Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Dec 21;8(1):934-945.
doi: 10.1021/acsomega.2c06308. eCollection 2023 Jan 10.

An Advanced Long Short-Term Memory (LSTM) Neural Network Method for Predicting Rate of Penetration (ROP)

Hui Ji  1   2 , Yishan Lou  1   2 , Shuting Cheng  1 , Zelong Xie  1   2 , Liang Zhu  1   2
Affiliations

An Advanced Long Short-Term Memory (LSTM) Neural Network Method for Predicting Rate of Penetration (ROP)

Hui Ji et al. ACS Omega. .

Abstract

Rate of penetration (ROP) is an essential factor in drilling optimization and reducing the drilling cycle. Most of the traditional ROP prediction methods are based on building physical model and single intelligent algorithms, and the efficiency and accuracy of these prediction methods are very low. With the development of artificial intelligence, high-performance algorithms make reliable prediction possible from the data perspective. To improve ROP prediction efficiency and accuracy, this paper presents a method based on particle swarm algorithm for optimization of long short-term memory (LSTM) neural networks. In this paper, we consider the Tuha Shengbei block oilfield as an example. First, the Pearson correlation coefficient is used to measure the correlation between the characteristics and eight parameters are screened out, namely, the depth of the well, gamma, formation density, pore pressure, well diameter, drilling time, displacement, and drilling fluid density. Second, the PSO algorithm is employed to optimize the super-parameters in the construction of the LSTM model to the predict ROP. Third, we assessed model performance using the determination coefficient (R 2), root mean square error (RMSE), and mean absolute percentage error (MAPE). The evaluation results show that the optimized LSTM model achieves an R 2 of 0.978 and RMSE and MAPE are 0.287 and 12.862, respectively, hence overperforming the existing methods. The average accuracy of the optimized LSTM model is also improved by 44.2%, indicating that the prediction accuracy of the optimized model is higher. This proposed method can help to drill engineers and decision makers to better plan the drilling operation scheme and reduce the drilling cycle.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing financial interest.

Figures

Figure 1
Figure 1
Workflow chart of ROP forecasting.
Figure 2
Figure 2
Raw collection data. (a) Logging data. (b) Mud-logging data.
Figure 3
Figure 3
Heat map of correlation between features.
Figure 4
Figure 4
Logical structure diagram of the LSTM neural network.
Figure 5
Figure 5
Workflow of particle swarm optimization algorithm.
Figure 6
Figure 6
The structure of the PSO-LSTM model.
Figure 7
Figure 7
Loss curve of the model training process. (a) The training process of the LSTM model; (b) the training process of the PSO-LSTM model.
Figure 8
Figure 8
Prediction results of ROP: (a) prediction results of the LSTM model; (b) prediction results of the PSO-LSTM model.
Figure 9
Figure 9
Comparison of prediction results for the latter 20 steps of ROP. (a) Prediction results of the LSTM model; (b) prediction results of the PSO-LSTM model.
Figure 10
Figure 10
Box plot of the distribution of the raw values compared with the predicted values of the two models.
Figure 11
Figure 11
The statistical significance of the test results for training, testing, and validation.
Figure 12
Figure 12
Error comparison of LSTM model prediction results before and after optimization.
Figure 13
Figure 13
Accuracy box plot of the two models.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Hegde C.; Daigle H.; Gray K. E. Performance comparison of algorithms for real-time rate-of-penetration optimization in drilling using data-driven models. Spe J. 2018, 23, 1706–1722. 10.2118/191141-PA. - DOI
    1. Oyedere M.; Gray K. ROP and TOB optimization using machine learning classification algorithms. J. Nat. Gas Sci. Eng. 2020, 77, 10323010.1016/j.jngse.2020.103230. - DOI
    1. Ashrafi S. B.; Anemangely M.; Sabah M.; Ameri M. J. Application of hybrid artificial neural networks for predicting rate of penetration (ROP): A case study from Marun oil field. J. Pet. Sci. Eng. 2019, 175, 604–623. 10.1016/j.petrol.2018.12.013. - DOI
    1. Brenjkar E.; Delijani E. B. Computational prediction of the drilling rate of penetration (ROP): A comparison of various machine learning approaches and traditional models. J. Pet. Sci. Eng. 2022, 210, 11003310.1016/j.petrol.2021.110033. - DOI
    1. Mazen A. Z.; Rahmanian N.; Mujtaba I.; Hassanpour A. Prediction of Penetration Rate for PDC Bits Using Indices of Rock Drillability, Cuttings Removal, and Bit Wear. SPE Drill. Completion 2021, 36, 320–337. 10.2118/204231-PA. - DOI