基于BP神经网络的地震资料高频补偿
Journal: Geological and Mineral Surveying and Mapping DOI: 10.12238/gmsm.v7i7.1892
Abstract
常规地面数据常受分辨率问题的困扰,其主要原因为地震波传播过程中的地层对高频成分的吸收及衰减效应。而采用井间地震方法测得的井间地震数据则具有较高的分辨率。本文采用三层BP神经网络建立高频成分吸收衰减系统的逆响应模型以关联两类具有不同分辨率的数据——常规地面地震数据与井间地震数据。以常规地面地震数据作为网络输入,井间地震数据作为输出,通过逆响应模型进行高频补偿。从而达到提高常规地面地震资料分辨率的目的。针对某油田K1区块,本文提出的方法有效地提高主频约12Hz,频带宽度拓宽约8Hz。
Keywords
高频补偿；BP神经网络；井间地震
Full Text
PDF - Viewed/Downloaded: 0 TimesReferences
[1] Feng Gao, Prediction of sand thickness using seismic attributes based on BP-neural network[J]. Advanced Materials Research,2012;524:180-183.
[2] Yingming Zhou, Shuwei Wang.An Application of BP Neur al Network Model to Predict the Moisture Content of Crude Oil[J].Advanced Materials Research,2012;527:1327-1330.
[3] Wongpa J,Kiattikomol K,Jaturapitakkul C, Chindaprasirt P, Compressive strength, modulus of elasticity, and water permeability of inorganic polymer concrete[J]. Mater Design, 2010;31:4748-4754.
[4] Pak J, Jang J, Bhadeshia HKDH, Karlsson L, Optimization of neural network for Charpy toughness of steel welds[J]. Mater Manuf Process,2009;24:16-21.
[5] M. Desbazeille, R.B. Randall, F. Guillet, M. El Badaoui,C.Hoisnard. Model-based diagnosis of large diesel engines based on angular speed variations of the crankshaft[J]. Mecha nical System and Signal Processing,2011;24:1529-1541.
[6] Chopra, S., Alexeev, V., and Sudhakar, V. High-frequency restoration of surface seismic data[J].The Leading Edge, 2003.22.730-738.
[7] Mohamed N. Nounou, Hazem N. Nounou. Improving the prediction and parsimony of ARX models using multiscale estimation[J].Applied Soft Computing Journal,2006;7:711-721.
[8] Marjan Golob, Boris Tovornik. Input-output modeling with decomposed neuro-fuzzy ARX model[J]. Neurocomputing, 2007;71:875-884.
[9] Ince R. Prediction of fracture parameters of concrete by artificial neural networks[J]. Eng Fract Mech, 2004; 71: 2143-2159.
[2] Yingming Zhou, Shuwei Wang.An Application of BP Neur al Network Model to Predict the Moisture Content of Crude Oil[J].Advanced Materials Research,2012;527:1327-1330.
[3] Wongpa J,Kiattikomol K,Jaturapitakkul C, Chindaprasirt P, Compressive strength, modulus of elasticity, and water permeability of inorganic polymer concrete[J]. Mater Design, 2010;31:4748-4754.
[4] Pak J, Jang J, Bhadeshia HKDH, Karlsson L, Optimization of neural network for Charpy toughness of steel welds[J]. Mater Manuf Process,2009;24:16-21.
[5] M. Desbazeille, R.B. Randall, F. Guillet, M. El Badaoui,C.Hoisnard. Model-based diagnosis of large diesel engines based on angular speed variations of the crankshaft[J]. Mecha nical System and Signal Processing,2011;24:1529-1541.
[6] Chopra, S., Alexeev, V., and Sudhakar, V. High-frequency restoration of surface seismic data[J].The Leading Edge, 2003.22.730-738.
[7] Mohamed N. Nounou, Hazem N. Nounou. Improving the prediction and parsimony of ARX models using multiscale estimation[J].Applied Soft Computing Journal,2006;7:711-721.
[8] Marjan Golob, Boris Tovornik. Input-output modeling with decomposed neuro-fuzzy ARX model[J]. Neurocomputing, 2007;71:875-884.
[9] Ince R. Prediction of fracture parameters of concrete by artificial neural networks[J]. Eng Fract Mech, 2004; 71: 2143-2159.
Copyright © 2024 刘正文, 胡瑞卿, 陈飞旭, 顾小弟, 王兴军
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License