• 中国科技论文统计源期刊
  • 中文核心期刊
  • 中国科技核心期刊
  • 中国机械工程学会无损检测分会会刊
高级检索

基于FLDA与BP神经网络的超声3D目标识别

卢翠娥, 宋寿鹏, 张恒, 姜琴, 耿伟

卢翠娥, 宋寿鹏, 张恒, 姜琴, 耿伟. 基于FLDA与BP神经网络的超声3D目标识别[J]. 无损检测, 2013, 35(6): 5-10.
引用本文: 卢翠娥, 宋寿鹏, 张恒, 姜琴, 耿伟. 基于FLDA与BP神经网络的超声3D目标识别[J]. 无损检测, 2013, 35(6): 5-10.
LU Cui-E, SONG Shou-Peng, ZHANG Heng, JIANG Qin, GENG Wei. Ultrasonic 3D Target Recognition Based on FLDA and BP Network[J]. Nondestructive Testing, 2013, 35(6): 5-10.
Citation: LU Cui-E, SONG Shou-Peng, ZHANG Heng, JIANG Qin, GENG Wei. Ultrasonic 3D Target Recognition Based on FLDA and BP Network[J]. Nondestructive Testing, 2013, 35(6): 5-10.

基于FLDA与BP神经网络的超声3D目标识别

基金项目: 

江苏大学现代农业装备与技术重点实验室开放基金资助项目(No.NZ200807)

江苏省高校自然基金资助项目(No.08KJD460016)

详细信息
    作者简介:

    卢翠娥(1988-),女,硕士研究生,主要从事超声无损检测与信号处理。

  • 中图分类号: TG115.28;TP391

Ultrasonic 3D Target Recognition Based on FLDA and BP Network

  • 摘要: 针对目前超声3D识别普遍存在的识别率低、鲁棒性差等问题,以物体内部人工标准缺陷为超声靶标,通过对超声靶标脉冲超声回波信号进行处理,提取了相对能量、相对幅值、相对频域带宽、相对峰度系数、相对离散系数、相对包络面积、相对偏度系数和相对频谱半高宽等多个特征参数,利用Fisher线性判别分析(Fisher Linear Discriminative Analysis, FLDA)对这些特征参数进行融合,形成融合特征,并采用反向传播(Back Propagation, BP)神经网络对融合特征进行训练与识别,对物体内部矩形槽、横通孔及平底孔三类超声靶标进行识别。试验结果表明:三种靶标的识别率分别高达了93.3%,93.3%,100%;对噪声有抑制能力,对测试工况不敏感,识别稳健性得到了提高,可为超声3D目标识别提供理论和技术参考。
    Abstract: The technique has a broad prospect of applications in nondestructive testing and evaluation. However, low recognition rate and bad robustness have been faced with at present in ultrasonic 3D target recognition. Aiming to these problems, this paper proposed an effective method. The object inner artificial discontinuities were as the ultrasonic targets, and a few characteristic parameters were extracted by means of dealing with the pulse ultrasonic echo signals of the ultrasonic targets, such as relative energy, relative amplitude, relative frequency domain bandwidth, relative coefficient of kurtosis, relative coefficient of variation, relative envelope area, relative coefficient of skewness and relative FWHM of frequency spectrum, then, FLDA was utilized to fuse the characteristic parameters and integration features were discovered, finally, BP neural network was used to train and recognize integration features. The recognition rate of three kinds of ultrasonic targets, which were object interior rectangular groove, horizontal hole and flat-bottom hole, achieved 93.3%, 93.3% and 100% respectively. The experimental result shows that the method is quite effective, having inhibitory ability to noise, not sensitive to test condition and robust. It can provide theoretical and technical reference to ultrasonic 3D target recognition.
  • [1] 廖璘志,陈琪,严寒冰.基于Morlet小波的超声缺陷分类识别方法研究[J].机床与液压,2010, 38(17):55-57.
    [2] 阮晴,罗飞路,王鹏.基于BP网络和D-S证据理论的超声检测缺陷识别[J].兵工自动化,2011,30(9):72-76.
    [3] 杜秀丽,沈毅,王艳. 基于时频判别特征的焊缝超声检测缺陷分类[J].焊接学报,2008,29(2):89-92.
    [4] KOLEY C, MIDYA B L. 3-D Object Recognition System using Ultrasound [J].IEE, 2005:99-104.
    [5] SUN H C, SANIIE J. Nonlinear signal processing for ultrasonic target detection [J].IEE, 1998(1):855-858.
    [6] SONG Sung-Jin, KIM Hak-Joon, CHO Hyeon. Development of an intelligent system for ultrasonic flaw classification in weldments [J].Nuclear Engineering and Design, 2002, 212(1):307-320.
    [7] 曹玲玲,潘建寿.基于Fisher判别分析的贝叶斯分类器[J].计算机工程,2011,37(10):162-164.
    [8] 郭丹,闫德勤,郑宏亮.最大边际近邻线性判别分析[J].小型微型计算机系统,2011,32(12):2466-2470.
    [9] 张晓华,赵立强. 基于Fisher face和KNN组合分类器的人脸识别算法[J].河北科技师范学院学报, 2008, 22(2): 36-39.
    [10] 葛哲学,孙志强. 神经网络理论与MATLAB R2007实现[M].北京:电子工业出版社,2007.
计量
  • 文章访问数:  2
  • HTML全文浏览量:  0
  • PDF下载量:  1
  • 被引次数: 0
出版历程
  • 收稿日期:  2012-06-25
  • 刊出日期:  2013-06-09

目录

    /

    返回文章
    返回