无人机与计算机视觉在复杂油田提高输配电可靠性试点的成功案例与经验教训

M. Yudhy, Muhammad Pratama, R. Wibawa, Ardiyansyah Lubis, P. Pujihatma
{"title":"无人机与计算机视觉在复杂油田提高输配电可靠性试点的成功案例与经验教训","authors":"M. Yudhy, Muhammad Pratama, R. Wibawa, Ardiyansyah Lubis, P. Pujihatma","doi":"10.2523/iptc-22811-ea","DOIUrl":null,"url":null,"abstract":"\n Electrical power supply reliability is a key enabler in supporting massive and aggressive exploration and exploitation campaigns in the upstream sector. For a certain complex oilfield asset, a total of more than 3,000 km of power transmission and distribution lines are operated and maintained to support its massive operation. All these power lines shall be monitored and inspected regularly to ensure it is free of operational threat that could reduce their reliability. From historical data, there are two main threats in power line operations, vegetation risk (trees and animals) and broken insulators. The current method of manual inspection and monitoring through Operator Routine Duties Check (ORDC) is not very effective since it took a considerably long period to complete and can only cover a limited area for each inspection activity session whereas the area to be inspected is vast. As a result, the inspection and monitoring program was sub-optimal to detecting the operational threat earlier.\n The advances in digital technology, particularly computer vision, cloud computing, and artificial intelligence, enable every device with a camera and internet connection to become additional \"eyes\" that monitor, inspect and analyze everything in sight. One of the optical devices with high potential for utilization in power system inspection is the Unmanned Aerial Vehicle (UAV) or best known as the drone. Drone enhanced with computer vision will have the optimal capability for inspection and surveillance of vegetation risk and broken insulators for larger areas in each inspection round. Hence, we could automate the inspection and surveillance activities and even improve their effectiveness and efficiency compared with the manual method.\n In this paper, we will discuss the successful pilot implementation of drones, computer vision, and artificial intelligence technology in power system operations that have improved the effectiveness of the surveillance program at a lower cost. The pilot implementation has been proven to reduce the number of power outages caused by vegetation risk and broken insulators by 50% and bring verified financial benefit of USD 7,619 per month from avoiding loss of production opportunities due to power outages related to vegetation risk and broken insulators. The financial benefit can pay off the implementation cost in 4 months of continuous operation. As a path forward, the pilot implementation will be expanded further to several other areas with a high risk of vegetation threat and broken insulators to assess its applicability in other locations before full-scale implementation.","PeriodicalId":283978,"journal":{"name":"Day 1 Wed, March 01, 2023","volume":"94 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Success Stories and Lessons Learned from Pilot Implementation of Unmanned Air Vehicle and Computer Vision to Improve Transmission & Distribution Reliability in Complex Oilfield\",\"authors\":\"M. Yudhy, Muhammad Pratama, R. Wibawa, Ardiyansyah Lubis, P. Pujihatma\",\"doi\":\"10.2523/iptc-22811-ea\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"\\n Electrical power supply reliability is a key enabler in supporting massive and aggressive exploration and exploitation campaigns in the upstream sector. For a certain complex oilfield asset, a total of more than 3,000 km of power transmission and distribution lines are operated and maintained to support its massive operation. All these power lines shall be monitored and inspected regularly to ensure it is free of operational threat that could reduce their reliability. From historical data, there are two main threats in power line operations, vegetation risk (trees and animals) and broken insulators. The current method of manual inspection and monitoring through Operator Routine Duties Check (ORDC) is not very effective since it took a considerably long period to complete and can only cover a limited area for each inspection activity session whereas the area to be inspected is vast. As a result, the inspection and monitoring program was sub-optimal to detecting the operational threat earlier.\\n The advances in digital technology, particularly computer vision, cloud computing, and artificial intelligence, enable every device with a camera and internet connection to become additional \\\"eyes\\\" that monitor, inspect and analyze everything in sight. One of the optical devices with high potential for utilization in power system inspection is the Unmanned Aerial Vehicle (UAV) or best known as the drone. Drone enhanced with computer vision will have the optimal capability for inspection and surveillance of vegetation risk and broken insulators for larger areas in each inspection round. Hence, we could automate the inspection and surveillance activities and even improve their effectiveness and efficiency compared with the manual method.\\n In this paper, we will discuss the successful pilot implementation of drones, computer vision, and artificial intelligence technology in power system operations that have improved the effectiveness of the surveillance program at a lower cost. The pilot implementation has been proven to reduce the number of power outages caused by vegetation risk and broken insulators by 50% and bring verified financial benefit of USD 7,619 per month from avoiding loss of production opportunities due to power outages related to vegetation risk and broken insulators. The financial benefit can pay off the implementation cost in 4 months of continuous operation. As a path forward, the pilot implementation will be expanded further to several other areas with a high risk of vegetation threat and broken insulators to assess its applicability in other locations before full-scale implementation.\",\"PeriodicalId\":283978,\"journal\":{\"name\":\"Day 1 Wed, March 01, 2023\",\"volume\":\"94 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-02-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Day 1 Wed, March 01, 2023\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.2523/iptc-22811-ea\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Day 1 Wed, March 01, 2023","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2523/iptc-22811-ea","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

电力供应的可靠性是支持上游地区大规模积极勘探和开发活动的关键因素。某复杂油田资产,为支撑其大规模运行,输配电线路运行维护总里程达3000多公里。所有这些电力线路都应定期监测和检查,以确保其不受可能降低其可靠性的操作威胁。从历史数据来看,电力线运行中有两个主要威胁,植被风险(树木和动物)和绝缘体破碎。目前通过操作员例行职责检查(ORDC)进行人工检查和监测的方法不是很有效,因为它需要相当长的时间才能完成,并且每次检查活动只能覆盖有限的区域,而要检查的区域是巨大的。因此,检查和监控程序在早期发现操作威胁方面是次优的。数字技术的进步,特别是计算机视觉、云计算和人工智能,使每一个带有摄像头和互联网连接的设备都能成为额外的“眼睛”,监控、检查和分析眼前的一切。在电力系统检测中具有很高应用潜力的光学设备之一是无人驾驶飞行器(UAV)或最广为人知的无人机。通过计算机视觉增强的无人机将在每轮检查中对更大区域的植被风险和破损绝缘体进行最佳检查和监视。因此,我们可以使检查和监视活动自动化,甚至比人工方法提高其有效性和效率。在本文中,我们将讨论无人机、计算机视觉和人工智能技术在电力系统运行中的成功试点实施,这些技术以较低的成本提高了监视计划的有效性。实践证明,试点实施后,因植被风险和绝缘子破碎导致的停电次数减少了50%,避免了因植被风险和绝缘子破碎导致的停电造成的生产机会损失,每月可带来7619美元的经济效益。经济效益可在连续运行4个月的时间内收回实施成本。作为前进的道路,试点实施将进一步扩大到其他几个植被威胁和绝缘体破损风险较高的地区,以便在全面实施之前评估其在其他地区的适用性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Success Stories and Lessons Learned from Pilot Implementation of Unmanned Air Vehicle and Computer Vision to Improve Transmission & Distribution Reliability in Complex Oilfield
Electrical power supply reliability is a key enabler in supporting massive and aggressive exploration and exploitation campaigns in the upstream sector. For a certain complex oilfield asset, a total of more than 3,000 km of power transmission and distribution lines are operated and maintained to support its massive operation. All these power lines shall be monitored and inspected regularly to ensure it is free of operational threat that could reduce their reliability. From historical data, there are two main threats in power line operations, vegetation risk (trees and animals) and broken insulators. The current method of manual inspection and monitoring through Operator Routine Duties Check (ORDC) is not very effective since it took a considerably long period to complete and can only cover a limited area for each inspection activity session whereas the area to be inspected is vast. As a result, the inspection and monitoring program was sub-optimal to detecting the operational threat earlier. The advances in digital technology, particularly computer vision, cloud computing, and artificial intelligence, enable every device with a camera and internet connection to become additional "eyes" that monitor, inspect and analyze everything in sight. One of the optical devices with high potential for utilization in power system inspection is the Unmanned Aerial Vehicle (UAV) or best known as the drone. Drone enhanced with computer vision will have the optimal capability for inspection and surveillance of vegetation risk and broken insulators for larger areas in each inspection round. Hence, we could automate the inspection and surveillance activities and even improve their effectiveness and efficiency compared with the manual method. In this paper, we will discuss the successful pilot implementation of drones, computer vision, and artificial intelligence technology in power system operations that have improved the effectiveness of the surveillance program at a lower cost. The pilot implementation has been proven to reduce the number of power outages caused by vegetation risk and broken insulators by 50% and bring verified financial benefit of USD 7,619 per month from avoiding loss of production opportunities due to power outages related to vegetation risk and broken insulators. The financial benefit can pay off the implementation cost in 4 months of continuous operation. As a path forward, the pilot implementation will be expanded further to several other areas with a high risk of vegetation threat and broken insulators to assess its applicability in other locations before full-scale implementation.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
The Proper Well Spacings – A Supplementary Method to Maximize The Gulf of Thailand Development Project Value Seismic Driven Machine Learning to Improve Precision and Accelerate Screening Shallow Gas Potentials in Tunu Shallow Gas Zone, Mahakam Delta, Indonesia Rejuvenating Waterflood Reservoir in a Complex Geological Setting of a Matured Brown Field Intelligent Prediction of Downhole Drillstring Vibrations in Horizontal Wells by Employing Artificial Neural Network Sand Fill Clean-Out on Wireline Enables Access to Additional Perforation Zones in Gas Well Producer
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1