剪切痕迹激光检测信号溯源系统的设计与实现

孙亚军; 潘楠; 刘益

doi:10.3788/OPE.20162413.0690

您当前的位置：

首页 >

文章列表页 >

剪切痕迹激光检测信号溯源系统的设计与实现

更新时间：2020-08-13

- 剪切痕迹激光检测信号溯源系统的设计与实现
- Design and realization of laser detection signal traceability system with shearing trace
- 光学精密工程 2016年24卷第10s期页码：690-700
- 作者机构：
  
  1. 昆明理工大学机电工程学院,云南昆明,650500
  2. 云南省高校振动与噪声重点实验室,云南昆明,650500
  3. 昆明信诺莱伯科技有限公司,云南昆明,650228
- 作者简介：
- 基金信息：
  
  公安部应用创新计划项目（No.2014JSYJA020，2016JSYJA03）();云南科技计划项目（No.2016RA042）();昆明市科技计划项目（No.201
- DOI：10.3788/OPE.20162413.0690
  中图分类号： TH-39;TN911.72
- 收稿日期：2016-05-19，
  
  修回日期：2016-06-05，
  
  纸质出版日期：2016-11-14
- 稿件说明：
移动端阅览
孙亚军, 潘楠, 刘益. 剪切痕迹激光检测信号溯源系统的设计与实现[J]. 光学精密工程, 2016,24(10s): 690-700

SUN Ya-jun, PAN Nan, LIU Yi. Design and realization of laser detection signal traceability system with shearing trace[J]. Editorial Office of Optics and Precision Engineering, 2016,24(10s): 690-700
孙亚军, 潘楠, 刘益. 剪切痕迹激光检测信号溯源系统的设计与实现[J]. 光学精密工程, 2016,24(10s): 690-700 DOI： 10.3788/OPE.20162413.0690.

SUN Ya-jun, PAN Nan, LIU Yi. Design and realization of laser detection signal traceability system with shearing trace[J]. Editorial Office of Optics and Precision Engineering, 2016,24(10s): 690-700 DOI： 10.3788/OPE.20162413.0690.

摘要

针对目前图像及3D扫描方法难以通过痕迹有效快速溯源剪切工具的弊端，设计并实现了一套剪切痕迹激光检测信号溯源系统，该系统由运动控制子系统、激光检测子系统和显微摄像子系统三部分组成。通过夹持线缆断头，首先控制单点激光位移传感器拾取剪切类线性痕迹的表面特征信号，随后利用小波分解对拾取信号进行降噪，得到降噪后的信号，利用信号间方差大小差异度进行痕迹特征相似重合度匹配，使用梯度下降法进行参数的机器学习，构建相应的代价函数，通过不断的迭代使得代价函数值的代价最小，最终实现对应剪切工具的快速溯源。通过实际剪切痕迹多样本匹配试验对该系统效能进行测试，基于1000组样本对25组测试数据进行批量溯源试验，总计耗时近1.5 s，正确溯源率为98%，该实验证明了本系统对剪切痕迹激光检测信号溯源的准确性和有效性。

Abstract

Specific to disadvantage of current image and 3D scanning method difficult to make effective and rapid traceability shearing tool through trace

a set of laser detection signal traceability system with shearing trace was designed and realized; The system consists of three parts including motion control subsystem

laser detection subsystem and microscopic imaging subsystem. Through clamping cable breakage

firstly

single point laser displacement sensor was controlled to pickup surface characteristic signal of linear trace of shearing; secondly

wavelet decomposition was used to carry out noise reduction for pickup signal and obtain the signal after noise reduction. Variance diversity factor among signals was adopted to perform similarity coincidence degree matching of trace characteristic; and gradient descent method was used to implement parameter machine learning

and construct the corresponding cost function; by constant iteration

make cost function value minimum and finally realize the rapid traceability of shearing tool. System efficiency was verified through the actual shearing traces and multiple sample matching test. Batch traceability test for 25 groups of test data based on 1 000 groups of samples was put forward. Experiment results show that total time consuming is about 1.5 s; correct traceability rate is 98%; the experiment proves that this system has accuracy and validity for laser detection signal traceability system with shearing trace.

关键词

Keywords

references

杨敏, 彭颖. 基于专家知识的工具痕迹系统构建研究[J]. 中国人民公安大学学报(自然科学版), 2013, 2(2):1-5. YANG M, PENG Y. Toolmarks system construction based on experts knowledge[J]. Journal of People's Public Security University of China(Science and Technology), 2013, 2(2):1-5. (in Chinese)

BUNCH S,VEVER G. Application of likelihood ratios for rearm and toolmark analysis[J]. Science and Justice, 2013,53(2):223-229.

杨敏, 李冬云, 王纬东. 基于局部小波能量工具痕迹识别的研究[J]. 中国人民公安大学学报(自然科学版), 2008, 56(2):73-75. YANG M, L D Y, WANG W D. The study of tool mark identification based on local wavelet energy[J]. Journal of People's Public Security University of China(Science and Technology), 2008, 56(2):73-75. (in Chinese)

KASSAMAKOV I, BARBEAU C, LEHTO S, et.al.. CSI Helsinki:Comparing three-dimensional imaging of diagonal cutter toolmarks using confocal microscopy and SWLI[C]. Three-Dimensional Imaging, Visualization, and Display 2010 and Display Technologies and Applications for Defense, Security, and Avionics IV, Orlando, FL, United States, April 6-8, 2010, 7690:76900Y.

BUNCH S,VEVERS G. Significance of angle in the statistical comparison of forensic tool marks[C]. Technometrics, 2013, 55(4):548-561.

GAROL G,PATRICK M,LORETTA K, et al.. Forensic surface metrology:Tool mark evidence[J]. Scanning, 2011, 33(5):272-278.

ROBERT F,CLAU V. Forensic ballistic analysis using a 3D sensor device[C]. 14th ACM Multimedia and Security Workshop, MM and Sec 2012, Coventry, United Kingdom, Sep 6-7, 2012, 67-75.

MEIZMANN M.Techniques for the segmentation of striation patterns[J]. IEEE Trans on Image Processing,2006(3):624-631.

HU S X, XIA Y Y, ZAHNG A W. Research and development of 3D scanning system for dam monitoring based on singlepoint laser sensor[J]. Chinese Optical Society,2011,31(S1).

潘楠,伍星,刘益,等. 线性痕迹激光检测信号自适应匹配算法研究[J]. 仪器仪表学报,2015,36(6):1372-1380. PAN N,WU X, LIU Y, et al.. Research on the adaptive matching algorithm for laser linear mark detection signals[J]. Chinese Journal of Scientific Instrument, 2015,36(6):1372-1380. (in Chinese)

刘益,潘楠,沙生,等. 一种警用线性痕迹激光检测系统,中国专利:CN 105300996 A,20160203[P]. LIU Y, PAN N, SHA S, et al.. One police laser detection system for linear traces China Patent:CN 105300996 A,2016,02,03[P]. (in Chinese)

崔洪亮,刘野,于淼,等. 小波降噪在分布式光纤干涉振动检测及定位系统中的应用[J]. 光学精密工程, 2015,23(10):71-76. CUI H L, LIU Y, YU M, et al.. Application of wavelet denoising in distributed optical fiber interferometric vibration detection and location system[J]. Opt. Precision Eng., 2015,23(10):71-76. (in Chinese)

叶树亮,张玉德,张炜. 齿轮视觉检测中的尺度与方向相关性联合降噪[J]. 光学精密工程, 2014, 22(6):1622-1630. YE SH L, ZHANG Y D, ZHANG W. Scale and directional correlation combined denoiseing in gear visual inspection[J]. Opt. Precision Eng., 2014, 22(6):1622-1630. (in Chinese)

张明照,牟建华,刘扬,等. 应用复Morlet小波变换分析条纹图相位[J]. 光学精密工程, 2012,20(3):643-650. ZHANG M ZH,MOU J H,LIU Y,et al.. Phase extraction for fringe patterns based on complex Morlet wavelet transform[J]. Opt. Precision Eng., 2012,20(3):643-650. (in Chinese)

OGAWA K, SAKATA M, LI Y. Adaptive noise reduction of scintigrams with a wavelet transform[J]. Hindawi Publishing Corporation,2012:4.

ZHENG Y, XIAO L M, TANG W Q, et al.. Parallelization of dynamic time warping on a heterogeneous platform[J]. Maruzen Co., Ltd. 2014, E97A(11):2258-2262.

LI H L. On-line and dynamic time warping for time series data mining[J]. Springer Verlag,2014,6(1):145-153.

DUPAS R, TAVENARD R, OPHÉLIE F. Identifying seasonal patterns of phosphorus storm dynamics with dynamic time warping[J]. Blackwell Publishing Ltd,2015,51(11):8868-8882.

JIA N N, LAM E Y. Machine learning for inverse lithography:Using stochastic gradient descent for robust photomask synthesis[J]. Journal of Optics,2010,12(4):045601.

SHAO J, YANG J Y. Multi-robot reinforcement learning based on learning classifier system with gradient descent methods[J]. Binary Information Press,2010,6(8):2449-2455.

浏览量

474

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

航拍多光谱田间秸秆覆盖量反演模型的建立与优化

模拟初级视觉皮层增强CNN神经网络结构的稳定性

基于高斯过程的参数辨识及永磁同步电机模型电流预测控制策略

相位敏感光时域反射仪的信号处理方法综述

卷积循环神经网络的光学晶格中超冷原子动量分布预测