Automatic Assessment and Prediction of the Resilience of Utility Poles Using Unmanned Aerial Vehicles and Computer Vision Techniques

Abstract

The utility poles of electric power distribution lines are very vulnerable to many natural hazards, while power outages due to pole failures can lead to adverse economic and social consequences. Utility companies, therefore, need to monitor the conditions of poles regularly and predict their future conditions accurately and promptly to operate the distribution system continuously and safely. This article presents a novel pole monitoring method that uses state-of-the-art deep learning and computer vision methods to meet the need. The proposed method automatically captures the current pole inclination angles using an unmanned aerial vehicle. The method calculates the bending moment exerted on the poles due to wind and gravitational forces, as well as cable weight, to compare it with the moment of rupture. The method also includes a machine learning-based model that is built by using a support vector machine to predict the resilience conditions of a pole after a wind event in a faster manner. The three modules of the proposed method are effective tools to classify pole conditions and are expected to enable utility companies to increase the resilience of their systems.

Keywords

Angular deflection / Machine learning / Support vector machine / Texas / Utility pole resilience

References

[1] Alam MM, Eren Tokgoz B, Hwang S. Framework for measuring the resilience of utility poles of an electric power distribution network. International Journal of Disaster Risk Science, 2019, 10(2): 270-281

[2] AEP Texas (American Electric Power Texas). 2017. Hurricane Harvey restoration update 9-3-2017, 4:30 p.m. https://www.aeptexas.com/info/news/viewRelease.aspx?releaseID=2339. Accessed 14 Mar 2019.

[3] ANSI (American National Standards Institute). 2017. Specifications and dimensions (for wood poles, O5.1). New York: ANSI. https://webstore.ansi.org/Standards/ANSI/ANSIO52017?gclid=EAIaIQobChMI74yPio-E4QIVREOGCh1g5QX2EAAYAiAAEgKX2fD_BwE. Accessed 12 Apr 2019.

[4] Bhat, R., Y.M. Darestani, A. Shafieezadeh, A.P. Meliopoulos, and R. DesRoches. 2018. Resilience assessment of distribution systems considering the effect of hurricanes. In Proceedings of 2018 IEEE/PES Transmission and Distribution Conference and Exposition (T&D), 1–5, 16–19 April 2018, Denver, CO, USA. https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8440320. Accessed 12 Jan 2019.

[5] Bjarnadottir S, Li Y, Stewart MG. Hurricane risk assessment of power distribution poles considering impacts of a changing climate. Journal of Infrastructure Systems, 2013, 19(1): 12-24

[6] Bruneau M, Chang SE, Eguchi RT, Lee GC, O’Rourke TD, Reinhorn AM, Shinozuka M, Tierney K A framework to quantitatively assess and enhance the seismic resilience of communities. Earthquake Spectra, 2003, 19(4): 733-752

[7] Caribbean Disaster Mitigation Project. 1996. Hurricane vulnerability and risk analysis of the VINLEC transmission and distribution system. Washington, DC: Unit for Sustainable Development and Environment, Organization of American States. https://www.oas.org/cdmp/document/vinlec/vinlec.htm. Accessed 20 Mar 2018.

[8] Cetin, B., M. Bikdash, and M. McInerney. 2009. Automated electric utility pole detection from aerial images. In Proceedings of IEEE Southeastcon 2009, 5–8 March 2009, Atlanta, GA, USA. https://ieeexplore.ieee.org/abstract/document/5174047. Accessed 3 Mar 2019.

[9] Cheng, W., and Z. Song. 2008. Power pole detection based on graph cut. In Proceedings of 2008 Congress on Image and Signal Processing, 27–30 May, Sanya, Hainan, China. https://ieeexplore.ieee.org/abstract/document/4566577. Accessed 12 Feb 2019.

[10] Eren Tokgoz B, Safa M, Hwang S. Resilience assessment for power distribution systems. International Journal of Civil and Environmental Engineering, 2017, 11(7): 806-811.

[11] Eskandarpour, R., A. Khodaei, and A. Arab. 2017. Improving power grid resilience through predictive outage estimation. In Proceedings of 2017 North American Power Symposium (NAPS), IEEE. 17–19 September 2017, Morgantown, WV, USA. https://ieeexplore.ieee.org/abstract/document/8107262. Accessed 12 Apr 2019.

[12] Executive Office of the President. 2013. Economic benefits of increasing electric grid resilience to weather outages. Washington, DC: Executive Office of the President. https://www.energy.gov/sites/prod/files/2013/08/f2/Grid%20Resiliency%20Report_FINAL.pdf. Accessed 24 Mar 2019.

[13] Gholami A, Aminifar F, Shahidehpour M. Front lines against the darkness: enhancing the resilience of the electricity grid through microgrid facilities. IEEE Electrification Magazine, 2016, 4(1): 18-24

[14] Gholami A, Shekari T, Amirioun MH, Aminifar F, Amini MH, Sargolzaei A. Toward a consensus on the definition and taxonomy of power system resilience. IEEE Access, 2018, 6: 32035-32053

[15] Golightly I, Jones D. Corner detection and matching for visual tracking during power line inspection. Image and Vision Computing, 2003, 21(9): 827-840

[16] Guikema SD. Natural disaster risk analysis for critical infrastructure systems: an approach based on statistical learning theory. Reliability Engineering & System Safety, 2009, 94(4): 855-860

[17] Gustavsen B, Rolfseng L. Simulation of wood pole replacement rate and its application to life cycle economy studies. IEEE Transactions on Power Delivery, 2000, 15(1): 300-306

[18] Han SR, Rosowsky D, Guikema S. Integrating models and data to estimate the structural reliability of utility poles during hurricanes. Risk Analysis, 2014, 34(6): 1079-1094

[19] Hazelhoff, L., I. Creusen, and P.H. de With. 2014. System for semi-automated surveying of street-lighting poles from street-level panoramic images. In Proceedings of IEEE Winter Conference on Applications of Computer Vision, 24–26 March 2014, Steamboat Springs, CO, USA. https://ieeexplore.ieee.org/abstract/document/6836109. Accessed 2 Feb 2019.

[20] Hink, R.C.B., J.M. Beaver, M.A. Buckner, T. Morris, U. Adhikari, and S. Pan. 2014. Machine learning for power system disturbance and cyber-attack discrimination. In Proceedings of 2014 7th International Symposium on Resilient Control Systems (ISRCS), 19–21 August 2014, Denver, Colorado, USA. https://ieeexplore.ieee.org/abstract/document/6900095. Accessed 2 Feb 2019.

[21] Landa J, Ondroušek V. Detection of pole-like objects from LIDAR data. Procedia -Social and Behavioral Sciences, 2016, 220: 226-235

[22] Lehtomäki M, Jaakkola A, Hyyppä J, Kukko A, Kaartinen H. Detection of vertical pole-like objects in a road environment using vehicle-based laser scanning data. Remote Sensing, 2010, 2(3): 641-664

[23] Liberge S, Soheilian B, Chehata N, Paparoditis N. Extraction of vertical posts in 3D laser point clouds acquired in dense urban areas by a mobile mapping system. International Archives of Photogrammetry Remote Sensing and Spatial Information, 2010, 38: 126-130.

[24] Mitchell MD, Beyeler WE. Studying the relationship between system-level and component-level resilience. Journal of Complex Systems, 2015

[25] Natvig B, Huseby AB, Reistadbakk MO. Measures of component importance in repairable multistate systems—a numerical study. Reliability Engineering & System Safety, 2011, 96(12): 1680-1690

[26] NESC (National Electrical Safety Code) IEEE standard, 2017, New York: The Institute of Electrical and Electronic Engineers Inc

[27] NOAA (National Oceanic and Atmospheric Administration/National Weather Service). 2019a. Saffir-Simpson Hurricane wind scale. Washington, DC: NOAA. https://www.nhc.noaa.gov/aboutgloss.shtml. Accessed 5 Feb 2020.

[28] NOAA (National Oceanic and Atmospheric Administration). 2019b. Hurricane research division: Frequently asked questions contributed by Chris Landsea. Washington, DC: NOAA. https://www.aoml.noaa.gov/hrd/tcfaq/E23.html. Accessed 20 Jul 2019.

[29] Ordóñez Celestino, Cabo Carlos, Sanz-Ablanedo Enoc. Automatic Detection and Classification of Pole-Like Objects for Urban Cartography Using Mobile Laser Scanning Data. Sensors, 2017, 17(7): 1465

[30] Potvin, J., and T. Short. 2016. Resiliency testing of overhead distribution components and systems. In Proceedings of 2016 IEEE/PES Transmission and Distribution Conference and Exposition (T&D), 2–5 May 2016, Dallas, TX, USA. https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7519934. Accessed 16 Mar 2019.

[31] Quanta Technology. 2009. Cost-benefit analysis of the deployment of utility infrastructure upgrades and storm hardening programs: Final report. Public Utility Commission of Texas Project No. 36375. Raleigh, NC: Quanta Technology. http://www.puc.texas.gov/industry/electric/reports/infra/utlity_infrastructure_upgrades_rpt.pdf. Accessed 10 May 2019. http://www.puc.texas.gov/industry/electric/reports/infra/utlity_infrastructure_upgrades_rpt.pdf. Accessed 10 May 2019.

[32] Sharma, H., V. Adithya, T. Dutta, and P. Balamuralidhar. 2015. Image analysis-based automatic utility pole detection for remote surveillance. In Proceedings of 2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA), 23–25 November 2015, Adelaide, Australia. https://ieeexplore.ieee.org/abstract/document/7371267. Accessed 4 Apr 2019.

[33] Thukaram D, Khincha HP, Vijaynarasimha HP. Artificial neural network and support vector machine approach for locating faults in radial distribution systems. IEEE Transactions on Power Delivery, 2005, 20(2): 710-721

[34] U.S. Environmental Protection Agency. 2016. Climate change indicators: weather and climate. https://www.epa.gov/climate-indicators/weather-climate. Accessed 2 Feb 2020.

[35] U.S. Department of Energy. 2013. Comparing the impacts of northeast hurricanes on energy infrastructure. Office of Electricity Delivery and Energy Reliability. http://www.oe.netl.doe.gov/docs/Northeast%20Storm%20Comparison_FINAL_041513c.pdf. Accessed 14 Mar 2019.

[36] Yokoyama H, Date H, Kanai S, Takeda H. Detection and classification of pole-like objects from mobile laser scanning data of urban environments. International Journal of Cad/Cam, 2013, 13(2): 31-40.

[37] Zobel CW. Representing perceived tradeoffs in defining disaster resilience. Decision Support Systems, 2011, 50(2): 394-403

[38] Zobel CW, Khansa L. Quantifying cyberinfrastructure resilience against multi-event attacks. Decision Sciences, 2012, 43(4): 687-710