Please wait a minute...
E-mail Alert Rss
 
物探与化探  2020, Vol. 44 Issue (6): 1381-1386    DOI: 10.11720/wtyht.2020.1551
  方法研究·信息处理·仪器研制 本期目录 | 过刊浏览 | 高级检索 |
基于优选地震属性与PSO-BP模型的煤层含气量预测
臧子婧1, 吴海波1(), 丁海2, 张平松1, 董守华3
1.安徽理工大学 地球与环境学院,安徽 淮南 232001
2.安徽省煤田地质局勘查研究院 非常规气研究室,安徽 合肥 230088
3.中国矿业大学 资源与地球科学学院,江苏 徐州 221116
Prediction of coalbed methane content based on preferred seismic attributes and PSO-BP model
ZANG Zi-Jing1, WU Hai-Bo1(), DING Hai2, ZHANG Ping-Song1, DONG Shou-Hua3
1. School of Earth and Environment,Anhui University of Science and Technology,Huainan 232001,China
2. Laboratory of Unconventional Gas,Institute of Exploration,Anhui Coalfield Geology Bureau,Hefei 230088,China
3. School of Resources and Earth Sciences,China University of Mining and Technology,Xuzhou 221116,China
全文: PDF(2320 KB)   HTML
输出: BibTeX | EndNote (RIS)      
摘要 

常规煤层含气量预测方法多基于测井约束的地震属性反演以及线性映射模型,造成预测结果的精度难以控制,严重限制了方法的普适性。本文从地震属性优选与BP神经网络预测模型改进两方面入手开展研究。利用Q型聚类分析方法,对提取的目标储层地震属性进行分类优选,得到了与地质目标相关性好且相互独立的4种地震属性;进一步利用粒子群寻优算法对BP神经网络算法的输入层与隐含层的连接权值和隐含层的阈值进行了优化,构建PSO-BP预测模型,并利用井位置的优选地震属性和含气量数据训练PSO-BP模型。基于训练好的PSO-BP模型,以整个工区的优选地震属性作为输入,进行研究区内煤层含气量预测。井位置含气量预测结果与实测结果对比表明,该预测方法准确率高。因此,可认为PSO-BP预测模型以及相应的预测方法流程能有效适用于煤储层含气量的预测。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
臧子婧
吴海波
丁海
张平松
董守华
关键词 煤层含气量预测粒子群算法神经网络地震属性优选    
Abstract

Conventional coal seam gas content prediction methods are mostly based on logging constrained seismic attribute inversion and linear mapping model,which makes the prediction accuracy difficult to control,and severely limits the universality of the method.This paper starts with two aspects:seismic attribute optimization and BP neural network prediction model improvement.Using the Q-type clustering analysis method,the seismic attributes of the extracted target reservoirs are classified and optimized,and four kinds of seismic attributes with good correlation with the geological targets are obtained.The particle swarm optimization algorithm is further used to BP neural network algorithm.The connection weights of the input layer and the hidden layer and the threshold of the hidden layer are optimized,and the PSO-BP prediction model is constructed.The PSO-BP model is trained by using the preferred seismic attributes and gas content data of the well location.Based on the trained PSO-BP model,the coal seam gas content prediction in the study area is carried out with the preferred seismic attributes of the entire work area as input.The comparison between the predicted gas content of the well position and the measured results shows that the prediction method has high accuracy.Therefore,it can be considered that the PSO-BP prediction model and the corresponding prediction method flow can be effectively applied to the prediction of coal gas content in coal reservoirs.

Key wordscoal seam    gas content prediction    particle swarm optimization    neural network    seismic attribute optimization
收稿日期: 2019-11-25      出版日期: 2020-12-29
ZTFLH:  P631.4  
基金资助:安徽省重点研究与开发计划项目(1804a0802203);安徽省自然科学基金(1908085QD169);国家自然科学基金(41902167)
通讯作者: 吴海波
作者简介: 臧子婧(1995-),女,江苏扬州人,硕士研究生,从事地震属性优化与反演方面的研究工作
引用本文:   
臧子婧, 吴海波, 丁海, 张平松, 董守华. 基于优选地震属性与PSO-BP模型的煤层含气量预测[J]. 物探与化探, 2020, 44(6): 1381-1386.
ZANG Zi-Jing, WU Hai-Bo, DING Hai, ZHANG Ping-Song, DONG Shou-Hua. Prediction of coalbed methane content based on preferred seismic attributes and PSO-BP model. Geophysical and Geochemical Exploration, 2020, 44(6): 1381-1386.
链接本文:  
http://www.wutanyuhuatan.com/CN/10.11720/wtyht.2020.1551      或      http://www.wutanyuhuatan.com/CN/Y2020/V44/I6/1381
Fig.1  研究区概况
Fig.2  典型地震剖面
地震属性 声阻抗 最大曲率 倾角属性 甜点属性 薄层属性 瞬时加速度 瞬时振幅 瞬时频率 瞬时Q
属性编号 1 2 3 4 5 6 7 8 9
煤层含气量 -0.0154 -0.1314 -0.2406 0.0154 -0.3609 -0.2636 0.1212 0.0548 -0.1073
Table 1  井位置的各属性与煤层含气量相关系数
Fig.3  地震属性聚类分析
Fig.4  优选地震属性
a—倾角;b—薄层属性;c—瞬时振幅;d—瞬时Q
Fig.5  BP神经网络结构图
Fig.6  粒子群改进BP神经网络流程
Fig.7  预测模型流程
Fig.8  目标煤储层含气量预测结果
井号 实测值/(m3·t-1) 预测值/(m3·t-1) 误差率/%
Q1201 18.9 18.904 0.02
Q1202 7.97 8.041 0.89
Q1203 13.39 13.453 0.47
Q1204 25.50 25.502 0.01
Q1205 5.39 5.4110 0.39
Q1206 10.27 10.230 0.39
Q1208 12.66 12.728 0.54
Q1501 15.45 15.504 0.35
Q1502 25.7 25.657 0.17
Q1503 18.8 18.825 0.13
Table 2  井位置预测值与实测值对比
[1] 邵林海. 基于三维地震资料的煤层气富集区预测[D]. 西安:西北大学, 2016.
[1] Shao L H. The application of 3D seismic date for the CBM enrichment region predication[D]. Xi'an: Northwest University, 2016.
[2] 卜小平. 中国煤层气产业发展途径与前景分析[D]. 北京:中国地质大学(北京), 2011.
[2] Bu X P. Analysis of development approaches and prospects of coalbed methane industry in China[D]. Beijing:China University of Geosciences (Beijing), 2011.
[3] 张勇昌. 煤层气开发风险形成机制与评价模型研究[D]. 徐州:中国矿业大学, 2017.
[3] Zhang Y C. Study on risk formation mechanism and evaluation model of coalbed methane development[D]. Xuzhou:China University of Mining and Technology, 2017.
[4] 秦勇, 袁亮, 胡千庭, 等. 我国煤层气勘探与开发技术现状及发展方向[J]. 煤炭科学技术, 2012,40(10):1-6.
[4] Qin Y, Yuan L, Hu Q T, et al. Status and development orientation of coal bed methane exploration and development technology in china[J]. Coal Science and Technology, 2012,40(10):1-6.
[5] 祁雪梅. 煤层气储层地震属性响应特征及应用[D]. 徐州:中国矿业大学, 2013.
[5] Qi X M. Coalbed methane reservoir seismic response characteristics and applications[D]. Xuzhou:China University of Mining and Technology, 2013.
[6] 孟召平, 郭彦省, 张纪星. 基于测井参数的煤层含气量预测模型与应用[J]. 煤炭科学技术, 2014,42(6):25-30.
[6] Meng Z P, Guo Y S, Zhang J X. Application and prediction model of coalbed methane content based on logging parameters[J]. Coal Science and Technology, 2014,42(6):25-30.
[7] 田敏. 煤层气资源量预测中的灰色系统理论研究[D]. 北京:中国石油大学, 2008.
[7] Tian M. Study on the grey system theory in the prediction of coalbed methane resources[D]. Beijing:China University of Petroleum, 2008.
[8] 彭苏萍, 杜文凤, 殷裁云, 等. 高丰度煤层气富集区地球物理识别[J]. 煤炭学报, 2014,39(8):1398-1403.
[8] Peng S P, Du W F, Yin C Y, et al. Geophysical identification of high abundance coalbed methane enrichment area[J]. Journal of Coal, 2014,39(8):1398-1403.
[9] 陈贵武, 董守华, 吴海波, 等. 高丰度煤层气富集区地球物理定量识别技术研究与应用[J]. 地球物理学进展, 2014,29(5):2151-2156.
[9] Chen G W, Dong S H, Wu H B, et al. Research and application of quantitative geophysics recognition in high abundance of coalbed methane rich region[J]. Progress in Geophysics, 2014,29(5):2151-2156.
[10] 曹军涛, 赵军龙, 王轶平, 等. 煤层气含量影响因素及预测方法[J]. 西安石油大学学报:自然科学版, 2013,28(4):28-34.
[10] Chao J T, Zhao J L, Wang Y P, et al. Factors affecting coalbed methane content and prediction methods[J]. Journal of Xi'an Shiyou University:Natural Science Edition, 2013,28(4):28-34.
[11] 祁雪梅, 董守华. 地震相技术在煤层气勘探中的应用[J]. 物探与化探, 2012,36(2):170-173.
[11] Qi X M, Dong S H. Application of seismic facies technology in coalbed methane exploration[J]. Geophysical and Geochemical Exploration, 2012,36(2):170-173.
[12] 张瑞, 陈刚, 潘保芝, 等. 基于细菌觅食优化广义回归神经网络的煤层气含量预测[J]. 物探与化探, 2016,40(2):327-332.
[12] Zhang R, Chen G, Pan B Z, et al. Prediction of coalbed methane content based on generalized regression neural network optimized by bacterial foraging[J]. Geophysical and Geochemical Exploration, 2016,40(2):327-332.
[13] 李刚. 基于BP算法的煤层厚度预测技术应用研究[J]. 中国煤炭地质, 2011,23(5):45-48.
[13] Li G. An applied research on coal thickness prediction technology based on BP algorithm[J]. Coal Geology of China, 2011,23(5):45-48.
[14] 梅洋洋, 秦云强. 基于BP神经网络的煤层气井产水量预测研究[J]. 煤炭技术, 2018,37(12):163-165.
[14] Mei Y Y, Qin Y Q. Study on water production of coalbed methane well by using BP neural network[J]. Coal Technology, 2018,37(12):163-165.
[15] 胡胜利, 钱旭, 钟峰. 基于遗传算法和人工神经网络的煤层厚度预测[J]. 中国煤炭, 2010,36(2):69-71,76.
[15] Hu S L, Qian X, Zhong F. Genetic algorithm and artificial neural network based coal seam thickness forecasting[J]. Coal of China, 2010,36(2):69-71,76.
[16] 张丽平. 粒子群优化算法的理论及实践[D]. 杭州:浙江大学, 2005.
[16] Zhang L P. The theorem and practice upon the particle swarm optimization algorithm[D]. Hangzhou:Zhejiang University, 2005.
[17] 马秋芳. 改进PSO优化的BP神经网络短时交通流预测[J]. 计算机仿真, 2019,36(4):94-98.
[17] Ma Q F. BP neural network short-term traffic flow prediction based on improved particle swarm optimization[J]. Computer Simulation, 2019,36(4):94-98.
[18] 徐开, 陈志刚, 赵靖华, 等. 基于粒子群算法的星敏感器布局设计[J]. 吉林大学学报:工学版, 2019,49(3):972-978.
[18] Xu K, Chen Z G, Zhao J H, et al. Layout design method of star sensor based on particle swarm optimization algorithm[J]. Journal of Jilin University:Engineering and Technology Edition, 2019,49(3):972-978.
[19] 徐星, 李喆. 基于改进粒子群BP神经网络的矿井突水水源判别[J]. 煤炭技术, 2018,37(6):157-158.
[19] Xu X, Li Z. Identification of mine water inrush source based on improved particle swarm optimization and BP neural network[J]. Coal Technology, 2018,37(6):157-158.
[20] 张德慧, 张德育, 刘清云, 等. 基于粒子群算法的BP神经网络优化技术[J]. 计算机工程与设计, 2015,36(5):1321-1326.
[20] Zhang D H, Zhang D Y, Liu Q Y, et al. BP neural network optimized by improved PSO[J]. Computer Engineering and Deign, 2015,36(5):1321-1326.
[21] Wu D M, Zhao Y M, Cheng Y P, et al. ΔP index with different gas compositions for instantaneous outburst prediction in coal mines[J]. Mining Science and Technology(China), 2010,20(5):723-726.
[1] 郭建宏, 张占松, 张超谟, 陈芷若, 张鹏浩, 汤潇, 秦瑞宝, 余杰. 基于灰色系统与测井方法的煤层气含量预测及应用[J]. 物探与化探, 2020, 44(5): 1190-1200.
[2] 崔方智, 周韬, 张兵. 煤层中CO2注入运移瞬变电磁法监测技术探索[J]. 物探与化探, 2020, 44(3): 573-581.
[3] 王逸宸, 柳林涛, 许厚泽. 基于卷积神经网络识别重力异常体[J]. 物探与化探, 2020, 44(2): 394-400.
[4] 杨雪, 裴家学, 何绍勇, 蒋学峰, 谢天寿, 高建军. 煤层发育条件下薄储层预测方法研究[J]. 物探与化探, 2020, 44(2): 406-411.
[5] 陈彦虎, 陈佳. 波形指示反演在煤层屏蔽薄砂岩分布预测中的应用[J]. 物探与化探, 2019, 43(6): 1254-1261.
[6] 付康伟, 张学强, 彭炎. BP神经网络算法在陆域天然气水合物成藏预测中的应用[J]. 物探与化探, 2019, 43(3): 486-493.
[7] 王嘉怡, 郝立波, 赵新运, 马成有, 陆继龙, 赵玉岩, 魏俏巧. 基于土壤化学成分的基岩岩石类型识别[J]. 物探与化探, 2018, 42(6): 1180-1185.
[8] 梁亚林, 原文涛. 测井预测煤层气含量及分布规律——以山西省沁水煤田为例[J]. 物探与化探, 2018, 42(6): 1144-1149.
[9] 张兆龙, 王跃钢, 腾红磊, 王乐. 一种基于遗传算法和BP神经网络的选星方法[J]. 物探与化探, 2017, 41(5): 946-950.
[10] 贾跃玮, 魏水建, 游瑜春, 王丹. 兴隆气田长兴组生物礁储层预测研究[J]. 物探与化探, 2017, 41(4): 605-610.
[11] 王建青, 杨晓东, 田忠斌, 申有义. 基于地震频谱属性的煤层厚度预测方法[J]. 物探与化探, 2017, 41(2): 364-368.
[12] 高磊, 陈文雄, 薛明星. 渤海A油田气烟囱识别及其研究意义[J]. 物探与化探, 2016, 40(4): 675-680.
[13] 陈浙春, 蒋涛, 汤玉平, 李吉鹏, 程同锦, 王国建. 油气化探在鄂尔多斯盆地延川煤层气勘探中的应用[J]. 物探与化探, 2016, 40(2): 318-326.
[14] 张瑞, 陈刚, 潘保芝, 蒋必辞, 杨雪, 刘丹. 基于细菌觅食优化广义回归神经网络的煤层气含量预测[J]. 物探与化探, 2016, 40(2): 327-332.
[15] 魏文希, 师素珍, 孙超, 李世杰. 拟声波反演技术在识别煤层顶底板砂泥岩中的应用[J]. 物探与化探, 2016, 40(1): 220-224.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
京ICP备05055290号-3
版权所有 © 2017《物探与化探》编辑部
通讯地址:北京市学院路29号航遥中心 邮编:100083
电话:010-62060192;62060193 E-mail:whtbjb@sina.com