"Fault Prediction of Online Power Metering Equipment Based on Hierarchical Bayesian Network"

IF 0.6 4区工程技术 Q4 ENGINEERING, ELECTRICAL & ELECTRONIC

Informacije Midem-Journal of Microelectronics Electronic Components and Materials Pub Date : 2019-09-23 DOI:10.33180/infmidem2019.205

Daosheng Cheng, Penghe Zhang, Fan Zhang, Jiayu Huang

{"title":"\"Fault Prediction of Online Power Metering\nEquipment Based on Hierarchical Bayesian Network\"","authors":"Daosheng Cheng, Penghe Zhang, Fan Zhang, Jiayu Huang","doi":"10.33180/infmidem2019.205","DOIUrl":null,"url":null,"abstract":"The failure rate assessment of online metering equipment is significan t for power metering. For traditional methods, the performance of the model is not satisfactory especially in the case of small samples. In this paper, a n online power measuring equipment fault evaluation method based on Weibull parameter hierarchical Bayesian model is proposed. Firstly, the z-score method is used to eliminate outliers in the raw failure data. Then, a generalized linear function with variable intercept is established according to the characteristics of failure data. The information of each region is merged using the characteristics of multi-layer Bayesian network uncertainty reasoning. The model parameters are updated based on the Markov chain Monte Carlo method. Thereafter, the trend of failure rate is provided with time-dependent. Finally, the proposed method is verified by the failure samples of the online measurement equipment in three typical environmental areas. The accuracy and validity of the hierarchical Bayesian model is verified by a series of experiments","PeriodicalId":56293,"journal":{"name":"Informacije Midem-Journal of Microelectronics Electronic Components and Materials","volume":"16 1","pages":""},"PeriodicalIF":0.6000,"publicationDate":"2019-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Informacije Midem-Journal of Microelectronics Electronic Components and Materials","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.33180/infmidem2019.205","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}

引用次数: 2

Abstract

The failure rate assessment of online metering equipment is significan t for power metering. For traditional methods, the performance of the model is not satisfactory especially in the case of small samples. In this paper, a n online power measuring equipment fault evaluation method based on Weibull parameter hierarchical Bayesian model is proposed. Firstly, the z-score method is used to eliminate outliers in the raw failure data. Then, a generalized linear function with variable intercept is established according to the characteristics of failure data. The information of each region is merged using the characteristics of multi-layer Bayesian network uncertainty reasoning. The model parameters are updated based on the Markov chain Monte Carlo method. Thereafter, the trend of failure rate is provided with time-dependent. Finally, the proposed method is verified by the failure samples of the online measurement equipment in three typical environmental areas. The accuracy and validity of the hierarchical Bayesian model is verified by a series of experiments

查看原文本刊更多论文

基于层次贝叶斯网络的在线电力计量设备故障预测

在线计量设备的故障率评估对电力计量具有重要意义。对于传统的方法，特别是在小样本情况下，模型的性能并不令人满意。提出了一种基于威布尔参数层次贝叶斯模型的电力测量设备在线故障评估方法。首先，使用z-score方法消除原始失效数据中的异常值。然后，根据失效数据的特点，建立了广义变截距线性函数。利用多层贝叶斯网络不确定性推理的特点，对各区域信息进行合并。基于马尔可夫链蒙特卡罗方法更新模型参数。故障率的变化趋势具有时间依赖性。最后，通过三种典型环境下在线测量设备的故障样本对所提方法进行了验证。通过一系列实验验证了层次贝叶斯模型的准确性和有效性

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

Informacije Midem-Journal of Microelectronics Electronic Components and Materials 工程技术-材料科学：综合

CiteScore

1.80

自引率

0.00%

发文量

审稿时长

>12 weeks

期刊介绍： Informacije MIDEM publishes original research papers in the fields of microelectronics, electronic components and materials. Review papers are published upon invitation only. Scientific novelty and potential interest for a wider spectrum of readers is desired. Authors are encouraged to provide as much detail as possible for others to be able to replicate their results. Therefore, there is no page limit, provided that the text is concise and comprehensive, and any data that does not fit within a classical manuscript can be added as supplementary material. Topics of interest include: Microelectronics, Semiconductor devices, Nanotechnology, Electronic circuits and devices, Electronic sensors and actuators, Microelectromechanical systems (MEMS), Medical electronics, Bioelectronics, Power electronics, Embedded system electronics, System control electronics, Signal processing, Microwave and millimetre-wave techniques, Wireless and optical communications, Antenna technology, Optoelectronics, Photovoltaics, Ceramic materials for electronic devices, Thick and thin film materials for electronic devices.