基于时间序列的电能表月故障数预测方法

doi:10.11930/j.issn.1004-9649.201910016

中国电力 ›› 2020, Vol. 53 ›› Issue (6): 72-80.DOI: 10.11930/j.issn.1004-9649.201910016

基于时间序列的电能表月故障数预测方法

李媛¹, 郑安刚¹, 谭煌¹, 陈昊¹, 程淑亚², 蔡慧², 王黎欣³

1. 中国电力科学研究院有限公司，北京 100192;
2. 中国计量大学机电工程学院，浙江杭州 310018;
3. 国网浙江省电力有限公司电力科学研究院，浙江杭州 310014

收稿日期:2019-10-09 修回日期:2020-02-22 发布日期:2020-06-05
作者简介:李媛(1991-),女,硕士,助理工程师,从事电测量技术研究,E-mail:liyuan3@epri.sgcc.com.cn;郑安刚(1976-),男,硕士,高级工程师(教授级),从事电测量技术研究,E-mail:zhengangang@epri.sgcc.com.cn;谭煌(1991-),男,硕士,工程师,从事计量及用电信息采集技术研究,E-mail:tanhuang@epri.sgcc.com.cn;陈昊(1984-),男,硕士,高级工程师,从事电测量技术研究,E-mail:chenhao2010@epri.sgcc.com.cn;程淑亚(1995-),女,硕士研究生,从事电参数检测与控制和电力大数据分析研究,E-mail:1820760593@qq.com;蔡慧(1980-),男,博士,副教授,从事电参数检测与控制和电力大数据分析研究,E-mail:caihui@cjlu.edu.cn;王黎欣(1991-),女,硕士,工程师,从事电力计量技术研究,E-mail:wlx417@163.com
基金资助:
国家电网公司科技项目(配用电设备健康状态在线监测、高效运维及智能评价关键技术研究及应用，JL71-18-019)

A New Method for Predicting the Monthly Fault Number of Watt-hour Meters Based on Time Series

LI Yuan¹, ZHENG Angang¹, TAN Huang¹, CHEN Hao¹, CHENG Shuya², CAI Hui², WANG Lixin³

1. China Electric Power Research Institute Co., Ltd., Beijing 100192, China;
2. College of Mechanical and Electrical Engineering, China Jiliang University, Hangzhou 310018, China;
3. State Grid Zhejiang Electric Power Research Institute, Hangzhou 310014, China

Received:2019-10-09 Revised:2020-02-22 Published:2020-06-05
Supported by:
This work is supported by Science and Technology Project of State Grid Corporation of China (Research and Application of Key Technologies for Online Health Monitoring, Efficient Operation and Maintenance and Intelligent Evaluation of Distributed Electrical Equipment, No. JL71-18-019)

摘要/Abstract

摘要： 针对当前国网信息系统中电能表故障预测模型比较简单、不够全面和没有具体电能表月故障数预测模型的问题，基于时间序列建立综合时间序列预测模型，实现对批次电能表月故障数较准确的预测。首先计算电能表月故障数的移动平均序列，去除微小波动；然后根据序列是否有明显长期趋势，选用ARIMA模型或指数平滑模型对移动平均序列进行预测；最后采用反向移动平均，实现对整个批次电能表月故障数准确的短期预测。通过与BP神经网络模型的预测进行对比，验证了综合时间序列模型的实用性和准确性。在此基础上，建立电能表月故障总数预测模型。计量资产管理部门可以根据所提方法对故障电能表数进行预测，根据预测结果进行备货，提高管理部门的资源配置合理性和工作效率。

关键词: 电能表, 月故障数, 时间序列, BP神经网络, 电能表合理分配

Abstract: The existing watt-hour meter fault prediction models in the State Grid information system are relatively simple and insufficient, and there is no specific model for predicting the monthly fault number of watt-hour meters. Based on time series, an integrated time series prediction model is established for an accurate prediction of the monthly fault number of batch watt-hour meters. Firstly, the moving average sequence is calculated for the monthly fault number of watt-hour meters to remove small fluctuations. And then, the ARIMA model or exponential smoothing model is selected to predict the moving average sequence according to the long-term trend of the sequence. Finally, the reverse moving average is used to realize the accurate short-term prediction of the monthly fault number of the whole batch of watt-hour meters. By comparison with the BP neural network model, the practicability and accuracy of the proposed time series model is verified. On this basis, a monthly fault prediction model is established. The measurement asset management departments can use the proposed method to predict the number of faulted watt-hour meters, and prepare the stock according to the prediction results, consequently improving the rationality of resource allocation and work efficiency.

Key words: watt-hour meter, monthly fault number, time series, BP neural network, reasonable distribution of watt-hour meters

李媛, 郑安刚, 谭煌, 陈昊, 程淑亚, 蔡慧, 王黎欣. 基于时间序列的电能表月故障数预测方法[J]. 中国电力, 2020, 53(6): 72-80.

LI Yuan, ZHENG Angang, TAN Huang, CHEN Hao, CHENG Shuya, CAI Hui, WANG Lixin. A New Method for Predicting the Monthly Fault Number of Watt-hour Meters Based on Time Series[J]. Electric Power, 2020, 53(6): 72-80.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.201910016

https://www.electricpower.com.cn/CN/Y2020/V53/I6/72

参考文献

[1] 李梦宁, 张泽亚, 张知, 等. 基于GRAT算法的电能表故障概率决策树分析[J]. 电力大数据, 2017, 20(10): 7-10, 60
LI Mengning, ZHANG Zeya, ZHANG Zhi, et al. Analysis of decision tree for power meter fault probability based on GRAT algorithm[J]. Power Systems and Big Data, 2017, 20(10): 7-10, 60
[2] 张鹏飞, 瞿海妮, 肖其师, 等. 基于气象因素和时间序列分析的配电网故障数量预测[J]. 陕西电力, 2016, 44(1): 68-72
ZHANG Pengfei, QU Haini, XIAO Qishi, et al. Distribution network faults prediction based on meteorological factors and time series analysis[J]. Shaanxi Electric Power, 2016, 44(1): 68-72
[3] 李生彪. 基于ARMA模型的故障率时间序列预测[J]. 自动化与仪器仪表, 2015(12): 218-219
LI Shengbiao. Fault rate time series prediction based on ARMA model[J]. Automation & Instrumentation, 2015(12): 218-219
[4] 丁明, 张立军, 吴义纯. 基于时间序列分析的风电场风速预测模型[J]. 电力自动化设备, 2005, 25(8): 32-34
DING Ming, ZHANG Lijun, WU Yichun. Wind speed forecast model for wind farms based on time series analysis[J]. Electric Power Automation Equipment, 2005, 25(8): 32-34
[5] 贺宁. 智能电表故障大数据分析探究[J]. 中小企业管理与科技(上旬刊), 2016(7): 142-14
[6] 潘迪夫, 刘辉, 李燕飞. 基于时间序列分析和卡尔曼滤波算法的风电场风速预测优化模型[J]. 电网技术, 2008, 32(7): 82-86
PAN Difu, LIU Hui, LI Yanfei. A wind speed forecasting optimization model for wind farms based on time series analysis and Kalman filter algorithm[J]. Power System Technology, 2008, 32(7): 82-86
[7] 张立栋, 李继影, 吴颖, 等. 不同时间分辨率的风功率时间序列ARIMA模型预测[J]. 中国电力, 2016, 49(6): 176-180
ZHANG Lidong, LI Jiying, WU Ying, et al. ARIMA model forecast for wind power time series with different temporal resolutions[J]. Electric Power, 2016, 49(6): 176-180
[8] 贡文伟, 黄晶. 基于灰色理论与指数平滑法的需求预测综合模型[J]. 统计与决策, 2017(1): 72-76
GONG Weiwen, HUANG Jing. A demand forecast model based on the gray theory and exponential smoothing method[J]. Statistics and Decision, 2017(1): 72-76
[9] 彭凯, 邓建明, 张运林, 等. 1957~2015年我国春季短期温度波动规律[J]. 气候与环境研究, 2019, 24(1): 125-134
PENG Kai, DENG Jianming, ZHANG Yunlin, et al. Short-term temperature fluctuation in the spring in China during 1957-2015[J]. Climatic and Environmental Research, 2019, 24(1): 125-134
[10] 薛阳, 杜新纲, 张蓬鹤, 等. 电能表故障与地域气候、行业负荷关系研究[J]. 中国电力, 2017, 50(8): 98-105
XUE Yang, DU Xingang, ZHANG Penghe, et al. Research on the relationship between electric energy meter fault and regional climate & load in different industries[J]. Electric Power, 2017, 50(8): 98-105
[11] 韦跃. 基于长期监测数据的混凝土梁桥健康状态评判方法研究[D]. 重庆: 重庆交通大学, 2014.
WEI Yue. Assessment method research to concrete beam bridges health conditions based on long-term monitoring data[D]. Chongqing: Chongqing Jiaotong University, 2014.
[12] 杨平, 彭道刚, 韩璞, 等. 神经网络预测控制算法及其应用[J]. 控制工程, 2003, 10(4): 349-351
YANG Ping, PENG Daogang, HAN Pu, et al. Neural networks predictive control algorithm and its application study[J]. Control Engineering of China, 2003, 10(4): 349-351
[13] 王文剑. BP神经网络模型的优化[J]. 计算机工程与设计, 2000, 21(6): 8-10
WANG Wenjian. The optimization of BP neural networks[J]. Computer Engineering and Design, 2000, 21(6): 8-10
[14] 赵忠明, 施天威, 董伟, 等. 灰色关联分析与BP神经网络的概率积分法参数预测[J]. 测绘科学, 2017, 42(7): 36-40, 51
ZHAO Zhongming, SHI Tianwei, DONG Wei, et al. The prediction of probability-integral method parameters based on grey relational analysis and BP neural network[J]. Science of Surveying and Mapping, 2017, 42(7): 36-40, 51
[15] QI X N, BAO H B, GAO J D. Exponential input-to-state stability of quaternion-valued neural network with time delay[J]. Applied Mathematics and Computation, 2019, 358: 382-393.
[16] 焦李成, 杨淑媛, 刘芳, 等. 神经网络七十年: 回顾与展望[J]. 计算机学报, 2016, 39(8): 1697-1716
JIAO Licheng, YANG Shuyuan, LIU Fang, et al. Seventy years beyond neural networks: retrospect and prospect[J]. Chinese Journal of Computers, 2016, 39(8): 1697-1716
[17] 孙一睿, 李钰鑫, 陈磊, 等. 基于遗传算法优化神经网络的SCR催化剂失效预测[J]. 中国电机工程学报, 2016, 36(增刊1): 112-120
SUN Yirui, LI Yuxin, CHEN Lei, et al. Deactivation forecasting of SCR catalyst based on GABP neural networks[J]. Proceedings of the CSEE, 2016, 36(S1): 112-120
[18] 胡鹏飞, 谢诞梅, 熊扬恒. 一种基于白箱模型的人工神经网络参数辨识算法[J]. 中国电机工程学报, 2016, 36(10): 2734-2741
HU Pengfei, XIE Danmei, XIONG Yangheng. An algorithm of parameter identification for wright-box models based on artificial neuron network[J]. Proceedings of the CSEE, 2016, 36(10): 2734-2741
[19] 颜廷鑫, 刘光晔, 谢冬冬. 基于神经网络的法向阻抗模裕度快速计算方法[J]. 电网技术, 2016, 40(8): 2389-2395
YAN Tingxin, LIU Guangye, XIE Dongdong. Fast estimation method for normal impedance modulus margin based on neural network[J]. Power System Technology, 2016, 40(8): 2389-2395
[20] 高正中, 龚群英, 刘隆吉, 等. 基于BP网络算法优化粗糙-Petri网的电网故障诊断[J]. 中国电力, 2016, 49(8): 12-16, 30
GAO Zhengzhong, GONG Qunying, LIU Longji, et al. Power system fault diagnosis based on rough set and petri network optimized by BP algorithm[J]. Electric Power, 2016, 49(8): 12-16, 30
[21] 闫龙川, 张晓亮, 杨猛, 等. 基于BP神经网络的信息系统故障自动恢复技术[J]. 中国电力, 2017, 50(8): 146-149, 184
YAN Longchuan, ZHANG Xiaoliang, YANG Meng, et al. Research and application of information system fault automatic recovery technology based on BP neural network[J]. Electric Power, 2017, 50(8): 146-149, 184
[22] 陈忱, 胡薇薇, 孙宇锋, 等. 基于BP-AdaBoost的电子式电能表故障检测方法[J]. 电光与控制, 2013, 20(4): 72-76
CHEN Chen, HU Weiwei, SUN Yufeng, et al. Failure supervising method for electricity meter based on BP-AdaBoost algorithm[J]. Electronics Optics & Control, 2013, 20(4): 72-76

基于时间序列的电能表月故障数预测方法

A New Method for Predicting the Monthly Fault Number of Watt-hour Meters Based on Time Series

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	吴小忠, 肖立华, 童超, 夏向阳, 袁翎, 甘星, 江志文, 黄湘源. 基于传递熵与JS-BP神经网络的锂离子电池容量预测模型[J]. 中国电力, 2025, 58(2): 186-192, 215.
[2]	马汝括, 董杰, 王雅湉, 伊国鑫, 丁祥浩, 马乐. 基于神经网络的高寒地区CF₄和SF₆/CF₄检测[J]. 中国电力, 2024, 57(3): 103-112.
[3]	周颖, 白雪峰, 王阳, 邱敏, 孙冲, 武亚杰, 李彬. 面向虚拟电厂运营的温度敏感负荷分析与演变趋势研判[J]. 中国电力, 2024, 57(1): 9-17.
[4]	黄友朋, 路韬, 陈亮, 党三磊, 张捷, 余思达. 智能电能表批次故障预警和寿命预估方法[J]. 中国电力, 2022, 55(7): 87-92.
[5]	杨桢, 马钰超, 李丽, 李鑫, 马子莹. 基于HHT和GA-BP的电压暂降源定位方法[J]. 中国电力, 2022, 55(3): 97-104.
[6]	王新刚, 朱彬若, 顾臻. 基于综合能源计量大数据的中长期用电量预测[J]. 中国电力, 2021, 54(10): 211-216.
[7]	程瑛颖, 杜杰, 周全, 张家铭, 张晓勇, 李刚. 基于随机矩阵理论和聚类算法的电能表运行状态评估方法[J]. 中国电力, 2020, 53(11): 116-125.
[8]	孙凤杰, 赵晨凯. 光伏串列信道噪声特性研究与建模[J]. 中国电力, 2019, 52(6): 147-153.
[9]	解进军, 周文斌, 刘士峰, 蒋紫娟, 靳阳, 赵磊. 考虑现场校验的智能电能表可靠性分析与改进[J]. 中国电力, 2019, 52(10): 79-84.
[10]	邓博, 徐鸿, 郭鹏, 张乃强, 倪永中. 变负荷下超（超）临界机组过热器壁温预测[J]. 中国电力, 2018, 51(3): 13-20.
[11]	于群, 张铮, 屈玉清, 贺庆. 基于ARMA-GABP组合模型的电网大停电事故损失负荷预测[J]. 中国电力, 2018, 51(11): 38-44.
[12]	林芳, 林焱, 吕宪龙, 程新功, 张慧瑜, 陈伯建. 基于均衡KNN算法的电力负荷短期并行预测[J]. 中国电力, 2018, 51(10): 88-94,102.
[13]	闫龙川, 张晓亮, 杨猛, 刘冬梅. 基于BP神经网络的信息系统故障自动恢复技术[J]. 中国电力, 2017, 50(8): 146-149.
[14]	薛阳, 杜新纲, 张蓬鹤, 张加海, 邹宇汉, 彭楚宁. 电能表故障与地域气候、行业负荷关系研究[J]. 中国电力, 2017, 50(8): 98-105.
[15]	苏慧玲，，王忠东，，蔡奇新，，宋瑞鹏，，李纬，. 大规模智能电能表自动化检定的关键技术[J]. 中国电力, 2016, 49(6): 126-131.

模态框（Modal）标题

基于时间序列的电能表月故障数预测方法

A New Method for Predicting the Monthly Fault Number of Watt-hour Meters Based on Time Series

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics