Prediction of crack width of drilling fluid leakage based on neural network

Authors

WANG Jian, School of Petroleum Engineering, China University of Petroleum (East China), Qingdao 266580, ChinaFollow
XU Jiafang, School of Petroleum Engineering, China University of Petroleum (East China), Qingdao 266580, China; National Engineering Research Center for Oil & Gas Drilling and Completion Technology, Qingdao 266580, China; Key Laboratory of Unconventional Oil & Gas Development, China University of Petroleum (East China), Ministry of Education, Qingdao 266580, ChinaFollow
ZHAO Mifu, Dongbei Oil and Gas Branch, China Petroleum and Chemical Corporation, Changchun 130000, China
WANG Bowen, School of Petroleum Engineering, China University of Petroleum (East China), Qingdao 266580, China
WANG Yahua, School of Petroleum Engineering, China University of Petroleum (East China), Qingdao 266580, China
CHEN Jie, School of Petroleum Engineering, China University of Petroleum (East China), Qingdao 266580, China
WANG Xiaohui, School of Petroleum Engineering, China University of Petroleum (East China), Qingdao 266580, China
YANG Gang, China United Coalbed Methane Co., Ltd., Beijing 100011, China
MA Tengfei, China United Coalbed Methane Co., Ltd., Beijing 100011, China

Abstract

During the drilling, it is difficult to select the appropriate leakage prevention and plugging methods and materials as the development of reservoir fractures is unknown. Herein, a reservoir crack width prediction method based on neural network was proposed with reference to the actual history data of wells. Firstly, the main influencing factors of reservoir fracture width were explored and ranked by correlation analysis, and seven main influencing factors, including pump pressure, drilling fluid displacement and drilling speed, were selected as the input parameters. The rate of convergence of the model was improved using the additional momentum algorithm and the variable learning rate algorithm, and the model structure was optimized. Secondly, the Genetic Algorithm (GA) and Adaboost algorithm were used to optimize the BP neural network (BPNN), overcoming the problem of its tendency to fall into local minima and improving the prediction accuracy of the model. Finally, an Adaboost-GA-BP neural network prediction model was established to predict the reservoir crack width, with the prediction accuracy analyzed comparatively. The research results show that the parameters correlated with the reservoir crack width include the loss rate and loss amount, pump pressure, drilling fluid displacement, drilling speed, well depth, plastic viscosity and static shear force in a descending order. In addition, the additional momentum algorithm and the variable learning rate algorithm can reduce the sum of train set absolute error at the end of training by 27%, significantly improving the model performance. At the same time, the weight and threshold of the model were optimized by the GA algorithm, and the integrated optimization was realized by the Adaboost algorithm to further improve the prediction accuracy. Thus, the final reservoir crack width prediction model established based on Adaboost-GA-BP neural network has a root mean square error (RMSE) and a correlation coefficient of 18% and 0.98, respectively. Compared with other models such as the random forest, the model proposed herein has a higher accuracy, which could provide some guidance for the calculation of reservoir fracture crack and the preparation of leakage plugging scheme during the process of exploration and development.

Keywords

leakage prevention and plugging, reservoir crack width, neural network, genetic algorithm (GA), Adaboost algorithm, drilling fluid

DOI

10.12363/issn.1001-1986.23.05.0240

Recommended Citation

WANG Jian, XU Jiafang, ZHAO Mifu, et al. (2023) "Prediction of crack width of drilling fluid leakage based on neural network," Coal Geology & Exploration: Vol. 51: Iss. 9, Article 21.
DOI: 10.12363/issn.1001-1986.23.05.0240
Available at: https://cge.researchcommons.org/journal/vol51/iss9/21

Reference

[1] 吕帅锋,王生维,张晓飞,等. 煤层气钻井固相物污染特征及评价[J]. 煤田地质与勘探,2017,45(1):162−167.

LYU Shuaifeng,WANG Shengwei,ZHANG Xiaofei,et al. Pollution characteristics and evaluation of solid–phase materials in CBM drilling[J]. Coal Geology & Exploration,2017,45(1):162−167.

[2] 吕开河,王晨烨,雷少飞,等. 裂缝性地层钻井液漏失规律及堵漏对策[J]. 中国石油大学学报(自然科学版),2022,46(2):85−93.

LYU Kaihe,WANG Chenye,LEI Shaofei,et al. Dynamic behavior and mitigation methods for drilling fluid loss in fractured formations[J]. Journal of China University of Petroleum(Edition of Natural Science),2022,46(2):85−93.

[3] LUTHI S M,SOUHAITÉ P. Fracture apertures from electrical borehole scans[J]. Geophysics,1990,55(7):806−948.

[4] HORNBY B E,JOHNSON D L,WINKLER K W,et al. Fracture evaluation using reflected stoneley–wave arrivals[J]. Geophysics,2012,54(10):1274−1288.

[5] 何涛,谢显涛,王君,等. 利用优化BP神经网络建立裂缝宽度预测模型[J]. 钻井液与完井液,2021,38(2):201−206.

HE Tao,XIE Xiantao,WANG Jun,et al. Crack width prediction model based on optimized BP neural network[J]. Drilling Fluid & Completion Fluid,2021,38(2):201−206.

[6] SANFILLIPPO F，BRIGNOLI M，SANTARELLI F J，et al. Characterization of conductive fractures while drilling：SPE European Formation Damage Conference[C]. The Hague，1997.

[7] LIETARD O，UNWIN T，GUILLOT D，et al. Fracture width LWD and drilling mud/LCM selection guidelines in naturally fractured reservoirs：European Petroleum Conference[C]. Milan，1996.

[8] VERGA F M，CARUGO C，CHELINI V，et al. Detection and characterization of fractures in naturally fractured reservoirs：SPE Annual Technical Conference and Exhibition[C]. Dallas，2000.

[9] 陈芊澍,文晓涛,何健,等. 基于极限学习机的裂缝带预测[J]. 石油物探,2021,60(1):149−156.

CHEN Qianshu,WEN Xiaotao,HE Jian,et al. Prediction of a fracture zone using an extreme learning machine[J]. Geophysical Prospecting for Petroleum,2021,60(1):149−156.

[10] 臧子婧,吴海波,张平松,等. 基于ABC–BP模型的煤层含气量预测[J]. 煤田地质与勘探,2021,49(2):152−158.

ZANG Zijing,WU Haibo,ZHANG Pingsong,et al. Prediction of coal seam gas content based on ABC–BP model[J]. Coal Geology & Exploration,2021,49(2):152−158.

[11] 宁永香,崔希民,崔建国. 基于ABC–GRNN组合模型的露天矿边坡变形预测[J]. 煤田地质与勘探,2023,51(3):65−72.

NING Yongxiang,CUI Ximin,CUI Jianguo. Deformation prediction of open–pit mine slope based on ABC–GRNN combined model[J]. Coal Geology & Exploration,2023,51(3):65−72.

[12] 娄高中,谭毅. 基于PSO–BP神经网络的导水裂隙带高度预测[J]. 煤田地质与勘探,2021,49(4):198−204.

LOU Gaozhong,TAN Yi. Prediction of the height of water flowing fractured zone based on PSO–BP neural network[J]. Coal Geology & Exploration,2021,49(4):198−204.

[13] 陈兰兰,杨雨云,肖海平,等. 基于GA–BP神经网络的露天矿边坡变形预测分析[J]. 有色金属科学与工程,2022,13(6):106−112.

CHEN Lanlan,YANG Yuyun,XIAO Haiping,et al. Prediction and analysis of open pit slope deformation based on a GA–BP neural network[J]. Nonferrous Metals Science and Engineering,2022,13(6):106−112.

[14] 颜建国,郑书闽,郭鹏程,等. 基于GA–BP神经网络的超临界CO2传热特性预测研究[J]. 化工学报,2021,72(9):4649−4657.

YAN Jianguo,ZHENG Shumin,GUO Pengcheng,et al. Prediction of heat transfer characteristics for supercritical CO2 based on GA–BP neural network[J]. CIESC Journal,2021,72(9):4649−4657.

[15] 杨利纳,李文竹,刘心. 基于灰色遗传BP神经网络的校园区间需水预测研究[J]. 水资源与水工程学报,2019,30(3):133−138.

YANG Lina,LI Wenzhu,LIU Xin. On campus interval water demand prediction based on grey genetic BP neural network[J]. Journal of Water Resources & Water Engineering,2019,30(3):133−138.

[16] 苏志伟,吴元梅,张丽娟,等. 基于MEA–GA–BP耦合模型的城市需水量预测[J]. 水电能源科学,2022,40(11):31−34.

SU Zhiwei,WU Yuanmei,ZHANG Lijuan,et al. Urban water demand prediction based on MEA–GA–BP coupling model[J]. Water Resources and Power,2022,40(11):31−34.

[17] 冷晟,付有为,马万太,等. 基于GA–BP神经网络的喷射成形锭坯形貌调控技术[J]. 华南理工大学学报(自然科学版),2023,51(2):27−34.

LENG Sheng,FU Youwei,MA Wantai,et al. Study on the morphology control technology of spray forming ingot billets based on GA–BP neural network[J]. Journal of South China University of Technology(Natural Science Edition),2023,51(2):27−34.

[18] 李广儒,张新,朱庆辉. 基于Adaboost的改进Elman神经网络港口吞吐量预测方法[J]. 重庆交通大学学报(自然科学版),2021,40(5):1−5.

LI Guangru,ZHANG Xin,ZHU Qinghui. Prediction method of port throughput with improved Elman neural network based on Adaboost[J]. Journal of Chongqing Jiaotong University(Natural Science),2021,40(5):1−5.

[19] 王小川，史峰，郁磊，等. MATLAB神经网络43个案例分析[M]. 北京：北京航空航天大学出版社，2013.

[20] 戴成. 碳酸盐岩钻井井筒–裂缝耦合流动特征研究[D]. 成都：西南石油大学，2019.

DAI Cheng. Research on coupling flowing characteristics of wellbore–fracture drilling in carbonate formation[D]. Chengdu：Southwest Petroleum University，2019.

[21] 李伟. 裂缝性地层堵漏技术研究[D]. 成都：西南石油大学，2013.

LI Wei. Research on sealing technology for fractured formation[D]. Chengdu：Southwest Petroleum University，2013.

[22] 彭浩,李黔,尹虎,等. Lietard天然裂缝宽度预测模型求解新方法[J]. 石油钻探技术,2016,44(3):72−76.

PENG Hao,LI Qian,YIN Hu,et al. A new solution method for the Lietard natural fracture width prediction model[J]. Petroleum Drilling Techniques,2016,44(3):72−76.

[23] 王雷雯. 基于BP神经网络的钻井防漏堵漏关键参数研究[D]. 成都：西南石油大学，2019.

WANG Leiwen. Research on key parameters of drilling leakage prevention and plugging based on BP neural network[D]. Chengdu：Southwest Petroleum University，2019.

[24] ZHANG Xinru,HOU Lei,LIU Jiaquan,et al. Energy consumption prediction for crude oil pipelines based on integrating mechanism analysis and data mining[J]. Energy,2022,254:124382.

[25] 陈志高,吴子豪,班亚,等. 基于调和分析及VMD–BP神经网络的感潮河段流量预报[J]. 武汉大学学报(信息科学版),2023,48(8):1389−1397.

CHEN Zhigao,WU Zihao,BAN Ya,et al. Discharge prediction in tidal reach using harmonic analysis and VMD–BP neural network[J]. Geomatics and Information Science of Wuhan University,2023,48(8):1389−1397.

[26] TANG Songzhen,LI Mingjia,WANG Feilong,et al. Fouling potential prediction and multi–objective optimization of a flue gas heat exchanger using neural networks and genetic algorithms[J]. International Journal of Heat and Mass Transfer,2020,152:119488.

[27] 高淑芝,裴志明,张义民. 动态自适应学习率优化的卷积神经网络轴承故障诊断方法[J]. 机械设计与制造,2023(7):211−214.

GAO Shuzhi,PEI Zhiming,ZHANG Yimin. Bearing fault diagnosis method based on convolutional neural network optimized by dynamic adaptive learning rate[J]. Machinery Design & Manufacture,2023(7):211−214.

[28] 尹会永,周鑫龙,郎宁,等. 基于SSA优化的GA–BP 神经网络煤层底板突水预测模型与应用[J]. 煤田地质与勘探,2021,49(6):175−185.

YIN Huiyong,ZHOU Xinlong,LANG Ning,et al. Prediction model of water inrush from coal floor based on GA–BP neural network optimized by SSA and its application[J]. Coal Geology & Exploration,2021,49(6):175−185.

[29] YE Kaiqiang,WANG Jianbin,GAO Hong,et al. Optimization of lapping process parameters of CP–Ti based on PSO with mutation and BPNN[J]. The International Journal of Advanced Manufacturing Technology,2021,117:2859−2866.

[30] BELAABED F,GOUDJIL K,ARABET L,et al. Utilization of computational intelligence approaches to estimate the relative head of PK–Weir for submerged flow[J]. Neural Computing and Applications,2021,33(19):13001−13013.

[31] YAN Hao,ZHANG Jixiong,ZHOU Nan,et al. Application of hybrid artificial intelligence model to predict coal strength alteration during CO₂ geological sequestration in coal seams[J]. Science of the Total Environment,2020,711:135029.