Coalbed Methane Fracturing Effect Prediction Based on FCMFS Feature Selection Algorithm

doi:10.11885/j.issn.1674-5086.2023.02.27.01

Abstract

Abstract: It is difficult to analyze the nonlinear relationship between the fracturing effect and characteristics of coalbed methane from the mechanism level. Aiming at the problem, the internal relationship between the characteristics of coalbed methane fracturing effect is studied, and a prediction method of coalbed methane fracturing effect based on FCMFS feature selection algorithm is proposed. The method uses fuzzy comprehensive evaluation to calibrate the label, and uses genetic programming and XGBoost algorithm to construct and screen the characteristics of influencing factors, including two new structural features (stress ratio and genetic factors of geological construction) and six characteristics of perforation section thickness, permeability, fracture pressure, coal structure, gas saturation and sand strength. The experimental results show that based on the eight features constructed and screened by the FCMFS feature selection algorithm, combined with a variety of machine learning algorithms to predict the effect of coalbed methane fracturing, the accuracy, recall rate, and F1 classification evaluation indicators are improved by about 5%～10%. Among them, the Deep Forest algorithm has the best prediction classification effect on the training set and the test set, and the three classification evaluation indicators are all above 95% and 80%.

Key words: coalbed methane, fracturing performance, main controlling factor, gene programming, Deep Forest model

CLC Number:

TE122

MIN Chao, GUO Xing, HUA Qing, ZHANG Na, ZHANG Xinhui. Coalbed Methane Fracturing Effect Prediction Based on FCMFS Feature Selection Algorithm[J]. Journal of Southwest Petroleum University(Science & Technology Edition), 2025, 47(2): 95-104.

0
/ / Recommend

Add to citation manager EndNote|Ris|BibTeX

URL: http://journal15.magtechjournal.com/Jwk_xnzk/EN/10.11885/j.issn.1674-5086.2023.02.27.01

http://journal15.magtechjournal.com/Jwk_xnzk/EN/Y2025/V47/I2/95

References

[1] 刘大锰，刘正帅，蔡益栋. 煤层气成藏机理及形成地质条件研究进展[J]. 煤炭科学技术， 2020， 48（10）： 1-16. LIU Dameng, LIU Zhengshuai, CAI Yidong. Research progress on accumulation mechanism and formation geological conditions of coalbed methane[J]. Coal Science and Technology, 2020, 48(10): 1-16.
[2] 刘大锰，贾奇锋，蔡益栋. 中国煤层气储层地质与表征技术研究进展[J]. 煤炭科学技术， 2022， 50（1）： 196203. LIU Dameng, JIA Qifeng, CAI Yidong. Research progress on coalbed methane reservoir geology and characterization technology in China[J]. Coal Science and Technology, 2022, 50(1): 196-203.
[3] 杨长鑫，杨兆中，李小刚，等. 中国煤层气地面井开采储层改造技术现状与展望[J]. 天然气工业， 2022， 42（6）： 154-162. doi: 10.3787/j.issn.1000-0976.2022.06.013 YANG Changxin, YANG Zhaozhong, LI Xiaogang, et al. Status and prospect of reservoir stimulation technologies for CBM surface well production in China[J]. Natural Gas Industry, 2022, 42(6): 154-162. doi: 10.3787/j.issn.1000-0976.2022.06.013
[4] 王艳. 煤层气产能数值模拟及预测方法研究[D]. 徐州：中国矿业大学， 2015. WANG Yan. Study of methods of CBM productivity numerical simulation and its prediction[D]. Xuzhou: China University of Mining and Technology, 2015.
[5] 陈娟，黄浩勇，刘俊辰，等. 基于GA BP神经网络的长宁地区页岩气水平井产能预测技术[J]. 科学技术与工程， 2020， 20（5）： 1851-1858. doi: 10.3969/j.issn.1671-1815.2020.05.021 CHEN Juan, HUANG Haoyong, LIU Junchen, et al. Production predicting technology of shale gas fracturing horizontal well in Changning Area based on the GA-BP neural network mode[J]. Science Technology and Engineering, 2020, 20(5): 1851-1858. doi: 10.3969/j.issn.1671-1815.2020.05.021
[6] 马文礼，李治平，孙玉平，等. 基于机器学习的页岩气产能非确定性预测方法研究[J]. 特种油气藏， 2019， 26（2）： 101-105. doi: 10.3969/j.issn.1006-6535. 2019.02.018 MA Wenli, LI Zhiping, SUN Yuping, et al. Non-deterministic shale gas productivity forecast based on machine learning[J]. Special Oil and Gas Reservoirs, 2019, 26(2): 101-105. doi: 10.3969/j.issn.1006-6535.2019.02. 018
[7] 马先林，周德胜，蔡文斌，等. 基于可解释机器学习的水平井产能预测方法[J]. 西南石油大学学报（自然科学版）， 2022， 44（4）： 81-90. doi: 10.11885/j.issn.1674-5086.2021.10.23.01 MA Xianlin, ZHOU Desheng, CAI Wenbin, et al. An interpretable machine learning approach to prediction horizontal well productivity[J]. Journal of Southwest Petroleum University (Science & Technology Edition), 2022, 44(4): 81-90. doi: 10.11885/j.issn.1674-5086.2021.10.23.01
[8] SNEHALIKA L, DEBAJYOTI S, ABHIK G, et al. Stable feature selection using copula based mutual information[J]. Pattern Recognition, 2020, 112(1): 107697. doi: 10.1016/j.patcog.2020.107697
[9] 刘达，刘雨萌，许晓敏. 基于Copula函数特征筛选的电力物资供应商投标价格预测[J]. 技术经济， 2021， 40（10）： 1-9. doi: 10.3969/j.issn.1002-980X.2021.10.001 LIU Da, LIU Yumeng, XU Xiaomin. Tender price prediction of power materials suppliers based on copula function feature selection[J]. Technology Economics, 2021, 40(10): 1-9. doi: 10.3969/j.issn.1002-980X.2021.10.001
[10] 闵超，张馨慧，杨兆中，等. 基于CBFS CV算法的煤层气井压裂效果主控因素识别[J]. 油气地质与采收率， 2022， 29（1）： 168-174. doi： 10.13673/j.cnki.cn37-1359/te.2022.01.021 MIN Chao, ZHANG Xinhui, YANG Zhaozhong, et al. Identification of main controlling factors of fracturing performance in coalbed methane wells based on CBFS-CV algorithm[J]. Petroleum Geology and Recovery Efficiency, 2022, 29(1): 168-174. doi: 10.13673/j.cnki.cn37-1359/te.2022.01.021
[11] MA Jianbin, GAO Xiaoying. A filter-based feature construction and feature selection approach for classification using genetic programming[J]. Knowledge-Based Systems, 2020, 196: 105806. doi: 10.1016/j.knosys.2020.105806
[12] 任玉珑，陆位忠. 模糊综合评判原理在土建工程造价估算中的应用[J]. 重庆大学学报（自然科学版）， 1995， 18（1）： 97-103. REN Yulong, LU Weizhong. The application of fuzzy multicriteria decisions theoryin evaluation of construction cost of civil engineering[J]. Journal of Chongqing University (Natural Science Edition), 1995, 18(1): 97-103.
[13] 郭江雁，臧必鹏，梁晖，等. 基于模糊综合评判的电网应灾能力量化评估[J]. 中国安全生产科学技术， 2021， 17（3）： 117-123. doi: 10.11731/j.issn.1673-193x.2021.03.018 GUO Jiangyan, ZANG Bipeng, LIANG Hui, et al. Quantitative assessment on disaster response capability of power grid based on fuzzy comprehensive evaluation[J]. Journal of Safety Science and Technology, 2021, 17(3): 117-123. doi: 10.11731/j.issn.1673-193x.2021.03.018
[14] 李良敏，屈梁生. 基于遗传编程和支持向量机的故障诊断模型[J]. 西安交通大学学报， 2004， 38（3）： 239-242. doi: 10.3321/j.issn:0253-987X.2004.03.005 LI Liangmin, QU Liangsheng. Fault detection based on genetic programming and support vector machines[J]. Journal of Xi'an Jiaotong University, 2004, 38(3): 239-242. doi: 10.3321/j.issn:0253-987X.2004.03.005
[15] CRAMER N L. A representation for the adaptive generation of simple sequential programs[C]. Pittsburgh: Proceedings of the 1st International Conference on Genetic Algorithms, 1985: 183-187.
[16] OTERO F E B, S. SILVA M M, FREITAS A A, et al. Genetic programming for attribute construction in data mining[C]. Berlin: Proceedings of 2003 European Conference on Genetic Programming, 2003, 2610: 384-393.
[17] MUHARRAM M A, SMITH G D. Evolutionary feature construction using information gain and gini index[C]. Coimbra: Proceedings of 2004 European Conference on Genetic Programming, 2004, 3003(1): 379-388. doi: 10.1007/978-3-540-24650-3_36
[18] 刘超，靖洪文，蔚立元，等. 高压流体注入对煤岩变形和破裂特性的影响[J]. 煤炭学报， 2022， 47（5）： 2027-2040. doi： 10.13225/j.cnki.jccs.2021.1006 LIU Chao, JING Hongwen, WEI Liyuan, et al. Effect of high-pressure fluid injection on deformation and fracture characteristics of coal[J]. Journal of China Coal Society, 2022, 47(5): 2027-2040. doi: 10.13225/j.cnki.jccs.2021.1006
[19] 高向东，孙昊，王延斌，等. 临兴地区深部煤储层地应力场及其对压裂缝形态的控制[J]. 煤炭科学技术， 2022， 50（8）： 140-150. doi： 10.13199/j.cnki.cst.MCQ20-039 GAO Xiangdong, SUN Hao, WANG Yanbin, et al. In-situ stress field of deep coal reservoir in Linxing Area and its control on fracturing crack[J]. Coal Science and Technology, 2022, 50(8): 140-150. doi: 10.13199/j.cnki.cst.MCQ 20-039
[20] 王丽，王涛，肖巍，等. XGBoost启发的双向特征选择算法[J]. 吉林大学学报（理学版）， 2021， 59（3）： 627-634. doi： 10.13413/j.cnki.jdxblxb.2020332 WANG Li, WANG Tao, XIAO Wei, et al. Bidirectional feature selection algorithm inspired by XGBoost[J]. Journal of Jilin University (Science Edition), 2021, 59(3): 627-634. doi: 10.13413/j.cnki.jdxblxb.2020332
[21] 周志华. 集成学习：基础与算法[M]. 北京：电子工业出版社， 2020. ZHOU Zhihua. Ensemble learning: Fundamentals and algorithms[M]. Beijing: Publishing House of Electronics Industry, 2020.
[22] ZHOU Zhihua, FENG Ji. Deep forest: Towards an alternative to deep neural networks[J]. National Science Review, 2019, 6(1): 74-86. doi: 10.48550/arXiv.1702.08835
[23] 杨兆中，杨晨曦，李小刚，等. 基于灰色关联的逼近理想解排序法的煤层气井重复压裂选井——以沁水盆地柿庄南区块为例[J]. 科学技术与工程， 2020， 20（12）： 4680-4686. doi: 10.3969/j.issn.1671-1815.2020.12.010 YANG Zhaozhong, YANG Chenxi, LI Xiaogang, et al. Multiple fracturing well selection of coalbed methane wells based on technique for order preference by similarity to ideal solution method of gray correlation: Taking the case of Qinshui Basin Shizhuang south Block as an examples[J]. Science Technology and Engineering, 2020, 20(12): 4680-4686. doi: 10.3969/j.issn.1671-1815.2020.12.010