Fault detection for district heating substations: Beyond three-sigma approaches

IF 5.4 Q2 ENERGY & FUELS Smart Energy Pub Date : 2024-09-30 DOI:10.1016/j.segy.2024.100159
Chris Hermans, Jad Al Koussa, Tijs Van Oevelen, Dirk Vanhoudt
{"title":"Fault detection for district heating substations: Beyond three-sigma approaches","authors":"Chris Hermans,&nbsp;Jad Al Koussa,&nbsp;Tijs Van Oevelen,&nbsp;Dirk Vanhoudt","doi":"10.1016/j.segy.2024.100159","DOIUrl":null,"url":null,"abstract":"<div><div>The topic of this paper is fault detection for district heating substations, which is an important enabler for the transition towards fourth-generation district heating systems. Classical fault detection approaches are often based on anomaly detection, commonly making the implicit assumption that the errors between the measurements and the predictions made by the baseline model are i.i.d. and following an underlying Gaussian distribution. Our analysis shows that this does not hold up in the field, showing clear seasonality in the error over time. We propose to replace the Gaussian error model by a quantile regression model in order to provide a more nuanced fault threshold, conditioned on time and other input variables. Additionally, we observed that properly training the baseline model comes with its own challenges due to this time dependency, which we propose to resolve by employing an ensemble of models, trained on different periods of time. We demonstrate our method on unlabelled operational data obtained from a Swedish district heating operator to illustrate its use in the field. In addition, we validate it on labelled data from our residential lab setup, testing a variety of common faults.</div></div>","PeriodicalId":34738,"journal":{"name":"Smart Energy","volume":null,"pages":null},"PeriodicalIF":5.4000,"publicationDate":"2024-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Smart Energy","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2666955224000297","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENERGY & FUELS","Score":null,"Total":0}
引用次数: 0

Abstract

The topic of this paper is fault detection for district heating substations, which is an important enabler for the transition towards fourth-generation district heating systems. Classical fault detection approaches are often based on anomaly detection, commonly making the implicit assumption that the errors between the measurements and the predictions made by the baseline model are i.i.d. and following an underlying Gaussian distribution. Our analysis shows that this does not hold up in the field, showing clear seasonality in the error over time. We propose to replace the Gaussian error model by a quantile regression model in order to provide a more nuanced fault threshold, conditioned on time and other input variables. Additionally, we observed that properly training the baseline model comes with its own challenges due to this time dependency, which we propose to resolve by employing an ensemble of models, trained on different periods of time. We demonstrate our method on unlabelled operational data obtained from a Swedish district heating operator to illustrate its use in the field. In addition, we validate it on labelled data from our residential lab setup, testing a variety of common faults.

Abstract Image

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
区域供热变电站的故障检测:超越三西格玛方法
本文的主题是区域供热变电站的故障检测,这是向第四代区域供热系统过渡的重要推动因素。经典的故障检测方法通常以异常检测为基础,通常隐含的假设是测量误差与基线模型的预测误差均为 i.i.d.,且遵循基本的高斯分布。我们的分析表明,这一假设在实际应用中并不成立,误差随时间的变化具有明显的季节性。我们建议用量子回归模型取代高斯误差模型,以便根据时间和其他输入变量提供更细致的故障阈值。此外,我们观察到,由于这种时间依赖性,正确训练基线模型本身就存在挑战,我们建议采用在不同时间段训练的集合模型来解决这一问题。我们在瑞典地区供热运营商提供的无标签运行数据上演示了我们的方法,以说明其在实际中的应用。此外,我们还在住宅实验室设置的标记数据上对其进行了验证,测试了各种常见故障。
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 去求助
来源期刊
Smart Energy
Smart Energy Engineering-Mechanical Engineering
CiteScore
9.20
自引率
0.00%
发文量
29
审稿时长
73 days
期刊最新文献
Predictive building energy management with user feedback in the loop Optimal energy management in smart energy systems: A deep reinforcement learning approach and a digital twin case-study Economic viability of decentralised battery storage systems for single-family buildings up to cross-building utilisation The impact of offshore energy hub and hydrogen integration on the Faroe Island’s energy system The cost of CO2 emissions abatement in a micro energy community in a Belgian context
×
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