Performance Analysis of Deep Learning Implementation in Operational Condition Forecasting of a Gas Transmission Pipeline Network

Aditya Firman Ihsan (1), - Darmadi (2), Saladin Uttunggadewa (3), Silvya Dewi Rahmawati (4), Irsyad Giovanni (5), Salamet Nur Himawan (6)
(1) School of Computing, Telkom University, Jl. Telekomunikasi No. 1, Bandung, 40257, Indonesia
(2) RC-OPPINET, Institut Teknologi Bandung, Jl. Ganesa No. 10, Bandung, 40132, Indonesia
(3) Mathematics Department, Institut Teknologi Bandung, Jl. Ganesa No. 10, Bandung, 40132, Indonesia
(4) Petroleum Engineering Department, Institut Teknologi Bandung, Jl. Ganesa No. 10, Bandung, 40132, Indonesia
(5) RC-OPPINET, Institut Teknologi Bandung, Jl. Ganesa No. 10, Bandung, 40132, Indonesia
(6) RC-OPPINET, Institut Teknologi Bandung, Jl. Ganesa No. 10, Bandung, 40132, Indonesia
Fulltext View | Download
How to cite (IJASEIT) :
Ihsan, Aditya Firman, et al. “Performance Analysis of Deep Learning Implementation in Operational Condition Forecasting of a Gas Transmission Pipeline Network”. International Journal on Advanced Science, Engineering and Information Technology, vol. 13, no. 4, Aug. 2023, pp. 1423-9, doi:10.18517/ijaseit.13.4.18250.
Monitoring natural gas transmission in a pipeline network is important to maintain the supply and demand balance in natural gas transactions and distribution. Gas pressure, temperature, flowrate, and gas properties must be monitored during the transmission process. These variables, also known as operational conditions, need to be simulated carefully to understand the dynamics and behavior over time. Commonly used physical equations, such as thermodynamic or hydraulic equations, have limitations in simulating future trends because they need some known boundary conditions to be solved. In that case, data-driven method is needed, especially nowadays when data management is widely implemented. This paper implements a deep Recurrent Neural Network (RNN) to forecast the future behavior of gas pressure as an operational condition in a gas pipeline network receiving platform. Different types of recurrent cells are used, i.e., Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU). The model is trained in 8 years of a gas pipeline network operational data. Historical flowrate data in the end-nodes become the forecast input in addition to the past pressure data. The sensitivity of the model and learning parameters is experimented with and analyzed to understand the capacity of the RNN in the given task. Mean absolute error is set as the satisficing metric, whereas the training time is set as optimizing metrics. The obtained best model successfully forecasts the future pressure of one day ahead with only around 2% relative error.

T. Kiuchi, “An implicit method for transient gas flows in pipe networks,” Int J Heat Fluid Flow, vol. 15, no. 5, pp. 378-383, 1994, doi: 10.1016/0142-727X(94)90051-5.

C. Li, H. Wang, H. Yue, and S. Guo, “Fast difference scheme for the reaction-diffusion-advection equation with exact artificial boundary conditions,” Applied Numerical Mathematics, vol. 173, no. 2018, pp. 395-417, 2022, doi: 10.1016/j.apnum.2021.12.013.

Q. Guo, Y. Liu, Y. Yang, T. Song, and S. Wang, “Improved Adaptive Time Step Method for Natural Gas Pipeline Transient Simulation,” Energies (Basel), vol. 15, no. 14, p. 4961, Jul. 2022, doi: 10.3390/en15144961.

P. Wang, S. Ao, B. Yu, D. Han, and Y. Xiang, “An efficiently decoupled implicit method for complex natural gas pipeline network simulation,” Energies (Basel), vol. 12, no. 8, 2019, doi: 10.3390/en12081516.

P. Bangert, “Introduction to Machine Learning in the Oil and Gas Industry,” in Machine Learning and Data Science in the Oil and Gas Industry, Elsevier, 2021, pp. 69-81. doi: 10.1016/B978-0-12-820714-7.00004-2.

K. M. Hanga and Y. Kovalchuk, “Machine learning and multi-agent systems in oil and gas industry applications: A survey,” Comput Sci Rev, vol. 34, p. 100191, 2019, doi: 10.1016/j.cosrev.2019.08.002.

R. N. Anderson et al., “Petroleum analytics learning machine to forecast production in the wet gas marcellus shale,” SPE/AAPG/SEG Unconventional Resources Technology Conference 2016, pp. 132-147, 2016, doi: 10.15530/urtec-2016-2426612.

Q. Cao, R. Banerjee, S. Gupta, J. Li, W. Zhou, and B. Jeyachandra, “Data driven production forecasting using machine learning,” Society of Petroleum Engineers - SPE Argentina Exploration and Production of Unconventional Resources Symposium, 2016, doi: 10.2118/180984-ms.

S. A. Sharaf, P. Bangert, M. Fardan, K. Alqassab, M. Abubakr, and M. Ahmed, “Beam pump dynamometer card classification using machine learning,” SPE Middle East Oil and Gas Show and Conference, MEOS, Proceedings, vol. 2019-March, 2019, doi: 10.2118/194949-ms.

U. Sinha, B. Dindoruk, and M. Soliman, “Machine learning augmented dead oil viscosity model for all oil types,” J Pet Sci Eng, vol. 195, no. July, p. 107603, 2020, doi: 10.1016/j.petrol.2020.107603.

U. T. Tygesen, K. Worden, T. Rogers, G. Manson, and E. J. Cross, “State-of-the-art and future directions for predictive modelling of offshore structure dynamics using machine learning,” Conference Proceedings of the Society for Experimental Mechanics Series, vol. 2, pp. 223-233, 2019, doi: 10.1007/978-3-319-74421-6_30.

K. Patel and R. Patwardhan, “Machine learning in oil & gas industry: A novel application of clustering for oilfield advanced process control,” SPE Middle East Oil and Gas Show and Conference, MEOS, Proceedings, vol. 2019-March, 2019, doi: 10.2118/194827-ms.

J. Zenisek, F. Holzinger, and M. Affenzeller, “Machine learning based concept drift detection for predictive maintenance,” Comput Ind Eng, vol. 137, no. August, p. 106031, 2019, doi: 10.1016/j.cie.2019.106031.

R. Pelta, N. Carmon, and E. Ben-Dor, “A machine learning approach to detect crude oil contamination in a real scenario using hyperspectral remote sensing,” International Journal of Applied Earth Observation and Geoinformation, vol. 82, no. November 2018, p. 101901, 2019, doi: 10.1016/j.jag.2019.101901.

F. I. Syed, M. Alshamsi, A. K. Dahaghi, and S. Neghabhan, “Artificial lift system optimization using machine learning applications,” Petroleum, vol. 8, no. 2, pp. 219-226, Jun. 2022, doi: 10.1016/j.petlm.2020.08.003.

M. R. Khan, S. Alnuaim, Z. Tariq, and A. Abdulraheem, “Machine learning application for oil rate prediction in artificial gas lift wells,” SPE Middle East Oil and Gas Show and Conference, MEOS, Proceedings, vol. 2019-March, 2019, doi: 10.2118/194713-ms.

G. Cui, Q. S. Jia, X. Guan, and Q. Liu, “Data-driven computation of natural gas pipeline network hydraulics,” Results in Control and Optimization, vol. 1, no. December, p. 100004, 2020, doi: 10.1016/j.rico.2020.100004.

N. Elshaboury, A. Al-Sakkaf, G. Alfalah, and E. M. Abdelkader, “Data-Driven Models for Forecasting Failure Modes in Oil and Gas Pipes,” Processes, vol. 10, no. 2, pp. 1-17, 2022, doi: 10.3390/pr10020400.

X. Li, J. Wang, and G. Chen, “A machine learning methodology for probabilistic risk assessment of process operations: A case of subsea gas pipeline leak accidents,” Process Safety and Environmental Protection, vol. 165, pp. 959-968, Sep. 2022, doi: 10.1016/j.psep.2022.04.029.

M. Giuliani et al., “Flaring events prediction and prevention through advanced big data analytics and machine learning algorithms,” Offshore Mediterranean Conference and Exhibition 2019, OMC 2019, no. April 2021, 2019.

J. You et al., “Assessment of enhanced oil recovery and CO2 storage capacity using machine learning and optimization framework,” Society of Petroleum Engineers - SPE Europec Featured at 81st EAGE Conference and Exhibition 2019, vol. i, 2019, doi: 10.2118/195490-ms.

H. C. Phan and A. S. Dhar, “Predicting pipeline burst pressures with machine learning models,” International Journal of Pressure Vessels and Piping, vol. 191, no. March, 2021, doi: 10.1016/j.ijpvp.2021.104384.

Z. Zhong, A. Y. Sun, Y. Wang, and B. Ren, “Predicting field production rates for waterflooding using a machine learning-based proxy model,” J Pet Sci Eng, vol. 194, no. December 2019, p. 107574, 2020, doi: 10.1016/j.petrol.2020.107574.

M. Petkovic, T. Koch, and J. Zittel, “Deep learning for spatio”temporal supply and demand forecasting in natural gas transmission networks,” Energy Sci Eng, vol. 01, no. December, 2021, doi: 10.1002/ese3.932.

T. Bikmukhametov and J. Jí¤schke, “Oil production monitoring using gradient boosting machine learning algorithm,” IFAC-PapersOnLine, vol. 52, no. 1, pp. 514-519, 2019, doi: 10.1016/j.ifacol.2019.06.114.

E. A. M. Víƒlez, F. R. Consuegra, and C. A. B. Arias, “EOR Screening and Early Production Forecasting in Heavy Oil Fields: AMachine Learning Approach,” SPE Latin American and Caribbean Petroleum Engineering Conference Proceedings, 2020, doi: 10.2118/199047-MS.

Y. Zhang and S. Hamori, “Forecasting crude oil market crashes using machine learning technologies,” Energies (Basel), vol. 13, no. 10, 2020, doi: 10.3390/en13102440.

Sousa, Ribeiro, Relvas, and Barbosa-Póvoa, “Using Machine Learning for Enhancing the Understanding of Bullwhip Effect in the Oil and Gas Industry,” Mach Learn Knowl Extr, vol. 1, no. 3, pp. 994-1012, 2019, doi: 10.3390/make1030057.

Y. Bengio, A. Courville, and I. J. Goodfellow, Deep Learning. 2016. doi: 10.2172/1462436.

Y. Yu, X. Si, C. Hu, and J. Zhang, “A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures,” Neural Comput, vol. 31, no. 7, pp. 1235-1270, Jul. 2019, doi: 10.1162/neco_a_01199.

Authors who publish with this journal agree to the following terms:

    1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
    2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
    3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).