对电流互感器零点误差进行自适应校正。仿真结果表明,相对于其他校正方法,ACO-RBF可提高电流互感器自动测试系统的测量精度,减少测量误差,较好地反映零点误差变化的特点。

关键词: 电流互感器, 零点误差, 径向基函数神经网络, 蚁群算法, 非线性校正

Abstract: Aiming at zero error nonlinear correction problem of Current Transformer(CT), this paper presents a nonlinear sensor zero error correction algorithm based on Radial Basis Function(RBF) neural network optimized by Ant Colony Optimization(ACO) method(ACO-RBF). The parameters of RBF neural network are optimized by ACO algorithm, and the optimized RBF neural network is used to correct CT zero error adaptively. Simulation results show that the proposed method can effectively improve the measuring accuracy of automatic test system and reduce measurement error compared with other methods. It can reflect the characteristic of zero.

Key words: Current Transformer(CT), zero error, Radial Basis Function(RBF) neural network, ant colony algorithm, nonlinear correction

中图分类号: