Underground small target recognition using magnetic gradient tensor
ZHENG Jianyong1, FAN Hongbo1, ZHANG Qi2, LI Zhining1
1. Shijiazhuang Campus, Army Engineering University, Shijiazhuang, Hebei 050003, China; 2. Force Unit 94019, the Chinese People's Liberation Army, Hetian, Xinjiang 848000, China
Abstract：An underground small target recognition based on magnetic gradient tensor and support vector machine (SVM) is proposed in the paper.Firstly, underground target magnetic anomaly models with different shapes and different attitudes are used to build a magnetic gradient sample database.Then, nine attribute parameters of the magnetic gradient tensor matrix are analyzed and selected to construct eigenvectors to be used for the support vector machine.Finally, a support vector machine (QPSO-SVM) classification model based on quantum particle swarm optimization is established based on the test data.Simulations and experiments prove that the method can effectively identify the shape of underground small targets, and the accuracy of classification is up to 90%.
王林飞, 郭灿灿, 薛典军, 等.磁梯度张量解析信号分析法及其在场源位置识别中的应用[J].地球物理学进展, 2016, 31(3):1164-1172.WANG Linfei, GUO Cancan, XUE Dianjun, et al.Ana-lytic signals of magnetic gradient tensor and their application to estimate source location[J].Progress in Geophysics, 2016, 31(3):1164-1172.
[4]
李金朋, 张英堂, 范红波, 等.基于磁梯度张量的地下小目标相关成像方法[J].探测与控制学报, 2016, 38(3):75-78.LI Jinpeng, ZHANG Yingtang, FAN Hongbo, et al.Correlation imaging method of small subsurface target based on magnetic gradient tensor[J].Journal of Detection & Control, 2016, 38(3):75-78.
[5]
尹刚, 张英堂, 李志宁, 等.磁偶极子梯度张量的几何不变量及其应用[J].地球物理学报, 2016, 59(2):749-756.YIN Gang, ZHANG Yingtang, LI Zhining, et al.Research on geometric invariant of magnetic gradient tensors for a magnetic dipole source and its application[J].Chinese Journal of Geophysics, 2016, 59(2):749-756.
[6]
朱慧慧, 刘得军, 冯硕, 等.基于磁偶极子构造法几何建模的铁管磁异常正演[J].计算机测量与控制, 2017, 25(3):201-204.ZHU Huihui, LIU Dejun, FENG Shuo, et al.Magnetic dipole reconstruction geometry modeling for underground ferromagnetic pipe magnetic abnormal detection[J].Computer Measurement & Control, 2017, 25(3):201-204.
[7]
谢永茂.基于模板匹配的局部磁异常识别方法[D].北京:中国地质大学(北京), 2012.
[8]
张昌达.航空磁力梯度张量测量——航空磁测技术的最新进展[J].工程地球物理学报, 2006, 3(5):354-361.ZHANG Changda.Airborne tensor magnetic gradio-metry:the latest progress of airborne magnetometric technology[J].Chinese Journal of Engineering Geophysics, 2006, 3(5):354-361.
[9]
Hyoungrea R, Young S P, Hyen K J.Interpretation of magnetic gradient tensor for automatic locating a dipole source[J].ASEG Extended Abstracts, 2012, 26-29.
[10]
余天庆, 毛为民编著.张量分析及应用[M].北京:清华大学出版社, 2006.
[11]
张光辉, 程昱.干扰识别的量子粒子群和支持向量机算法[J].中国电子科学研究院学报, 2011, 6(5):490-493.ZHANG Guanghui, CHENG Yu.The quantum-behave particle swarm optimization support vectors machine method of jamming recognition[J].Journal of China Academy of Electronics and Information Technology, 2011, 6(5):490-493.
[12]
孙瑶琴.改进粒子群算法优化支持向量机在故障诊断中的应用研究[J].计算机测量与控制, 2017, 25(3):48-50.SUN Yaoqin.Application of improved particle swarm optimization support vector machine in fault diagnosis[J].Computer Measurement & Control, 2017, 25(3):48-50.
[13]
Sun J, Feng B, Xu W.Particle swarm optimization withparticles having quantum behavior[C].Proceedings of the 2004 IEEE Congress on Evolutionary Computation, 2004.
[14]
李旭芳, 王士同.基于QPSO训练支持向量机的网络入侵检测[J].计算机工程与设计, 2008, 29(1):34-36.LI Xufang, WANG Shitong.Network intrusion detection method based on novel support vector machine[J].Computer Engineering and Design, 2008, 29(1):34-36.
