No Access

Condition Monitoring of Equipment in Oil Wells using Deep Learning

Yadigar N. Imamverdiyev

Institute of Information Technology, Azerbaijan National Academy of Sciences, Baku AZ1141, Azerbaijan

E-mail Address: yadigar@iit.science.az

Search for more papers by this author

and

Fargana J. Abdullayeva

http://orcid.org/0000-0003-2288-6255

Institute of Information Technology, Azerbaijan National Academy of Sciences, Baku AZ1141, Azerbaijan

E-mail Address: a_farqana@mail.ru

Corresponding author.

Search for more papers by this author

https://doi.org/10.1142/S2424922X20500011Cited by:1 (Source: Crossref)

Abstract

In this paper, a fault prediction method for oil well equipment based on the analysis of time series data obtained from multiple sensors is proposed. The proposed method is based on deep learning (DL). For this purpose, comparative analysis of single-layer long short-term memory (LSTM) with the convolutional neural network (CNN) and stacked LSTM methods is provided. To demonstrate the efficacy of the proposed method, some experiments are conducted on the real data set obtained from eight sensors installed in oil wells. In this paper, compared to the single-layer LSTM model, the CNN and stacked LSTM predicted the faulty time series with a minimal loss.

Keywords:

References

Al-Dahidia, S., Maioa, F. D., Baraldia, P. and Zio, E. (2015). Ensemble clustering for fault diagnosis in industrial plants. Chem. Eng. Trans., 43: 1225–1230. Google Scholar
Alguliyev, R. and Imamverdiyev, Y. (2014). Big data: Big promises for information security. Proc. IEEE 8th Int. Conf. Application of Information and Communication Technologies (AICT), IEEE, Piscataway, pp. 1–4. Crossref, Google Scholar
Animah, I. and Shafiee, M. (2018). Condition assessment, remaining useful life prediction and life extension decision making for offshore oil and gas assets. J. Loss Prev. Process Ind., 53: 17–28. Crossref, Google Scholar
Bengio, Y., Simard, P. and Frasconi, P. (1994). Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Netw., 5(5): 157–166. Crossref, Google Scholar
Bengio, Y. (2009). Learning Deep Architectures for AI, Foundations and Trends in Machine Learning, Vol. 2(1). now Publishers, Inc., Delft. Crossref, Google Scholar
Chen, K. Y., Chen, L. S., Chen, M. C. and Lee, C. L. (2011). Using SVM based method for equipment fault detection in a thermal power plant. Comput. Ind., 62(1): 42–50. Crossref, Google Scholar
Cheng, F., Wang, J., Qu, L., and Qiao, W. (2018). Rotor-current-based fault diagnosis for DFIG wind turbine drivetrain gearboxes using frequency analysis and a deep classifier. IEEE Trans. Ind. Appl., 54(2): 1062–1071. Crossref, Google Scholar
Diez-Olivan, A., Pagan, J. A., Khoa, N. L., Sanz, R. and Sierra, B. (2018). Kernel-based support vector machines for automated health status assessment in monitoring sensor data. Int. J. Adv. Manuf. Technol., 95(1–4): 327–340. Crossref, Google Scholar
Eklund, N. (2016). Revolutionizing oil & gas prognostics and health management. Proc. PHM Society Annu. Meeting. Available at: https://pdfs.semanticscholar.org/presentation/151f/81219658d8b730d820ce04dfd7b61af3b7ea.pdf. Accessed on. AQ: Please provide accessed date and also publisher, location and page range. Google Scholar
Ferreiro, S., Konde, E., Fernández, S. and Prado, A. (2016). Industry 4.0: Predictive intelligent maintenance for production equipment. Proc. Third European Conf. Prognostics and Health Management Society, PHM Society, Rochester, pp. 1–8. Google Scholar
Galicia, A., Talavera-Llames, R., Troncoso, A., Koprinska, I. and Martínez-Álvarez, F. (2019). Multi-step forecasting for big data time series based on ensemble learning. Knowl.-Based Syst., 163: 830–841. Crossref, Google Scholar
GitHub (2019). Time-series prediction for predictive maintenance. Available at: https://github.com/limingwu8/Predictive-Maintenance. Accessed on. AQ: Please provide accessed date. Google Scholar
Helwing, N., Pignanelli, E. and Schutze, A. (2015). Detecting and compensating sensor faults in a hydraulic condition monitoring system. Proc. 17th Int. Conf. Sensors and Measurement Technology, AMA Association for Sensors and Measurement, Berlin, pp. 641–646. Google Scholar
Hinton, G. E., Osindero, S. and Teh, Y. W. (2006). A fast learning algorithm for deep belief nets. Neural Comput., 18(7): 1527–1554. Crossref, Google Scholar
Hu, J., Zhang, L., Tian, W. and Zhou, S. (2017). DBN based failure prognosis method considering the response of protective layers for the complex industrial systems. Eng. Fail. Anal., 79: 504–519. Crossref, Google Scholar
Imamverdiyev, Y. N. and Abdullayeva, F. J. (2018). Deep learning method for denial of service attack detection based on restricted Boltzmann machine. Big Data, 6(2): 159–169. AQ: Please cite inside. Crossref, Google Scholar
Jia, F., Lei, Y., Guo, L., Lin, J. and Xing, S. (2018). A neural network constructed by deep learning technique and its application to intelligent fault diagnosis of machines. Neurocomputing, 272: 619–628. Crossref, Google Scholar
Khan, S. and Yairi, T. (2018). A review on the application of deep learning in system health management. Mech. Syst. Signal Process., 107: 241–265. Crossref, Google Scholar
Khan, S. and Yairi, T. (2018). A review on the application of deep learning in system health management. Mech. Syst. Signal Process., 107: 241–265. TS: Same as Ref. 8. Please remove. Crossref, Google Scholar
Kim, K., Parthasarathy, G. and Uluyol, O. (2011). Use of SCADA data for failure detection in wind turbines. Proc. 2011 5th Energy Sustainability Conf. and Fuel Cell Conf., ASME, New York, pp. 1–11. Crossref, Google Scholar
Kumar, A., Shankar, R. and Thakur, L. S. (2018). A big data driven sustainable manufacturing framework for condition-based maintenance prediction. Journal of Computational Science, 27: 428–439. Crossref, Google Scholar
Li, X., Ding, Q. and Sun, J. Q. (2018). Remaining useful life estimation in prognostics using deep convolution neural networks. Reliab. Eng. Syst. Saf., 172: 1–11. Crossref, Google Scholar
Lu, C., Wang, Z. Y., Qin, W. L. and Ma, J. (2017). Fault diagnosis of rotary machinery components using a stacked denoising autoencoder-based health state identification. Signal Process., 130: 377–388. Crossref, Google Scholar
Moore, R. (2006). Predictive maintenance/condition monitoring. Selecting the Right Manufacturing Improvement Tools, 1st edn. Butterworth-Heinemann, Burlington, pp. 247–284. Google Scholar
Raza, J., Liyanage, J. P., Atat, H. A. and Lee, J. (2010). A comparative study of maintenance data classification based on neural networks, logistic regression and support vector machines. J. Qual. Maint. Eng., 16(3): 303–318. Crossref, Google Scholar
Sagheer, A. and Kotb, M. (2019). Time series forecasting of petroleum production using deep LSTM recurrent networks. Neurocomputing, 323: 203–213. Crossref, Google Scholar
Sak, H., Senior, A. and Beaufays, F. (2014). Long short-term memory recurrent neural network architectures for large scale acoustic modeling. Proc. 15th Annu. Conf. International Speech Communication Association, International Speech Communication Association, pp. 338–342. AQ: Please provide publisher location. Crossref, Google Scholar
Si, J., Li, Y. and Ma, S. (2018). Intelligent fault diagnosis for industrial big data. J. Signal Process. Syst., 90(8–9): 1221–1233. Crossref, Google Scholar
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I. and Salakhutdinov, R. (2014). Dropout: A simple way to prevent neural networks from overfitting. J. Mach. Learn. Res., 15: 1929–1958. Google Scholar
Su, H., Zio, E., Zhang, J., Yang, Z., Li, X. and Zhang, Z. (2018). A systematic hybrid method for real-time prediction of system conditions in natural gas pipeline networks. J. Nat. Gas Sci. Eng., 57: 31–44. Crossref, Google Scholar
Sugumaran, V., Muralidharan, V. and Ramachandran, K. I. (2007). Feature selection using decision tree and classification through proximal support vector machine for fault diagnostics of roller bearing. Mech. Syst. Signal Process., 21(2): 930–942. Crossref, Google Scholar
Sun, W., Shao, S., Zhao, R., Yan, R., Zhang, X. and Chen, X. (2016). A sparse auto-encoder-based deep neural network approach for ınduction motor faults classification. Measurement, 89: 171–178. Crossref, Google Scholar
Sun, J., Zuo, H., Wang, W. and Pecht, M. G. (2012). Application of a state space modeling technique to system prognostics based on a health index for condition-based maintenance. Mech. Syst. Signal Process., 28: 585–596. Crossref, Google Scholar
Tao, S., Zhang, T., Yang, J., Wang, X. and Lu, W. (2015). Bearing fault diagnosis method based on stacked autoencoder and softmax regression. Proc. 2015 34th Chinese Control Conf. (CCC), IEEE, Piscataway, pp. 6331–6335. Crossref, Google Scholar
Tibbetts, M. (2017). Machine learning with industrial data. Arundo Analytics. Available at: https://www.sintef.no/contentassets/4817fcaabf034bcfacadd625ac89498c/tibbetts_geilotalk.pdf. Accessed on. AQ: Please provide accessed date. Google Scholar
Wandekokem, E. D., Mendel, E., Fabris, F., Valentim, M., Batista, R. J., Varejão, F. M. and Rauber, T. W. (2011). Diagnosing multiple faults in oil rig motor pumps using support vector machine classifier ensembles. Integr. Comput.-Aided Eng., 18(1): 61–74. Crossref, Google Scholar
Wang, H., Yang, Z., Yu, Q., Hong, T. and Lin, X. (2018). Online reliability time series prediction via convolutional neural network and long short term memory for service-oriented systems. Knowl.-Based Syst., 159: 132–147. Crossref, Google Scholar
Widodo, A. and Yang, B. S. (2007). Support vector machine in machine condition monitoring and fault diagnosis. Mech. Syst. Signal Process., 21(6): 2560–2574. Crossref, Google Scholar
Wu, H. X., Yu, Z. H. and Wang, Y. (2016). Real-time FDM machine condition monitoring and diagnosis based on acoustic emission and hidden semi-Markov model. Int. J. Adv. Manuf. Technol., 90(5–8): 2027–2036. Crossref, Google Scholar
Xia, M., Li, T., Liu, L., Xu, L. and Silva, C. W. (2017). Intelligent fault diagnosis approach with unsupervised feature learning by stacked denoising autoencoder. IET Sci. Meas. Technol., 11(6): 687–695. Crossref, Google Scholar
Yu, J. B. (2013). A nonlinear probabilistic method and contribution analysis for machine condition monitoring. Mech. Syst. Signal Process., 37(1–2): 293–314. Crossref, Google Scholar
Zhang, L. (2016). Big data analytics for fault detection and its application in maintenance. Doctoral thesis, Luleå University of Technology, Sweden. Google Scholar
Zhang, Y. S., Gao, Q. W., Lu, Y. X., Sun, D., Xia, Y. and Peng, X. M. (2018). A novel intelligent method for bearing fault diagnosis based on Hermitian scale-energy spectrum. IEEE Sens. J., 18(16): 6743–6755. Crossref, Google Scholar
Zhao, R., Yan, R., Chen, Z., Mao, K., Wang, P. and Gao, R. X. (2015). Deep learning and its applications to machine health monitoring: A survey. IEEE Trans. Neural Netw. Learn. Syst., 14(8): 1–14. Google Scholar