The residual life prediction of power grid transformers based on GA-ELM computational model and digital twin data

Q3 Engineering

EAI Endorsed Transactions on Energy Web Pub Date : 2024-04-04 DOI:10.4108/ew.4896

Xiangshang Wang, Chunlin Li, Jianguang Zhang

{"title":"The residual life prediction of power grid transformers based on GA-ELM computational model and digital twin data","authors":"Xiangshang Wang, Chunlin Li, Jianguang Zhang","doi":"10.4108/ew.4896","DOIUrl":null,"url":null,"abstract":"As one of the core equipment of the power grid, the operation status of transformers directly affects the stability and reliability of the power system. To accurately evaluate the remaining life of power grid transformers, a genetic algorithm is applied to optimize the Extreme Learning Machine based on digital twin technology. Then, considering changes in load rate, a residual life prediction model for power grid transformers is constructed. From the results, the error of the research method was within 2℃, with a maximum error of only 1.76℃. The research model converged with a fitness value of 0.04 at 150 iterations. It showed good predictive performance for hot spot temperatures under different load rates, with an average accuracy of 99.97%. Compared with backpropagation models and extreme learning machine models, the research method improved accuracy by 2.85% and 1.01%, respectively, with small and stable prediction errors. It verified the superiority of the research model, indicating that the research method can improve the accuracy of predicting the remaining life for power grid transformers. By monitoring the operation status of transformers in real-time, potential faults can be detected in a timely manner. The maintenance and replacement can be carried out in advance to avoid power outages caused by equipment damage. In addition, the research can provide reference for the planning and design of power systems, and support the stability and reliability of power systems.","PeriodicalId":53458,"journal":{"name":"EAI Endorsed Transactions on Energy Web","volume":"9 15","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"EAI Endorsed Transactions on Energy Web","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4108/ew.4896","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Engineering","Score":null,"Total":0}

引用次数: 0

Abstract

As one of the core equipment of the power grid, the operation status of transformers directly affects the stability and reliability of the power system. To accurately evaluate the remaining life of power grid transformers, a genetic algorithm is applied to optimize the Extreme Learning Machine based on digital twin technology. Then, considering changes in load rate, a residual life prediction model for power grid transformers is constructed. From the results, the error of the research method was within 2℃, with a maximum error of only 1.76℃. The research model converged with a fitness value of 0.04 at 150 iterations. It showed good predictive performance for hot spot temperatures under different load rates, with an average accuracy of 99.97%. Compared with backpropagation models and extreme learning machine models, the research method improved accuracy by 2.85% and 1.01%, respectively, with small and stable prediction errors. It verified the superiority of the research model, indicating that the research method can improve the accuracy of predicting the remaining life for power grid transformers. By monitoring the operation status of transformers in real-time, potential faults can be detected in a timely manner. The maintenance and replacement can be carried out in advance to avoid power outages caused by equipment damage. In addition, the research can provide reference for the planning and design of power systems, and support the stability and reliability of power systems.

查看原文本刊更多论文

基于 GA-ELM 计算模型和数字孪生数据的电网变压器残余寿命预测

变压器作为电网的核心设备之一，其运行状况直接影响着电力系统的稳定性和可靠性。为准确评估电网变压器的剩余寿命，基于数字孪生技术，应用遗传算法对极限学习机进行优化。然后，考虑负载率的变化，构建了电网变压器剩余寿命预测模型。从结果来看，研究方法的误差在 2℃以内，最大误差仅为 1.76℃。研究模型在迭代 150 次后收敛，适配值为 0.04。该模型对不同负载率下的热点温度具有良好的预测性能，平均准确率为 99.97%。与反向传播模型和极端学习机模型相比，该研究方法的准确率分别提高了 2.85% 和 1.01%，预测误差小且稳定。这验证了该研究模型的优越性，表明该研究方法可以提高电网变压器剩余寿命预测的准确性。通过实时监控变压器的运行状态，可以及时发现潜在故障。可以提前进行维护和更换，避免因设备损坏造成停电。此外，该研究还可为电力系统的规划和设计提供参考，为电力系统的稳定性和可靠性提供支持。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

EAI Endorsed Transactions on Energy Web Energy-Energy Engineering and Power Technology

CiteScore

2.60

自引率

0.00%

发文量

审稿时长

10 weeks

期刊介绍： With ICT pervading everyday objects and infrastructures, the ‘Future Internet’ is envisioned to undergo a radical transformation from how we know it today (a mere communication highway) into a vast hybrid network seamlessly integrating knowledge, people and machines into techno-social ecosystems whose behaviour transcends the boundaries of today’s engineering science. As the internet of things continues to grow, billions and trillions of data bytes need to be moved, stored and shared. The energy thus consumed and the climate impact of data centers are increasing dramatically, thereby becoming significant contributors to global warming and climate change. As reported recently, the combined electricity consumption of the world’s data centers has already exceeded that of some of the world''s top ten economies. In the ensuing process of integrating traditional and renewable energy, monitoring and managing various energy sources, and processing and transferring technological information through various channels, IT will undoubtedly play an ever-increasing and central role. Several technologies are currently racing to production to meet this challenge, from ‘smart dust’ to hybrid networks capable of controlling the emergence of dependable and reliable green and energy-efficient ecosystems – which we generically term the ‘energy web’ – calling for major paradigm shifts highly disruptive of the ways the energy sector functions today. The EAI Transactions on Energy Web are positioned at the forefront of these efforts and provide a forum for the most forward-looking, state-of-the-art research bringing together the cross section of IT and Energy communities. The journal will publish original works reporting on prominent advances that challenge traditional thinking.