首页 | 本学科首页   官方微博 | 高级检索  
     

双小波神经网络迭代的漏磁缺陷轮廓重构技术
引用本文:徐超,王长龙,孙世宇,陈鹏,绳慧.双小波神经网络迭代的漏磁缺陷轮廓重构技术[J].兵工学报,2012,33(6):730-735.
作者姓名:徐超  王长龙  孙世宇  陈鹏  绳慧
作者单位:军械工程学院电气工程系,河北石家庄,050003;军械工程学院基础部,河北石家庄,050003
基金项目:军队科研计划项目,总装科技创新工程项目
摘    要:在二维漏磁缺陷重构中,建立基于径向基小波神经网络(RWBF)的正演和反演模型,提出了一个反馈形式的双小波神经网络迭代模型,通过迭代使目标函数最小化,实现对缺陷轮廓的快速逼近。用仿真和实验获取的训练样本分别对正演和反演模型的RWBF进行训练。为了提高径向基神经网络的适应性和精度,提出了一种新的训练算法。首先确定最优分解层数,然后利用梯度下降法修正网络的权值。对不同分辨率和不同信噪比下的漏磁信号进行了重构,并与其他方法进行了比较。结果表明,双小波神经网络迭代模型能够实现漏磁缺陷的精确逼近,具有良好的鲁棒性,是有效的二维轮廓重构方法。

关 键 词:人工智能  双小波神经网络迭代模型  二维缺陷重构  多分辨率逼近  材料检测与分析技术

Magnetic Flux Leakage Defect Reconstruction Method Based on Wavelet Neural Network Iteration
XU Chao , WANG Chang-long , SUN Shi-yu , CHEN Peng , SHENG Hui.Magnetic Flux Leakage Defect Reconstruction Method Based on Wavelet Neural Network Iteration[J].Acta Armamentarii,2012,33(6):730-735.
Authors:XU Chao  WANG Chang-long  SUN Shi-yu  CHEN Peng  SHENG Hui
Affiliation:(1.Department of Electrical Engineering,Ordnance Engineering College,Shijiazhuang 050003,Hebei,China;2.Department of Basic Courses,Ordnance Engineering College,Shijiazhuang 050003,Hebei,China)
Abstract:To reconstruct 2-D defect profile from magnetic flux leakage(MFL) signals,a dual wavelet neural network iteration model,including a forward model and an inverse model,based on radial wavelet basis function neural network was proposed.It iteratively adjusts the weights of the inverse network to minimize the error between the measured and predicted MFL signals.The network can be trained respectively by the same training samples from measurement and FEM calculation.To improve the network’s adaptability and accuracy,a novel training algorithm was proposed.Firstly,confirm the optimal number of layers,and then update the weights based on the conjugate gradient algorithm.The reconstruction results in different resolutions and SNRs indicate that the method is rapid,accurate and robust,and it is effective and feasible for reconstruction of 2-D defects comparing with other approaches.
Keywords:artificial intelligence  dual wavelet neural network iteration model  2-D defect reconstruction  multi-resolution approximation  material examination and analysis
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《兵工学报》浏览原始摘要信息
点击此处可从《兵工学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号