Lost circulation is a common complex condition in drilling operations that severely compromises safety and efficiency. Most existing early-warning models focus mainly on predicting when lost circulation occurs, with insufficient attention to its severity and risk assessment. To address this gap, an intelligent lost circulation diagnostic model integrating logging time series data and multi-scale decomposition was proposed, combining ICEEMDAN(improved complete ensemble empirical mode decomposition with adaptive noise), IMF (intrinsic mode function) screening criteria, and SVM (support vector machine) optimized by PSO (particle Swarm optimization). First, from drilling and completion reports of Iran’s Azadegan Oilfield, logging parameters that effectively characterize different leakage degrees were selected. Second, the logging data undergo multi-scale decomposition via ICEEMDAN. IMF components strongly correlated with leakage characteristics were filtered using Pearson correlation coefficients and energy entropy, and the data are reconstructed to eliminate medium-to-high-frequency noise. Finally, a diagnostic model was built with the PSO-optimized SVM, in which the PSO optimizes the penalty coefficient C and kernel parameter γ, to enhance accuracy and generalization. Results indicate the ICEEMDAN-PSO-SVM model’s test set accuracy exceeds 98%, outperforming PSO-SVM, RF (random forest) and SVM across key performance metrics. This study offers valuable support for mitigating drilling safety risks and enhancing engineering efficiency and economic benefits.
LIU Hong, LI Jun, YANG Hong-wei, QI Wen-li, LIU Gong-hui, YANG Yu-long.
Intelligent Lost Circulation Diagnosis Model Based on Logging Time Series Data and Multi-scale Decomposition: Azadegan Oilfield in Iran[J].
Science Technology and Engineering, 2026, 26(26): 11297-11307 DOI:10.12404/j.issn.1671-1815.2507596
ZhangR H, SuN Y, LiaoL M, et al. Effects of different thermal insulated drill pipe deployment methods on wellbore temperature control in ultra-deep wells[J]. Petroleum Science, 2025, 22(10): 4174-4194.
GaoYangdong, LaiWeicheng, ZhangXintao, et al. New progress and future directions of CNOOC oil and gas exploration[J]. China Offshore Oil and Gas, 2024, 36(3): 1-10.
ChenWeiting, ZhuZhongxi, WuDesheng, et al. Well leakage location method based on transient pressure wave neighbourhood difference calculation[J]. Science Technology and Engineering, 2025, 25(34): 14649-14661.
[6]
AoY, ZhuZ X, ZhangN, et al. Solution and analysis of wellbore temperature and pressure field coupling model under lost circulation[J]. ACS Omega, 2022, 7(32): 28675-28684.
[7]
WangN, WangJ, SunB, et al. Study of transient responses in the APWD measurements during gas influx[J]. Journal of Natural Gas Science and Engineering, 2016, 35: 522-531.
LinYanfeng, MinChao, DaiBoren, et al. Prediction of drilling leakage accident based on dynamic features and deep neural network[J]. Journal of Xi’an Shiyou University(Natural Science Edition), 2022, 37(3): 64-69.
ZhangKuangsheng, GongChenxing, LuHongjun, et al. Intelligent early warning model and intelligent reasoning method based on integrated learning for loss circulation[J]. Oil Drilling & Production Technology, 2023, 45(1): 47-54.
DuanShiming, SongXianzhi, YaoXuezhe, et al. Intelligent warning model for overflow under constraints of pressure and rules[J]. China Petroleum Machinery, 2025, 53(1): 1-9.
YangMiao, RenLing, WangShuang, et al. Noise reduction method of capacitive cotton seed monitoring signal based on CEEMDAN-wavelet threshold[J]. Transactions of the Chinese Society for Agricultural Machinery, 2025, 56(5): 71-81.
LiKaiyang, HanTuanjun, LiuQingjiang. Gesture recognition method based on surface electromyography (sEMG) entropy features and improved PSO-SVM[J]. Science Technology and Engineering, 2025, 25(35): 15155-15164.
XingZhao, MengXiaojun, YuanJingjing, et al. Landslides hazard assessment based on SVM-GBDT and gradient boosting decision tree model supported by information quantity[J]. Science Technology and Engineering, 2025, 25(7): 2712-2720.
[20]
DengS, PeiC Y, YanX P, et al. Lost circulation prediction method based on an improved fruit fly algorithm for support vector machine optimization[J]. ACS Omega, 2023, 8(36): 32838-32847.
BaiKai, DaiShengsheng, ZhangZhaoshuo, et al. Lost circulation prediction based on improved random forest algorithmoptimized by swarm intelligence algorithm[J]. Modern Electronics Technique, 2025, 48(14): 159-168.
SunJinsheng, YangJingbin, BaiYingrui, et al. Research progress and development of deep and ultra-deep drilling fluid technology[J]. Petroleum Exploration and Development, 2024, 51(4): 889-898.
LiuYingbiao, XuShengjiang, TianLong, et al. Research progress on earlywarning technology of drilling complex accidents[J]. Xinjiang Oil & Gas, 2025, 21(2): 15-23.
[29]
MardaniradS, WoodD A, ZakeriH. The application of deep learning algorithms to classify subsurface drilling lost circulation severity in large oil field datasets[J]. SN Applied Sciences, 2021, 3(9): 785.
LiHengfeng, LiLin, ZhaoZhifeng. Drilling fluid lost-circulation prediction model hyperparameter optimization and interpretation: a case study of the Marun Field in Iran[J]. Science Technology and Engineering, 2024, 24(35): 15006-15013.
LiSiqi, XiaMao, LuSizhao, et al. Lightweight OLTC mechanical fault recognition method based on secondary decomposition time-frequency maps and SE-DSMC-BSA[J] Journal of Vibration and Shock, 2025, 44(11): 268-279, 308.
ChenYonggao, ZhongZhenyu. Research on modal modal decomposition of response signals for a bridge structure based on the improved EEMD[J]. Journal of Vibration and Shock, 2019, 38(10): 23-30.
ZhangLong, SongChengyang, ZouYoujun, et al. A rolling bearingfault diagnosis method based on VMD multi-feature fusion and PSO-SVM[J] Machine Design & Research, 2019, 35(6): 96-104.
[38]
VladimirN. Vapnik. The nature of statistical learning theory[M]. New York: Springe, 1995.
[39]
ZhuZ X, LiuH, WuD S, et al. A diagnosis method for loss of circulation based on transient-pressure wave analysis and particle swarm optimization[J]. Physics of Fluids, 2024, 36(7): 077121.
ShengWu, FanBinbin. Application of the EMD-GRU combined model for predicting gas volume fraction in coal mines[J]. Journal of Safety and Environment, 2025, 25(4): 1339-1348.
ChenKaifeng, YangXuewen, SongXianzhi, et al. An intelligent diagnosis method for lost circulation based on engineering logging data[J]. China Petroleum Machinery, 2022, 50(11): 16-22.