分析了钢管缺陷几何大小与缺陷漏磁信号(MFL)特征量之间关系,建立了一组全方位的钢管缺陷信号特征量,并将人工神经网络理论和算法应用于钢管缺陷预测.通过实验取得样本,在对网络进行训练的基础上,建立了基于钢管缺陷漏磁信号特征量和神经网络的缺陷预测模型,继而根据漏磁信号对缺陷进行定量预测.给出了实验结果,结果表明采用这种方法能够较好地实现管道缺陷的定量识别.
参考文献
[1] | 徐丽娜.神经网络控制[M].哈尔滨:哈尔滨工业大学出版社,1999 |
[2] | Leonard S.;Atherton D.L. .Calculations of the effects of anisotropy on magnetic flux leakage detector signals[J].IEEE Transactions on Magnetics,1996(3):1905-1909. |
[3] | WANG Yangsheng;SHI Hanmin;YANG Shuzi .Man-machine Cooperative Analysis and Quantitative Recognition for Broken[J].Chinese Journal of Mechanical Engineering,1989,25(04):93-98. |
[4] | Eduardo Altschuler .Nonlinear Model of Flaw Detection in Steel Pipes by Magnetic Flux Leakage[J].NDT & E International,1995,28(01):35-41. |
[5] | S.Mukhopadhyay;G.P. Srivastava .Characterisation of metal loss defects from magnetic flux leakage signals with discrete wavelet transform[J].NDT & E international: Independent nondestructive testing and evaluation,2000(1):57-65. |
上一张
下一张
上一张
下一张
计量
- 下载量()
- 访问量()
文章评分
- 您的评分:
-
10%
-
20%
-
30%
-
40%
-
50%