基于实时数据流的钻速频域特征匹配与自适应建模
Frequency Domain Feature Matching and Adaptive Modeling for Rate of Penetration Prediction Based on Real⁃Time Data Streams
针对深部复杂地层钻速预测中数据流非平稳及工况漂移难题,提出基于频域感知与自适应反馈的动态建模方法. 该方法利用滑动窗口与快速傅里叶变换提取实时数据流频域特征,通过余弦相似度量化主井与邻井工况匹配度. 创新构建基于反馈的动态阈值机制,实时调节判别标准:工况相似时复用历史模型,突变时采用主井累积+邻井深度匹配混合数据重训随机森林模型. 10口井实钻数据验证表明,该方法全井段预测平均达0.96,均方误差0.001 5;相较于固定阈值策略(复用率为0%),动态机制将模型复用率显著提升至18%. 进一步通过3口独立新井盲测验证模型泛化能力,平均达到0.91. 该研究有效解决了时域信号量化困难与模型适应性差的矛盾,在保证高精度的同时显著降低了计算开销,为复杂非平稳钻井工况下的实时钻速预测及智能钻井辅助决策提供了新的技术方案.
To address the challenges of non⁃stationary data streams and working condition drift in Rate of Penetration (ROP) prediction for deep complex formations, a dynamic modeling method based on frequency domain perception and adaptive feedback is proposed. The method utilizes sliding windows and Fast Fourier Transform (FFT) to extract frequency domain features from real⁃time data streams, quantifying the matching degree of working conditions between the main well and neighboring wells via cosine similarity. An innovative dynamic threshold mechanism based on feedback is constructed to adjust discrimination standards in real time: historical models are reused when conditions are similar, while the Random Forest model is retrained using hybrid data (main well accumulation plus neighbor well depth matching) during abrupt changes. Validation with real drilling data from 10 wells demonstrates that the method achieves an average of 0.96 across the entire well section, with a Mean Squared Error (MSE) of 0.001 5. Compared to the fixed threshold strategy (with a reuse rate of 0%), the dynamic mechanism significantly increases the model reuse rate to 18%.Furthermore, the generalization capability of the proposed method was validated through blind tests on three previously unseen wells, achieving an average R² of 0.91. This study effectively resolves the contradiction between the difficulty of quantifying time⁃domain signals and poor model adaptability. It significantly reduces computational overhead while ensuring high accuracy.The proposed method provides a new technical framework for real⁃time rate of penetration prediction and intelligent drilling decision support under complex non⁃stationary drilling conditions.
| [1] |
Chen, H. D., Jin, Y., Zhang, W. D., et al., 2022. Deep Neural Network Prediction of Mechanical Drilling Speed. Energies, 15(9): 3037. https://doi.org/10.3390/en15093037 |
| [2] |
Ehsan,B.,Ebrahim,D.B.,2022.Computational Prediction of the Drilling Rate of Penetration (ROP): A Comparison of Various Machine Learning Approaches and Traditional Models.Journal of Petroleum Science and Engineering,210.https://doi.org/10.1016/J.PETROL.2021.110033. |
| [3] |
Encinas, M. A., Tunkiel, A. T., Sui, D., 2022. Downhole Data Correction for Data⁃Driven Rate of Penetration Prediction Modeling. Journal of Petroleum Science and Engineering, 210: 109904. https://doi.org/10.1016/j.petrol.2021.109904 |
| [4] |
Hegde, C., Daigle, H., Millwater, H., et al., 2017. Analysis of Rate of Penetration (ROP) Prediction in Drilling Using Physics⁃Based and Data⁃Driven Models. Journal of Petroleum Science and Engineering, 159: 295-306. https://doi.org/10.1016/j.petrol.2017.09.020 |
| [5] |
Huang, X. L., Liu, D. T., Song, J. M., et al., 2021. Real⁃Time ROP Optimization Technology Based on Big Data and Artificial Intelligence. Oil Drilling & Production Technology, 43(4): 442-448 (in Chinese with English abstract). |
| [6] |
Li, B. Z., Yang, M. H., Xu, K., et al., 2024. Prediction Method for ROP Based on Attention Mechanism of Convolutional Neural Network. Science Technology and Engineering, 24(21): 8910-8916 (in Chinese with English abstract). |
| [7] |
Li, P., Yu, C., Wang, J.L., et al., 2024. Intelligent Prediction of Pore Pressure Using Real⁃Time Drilling Parameters. China Petroleum Machinery, 52(5):1-8 (in Chinese with English abstract). |
| [8] |
Mehmood, E., Anees, T., 2020. Challenges and Solutions for Processing Real⁃Time Big Data Stream: a Systematic Literature Review. IEEE Access, 8: 119123-119143. https://doi.org/10.1109/ACCESS.2020.3005268 |
| [9] |
Tu, B. R., Bai, K., Zhan, C., et al., 2024. Real⁃Time Prediction of ROP Based on GRU⁃Informer. Scientific Reports, 14: 2133. https://doi.org/10.1038/s41598⁃024⁃52261⁃7 |
| [10] |
Zhang, H. J., Zhang, G. F., Wang, G. N., et al., 2022. Classification and Prediction Method for ROP Based on Genetic Algorithm Optimization Random Forest Model. Science Technology and Engineering, 22(35): 15572-15578 (in Chinese with English abstract). |
| [11] |
Zhang, R., Zhu, Z. P., Li, D. Y., et al., 2024. Interpretable Real⁃Time Prediction of Drilling Parameters Based on Improved Sequential Network. China Petroleum Machinery, 52(4): 1-10 (in Chinese with English abstract). |
| [12] |
Zhang, Y., Zhou, B. F., Guo, W. X., et al., 2026. Spike Waveform Recognition for Strong⁃Motion Records Based on Light GBM⁃SVM Stacking Algorithm. Earth Science, 51(1): 185-198 (in Chinese with English abstract). |
| [13] |
Zhou, C. C., Jiang, J., Li, Q., et al., 2022. Research on Drilling Rate Prediction Model Based on Fusion Feature Selection Algorithm. Drilling Engineering, 49(4): 31-40 (in Chinese with English abstract). |
| [14] |
Zhu,J.B.,Liu,H.Y., Luan, S.C.,et al.,2025.Prediction of On⁃Site Peak Ground Motion Based on Machine Learning and Transfer Learning.Earth Science, 50(5):1842-1860 (in Chinese with English abstract). |
四川省自然科学基金项目青年基金“基于数字孪生的动态时变钻进工况自适应迁移模型研究”(2024NSFSC0817)
珠海市产学研项目“一种数字化工程勘察钻探装备的研发及其产业化”(2320004002792)
中海石油(中国)有限公司项目“南海西部油田上产2000万方钻完井关键技术研究”子课题“乐东10区超高温高压井综合提速技术研究”(CNOOC⁃KJ135ZDXM38ZJ05ZJ)
/
| 〈 |
|
〉 |