Research on Well Depth Tracking Calculation Method Based on Branching Parallel Neural Networks
Abstract
1. Introduction
2. Well Logging Data Preprocessing
2.1. Standardized Processing of Data
2.2. Outlier Culling
3. Calculation Model for Downhole Depth Tracking
3.1. Multi-Branch Parallel Neural Networks
3.2. Evaluation Methodology
4. Instance Calculation
5. Conclusions
- (1)
- For the first time, the calculation method and evaluation method of underground well depth tracking were proposed, the traditional neural network was innovatively improved in structure, and a multi-branch parallel neural network was designed and used to realize underground well depth tracking. Compared to the original BP neural network, the MAE improved by 66.55%, and the R2 evaluation method improved by 61.82%. An evaluation method for point-by-point analysis and comparison of well depth was established.
- (2)
- In pass instance validation, the multi-branch parallel neural network takes 129 s after 1000 iterations of training, the average error of the point-by-point comparison calculated by the example is 0.012 m, and the maximum error is 0.268 m, which can meet the engineering requirements of underground depth tracking.
- (3)
- In this paper, the five parameters of drilling, pressure, speed, displacement, pump pressure, and torque, are selected to predict and calculate the downhole depth tracking. If the data is collected downhole, more and more accurate parameters such as drill bit pressure drop and geological parameters can be collected, and the effect of prediction calculation will be better.
- (4)
- By optimizing the structure of the traditional artificial BP neural network, a multi-branch parallel neural network is proposed, which solves the problems of the traditional BP neural network easily falling into the local optimal solution instead of the global optimal solution, resulting in a decrease in accuracy, and effectively improves the operation accuracy and operation time.
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Zhang, S.N. Optimization of horizontal well drilling parameters and technology. Chem. Eng. Equip. 2020, 2020, 81–82. [Google Scholar] [CrossRef]
- Noureldin, A.; Tabler, H.; Irvine-Halliday, D.; Mintchev, M.P. A new borehole surveying technique for horizontal drilling processes using one fiber optic gyroscope and three accelerometers. In Proceedings of the SPE/IADC Drilling Conference and Exhibition, New Orleans, LA, USA, 23 February 2000. [Google Scholar] [CrossRef]
- Imanian, A.; Ghassemi, M.; Karbasian, M. Bit pressure control during drilling operation using engineering process control. Energy Sources Part A Recovery Util. Environ. Eff. 2018, 40, 2193–2202. [Google Scholar] [CrossRef]
- Yan, B.; Zhang, X.; Tang, C.; Wang, X.; Yang, Y.; Xu, W. A random forest-based method for predicting borehole trajectories. Mathematics 2023, 11, 1297. [Google Scholar] [CrossRef]
- Wang, H.; Xu, Y.; Tang, S.; Wu, L.; Cao, W.; Huang, X. Well log prediction while drilling using seismic impedance with an improved LSTM artificial neural networks. Front. Earth Sci. 2023, 11, 1153619. [Google Scholar] [CrossRef]
- Shan, L.; Liu, Y.; Tang, M.; Yang, M.; Bai, X. CNN-BiLSTM hybrid neural networks with attention mechanism for well log prediction. J. Pet. Sci. Eng. 2021, 205, 108838. [Google Scholar] [CrossRef]
- Li, Q.; Qu, F.T.; He, J.B. Prediction model of ROP of drilling machinery based on PSO-BP. Sci. Technol. Eng. 2021, 21, 7984–7990. [Google Scholar] [CrossRef]
- Lawal, A.I.; Kwon, S.; Onifade, M. Prediction of rock penetration rate using a novel antlion optimized ANN and statistical modelling. J. Afr. Earth Sci. 2021, 182, 104287. [Google Scholar] [CrossRef]
- Su, K.H.; Da, W.H.; Li, M.; Li, H.; Wei, J. Research on a drilling rate of penetration prediction model based on the improved chaos whale optimization and back propagation algorithm. Geoenergy Sci. Eng. 2024, 240, 213017. [Google Scholar] [CrossRef]
- Avcı, E. An artificial neural network approach for the prediction of water-based drilling fluid rheological behaviour. Int. Adv. Res. Eng. J. 2018, 2018, 124–131. Available online: https://api.semanticscholar.org/CorpusID:119062297 (accessed on 15 September 2025).
- Zhai, Y.J.; Yu, C.Z.; Gao, X. A radar trace processing method based on DBSCAN clustering. Shipboard Electron. Countermeas. 2021, 44, 58–61. [Google Scholar] [CrossRef]
- Liu, J.B.; Wei, H.Z.; Zhao, J.F. A new three-dimensional ROP equation considering the influence of bit speed. Pet. Drill. Technol. 2015, 43, 52–57. [Google Scholar] [CrossRef]
- Zhang, S.; Gong, Y.H.; Wang, J.J. Development of deep convolution neural network and its application in the field of computer vision. Chin. J. Comput. 2019, 42, 453–482. [Google Scholar] [CrossRef]
- Suppes, R.; Ebrahimi, A.; Krampe, J. Optimising casing milling rate of penetration (ROP) by applying the concept of mechanical specific energy (MSE): A justification of the concept’s applicability by literature review and a pilot study. J. Pet. Sci. Eng. 2019, 179, 894–903. [Google Scholar] [CrossRef]
- Li, W.W.; Yi, P.T.; Li, L.Y. Identification and dimensionless treatment of outliers in comprehensive evaluation. Oper. Res. Manag. Sci. 2018, 27, 173–178. Available online: https://qikan.cqvip.com/Qikan/Article/Detail?id=675124934 (accessed on 15 September 2025).
- Li, J.; Yao, X.; Wang, X. Multiscale local features learning based on BP neural network for rolling bearing intelligent fault diagnosis. Measurement 2019, 153, 107419. [Google Scholar] [CrossRef]
- Liang, H.B.; Zou, J.L.; Liang, W.L. An early intelligent diagnosis model for drilling overflow based on GA-BP algorithm. Cluster Comput. 2019, 22, 10649–10668. [Google Scholar] [CrossRef]
- Liu, J.L. Application of BP neural network prediction model to the electromagnetic fields. Electr. Power Technol. Environ. Prot. 2017, 33, 45–48. Available online: https://d.wanfangdata.com.cn/periodical/dlhjbh201704002 (accessed on 15 September 2025).
- Yuan, S.; Wang, K.; Shan, Y.; Yang, J.F. Multiscale target detection algorithm based on multi-branch parallel atrous convolution. J. Comput.-Aided Des. Comput. Graph. 2021, 33, 864–872. Available online: https://qikan.cqvip.com/Qikan/Article/Detail?id=7104901489 (accessed on 15 September 2025).
- Yang, Q.; Wang, C.W. Research on global stock index prediction based on deep learning LSTM neural network. Stat. Res. 2019, 36, 65–77. [Google Scholar] [CrossRef]
- Yang, Z.Z.; Kuang, N.; Fan, L. Overview of image classification algorithms based on convolutional neural network. J. Signal Process. 2018, 34, 1474–1489. [Google Scholar] [CrossRef]
- Kingma, D.P.; Ba, J.L. Adam: A method for stochastic optimization. arXiv 2014. [Google Scholar] [CrossRef]
- Kang, Q.K.; Lu, L.J. Application of random forest algorithm in lithology classification of logging wells. Glob. Geol. 2020, 39, 398–405. [Google Scholar] [CrossRef]
- Zheng, Y.Z.; Niu, L.K.; Xiong, X.Y. Fault diagnosis of cylindrical roller bearing cage based on one-dimensional convolutional neural network. J. Vib. Shock 2021, 40, 230–238+285. [Google Scholar] [CrossRef]
- Zhuo, P.C.; Yan, J.; Zheng, M.M. GA-OIHF-Elman neural network algorithm for rolling bearing life cycle fault diagnosis. J. Shanghai Jiaotong Univ. 2021, 55, 1255–1262. [Google Scholar] [CrossRef]
- Mokhtari, A.; Ozdaglar, A.; Pattathil, S. A unified analysis of extra-gradient and optimistic gradient methods for saddle point problems: Proximal point approach. arXiv 2019. [Google Scholar] [CrossRef]
- SY/T 6243-2009; Technical Specification for Fire and Explosion Prevention in Oil and Gas Drilling, Development, Storage and Transportation. National Energy Admin: Beijing, China, 2009.
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Liu, W.; Ma, B.; Yu, X. Research on Well Depth Tracking Calculation Method Based on Branching Parallel Neural Networks. Processes 2025, 13, 3147. https://doi.org/10.3390/pr13103147
Liu W, Ma B, Yu X. Research on Well Depth Tracking Calculation Method Based on Branching Parallel Neural Networks. Processes. 2025; 13(10):3147. https://doi.org/10.3390/pr13103147
Chicago/Turabian StyleLiu, Weikai, Baoquan Ma, and Xiaolei Yu. 2025. "Research on Well Depth Tracking Calculation Method Based on Branching Parallel Neural Networks" Processes 13, no. 10: 3147. https://doi.org/10.3390/pr13103147
APA StyleLiu, W., Ma, B., & Yu, X. (2025). Research on Well Depth Tracking Calculation Method Based on Branching Parallel Neural Networks. Processes, 13(10), 3147. https://doi.org/10.3390/pr13103147