A Hybrid Model-Based System for Well Logging Cable Tension Prediction

doi:10.12388/j.issn.1673-2677.2025.02.007

Abstract

Abstract:

In cable logging operations，accurately regulating the cable tension is crucial to ensure the safe arrival of the logging instruments at the wellbore bottom and accurate data acquisition. In order to precisely predict the change of cable tension during well logging，a well logging cable tension prediction system based on the hybrid model was designed，which combines the physical model with in-depth understanding of the mechanical nature of the logging process and the data-driven model SC-PBiGRU with advantages in data processing and analysis. The system was validated using a large number of well logging data. The system can keep the maximum error of the prediction results within 5% and deliver stable prediction accuracy under complex geological conditions and equipment status. It is a powerful tool to provide technical support for tension regulation in cable logging operations.

Key words:

logging cable tension, hybrid model, logging cable tension prediction system, physical model, data-driven model

摘要：

在电缆测井作业中，测井电缆张力的准确调控是确保测井仪器安全抵达井底并准确获取数据的关键。为了准确预测测井电缆张力变化情况，设计了一种基于混合模型的测井电缆张力预测系统。该系统结合了物理模型对测井过程中力学特性的深入理解以及数据驱动模型SC-PBiGRU在数据处理和解析上的优势，以实现对测井电缆张力的精准预测。通过大量测井数据验证，该系统在预测结果上误差保持在5%以内，能在复杂地质条件和设备状态下保持稳定的预测精度，可以为电缆测井作业中的张力调控提供有力的技术支持。

关键词:

测井电缆张力, 混合模型, 测井电缆张力预测系统, 物理模型, 数据驱动模型

CLC Number:

TE19 ','1');return false;" target="_blank">
TE19

WU Runtong.

A Hybrid Model-Based System for Well Logging Cable Tension Prediction

[J]. Xinjiang Oil & Gas, 2025, 21(2): 64-.

吴润桐.

基于混合模型的测井电缆张力预测系统

[J]. 新疆石油天然气, 2025, 21(2): 64-.

References

［1］BRINDLE F，RAFIQUE M，THATHA R，et al. Use of new wireline conveyance technologies on an offshore abu dhabi well saves significant rig time and results in improved sonic and nuclear magnetic resonance data quality［C］. Abu Dhabi International Petroleum Exhibition and Conference. SPE，2018：D012S130R001.

［2］许磊，刘晓斌. 电缆测井智能深度监测系统设计［J］.石油管材与仪器，2023，9（2）：22-24.XU Lei，LIU Xiaobin. Design of intelligent depth monitoring system for wireline logging［J］.Petroleum Tubular Goods and Instruments，2023，9（2）：22-24.

［3］ALI M，ZHU P，HUOLIN M，et al.A novel machine learning approach for detecting outliers，rebuilding well logs，and enhancing reservoir characterization［J］.Natural Resources Research，2023，32（3）：1047-1066.

［4］LIU B，ROSTAMIAN A，KHEIROLLAHI M，et al. NMR log response prediction from conventional petrophysical logs with XGBoost-PSO framework［J］. Geoenergy Science and Engineering，2023，224：211561.

［5］于志军，汤清源，黄立华，等. 连续管水平井下入深度预测软件开发及应用［J］.石油机械，2020，48（11）：90-96.YU Zhijun，TANG Qingyuan，HUANG Lihua，et al. Development and application of software for predicting the running depth of coiled tubing in horizontal well［J］. China Petroleum Machinery，2020，48（11）：90-96.

［6］ELSHAHAWI H，GARCIA M D，GARCIA J P，et al.Real time monitoring and control of wireline logging operations［C］. SPWLA Annual Logging Symposium，SPWLA，2020：D363S021R001.

［7］李国锐. 电缆测井智能深度监测系统设计探讨［J］.中国石油和化工标准与质量，2024，44（12）：150-152.LI Guorui. Discussion on the design of intelligent depth monitoring system for wireline logging［J］.China Petroleum and Chemical Industry Standard and Quality，2024，44（12）：150-152.

［8］QU F，LIAO H，YAN X Y，et al. Data-driven wireline sticking risk assessment and control factor analysis［J］.Geoenergy Science and Engineering，2023，230：212220.

［9］赵耀. 基于深度学习的井下视频图像接箍识别校深研究［D］. 陕西西安：西安石油大学，2023.ZHAO Yao. Research on depth calibration of downhole video image coupling recognition based on deep learning［D］. Xi'an ，Shanxi：Xi'an Shiyou University，2023.

［10］KHAVARI S，DASHTI R，SHAKER H R，et al. High impedance fault detection and location in combined overhead line and underground cable distribution networks equipped with data loggers ［J］. Energies，2020，13 （9）：2331.

［11］王松，邱森，夏竹君，等. 基于流动保障技术对海上油气井井下安全阀下入深度的优化设计［J］.石油和化工设备，2024，27（5）：184-188.WANG Song，QIU Sen，XIA Zhujun，et al. Design optimization of downhole safety valve depth in offshore oil and gas wells based on flow assurance technology［J］.Petroleum and Chemical Equipment，2024，27（5）：184-188.

［12］FOLCH A，DEL VAL L，LUQUOT L，et al. Combining fiber optic DTS，cross-hole ERT and time-lapse induction logging to characterize and monitor a coastal aquifer［J］.Journal of Hydrology，2020，588：125050.

［13］MINGJIAN Y，LIU J，DU Z，et al. Research on a calculation model of cable tension and pumping displacement of a logging tool string of horizontal-well drillpipes［J］.SPE Journal，2024，29（2）：815-829.

［14］魏荣江，耿岱，郭帅，等. 测井作业中电缆井口张力计算［J］.佳木斯大学学报（自然科学版），2024，42（8）：66-70.WEI Rongjiang，GENG Dai，GUO Shuai，et al. Calculation of cable tension in logging operations［J］.Journal of Jiamusi University （Natural Science Edition），2024，42（8）：66-70.

［15］覃岚，董国昌，郭建勋，等. 基于分段摩阻因数的水平井延伸极限分析及应用［J］.东北石油大学学报，2022，46（2）：107-116.QIN Lan，DONG Guochang，GUO Jianxun，et al. Analysis and application of horizontal well extension limit based on segmented friction factor［J］.Journal of Northeast Petroleum University，2022，46（2）：107-116.

［16］严春满，王铖. 卷积神经网络模型发展及应用［J］.计算机科学与探索，2021，15（1）：27-46.YAN Chunman，WANG Cheng. Development and application of convolutional neural network model［J］.Journal of Frontiers of Computer Science & Technology，2021，15（1）：27-46.

［17］李勇成，李文骁，雷印杰. 基于特征增强与时空信息嵌入的涡扇发动机剩余寿命预测［J］.计算机应用研究，2024，41（4）：1001-1007.LI Yongcheng，LI Wenxiao，LEI Yinjie. Remaining useful life prediction of turbofan engines based on feature enhancement and spatio-temporal information embedding［J］. Application Research of Computer，2024，41（4）：1001-1007.

［18］杨菲，刘洋，常锁亮，等. 基于双向 GRU 和注意力机制的叠前地震孔隙度预测方法［J］.石油物探，2024，63（3）：598-609.YANG Fei，LIU Yang，CHANG Suoliang，et al. Prestack seismic porosity prediction method based on bidirectional gru and attention mechanism［J］. Geophysical Prospecting for Petroleum，2024，63（3）：598-609.

［19］YU C，VELU A，VINITSKY E，et al.The surprising effectiveness of ppo in cooperative multi-agent games［J］.Advances in Neural Information Processing Systems，2022，35：24611-24624.

［20］NING D，CHEN X，CHEN J，et al.PPO-MixClip：An energy scheduling algorithm for low-carbon parks［J］.Energy Reports，2024，124195-4207.

［21］张健飞，黄朝东，王子凡. 基于多头自注意力机制和卷积神经网络的结构损伤识别研究［J］.振动与冲击，2022，41（24）：60-71.ZHANG Jianfei，HUANG Chaodong，WANG Zifan. Research on structural damage identification based on multi-head self-attention mechanism and convolutional neural networks［J］.Journal of Vibration and Shock，2022，41（24）：60-71.

［22］尚天鹏，王友国. 基于 Adam 优化的卷积神经网络随机共振现象研究［J］.计算机与数字工程，2023，51（11）：2553-2556.SHANG Tianpeng，WANG Youguo. Research on stochastic resonance of convolutional neural network based on adam optimization［J］.Computer and Digital Engineering，2023，51（11）：2553-2556.

［23］冯琼，谢晓扬，王鹏辉，等. 基于鲸鱼优化算法-反向传播神经网络的钢筋混凝土耐久性预测［J/OL］.吉林大学学报（工学版），1-11［2025-05-30］.FENG Qiong，XIE Xiaoyang，WANG Penghui，et al. Prediction of reinforced concrete durability based on whale optimization algorithm-backpropagation neural network［J/OL］.Journal of Jilin University （Engineering and Technology Edition），1-11［2025-05-30］.

[1]	PAN Liyan, HAO Lihua, LIU Kaixin, SUN Xize, ZHU Zhenlong, ZHAO Yanxin, . Fracture Propagation Law of Hydraulic Fracturing in High-Salinity Reservoir of Fengcheng Formation in Mahu #br# [J]. Xinjiang Oil & Gas, 2023, 19(4): 20-28.
[2]	ZHANG Liwei. Experimental Research and Application of VHSD Dilatation Stimulation in Shallow Heavy Oil Reservoirs [J]. Xinjiang Oil & Gas, 2023, 19(2): 69-74.