Data-Driven Predictive Maintenance for Gas Distribution Networks
Publication: ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering
Volume 8, Issue 2
Abstract
A generic data-driven approach is presented that employs machine learning to predict the future reliability of components in utility networks. The proposed approach enables utilities to implement a predictive maintenance strategy that optimizes life-cycle costs without compromising safety or creating environmental issues. Any machine learning technique that qualifies as a probabilistic classifier can be employed within the proposed approach. To identify the data-driven model that performs best, a practical metric to assess the performance of the competing models is proposed. This metric is specifically designed to quantify the forecasting performance with respect to maintenance planning. Additionally, a data-driven sensitivity analysis approach is discussed that allows for an assessment of the influence of the different features on the model prediction. Through an application example, it is demonstrated how the proposed approach can be applied to predict future defect rates of pipe sections for maintenance planning in a large gas distribution network.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all of the data, models, or code generated or used during the study are proprietary or confidential in nature and may only be provided with restrictions.
All of the data used in the application example are proprietary and confidential. The data were provided by the utility service provider NetzeBW and cannot be shared.
References
Ambühl, S., and J. D. Sørensen. 2017. On different maintenance strategies for casted components of offshore wind turbines. Aalborg, Denmark: Aalborg Univ.
Asgarpoor, S., and M. Doghman. 1999. “A maintenance optimization program for utilities’ transmission and distribution systems.” In Proc., 1999 North American Power Symp., 454–459. Boca Raton, FL: CRC Press.
Au, S.-K., and J. L. Beck. 2001. “Estimation of small failure probabilities in high dimensions by subset simulation.” Probab. Eng. Mech. 16 (4): 263–277. https://doi.org/10.1016/S0266-8920(01)00019-4.
Bao, Z., C. Gui, and X. Guo. 2018. “Short-term line maintenance scheduling of distribution network with PV penetration considering uncertainties.” IEEE Access 6 (May): 33621–33630. https://doi.org/10.1109/ACCESS.2018.2838082.
Baptista, M., S. Sankararaman, I. P. de Medeiros, C. Nascimento Jr., H. Prendinger, and E. M. Henriques. 2018. “Forecasting fault events for predictive maintenance using data-driven techniques and ARMA modeling.” Comput. Ind. Eng. 115 (Jan): 41–53. https://doi.org/10.1016/j.cie.2017.10.033.
Betz, W., J. L. Beck, I. Papaioannou, and D. Straub. 2018a. “Bayesian inference with reliability methods without knowing the maximum of the likelihood function.” Probab. Eng. Mech. 53 (Jun): 14–22. https://doi.org/10.1016/j.probengmech.2018.03.004.
Betz, W., I. Papaioannou, J. L. Beck, and D. Straub. 2018b. “Bayesian inference with subset simulation: Strategies and improvements.” Comput. Methods Appl. Mech. Eng. 331 (Apr): 72–93. https://doi.org/10.1016/j.cma.2017.11.021.
Bishop, C. M. 2006. Pattern recognition and machine learning. New York: Springer.
Breiman, L. 2001. “Random forests.” Mach. Learn. 45 (1): 5–32. https://doi.org/10.1023/A:1010933404324.
Butler, K. L. 1996. “An expert system based framework for an incipient failure detection and predictive maintenance system.” In Proc., Int. Conf. on Intelligent System Application to Power Systems, 321–326. New York: IEEE.
Chamoso, P., J. F. De Paz, J. Bajo, and G. Villarrubia. 2018. “Agent-based tool to reduce the maintenance cost of energy distribution networks.” Knowl. Inf. Syst. 54 (3): 659–675. https://doi.org/10.1007/s10115-017-1120-7.
Chen, T., and C. Guestrin. 2016. “XGBoost: A scalable tree boosting system.” In Proc., KDD 2016—22nd ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, 785–794. New York: Association for Computing Machinery. https://doi.org/10.1145/2939672.2939785.
Cline, B., R. S. Niculescu, D. Huffman, and B. Deckel. 2017. “Predictive maintenance applications for machine learning.” In Proc., 2017 Annual Reliability and Maintainability Symp., 1–7. New York: IEEE.
Coleman, C., S. Damodaran, M. Chandramouli, and E. Deuel. 2017. Making maintenance smarter: Predictive maintenance and the digital supply network. New York: Deloitte University Press.
Daily, J., and J. Peterson. 2017. “Predictive maintenance: How big data analysis can improve maintenance.” In Supply chain integration challenges in commercial aerospace, 267–278. New York: Springer.
Daniela, L., et al. 2011. “Decision-support tools for municipal infrastructure maintenance management.” Procedia Comput. Sci. 3 (Jan): 36–41. https://doi.org/10.1016/j.procs.2010.12.007.
de Faria, H., Jr., J. G. S. Costa, and J. L. M. Olivas. 2015. “A review of monitoring methods for predictive maintenance of electric power transformers based on dissolved gas analysis.” Renewable Sustainable Energy Rev. 46 (Jun): 201–209. https://doi.org/10.1016/j.rser.2015.02.052.
Friedman, J. H. 2001. “Greedy function approximation: A gradient boosting machine.” In Annals of statistics, 1189–1232. New York: JSTOR.
Friedman, J. H. 2002. “Stochastic gradient boosting.” Comput. Stat. Data Anal. 38 (4): 367–378. https://doi.org/10.1016/S0167-9473(01)00065-2.
Ghazvini, M. F., H. Morais, and Z. Vale. 2012. “Coordination between mid-term maintenance outage decisions and short-term security-constrained scheduling in smart distribution systems.” Appl. Energy 96 (Aug): 281–291. https://doi.org/10.1016/j.apenergy.2011.11.015.
Haladuick, S., and M. R. Dann. 2018. “Decision making for long-term pipeline system repair or replacement.” ASCE-ASME J. Risk Uncertainty Eng. Syst. Part A: Civ. Eng. 4 (2): 04018009. https://doi.org/10.1061/AJRUA6.0000956.
Hastie, T., R. Tibshirani, and J. Friedman. 2009. The elements of statistical learning: Data mining, inference, and prediction. New York: Springer.
Hastings, N. A. 2021. Physical asset management. 3rd ed. New York: Springer.
Kanakoudis, V., and D. Tolikas. 2001. “The role of leaks and breaks in water networks: Technical and economical solutions.” J. Water Supply Res. Technol. AQUA 50 (5): 301–311. https://doi.org/10.2166/aqua.2001.0025.
Kanakoudis, V., and D. Tolikas. 2004. “Assessing the performance level of a water system.” Water Air Soil Pollut. Focus 4 (4): 307–318. https://doi.org/10.1023/B:WAFO.0000044807.41719.c7.
Kaźmierczak, J., A. Loska, and M. Dabrowski. 2012. “Use of geospatial information for supporting maintenance management in a technical network system.” In Proc., 21st European Congress on Maintenance and Asset Management Euromaintenance, 287–297. Gliwice, Poland: Silesian Univ. of Technology.
Kelly, A. 2006. Vol. 1 of Strategic maintenance planning. Amsterdam, Netherlands: Elsevier.
Khan, F. I., and M. M. Haddara. 2003. “Risk-based maintenance (rbm): A quantitative approach for maintenance/inspection scheduling and planning.” J. Loss Prev. Process Ind. 16 (6): 561–573. https://doi.org/10.1016/j.jlp.2003.08.011.
Korvesis, P. 2017. “Machine learning for predictive maintenance in aviation.” Ph.D. thesis, Université Paris-Saclay. https://pastel.archives-ouvertes.fr/tel-02003508/document.
Langroudi, P. P., and I. Weidlich. 2020. “Applicable predictive maintenance diagnosis methods in service-life prediction of district heating pipes.” Environ. Clim. Technol. 24 (3): 294–304. https://doi.org/10.2478/rtuect-2020-0104.
Leoni, L., A. BahooToroody, M. M. Abaei, F. De Carlo, N. Paltrinieri, and F. Sgarbossa. 2021. “On hierarchical Bayesian based predictive maintenance of autonomous natural gas regulating operations.” Process Saf. Environ. Prot. 147 (Mar): 115–124. https://doi.org/10.1016/j.psep.2020.08.047.
Levitt, J. 2003. Complete guide to preventive and predictive maintenance. New York: Industrial Press.
Li, C., and S. Mahadevan. 2016. “An efficient modularized sample-based method to estimate the first-order Sobol index.” Reliab. Eng. Syst. Saf. 153 (Sep): 110–121. https://doi.org/10.1016/j.ress.2016.04.012.
Li, G., Y. Huang, Z. Bie, and T. Ding. 2020. “Machine-learning-based reliability evaluation framework for power distribution networks.” IET Gener. Transm. Distrib. 14 (12): 2282–2291. https://doi.org/10.1049/iet-gtd.2019.1520.
Mobley, R. K. 2002. An introduction to predictive maintenance. Amsterdam, Netherlands: Elsevier.
Montiel, H., J. A. Vílchez, J. Arnaldos, and J. Casal. 1996. “Historical analysis of accidents in the transportation of natural gas.” J. Hazard. Mater. 51 (1–3): 77–92. https://doi.org/10.1016/S0304-3894(96)01819-5.
Murphy, K. P. 2012. Machine learning: A probabilistic perspective. Cambridge, MA: MIT Press.
Narkhede, S. 2018. “Understanding AUC-ROC curve.” Towards Data Sci. 26 (1): 220–227.
NARUC (National Association of Regulatory Utility Commissioners). 2020. Artificial intelligence for natural gas utilities: A primer. Washington, DC: NARUC.
Niculescu-Mizil, A., and R. Caruana. 2005. “Predicting good probabilities with supervised learning.” In Proc., 22nd Int. Conf. on Machine Learning, 625–632. New York: Association for Computing Machinery. https://doi.org/10.1145/1102351.1102430.
Palmer, R. D. 2013. Maintenance planning and scheduling handbook. New York: McGraw-Hill.
Papadakis, G. A. 1999. “Major hazard pipelines: A comparative study of onshore transmission accidents.” J. Loss Prev. Process Ind. 12 (1): 91–107. https://doi.org/10.1016/S0950-4230(98)00048-5.
Pedregosa, F., et al. 2011. “Scikit-learn: Machine learning in Python.” J. Mach. Learn. Res. 12 (Nov): 2825–2830.
Rausand, M. 2013. Vol. 115 of Risk assessment: Theory, methods, and applications. New York: Wiley.
Sacco, T., M. Compare, E. Zio, and G. Sansavini. 2019. “Portfolio decision analysis for risk-based maintenance of gas networks.” J. Loss Prev. Process Ind. 60 (Jul): 269–281. https://doi.org/10.1016/j.jlp.2019.04.002.
Saltelli, A., M. Ratto, T. Andres, F. Campolongo, J. Cariboni, D. Gatelli, M. Saisana, and S. Tarantola. 2008a. Global sensitivity analysis: The primer. New York: Wiley.
Saltelli, A., M. Ratto, T. Andres, F. Campolongo, J. Cariboni, D. Gatelli, M. Saisana, and S. Tarantola. 2008b. “Introduction to sensitivity analysis.” In Global sensitivity analysis. The primer, 1–51. Hoboken, NJ: Wiley.
Selcuk, S. 2017. “Predictive maintenance, its implementation and latest trends.” Proc. Inst. Mech. Eng., Part B: J. Eng. Manuf. 231 (9): 1670–1679. https://doi.org/10.1177/0954405415601640.
Serradilla, O., E. Zugasti, and U. Zurutuza. 2020. “Deep learning models for predictive maintenance: A survey, comparison, challenges and prospect.” Preprint, submitted October 7, 2020. https://arxiv.org/abs/2010.03207.
Sobol, I. M. 1993. “Sensitivity estimates for nonlinear mathematical models.” Math. Model. Comput. Exp. 1 (4): 407–414.
Sobol, I. M. 2001. “Global sensitivity indices for nonlinear mathematical models and their Monte Carlo estimates.” Math. Comput. Simul. 55 (1–3): 271–280. https://doi.org/10.1016/S0378-4754(00)00270-6.
Straub, D., and I. Papaioannou. 2015. “Bayesian updating with structural reliability methods.” J. Eng. Mech. 141 (3): 04014134. https://doi.org/10.1061/(ASCE)EM.1943-7889.0000839.
Su, H., E. Zio, J. Zhang, Z. Yang, X. Li, and Z. Zhang. 2018. “A systematic hybrid method for real-time prediction of system conditions in natural gas pipeline networks.” J. Nat. Gas Sci. Eng. 57 (Sep): 31–44. https://doi.org/10.1016/j.jngse.2018.06.033.
Tsitsifli, S., V. Kanakoudis, and I. Bakouros. 2011. “Pipe networks risk assessment based on survival analysis.” Water Resour. Manage. 25 (14): 3729–3746. https://doi.org/10.1007/s11269-011-9881-3.
Tsui, K. L., N. Chen, Q. Zhou, Y. Hai, and W. Wang. 2015. “Prognostics and health management: A review on data driven approaches.” Math. Probl. Eng. 2015. https://doi.org/10.1155/2015/793161.
Uribe, F., I. Papaioannou, W. Betz, and D. Straub. 2020. “Bayesian inference of random fields represented with the Karhunenloève expansion.” Comput. Methods Appl. Mech. Eng. 358 (Jan): 112632. https://doi.org/10.1016/j.cma.2019.112632.
Vanmarcke, E. 2010. Random fields: Analysis and synthesis. 2nd ed. Singapore: World Scientific Publishing.
Wijs, R., G. Nane, G. Leontaris, T. Van Manen, and A. Wolfert. 2020. “Improving subsurface asset failure predictions for utility operators: A unique case study on cable and pipe failures resulting from excavation work.” ASCE-ASME J. Risk Uncertainty Eng. Syst. Part A: Civ. Eng. 6 (2): 05020002. https://doi.org/10.1061/AJRUA6.0001063.
Wiranowski, M. I., and S. B. Bergles. 2015. Big data: Opportunities and constraints for gas utilities. Washington, DC: Wilkinson Barker Knauer LLP.
Yuhua, D., and Y. Datao. 2005. “Estimation of failure probability of oil and gas transmission pipelines by fuzzy fault tree analysis.” J. Loss Prev. Process Ind. 18 (2): 83–88. https://doi.org/10.1016/j.jlp.2004.12.003.
Zemenkova, M. Y. 2019. “Neural network monitoring and predictive control of the reliability and safety of gas distribution networks using deep learning algorithms.” IOP Conf. Ser.: Mater. Sci. Eng. 663 (1): 012006. https://doi.org/10.1088/1757-899X/663/1/012006.
Information & Authors
Information
Published In
ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering
Volume 8 • Issue 2 • June 2022
Copyright
© 2022 American Society of Civil Engineers.
History
Received: Sep 23, 2021
Accepted: Feb 1, 2022
Published online: Mar 23, 2022
Published in print: Jun 1, 2022
Discussion open until: Aug 23, 2022
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.
Cited by
- Aysegul Ucar, Mehmet Karakose, Necim Kırımça, Artificial Intelligence for Predictive Maintenance Applications: Key Components, Trustworthiness, and Future Trends, Applied Sciences, 10.3390/app14020898, 14, 2, (898), (2024).
- Jun Yu, Min Chen, Hui Zhou, Liu-Wang Wang, Hua-Feng Luo, Jian-Bin Lan, Research on Application of Edge Calculation in Power Grid State Prediction, 2022 4th International Academic Exchange Conference on Science and Technology Innovation (IAECST), 10.1109/IAECST57965.2022.10061941, (651-655), (2022).