In order to prevent wellbore instability, wellbore collapse, and even severe safety incidents such as blowouts and overflow caused by casing damage in water injection wells, a precise prediction method was developed to identify casing failure in advance. ISSA (improved sparrow search algorithm) was used to optimize RF (random forest) model for predicting casing damage in injection wells within the following year. ISSA was enhanced by initializing the population using circle chaotic mapping and introducing Gaussian disturbance to improve its global search capability and convergence speed. The optimized ISSA was then employed to select the hyperparameters of RF model, and an ISSA-RF prediction model for casing damage was constructed. The results show that the model achieved a prediction accuracy of 0.92, with recall rates of 0.92, 0.89, and 0.90 for each category, respectively. It is concluded that the proposed method outperforms other comparative models in terms of prediction accuracy and recall, demonstrating its effectiveness and advancement. This study provides important technical support for casing damage prediction in oilfield water injection wells.
YE Nai-yu, KE Fu-yang, DUAN Lian, ZHANG Zi-xuan.
Prediction of Casing Damage in Oilfield Water Injection Wells Based on ISSA-RF Model[J].
Science Technology and Engineering, 2026, 26(10): 4276-4287 DOI:10.12404/j.issn.1671-1815.2502628
ZhangZheng, YuanJianpeng, MaLi, et al. Influence of thermal physical properties of drilling fluid on wellbore temperature and pressure during geothermal well drilling[J]. Science Technology and Engineering, 2025, 25(7): 2767-2775.
LiHengfeng, LiLin, ZhaoZhifeng. Hyperparameter optimization and interpretation of a lost circulation prediction model: a case study of the Marun Oilfield in Iran[J]. Science Technology and Engineering, 2024, 24(35): 15006-15013.
LiJunfeng, LiuJintang, YangLei, et al. Analysis of the mechanism and main control factors of casing damage in Daqing Oilfield water injection development[J]. Oil Production Engineering, 2023(3): 57-65, 106.
[7]
GholamiR, RasouliV, AadnoyB, et al. Geomechanical and numerical studies of casing damages in a reservoir with solid production[J]. Rock Mechanics and Rock Engineering, 2016, 49(4): 1441-1460.
WangPeng. Research on stress strain and casing damage mechanism simulation based on surface deformation in Daqing Sazhong Oilfield[D]. Beijing: University of Chinese Academy of Sciences, 2022.
JiangXueyan, ZhangShujuan, WangZhiguo, et al. Risk assessment method for geological factor casing damage based on determi-nistic coefficients[J]. Daqing Petroleum Geology and Development, 2016, 35(6): 104-108.
LiuXuhua, WangHaihua, WangXin, et al. Prevention and control technology for casing damage in Jurassic reservoirs[J]. Application in Petrochemical Industry, 2024, 43(6): 73-76.
[18]
ChangS, AoW, ZhaoX, et al. Research on casing damage mechanism and prevention and control under creep behavior of salt-gypsum layer[J]. Geoenergy Science and Engineering, 2024, 234: 1-14.
HeQiuli. Establishment and application of reservoir geological knowledge base in Daqing Lasaxing Oilfield[J]. China Petroleum and Chemical Industry Standards and Quality, 2023, 43(8): 7-9, 15.
LiRuowen, LiuShaohu, XuZeqing, et al. Erosion and wear prediction of fuel nozzles based on machine learning algorithms[J]. Science Technology and Engineering, 2025, 25(11): 4526-4533.
ShengJiahao, LiuLi, LiuZhaohui, et al. Performance prediction method of asphalt mixture based on BP neural network optimized by gene-tic algorithm[J]. Science Technology and Engineering, 2025, 25(3): 1214-1224.
HeJingqi, ZhengZhichao, MengFanshun. Casing damage prediction based on support vector machine model optimized by genetic algorithm[J]. Journal of Inner Mongolia Normal University (Natural Science Edition in Chinese), 2023, 52(4): 392-398.
CaoMaojun, WuShengkun. Multi arm logging casing damage detection method based on Bayesian neuralnetwork[J]. Computer Technology and Development, 2024, 34(8): 108-115.
TangQing, LiJuan, YangTao, et al. Development and application of risk prediction and prevention software for oil and gas well casing damage[J]. Petrochemical Applications, 2024, 43(4): 19-26, 42.
ZhaoJianmin, ZhangJunbo, CuiJiaxin. Research on stacking based casing damage prediction method[J]. Computer and Digital Engineering, 2024, 52(6): 1685-1690.
[39]
MohamadA Y, PayamG K, MarwanA, et al. Predictive data analytics application for enhanced oil recovery in a mature field in the Middle East[J]. Petroleum Exploration and Development, 2020, 47(2): 393-399.
[40]
NoshiC I, NoynaertS F, SchubertJ J. Casing failure data analy-tics: a novel data mining approach in predicting casing failures for improved drilling performance and production optimization[J]. SPE-Society of Petroleum Engineer, 2018(18): 1-24.
[41]
NoshiC, SamuelN, JeromeS. Data mining approaches for casing failure prediction and prevention[J]. International Petroleum Technology Conference, 2019.DOI: 10.2523/IPTC-19311-MS.
[42]
张珺博. 基于集成学习的套损井预测方法研究[D]. 大庆: 东北石油大学, 2022.
[43]
ZhangJunbo. Research on prediction method of casing damage wells based on ensemble learning[D]. Daqing: Northeast Petro-leum University, 2022.
LiangQichang. Optimization of LSSVM based on improved sparrow algorithm for building settlement prediction[J]. China New Technology and New Products, 2024(23): 99-101.