[1]李虎,范宜仁,丛云海,等.基于改进SADE算法的神经网络预测储层物性[J].测井技术,2012,36(06):585-589.
 LI Hu,FAN Yiren,CONG Yunhai,et al.A New Method Predicting Reservoir Properties with Neural Network Based on SADE Algorithm[J].WELL LOGGING TECHNOLOGY,2012,36(06):585-589.
点击复制

基于改进SADE算法的神经网络预测储层物性()
分享到:

《测井技术》[ISSN:1004-1338/CN:61-1223/TE]

卷:
第36卷
期数:
2012年06期
页码:
585-589
栏目:
方法研究
出版日期:
2012-12-31

文章信息/Info

Title:
A New Method Predicting Reservoir Properties with Neural Network Based on SADE Algorithm
作者:
李虎12 范宜仁12 丛云海12 胡云云12 刘智中3
1. 中国石油大学地球资源与信息学院, 山东 青岛 266580; 2. 中国石油大学 CNPC测井 重点实验室, 山东 青岛 266580; 3. 中国石油玉门油田分公司,甘肃 酒泉 735210
Author(s):
LI Hu12 FAN Yiren12 CONG Yunhai3 HU Yunyun12 LIU Zhizhong3
1. College of Geo-resources and Information, China University of Petroleum, Qingdao, Shandong 266580, China; 2. CNPC Key Laboratory for Well Logging, China University of Petroleum, Qingdao, Shandong 266580, China; 3. Yumen Oilfield Company, CNPC, Jiuquan, Gansu 735210, China
关键词:
测井评价 模拟退火 差分进化 神经网络 目标函数 储层物性预测
Keywords:
log evaluation simulated annealing differential evolution neural network objective function reservoir properties prediction
分类号:
TE122
文献标志码:
A
摘要:
为准确计算孔隙度、渗透率等储层物性参数,结合模拟退火和差分进化算法的主要优点,提出一种改进的模拟退火差分进化(SADE)算法,将复杂储层物性预测过程中神经网络权值的训练转化为无约束优化问题,并建立新目标函数,进而利用改进的SADE算法进行求解,并与传统方法计算结果进行比较。新目标函数使得神经网络权值的调整不受样本期望输出大小的影响,更适用于变化范围较大的样本数据训练; 改进的SADE算法利用退火温度控制差分进化的选择过程和差分策略的选用,前期具有很好的多样性,后期有较好的收敛能力,克服了经典算法早熟的缺点,提高了全局搜索能力和鲁棒性。利用该算法对现场实际资料进行计算,取得了很好的效果。
Abstract:
In order to accurately calculate reservoir properties, the improved Simulated Annealing Differential Evolution Algorithm(SADE)is proposed by combining simulated annaling with differential evolution algorithm. The training of neural network weights in the process of predicting complicated reservoir properties is transformed into an unconstrained optimization problem, and also a new objective function is offered. Then this problem can be solved by SADE algorithm. Compared with other traditional methods, the new objective function is independent of the desired output during the training of neural network, and thus is more suitable for large range of sample data. At the same time, the annealing temperature is used in the algorithm to control the selection process of differential evolution and the differential strategy. In the early stage, the algorithm is of good diversity, while in the late stage, it is of good convergence, overcoming the shortcoming of prematurity in the classical algorithm, and improving the general search ability and robustness. Finally we calculate the field reservoir properties with this algorithm, and obtain good effect.

参考文献/References:

[1] 洪有密.测井原理与综合解释[M].东营:中国石油大学出版社,2007,159-165.
[2] 雍世和,张超谟.测井数据处理与综合解释[M]. 东营:中国石油大学出版社,1996,121-129.
[3] 范宜仁. 非均质性砂砾岩储层渗透率预测方法研究[J].西南石油大学学报:自然科学版,2010,32(3):6-10.
[4] 连承波.基于测井资料的BP神经网络模型在孔隙度定量预测中的应用[J].天然气地质学,2006,17(3):382-384.
[5] 朱立峰,莫修文.火山碎屑岩层孔隙度的计算方法[J].吉林大学学报:地球科学版,2007,37:126-129.
[6] 邵红梅,安凤仙.一种训练前馈神经网络的梯度算法及收敛性[J].中国石油大学学报:自然科学版,2010,34(4):176-178.
[7] 王文娟,曹俊兴. 基于微粒群算法的神经网络储层物性参数预测[J].西南石油大学学报,2007,29(6):31-34.
[8] Store R, Price K. Differential Evolution-A Simpleand Efficient Adaptice Scheme for Global Optimization Over Continuous Spaces [R]. Berkeley, USA: University of California. International Computer Science Institute, 1995,11-19.
[9] Granville, Krivanek V M, Rasson J P. Simulated Annealing: A Proof of Convergence [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1994, 16(6): 652-656.
[10] Kunqi Liu.Differential Evolution Algorithm Based on Simulated Annealing:Advances in Computation and Intelligence[Z]. Springer Berlin / Heidelberg, 4683: 120-126.
[11] 刘明光.差分演化算法及其改进[J].系统工程,2005,23(2):108-1111.
[12] Lopez C I L, Van Willigenburg L G, Van Straten G. Efficient Differential Evolution Algorithmsfor Multimodal Optimal Control Problems [J]. Applied Soft Computing, 2003,3(2): 97-122.
[13] 徐宝昌,罗雄麟,王金山,等. 一种基于综合目标函数的神经网络学习算法[J]. 中国石油大学学报:自然科学版,2009,33(6):96-99.
[14] 孙文瑜,徐成贤. 最优化方法[M].北京:高等教育出版社,2004.

相似文献/References:

[1]万金彬,李庆华,白松涛.页岩气储层测井评价及进展[J].测井技术,2012,36(05):441.
 WAN Jinbin,LI Qinghua,BAI Songtao.Welllogging Evaluation in Shale Gas Reservoir and Its Advances[J].WELL LOGGING TECHNOLOGY,2012,36(06):441.
[2]张凤生,司马立强,赵冉,等.塔河油田储层裂缝测井识别和有效性评价[J].测井技术,2012,36(03):261.
 ZHANG Fengsheng,SIMA Liqiang,ZHAO Ran,et al.Log Identification and Effectiveness Evaluation on Reservoir Fractures in Tahe Oilfield[J].WELL LOGGING TECHNOLOGY,2012,36(06):261.
[3]冯春珍,林伟川,成志刚,等.低渗透储层测井分类和产能预测技术[J].测井技术,2012,36(03):308.
 FENG Chunzhen,LIN Weichuan,CHENG Zhigang,et al.Reservoir Classification and Productivity Forecasting Method for Low Prorosity and Permeability Reservoir with Log Data[J].WELL LOGGING TECHNOLOGY,2012,36(06):308.
[4]葛祥,何传亮,朱小红,等.川东北地区陆相地层井壁稳定性测井分析[J].测井技术,2012,36(02):164.
 GE Xiang,HE Chuanliang,ZHU Xiaohong,et al.Borehole Stability Logging Analysis in Terrestrial Formation in Northeastern Sichuan[J].WELL LOGGING TECHNOLOGY,2012,36(06):164.
[5]胡瑞波,常静春,张文胜,等.歧口凹陷湖相碳酸盐岩储层岩性识别及储集类型研究[J].测井技术,2012,36(02):179.
 HU Ruibo,CHANG Jingchun,ZHAN Wensheng,et al.On Lithology Identification of Limnetic Facies Carbonate Reservoir in Qikou Sag and Its Reservoir Types[J].WELL LOGGING TECHNOLOGY,2012,36(06):179.
[6]章海宁,张翔,李国瑛,等.三塘湖盆地火山岩储层测井定量评价方法[J].测井技术,2012,36(01):24.
 ZHANG Haining,ZHANG Xiang,LI Guoying,et al.Quantitative Log Evaluation Method for Volcanic Reservoir in Santanghu Basin[J].WELL LOGGING TECHNOLOGY,2012,36(06):24.
[7]肖承文.塔里木盆地高压气藏出砂测井评价方法研究[J].测井技术,2012,36(01):41.
 XIAO Chengwen.On Sand Production Log Evaluation of Highpressure Gas Reservoir in Tarim Basin[J].WELL LOGGING TECHNOLOGY,2012,36(06):41.
[8]张丽华,潘保芝,庄华,等.低孔隙度低渗透率储层压裂后产能测井预测方法研究[J].测井技术,2012,36(01):101.
 ZHANG Lihua,PAN Baozhi,ZHUANG Hua,et al.Productivity Log Forecasting Method for Postfrac Reservoir with Low Porosity and Low Permeability[J].WELL LOGGING TECHNOLOGY,2012,36(06):101.
[9]赵江青,匡立春,刘应,等.非均质储层孔喉结构的测井评价方法[J].测井技术,1998,22(S1):60.
[10]罗景美,郝曙嫣,李爱华,等.测井新技术在桩西地区生产井中的应用[J].测井技术,2003,27(S1):5.
 Luo Jingmei,Hao Shuyan,Li Aihua. et al...Applications of New Logging Technologies in Production Wells in Zhuangxi Region[J].WELL LOGGING TECHNOLOGY,2003,27(06):5.

备注/Memo

备注/Memo:
基金项目:中国石油天然气集团公司科学研究与技术开发项目(2011D-4101)、中国石油国家重大专项(2011ZX05020-008)、国家自然基金资助项目(41174099)联合资助
作者简介:李虎,男,1987年生,博士研究生,从事测井解释与电测井方法研究。
文章编号:1004-1338(2012)06-0585-05
更新日期/Last Update: 2012-12-31