Abstract:A seismic first-break picking method based on BP neural network integrated with momentum method and adaptive learning rate method was proposed in this paper.It improves the network weight updating process.If mean square error is not within the given error range,the weight update is cancelled.Otherwise,the weight is updated,and the learning rate changes accordingly.Through the analysis on the feasibility of first-break identification using different seismic attributes,four typical attributes,including RMS amplitude ratio,curve length ratio,amplitude and frequency,were chosen for model test.Model test results indicated that the improved method performs better than conventional BP neural network method.The application in real data demonstrated that the improved BP neural network algorithm has simple network structure,few parameters,fast convergence speed,good performance in stability and anti-noising and high first-break picking precision.
曾庆才,曾同生,欧阳永林,等.复杂山地层析反演静校正新方法及应用[J].石油地球物理勘探,2017,52(3):418-425,441.ZENG Qingcai,ZENG Tongsheng,OUYANG Yonglin,et al.A new tomographic inversion for static corrections in complex mountain areas[J].Oil Geophysical Prospecting,2017,52(3):418-425,441.
[2]
潘龙,刘宜文,郑鸿明,等.初至波剩余静校正技术在南安集海地区的应用[J].石油地球物理勘探,2019,54(2):274-279.PAN Long,LIU Yiwen,ZHENG Hongming,et al.First-break residual static corrections applied in the southern part of Anjihai area[J].Oil Geophysical Prospecting,2019,54(2):274-279.
[3]
谢春,刘玉柱,董良国,等.基于声波方程的有限频伴随状态法初至波旅行时层析[J].石油地球物理勘探,2015,50(2):274-282.XIE Chun,LIU Yuzhu,DONG Liangguo,et al.First arrival tomography with finite frequency adjoint state method based on acoustic wave equation[J].Oil Geophysical Prospecting,2015,50(2):274-282.
[4]
程远方,李素闪,张文栋,等.海底电缆资料处理关键技术及其应用[J].石油地球物理勘探,2017,52(增刊2):26-31.CHENG Yuanfang,LI Sushan,ZHANG Wendong,et al.Key techniques for OBC data processing[J].Oil Geophysical Prospecting,2017,52(S2):26-31.
[5]
杨国权,丁鹏程,李振春,等.应用线性方程程函方程和整形正则化的三维初至波旅行时层析[J].石油地球物理勘探,2017,52(2):264-272.YANG Guoquan,DING Pengcheng,LI Zhenchun,et al.3D first arrival traveltime tomography with lineari-zed eikonal equation and shaping regularization[J].Oil Geophysical Prospecting,2017,52(2):264-272.
[6]
左国平,王彦春,隋荣亮.利用能量比法拾取地震初至的一种改进方法[J].石油物探,2004,43(4):345-347.ZUO Guoping,WANG Yanchun,SUI Rongliang.An improved method for first arrival pickup using energy ratio[J].Geophysical Prospecting for Petroleum,2004,43(4):345-347.
[7]
岳龙,刘怀山,刘凯,等.基于时频分析的初至拾取方法研究[J].石油物探,2015,54(5):508-520.YUE Long,LIU Huaishan,LIU Kai,et al.First-break picking based on time-frequency analysis[J].Geophysical Prospecting for Petroleum,2015,54(5):508-520.
[8]
牛沛琛,张建中.基于数字图像处理的地震波初至时间检测[J].计算机与现代化,2007,(4):27-30.NIU Peichen,ZHANG Jianzhong.First arrival picking based on image processing methods[J].Computer and Modernization,2007,(4):27-30.
[9]
盛冠群,李振春,王维波,等.基于小波分解与高阶统计量的微地震初至拾取方法研究[J].石油物探,2015,54(5):388-395.SHENG Guanqun,LI Zhenchun,WANG Weibo,et al.A new automatic detection method of microseismic events based on wavelet decomposition and high-order statics[J].Geophysical Prospecting for Petroleum,2015,54(5):388-395.
[10]
曹茂森,任青文,万林梅,等.Length分形维算法拾去地震波初至[J].石油地球物理勘探,2004,39(5):509-514.CAO Maosen,REN Qingwen,WAN Linmei,et al.Length fractal dimension method for picking seismic first break[J].Oil Geophysical Prospecting,2004,39(5):509-514.
[11]
宋建国,李赋真,徐维秀,等.改进的神经网络级联相关算法及其在初至拾取中的应用[J].石油地球物理勘探,2018,53(1):8-16.SONG Jianguo,LI Fuzhen,XU Weixiu,et al.An improved neural-network cascade-correlation algorithm and its application in seismic first break picking[J].Oil Geophysical Prospecting,2018,53(1):8-16.
[12]
Murat M E,Rudman A J.Automated first arrival picking:A neural network approach[J].Geophysical Prospecting,1992,40(6):587-604.
[13]
王金峰,罗省贤.BP神经网络的改进及其在初至拾取中的应用[J].物探化探技术,2006,28(1):14-17.WANG Jinfeng,LUO Shengxian.The improved BP neural network and its application in seismic first breaks picking[J].Computing Techniques for Geophysical and Geochemical Exploration,2006,28(1):14-17.
[14]
Steven F.Multiple classifier architectures and their application to credit risk assessment[J].European Journal of Operational Research,2011,doi:10.1016/j.ejor.2010.09.029.
[15]
Thomas L,Crook J,Edelman D.Credit Scoring and Its Applications[M].Society for Industrial and Applied Mathematics,2017.
[16]
高明亮,于生宝,郑建波,等.基于IGA算法的电阻率神经网络反演成像研究[J].地球物理学报,2016,59(11):4372-4382.GAO Mingliang,YU Shengbao,ZHENG Jianbo,et al.Research of resistivity imaging using neural network based on immune genetic algorithm[J].Chinese Journal of Geophysics,2016,59(11):4372-4382.
[17]
Domingos P O,Silva F M,Neto H C.An efficient and scalable architecture for neural networks with backpropagation learning[C].International Conference on Field Programmable Logic and Applications,2005,89-94.
[18]
张繁昌,印兴耀.用模拟退火神经网络技术进行波阻抗反演[J].石油大学学报(自然科学版),1997,21(6):16-18.ZHANG Fanchang,YIN Xingyao.Impedance inversion by using annealing neural network[J].Journal of China University of Petroleum(Edition of Natural Science),1997,21(6):16-18.
[19]
宋江涛,邓小宝,魏海涛.航空发动机试车台推力仿真技术研究[J].计算机仿真,2012,29(1):67-70.SONG Jiangtao,DENG Xiaobao,WEI Haitao.Research on simulating test-bed thrusts of aero-engine[J].Computer Simulation,2012,29(1):67-70.
[20]
蒋宗礼.人工神经网络导论[M].北京:高等教育出版社,2001,39-44.
[21]
陈钢花,董维武.遗传神经网络在煤质测井评价中的应用[J].测井技术,2011,35(2):171-175.CHEN Ganghua,DONG Weiwu.Application of genetic neural network to coal quality evalution based on log data[J].Well Logging Technology,2011,35(2):171-175.
[22]
刘军伟,余小清,万旺根,等.基于改进型BP神经网络的音频多分类[J].上海大学学报(自然科学版),2012,18(2):127-131.LIU Junwei,YU Xiaoqing,WAN Wanggen,et al.Multiple classification of audio based on improved BP neural network[J].Journal of Shanghai University(Natural Science Edition),2012,18(2):127-131.
[23]
高伟华.基于混合智能技术的抽油机电力故障诊断方法的研究[J].计算机与数字工程,2018,46(9):1905-1910.GAO Weihua.Research on power fault diagnosis method of pumping unit based on HIS[J].Computer & Digital Engineering,2018,46(9):1905-1910.
[24]
李义宝,张学勇,马建国,等.基于BP神经网络的改进算法研究[J].合肥工业大学学报(自然科学版),2005,28(6):668-671.LI Yibao,ZHANG Xueyong,MA Jianguo,et al.Study of improving algorithms based on the BP neural network[J].Journal of Hefei University of Technology(Natural Science),2005,28(6):668-671.
[25]
Hart D I.Improving the reliability of first break picking with neural networks[C].SEG Technical Program Expanded Abstracts,1996,15:1662-1665.
[26]
刘志成.初至智能拾取技术[J].石油物探,2007,46(5):521-530.LIU Zhicheng.First break intelligent picking technique[J].Geophysical Prospecting for Petroleum,2007,46(5):521-530.