AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Petroleum Science Article
PDF (3.7 MB)
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Original Paper | Open Access

Interpretation and characterization of rate of penetration intelligent prediction model

Zhi-Jun Peia, Xian-Zhi Songa,b( ), Hai-Tao Wangc, Yi-Qi Shia,b, Shou-Ceng Tiana,b, Gen-Sheng Lia,b
College of Petroleum Engineering, China University of Petroleum (Beijing), Beijing, 102249, China
State Key Laboratory of Petroleum Resources and Prospecting, Beijing, 102249, China
Kunlun Digital Technology Co., Ltd., Beijing, 102206, China

Edited by Jia-Jia Fei

Show Author Information

Abstract

Accurate prediction of the rate of penetration (ROP) is significant for drilling optimization. While the intelligent ROP prediction model based on fully connected neural networks (FNN) outperforms traditional ROP equations and machine learning algorithms, its lack of interpretability undermines its credibility. This study proposes a novel interpretation and characterization method for the FNN ROP prediction model using the Rectified Linear Unit (ReLU) activation function. By leveraging the derivative of the ReLU function, the FNN function calculation process is transformed into vector operations. The FNN model is linearly characterized through further simplification, enabling its interpretation and analysis. The proposed method is applied in ROP prediction scenarios using drilling data from three vertical wells in the Tarim Oilfield. The results demonstrate that the FNN ROP prediction model with ReLU as the activation function performs exceptionally well. The relative activation frequency curve of hidden layer neurons aids in analyzing the overfitting of the FNN ROP model and determining drilling data similarity. In the well sections with similar drilling data, averaging the weight parameters enables linear characterization of the FNN ROP prediction model, leading to the establishment of a corresponding linear representation equation. Furthermore, the quantitative analysis of each feature's influence on ROP facilitates the proposal of drilling parameter optimization schemes for the current well section. The established linear characterization equation exhibits high precision, strong stability, and adaptability through the application and validation across multiple well sections.

Keywords

Fully connected neural networkExplainable artificial intelligenceRate of penetrationReLU active functionDeep learningMachine learning

References

 
Abdulmalek, A.S., Salaheldin, E., Abdulazeez, A., et al., 2018. Prediction of rate of penetration of deep and tight formation using support vector machine. SPE Kingdom of Saudi Arabia Annual Technical Symposium and Exhibition. Dammam, Saudi Arabia.
Crossref
 
Amadi, K., Iyalla, I., Prabhu, R., 2021. Modeling and predicting performance of autonomous rotary drilling system using machine learning techniques. SPE Nigeria Annual Int. Conf. Exhib. Lagos, Nigeria. https://doi.org/10.2118/208450-MS.
Crossref
 

Bardhan, A., Kardani, N., GuhaRay, A., et al., 2021. Hybrid ensemble soft computing approach for predicting penetration rate of tunnel boring machine in a rock environment. J. Rock Mech. Geotech. Eng. 13 (6), 1398–1412. https://doi.org/10.1016/j.jrmge.2021.06.015.
Crossref Google Scholar
 

Bingham, M., 1964. How to interpret drilling in the performance region. Oil Gas J. 62, 173–176.
Google Scholar
 

Bourgoyne, A.T., Young, F.S., 1974. A multiple regression approach to optimal drilling and abnormal pressure detection. Soc. Petrol. Eng. J. 14 (4), 371–384. https://doi.org/10.2118/4238-pa.
Crossref Google Scholar
 
Bourgoyne, A.T., Millheim, K.K., Chenevert, M.E., et al., 1986. Applied Drilling Engineering, 2. Society of Petroleum Engineers Richardson.
Crossref
 

Brito, L.C., Susto, G.A., Brito, J.N., et al., 2022. An explainable artificial intelligence approach for unsupervised fault detection and diagnosis in rotating machinery. Mech. Syst. Signal Process. 163. https://doi.org/10.1016/j.ymssp.2021.108105.
Crossref Google Scholar
 
Elmgerbi, A.M., Ettinger, C.P., Tekum, P.M., et al., 2021. Application of Machine Learning Techniques for Real Time Rate of Penetration Optimization. SPE/IADC Middle East Drilling Technology Conference and Exhibition. Abu Dhabi, UAE.
Crossref
 

Encinas, M.A., Tunkiel, A.T., Sui, D., 2022. Downhole data correction for data-driven rate of penetration prediction modeling. J. Petrol. Sci. Eng. 210. https://doi.org/10.1016/j.petrol.2021.109904.
Crossref Google Scholar
 

Ersoy, A., Waller, M., 1995. Wear characteristics of PDC pin and hybrid core bits in rock drilling. Wear 188 (1–2), 150–165.
Crossref Google Scholar
 

Etesami, D.G., Shirangi, M., Zhang, W.J., 2021. A Semiempirical model for rate of penetration with application to an offshore gas field. SPE Drill. Complet. 36 (1), 29–46. https://doi.org/10.2118/202481-pa.
Crossref Google Scholar
 

Garcia-Gavito, D., Azar, J., 1994. Proper nozzle location, bit profile, and cutter arrangement affect PDC-bit performance significantly. SPE Drill. Complet. 9 (3), 167–175.
Crossref Google Scholar
 

Gers, F.A., Schmidhuber, J., Cummins, F., 2000. Learning to forget: continual prediction with LSTM. Neural Comput. 12 (10), 2451–2471. https://doi.org/10.1162/089976600300015015.
Crossref Google Scholar
 

Gupta, I., Tran, N., Devegowda, D., et al., 2020. Looking ahead of the bit using surface drilling and petrophysical data: machine-learning-based real-time geosteering in volve field. SPE J. 25 (2), 990–1006. https://doi.org/10.2118/199882-pa.
Crossref Google Scholar
 
Hansson, M., Olsson, C., 2017. Feedforward Neural Networks with ReLU Activation Functions Are Linear Splines. Bachelor’s Theses in. Mathematical Sciences. Lund University.
 

Hazbeh, O., Aghdam, S.K.Y., Ghorbani, H., et al., 2021. Comparison of accuracy and computational performance between the machine learning algorithms for rate of penetration in directional drilling well. Petrol. Res. 6 (3), 271–282. https://doi.org/10.1016/j.ptlrs.2021.02.004.
Crossref Google Scholar
 
Hegde, C., Wallace, S., Gray, K., 2015. Using Trees, Bagging, and Random Forests to Predict Rate of Penetration during Drilling. SPE Middle East Intelligent Oil and Gas Conference and Exhibition. Abu Dhabi, UAE. https://doi.org/10.2118/176792-MS.
Crossref
 

Lawal, A.I., Kwon, S., Onifade, M., 2021. Prediction of rock penetration rate using a novel antlion optimized ANN and statistical modelling. J. Afr. Earth Sci. 182. https://doi.org/10.1016/j.jafrearsci.2021.104287.
Crossref Google Scholar
 
Li, Y., Samuel, R., 2019. Prediction of Penetration Rate Ahead of the Bit through RealTime Updated Machine Learning Models. In: SPE/IADC International Drilling Conference and Exhibition. The Hague, the Netherlands.
Crossref
 

Mahmoodzadeh, A., Nejati, H.R., Mohammadi, M., et al., 2022. Forecasting tunnel boring machine penetration rate using LSTM deep neural network optimized by grey wolf optimization algorithm. Expert Syst. Appl. 209. https://doi.org/10.1016/j.eswa.2022.118303.
Crossref Google Scholar
 

Mazen, A.Z., Rahmanian, N., Mujtaba, I., et al., 2021. Prediction of penetration rate for PDC bits using indices of rock drillability, cuttings removal, and bit wear. SPE Drill. Complet. 36 (2), 320–337. https://doi.org/10.2118/204231-pa.
Crossref Google Scholar
 

Nasiri, H., Homafar, A., Chelgani, S.C., 2021. Prediction of uniaxial compressive strength and modulus of elasticity for Travertine samples using an explainable artificial intelligence. Results in Geophysical Sciences 8. https://doi.org/10.1016/j.ringps.2021.100034.
Crossref Google Scholar
 
Negara, A., Saad, B., 2020. Combining Insight from Physics-Based Models into DataDriven Model for Predicting Drilling Rate of Penetration. In: International Petroleum Technology Conference. Dammam, Saudi Arabia.
Crossref
 

Pei, Z., Song, X., Ji, Y., et al., 2023. Wide and deep cross network for the rate of penetration prediction. Geoenergy Sci. Eng. 212066. https://doi.org/10.1016/j.geoen.2023.212066.
Crossref Google Scholar
 

Pei, Z., Song, X., Wang, P., et al., 2022. Intelligent prediction for rate of penetration based on support vector machine regression. Xinjiang Oil&Gas 18 (1), 14–20. https://doi.org/10.12388/j.issn.1673-2677.2022.01.002.
Crossref Google Scholar
 

Soares, C., Armenta, M., Panchal, N., 2020. Enhancing reamer drilling performance in deepwater Gulf of Mexico Wells. SPE Drill. Complet. 35 (3), 329–356.
Crossref Google Scholar
 

Tsoka, T., Ye, X., Chen, Y., et al., 2022. Explainable artificial intelligence for building energy performance certificate labelling classification. J. Clean. Prod. 355. https://doi.org/10.1016/j.jclepro.2022.131626.
Crossref Google Scholar
 
Van Lent, M., Fisher, W., Mancuso, M., 2004. An explainable artificial intelligence system for small-unit tactical behavior. In: Proceedings of the national conference on artificial intelligence. Menlo Park, CA; Cambridge, MA; London; AAAI Press; MIT Press.
 

Warren, T., 1987. Penetration-rate performance of roller-cone bits. SPE Drill. Eng. 2 (1), 9–18.
Crossref Google Scholar
 

Xiong, C., Huang, Z., Yang, R., et al., 2020. Comparative analysis cutting characteristics of stinger PDC cutter and conventional PDC cutter. J. Petrol. Sci. Eng. 189, 106792. https://doi.org/10.1016/j.petrol.2019.106792.
Crossref Google Scholar
 

Young, F., 1969. Computerized drilling control. J. Petrol. Technol. 21 (4), 483–496.
Crossref Google Scholar
 

Zhang, C., Cho, S., Vasarhelyi, M., 2022. Explainable artificial intelligence (XAI) in auditing. Int. J. Account. Inf. Syst. https://doi.org/10.1016/j.accinf.2022.100572.
Crossref Google Scholar
 
Zhang, H., Lu, B., Liao, L. et al., 2021. Combining Machine Learning and Classic Drilling Theories to Improve Rate of Penetration Prediction. SPE/IADC Middle East Drilling Technology Conference and Exhibition. Abu Dhabi, UAE. https://doi.org/10.2118/202202-MS.
Crossref
 
Zhou, F., Fan, H., Liu, Y., et al., 2022. Application of Xgboost Algorithm in Rate of Penetration Prediction with Accuracy. International Petroleum Technology Conference. Saudi Arabia, Riyadh.
Crossref
Petroleum Science
Volume 21 Issue 1,
February 2024
Pages 582-596
DOI: 10.1016/j.petsci.2023.10.011
Cite this article:
Pei Z-J, Song X-Z, Wang H-T, et al. Interpretation and characterization of rate of penetration intelligent prediction model. Petroleum Science, 2024, 21(1): 582-596. https://doi.org/10.1016/j.petsci.2023.10.011

44

Views

0

Downloads

1

Crossref

0

Web of Science

1

Scopus

0

CSCD

Altmetrics
Received: 13 September 2022
Revised: 16 October 2023
Accepted: 16 October 2023
Published: 16 October 2023
© 2023 The Authors.

This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
Return