Application of PSO-LSTM Neural Network Based on Improved Wavelet Denoising to Predict Drilling Rate of Penetration

Xinjie Fang; Zhongzhi Hu; Yan Zhou; Wei Song; Junying Pan

doi:10.54097/0b79se64

Authors

Xinjie Fang
Zhongzhi Hu
Yan Zhou
Wei Song
Junying Pan

DOI:

https://doi.org/10.54097/0b79se64

Keywords:

Wavelet noise reduction, ROP prediction, LSTM neural network, Particle swarm optimization

Abstract

Accurate prediction of the rate of penetration (ROP) is one of the important factors to improve the drilling efficiency of oil fields. At present, most of the established ROP prediction models have low accuracy, because the traditional noise reduction methods are generally used to process the drilling data. At the same time, the influence of wellbore friction and well deviation on WOB is not considered, and only the ground WOB is qualitatively used as the input parameter of the ROP prediction model. In this paper, seven deep directional wells in the central part of Bohai Bay, China are selected as the data source. Firstly, the drilling data are cleaned and screened, and the improved wavelet denoising method is adopted to effectively eliminate the noise interference while ensuring the data quality. Then the ground drilling pressure is corrected to improve the rationality of the data. The random forest feature selection method is used to analyze the correlation of various factors affecting the penetration rate and reduce the redundancy of the model. Finally, the particle swarm optimization algorithm is used to optimize the LSTM neural network mechanical drilling speed prediction model. The influence of traditional wavelet noise reduction method, ground drilling pressure and LSTM model hyperparameters on the error of mechanical drilling speed prediction model is discussed. The results show that the average error of the prediction model of the rate of penetration is reduced after the noise reduction method and the ground drilling pressure are modified. The optimized LSYM prediction model of the rate of penetration has higher prediction accuracy than other models, and the prediction accuracy reaches 87.3 %, which further verifies the superiority and effectiveness of the prediction model of the rate of penetration established in this paper.

Downloads

Download data is not yet available.

References

[1] Liu Shengwa, Sun Junming, Gao Xiang, et al. Analysis and establishment of prediction model of ROP based on artificial neural network [J]. Computer Science, 2019, 46(S1): 605-608.

[2] Young, F. S. Computerized Drilling Control [J]. Journal of Petroleum Technology, 1969, 21(4): 483-496.

[3] Bourgoyne A T, Young F S. A Multiple Regression Approach to Optimal Drilling and Abnormal Pressure Detection [J]. Society of Petroleum Engineers Journal, 1974, 14(04):371-384.

[4] Bahari A, Baradaran Seyed A. Trust-Region Approach To Find Constants of Bourgoyne and Young Penetration Rate Model in Khangiran Iranian Gas Field [J]. Society of Petroleum Engineers, 2023.

[5] Hasan B M, Aboozar B, Hamidrezaidreza M. INTELLIGENT DRILLING RATE PREDICTOR [J]. International Journal of Innovative Computing Information and Control, 2011, 7(4): p.1511-1519.

[6] Irawan S, Rahman A M A, Tunio S Q. Optimization of Weight on Bit During Drilling Operation Based on Rate of Penetration Model [J]. Research Journal of Applied Sciences Engineering & Technology, 2012, 4(12): 1690-1695.

[7] A S S L, B K Y K, A J W S. Development of a trip time for bit exchange simulator for drilling time estimation [J]. Geothermics, 2018, 71:24-33.

[8] Carbonell J G, Michalski R S, Mitchell T M. AN OVERVIEW OF MACHINE LEARNING [J]. Machine Learning, 1983: 3-23.

[9] Amer M M, Dahab A S, El-Sayed A A H. An ROP Predictive Model in Nile Delta Area Using Artificial Neural Networks [J]. 2017.

[10] Kor K A G. Is Support Vector Regression method suitable for predicting rate of penetration? [J]. Journal of Petroleum Science & Engineering, 2020, 194(1).

[11] Chao Gan, Wei-Hua Cao, Min Wu, et al. Prediction of drilling rate of penetration (ROP) using hybrid support vector regression: A case study on the Shennongjia area, Central China [J]. Journal of Petroleum Science and Engineering, 2019, 181: 106200.

[12] Li Qi, Qu Fengtao, He Jingbin et al. Drilling rate prediction model based on BAS-BP [J]. Journal of Xi'an Shiyou University(Natural Science Edition), 2021, 36(6): 89-95.

[13] Li Qi, Qu Fengtao, He Jingbin, et al. Drilling rate prediction model based on PSO-BP [J]. Science Technology and Engineering, 2021, 21(19): 7984-7990.

[14] Hongtao L, Yan J, Xianzhi S, et al. Rate of Penetration Prediction Method for Ultra-Deep Wells Based on LSTM–FNN [J]. Applied Sciences, 2022, 12(15).

[15] Ehsan Brenjkar, Ebrahim Biniaz Delijani. Computational prediction of the drilling rate of penetration (ROP): A comparison of various machine learning approaches and traditional models [J]. Journal of Petroleum Science and Engineering, 2022, 210: 110033.

[16] Shi Xiangchao, Wang Yuming. Drilling rate prediction method based on LSTM recurrent neural network model. CN202210022755.6 [2022-04-15].

[17] Zhang Ligang, Miao Zhenhua, Huang Xiaogang, et al. Prediction of ROP based on MEA-BP neural network [J]. Automation & Instrumentation, 2022, 37(11): 87-92.

[18] Liu Ye, Zhang Fuqiang, Yang Shuopeng, et al. Time series feature characterization and prediction method of ROP based on Attention-LSTM. 202211438623[2023-09-27].

[19] Mu Huayan, Sun Jinsheng, Ding Yan, et al. Drilling rate prediction model optimization based on mechanical specific energy [J]. Drilling & Production Technology, 2023, 46(3): 16-21.

[20] Ji Hui, Zhu Liang, Lou Yishan, et al. A prediction method of penetration rate based on particle swarm optimization LSTM neural network model. CN202211353816.3 [2023-09-27].