Prediction of coal seam gas content based on ABC-BP model

Authors

ZANG Zijing, School of Earth and Environment, Anhui University of Science and Technology, Huainan 232001, China
WU Haibo, School of Earth and Environment, Anhui University of Science and Technology, Huainan 232001, ChinaFollow
ZHANG Pingsong, School of Earth and Environment, Anhui University of Science and Technology, Huainan 232001, China
DONG Shouhua, School of Resources and Earth Sciences, China University of Mining and Technology, Xuzhou 221116, China

Abstract

It is valuable to exploit the coalbed-methane which is rich in our country. The prediction of gas content in coalbed methane reservoir is a key step in the early stage of development and utilization. In recent years, BP neural network algorithm has been often used in coalbed methane prediction, but the model has some shortcomings in the training process, such as slow convergence speed, sensitive to initial value and easy to fall into local minimum value. Therefore, this paper proposed an improved BP neural network prediction model characterized by artificial bee colony algorithm. Firstly, R-type cluster analysis was used to classify the seismic attributes extracted from the 3D seismic data, four seismic attributes which are most sensitive to the change of coalbed-methane and independent of each other were selected. Secondly, the artificial bee colony algorithm(ABC) was used to find the optimal connection weight of the input layer and the hidden layer and the optimal threshold of the hidden layer of BP neural network, to build a robust ABC-BP neural network prediction model, and the seismic attributes of well location and gas content data was used as samples to train the model. Finally, the coal seam gas content in the work area was predicted by taking the optimal seismic attributes of the target reservoir in the whole work area as input. The prediction results are basically consistent with the change trend of gas content in each well. Among them, the average error rate at the training well is 0.23%, and the error rate at the verification well is less than 15%. Therefore, the prediction method has high reliability and strong applicability, and can be effectively used for coal seam gas content prediction.

Keywords

coalbed methane reservoir, gas content, artificial bee colony algorithm, BP neural network, seismic attribute optimization

DOI

10.3969/j.issn.1001-1986.2021.02.019

Recommended Citation

ZANG Zijing, WU Haibo, ZHANG Pingsong, et al. (2021) "Prediction of coal seam gas content based on ABC-BP model," Coal Geology & Exploration: Vol. 49: Iss. 2, Article 20.
DOI: 10.3969/j.issn.1001-1986.2021.02.019
Available at: https://cge.researchcommons.org/journal/vol49/iss2/20

Reference

[1] 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. CHEN Guiwu,DONG Shouhua,WU Haibo,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.

[2] 苏海,田朋飞,杜中东,等. 鄂尔多斯盆地东部煤层气富集区预测:以午城地区为例[J]. 地球物理学进展,2016,31(2):775-781. SU Hai,TIAN Pengfei,DU Zhongdong,et al. Prediction of rich accumulation area of CBM in eastern Erdos Basin:A case study of Wucheng area[J]. Progress in Geophysics,2016,31(2):775-781.

[3] 朱正平,雷克辉,潘仁芳. 沁水盆地和顺区块基于地震多属性分析的煤层含气量预测[J]. 石油物探,2015,54(2):226-233. ZHU Zhengping,LEI Kehui,PAN Renfang. Coal seam gas content prediction based on seismic multi-attributes analysis in Heshun Block,Qinshui Basin[J]. Geophysical Prospecting for Petroleum,2015,54(2):226-233.

[4] 唐兆建. 基于地震多属性融合方法的煤层气富集区预测[D]. 徐州:中国矿业大学,2016. TANG Zhaojian. Prediction of coalbed methane enrichment area based on seismic multi attribute fusion method[D]. Xuzhou:China University of Mining and Technology,2016.

[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. QI Xuemei. Coalbed methane reservoir seismic response characteristics and applications[D]. Xuzhou:China University of Mining and Technology,2013.

[6] 李艳芳,程建远,王成. 基于支持向量机的地震属性优选及煤层气预测[J]. 煤田地质与勘探,2012,40(6):75-78. LI Yanfang,CHENG Jianyuan,WANG Cheng. Seismic attribute optimization based on support vector machine and coalbed methane prediction[J]. Coal Geology & Exploration,2012,40(6):75-78.

[7] 孟召平,田永东,雷旸. 煤层含气量预测的BP神经网络模型与应用[J]. 中国矿业大学学报,2008,37(4):456-461. MENG Zhaoping,TIAN Yongdong,LEI Yang. Prediction models of coal bed gas content based on BP neural networks and its applications[J]. Journal of China University of Mining & Technology,2008,37(4):456-461.

[8] 曹思远,梁春生. 储层预测中BP神经网络的应用[J]. 地球物理学进展,2002,17(1):84-90. CAO Siyuan,LIANG Chunsheng. The application of BP neural network in reservoir prediction[J]. Progress in Geophysics,2002,17(1):84-90.

[9] 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. ZHANG Rui,CHEN Gang,PAN Baozhi,et al. The prediction of the coalbed methane content based on bacteria foraging optimizing generalized regression neural network[J]. Geophysical and Geochemical Exploration,2016,40(2):327-332.

[10] 赵涛,于师建. 基于GA-BP神经网络算法的高密度电法非线性反演[J]. 煤田地质与勘探,2017,45(2):147-151. ZHAO Tao,YU Shijian. GA-BP neural network algorithm-based nonlinear inversion for high density resistivity method[J]. Coal Geology & Exploration,2017,45(2):147-151.

[11] 施式亮,伍爱友. 基于神经网络与遗传算法耦合的煤与瓦斯突出区域预测研究[J]. 中国工程科学,2009,11(9):91-96. SHI Shiliang,WU Aiyou. Study on area forecast of coal and gas outburst on coupling of neural network and genetic algorithm[J]. China Engineering Science,2009,11(9):91-96.

[12] 刘景艳,王福忠. 基于粒子群神经网络的煤层瓦斯含量预测[J]. 河南理工大学学报(自然科学版),2014,33(6):724-727. LIU Jingyan,WANG Fuzhong. Coal seam gas content prediction based on particle swarm neural network[J]. Journal of Henan University of Technology(Natural Science),2014,33(6):724-727.

[13] 杨桢,李鑫,付华,等. 基于蚁群优化算法的瓦斯预测模型研究[J]. 传感器与微系统,2009,28(10):61-63. YANG Zhen,LI Xin,FU Hua,et al. Study on gas forecast model based on ant colony optimization algorithm[J]. Transducer and Microsystem Technologies,2009,28(10):61-63.

[14] 苏彩红,向娜,林梅金. 基于ABC优化算法的神经网络水溶解氧预测[J]. 计算机仿真,2013,30(11):325-329. SU Caihong,XIANG Na,LIN Meijin. Dissolved oxygen prediction based on artificial bee colony optimization algorithm and BP neural network[J]. Computer Simulation,2013,30(11):325-329.

[15] 张旸,颜七笙. 基于ABC-ELM的上证综指收盘价格预测模型[J]. 计算机仿真,2020,37(5):154-160. ZHANG Yang,YAN Qisheng. Forecasting model of Shanghai composite index closing price based on ABC-ELM[J]. Computer Simulation,2020,37(5):154-160.

[16] KARABOGA D,AKAY B. A comparative study of artificial bee colony algorithm[J]. Applied Mathematics & Computation,2009,214(1):108-132.

[17] 肖恭伟,欧吉坤,刘国林,等. 基于改进的BP神经网络构建区域精密对流层延迟模型[J]. 地球物理学报,2018,61(8):3139-3148. XIAO Gongwei,OU Jikun,LIU Guolin,et al. Construction of regional precision tropospheric delay model based on improved BP neural network[J]. Chinese Journal of Geophysics,2016,61(8):3139-3148.

[18] 徐昕,李涛,伯晓晨,等. Matlab工具箱应用指南[M]. 北京:电子工业出版社,2000. XU Xin,LI Tao,BO Xiaochen,et al. Matlab toolbox application guide[M]. Beijing:Publishing House of Electronics Industry,2000.

[19] BAHRIYE A. A study on particle swarm optimization and artificial bee colony algorithms for multilevel thresholding[J]. Applied Soft Computing,2013,13(6):3066-3091.

[20] APALAK M K,KARABOGA D,AKAY B. The artificial bee colony algorithm in layer optimization for the maximum fundamental frequency of symmetrical laminated composite plates[J]. Engineering Optimization,2014,46(3):420-437.

[21] 侯征,熊盛青,杨进,等. 人工蜂群算法的电震非线性联合反演研究[J]. 地球物理学进展,2015,30(6):2666-2675. HOU Zheng,XIONG Shengqing,YANG Jin,et al. Application of artificial bee colony algorithm in electrical-seismic nonlinear joint inversion[J]. Progress in Geophysics,2015,30(6):2666-2675.