In the oil industry, the productivity of oil wells depends on the performance of the sub-surface equipment system. These systems often have problems stemming from sand, corrosion, internal pressure variation, or other factors. In order to ensure high equipment performance and avoid high-cost losses, it is essential to identify the source of possible failures in the early stage. However, this requires additional maintenance fees and human power. Moreover, the losses caused by these problems may lead to interruptions in the whole production process. In order to minimize maintenance costs, in this paper, we introduce a model for predicting equipment failure based on processing the historical data collected from multiple sensors. The state of the system is predicted by a Feed-Forward Neural Network (FFNN) with an SGD and Backpropagation algorithm？is？applied in the training process. Our model’s primary goal is to identify potential malfunctions at an early stage to ensure the production process’ continued high performance. We also evaluated the effectiveness of our model against other solutions currently available in the industry. The results of our study show that the FFNN can attain an accuracy score of 97% on the given dataset, which exceeds the performance of the models provided.
References
[1]
Brissaud, F., Varela, H., Declerck, B. and Bouvier, N. (2012) Production Availability Analysis for Oil and Gas Facilities: Concepts and Procedure. 11th International Probabilistic Safety Assessment and Management Conference and the Annual European Safety and Reliability Conference, Helsinki, June 2012, 4760-4769.
[2]
Tribedi, U. (2020) What Is the Maximum Accuracy That a Machine Learning Model Can Achieve?
https://medium.com/think-ai/what-is-the-maximum-accuracy-that-a-machine-learning-model-can-achieve-e43dba772080
[3]
Deyab, S.M., Taleb-berrouane, M., Khan, F. and Yang, M. (2018) Failure Analysis of the Offshore Process Component Considering Causation Dependence. Process Safety and Environmental Protection, 113, 220-232.
https://doi.org/10.1016/j.psep.2017.10.010
[4]
U.S. Fire Administration (1989) Technical Report Series Phillips Petroleum Chemical Plant Explosion and Fire Pasadena, Texas. USFA-TR-035.
https://ncsp.tamu.edu/reports/USFA/pasadena.pdf
[5]
Jackson, R.B. (2014) The Integrity of Oil and Gas Wells. Proceedings of the National Academy of Sciences of the United States of America, 111, 10902-10903.
https://www.pnas.org/content/111/30/10902
https://doi.org/10.1073/pnas.1410786111
[6]
Burt, J. (2018) Unifying Oil and Gas Data at Scale. The Next Platform.
https://www.nextplatform.com/2017/05/30/unifying-oil-gas-data-scale/
[7]
Al-Shehri, D.A. (2019) Oil and Gas Wells: Enhanced Wellbore Casing Integrity Management through Corrosion Rate Prediction Using an Augmented Intelligent Approach. Sustainability, 11, Article 818. https://doi.org/10.3390/su11030818
[8]
Martí, L., Sanchez-Pi, N., Molina, J.M. and Bicharra Garcia, A.C. (2014) YASA: Yet Another Time Series Segmentation Algorithm for Anomaly Detection in Big Data Problems. In: Polycarpou, M., et al., Eds., Hybrid Artificial Intelligence Systems. HAIS 2014. Lecture Notes in Computer Science, Springer, Cham, 697-708.
https://doi.org/10.1007/978-3-319-07617-1_61
[9]
Syah, R., Ahmadian, N., Elveny, M., Alizadeh, S.M., Hosseini, M. and Khan, A. (2021) Implementation of Artificial Intelligence and Support Vector Machine Learning to Estimate the Drilling Fluid Density in High-Pressure High-Temperature Wells. Energy Reports, 7, 4106-4113. https://doi.org/10.1016/j.egyr.2021.06.092
[10]
Kumar, A. and Kumari, M. (2020) Design and Analysis of IOT Based Real Time System for Door Locking/Unlocking Using Face Identification. International Journal of Recent Technology and Engineering, 8, 2093-2095.
https://doi.org/10.35940/ijrte.E5794.018520
[11]
Shi, F., Yan, L., Zhao, X. and Gao, R.X.-K. (2022) Machine Learning-Based Time-Series Data Analysis in Edge-Cloud-Assisted Oil Industrial IoT System. Mobile Information Systems, 2022, Article ID: 5988164. https://doi.org/10.1155/2022/5988164
[12]
Anderson, R.N. (2017) ‘Petroleum Analytics Learning Machine’ for Optimizing the Internet of Things of Today’s Digital Oil Field-to-Refinery Petroleum System. 2017 IEEE International Conference on Big Data (Big Data), Boston, MA, 11-14 December 2017, 4542-4545. https://doi.org/10.1109/BigData.2017.8258496
[13]
Al-Radhi, M.S., Al-Kamil, S.J. and Tamás, S. (2020) A Model-Based Machine Learning to Develop a PLC Control System for Rumaila Degassing Stations. Journal of Petroleum Research and Studies, 10, 1-18. https://doi.org/10.52716/jprs.v10i4.364
[14]
Rahmani, A.M., Ali, S., Malik, M.H., Yousefpoor, E., et al. (2022) An Energy-Aware and Q-Learning-Based Area Coverage for Oil Pipeline Monitoring Systems Using Sensors and Internet of Things. Scientific Reports, 12, Article No. 9638.
https://doi.org/10.1038/s41598-022-12181-w
[15]
Seide, F., Fu, H., Droppo, J., Li, G. and Yu, D. (2014) 1-Bit Stochastic Gradient Descent and Its Application to Data-Parallel Distributed Training of Speech DNNs. INTERSPEECH 2014, Singapore, 14-18 September 2014,1058-1062.
https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/IS140694.pdf
[16]
Rumelhart, D.E., Hinton, G.E. and Williams, R.J. (1986) Learning Representations by Back-Propagating Errors. Nature, 323, 533-536.
https://doi.org/10.1038/323533a0
Halgamuge, M.N., Daminda, E. and Nirmalathas, A. (2020) Best Optimizer Selection for Predicting Bushfire Occurrences Using Deep Learning. Natural Hazards, 103, 845-860. https://link.springer.com/article/10.1007/s11069-020-04015-7
https://doi.org/10.1007/s11069-020-04015-7
[19]
Keras (n.d.) Simple. Flexible. Powerful. https://keras.io/
[20]
Brownlee, J. (2022) How to Calculate Precision, Recall, F1, and More for Deep Learning Models.
https://machinelearningmastery.com/how-to-calculate-precision-recall-f1-and-more-for-deep-learning-models/
