基于气象特征挖掘与AdaBoost-MEA-ELM模型的绝缘子盐密预测

doi:10.11930/j.issn.1004-9649.202303084

摘要/Abstract

摘要： 为及时掌握输电线路绝缘子污秽情况，提出了一种基于气象的绝缘子盐密预测方法。挖掘了与积污相关性更强的气象特征，通过随机森林评估了气象特征的重要程度，结合序列前向搜索确立了最佳气象特征子集。基于台州市自然积污测试数据，使用极限学习机（extreme learning machine，ELM）建立盐密预测基础模型，并使用思维进化算法（mind evolution algorithm，MEA）对其初始权值与阈值进行优化，通过自适应提升（adaptive boosting，AdaBoost）算法集成进一步提高模型精度。结果表明：AdaBoost-MEA-ELM模型盐密预测平均绝对误差为0.0032 mg/cm²，相比原始ELM模型误差降低58.97%，优化效果显著；与其他模型对比验证了AdaBoost-MEA-ELM模型的性能以及3种算法结合的合理性；通过k折交叉验证获得了训练数据改变时模型误差的变化情况，进一步验证了模型的泛化性与稳定性。

关键词: 等值盐密预测, 气象特征, 随机森林, 极限学习机, 思维进化, AdaBoost算法

Abstract: In order to obtain the pollution condition of transmission line insulators in time, a method of insulator equivalent salt deposit density (ESDD) prediction based on meteorological data is proposed in this paper. The meteorological features that are more closely related to insulator pollution degree are mined, and the importance of each meteorological feature is evaluated by the random forest algorithm. Combined with the sequential forward search method, the optimal subset of meteorological features for ESDD prediction model could be determined. Based on the natural pollution test data of Taizhou City, the basic ESDD prediction model was established by using extreme learning machine (ELM), and its initial weights and thresholds were optimized by the mind evolution algorithm (MEA). Then the AdaBoost algorithm was applied to further improve the accuracy of the model. The results show that the average absolute error of ESDD prediction of AdaBoost-MEA-ELM model is 0.0032 mg/cm², which is 58.97% lower than that of the original ELM model. Compared with other common models, the performance of the proposed model and the rationality of the combination of these three algorithms are verified. The variation of prediction error when training data changed was obtained by k-fold verification method, which further prove the generalization performance and stability of the model.

Key words: ESDD prediction, meteorological characteristics, random forest, extreme learning machine, mind evolution algorithm, AdaBoost algorithm

王尧平, 李特, 姜凯华, 李文辉, 吴强, 王羽. 基于气象特征挖掘与AdaBoost-MEA-ELM模型的绝缘子盐密预测[J]. 中国电力, 2023, 56(9): 157-167.

WANG Yaoping, LI Te, JIANG Kaihua, LI Wenhui, WU Qiang, WANG Yu. Prediction of Insulator ESDD Based on Meteorological Feature Mining and AdaBoost-MEA-ELM Model[J]. Electric Power, 2023, 56(9): 157-167.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202303084

https://www.electricpower.com.cn/CN/Y2023/V56/I9/157

参考文献

[1] 王思华, 陈龙, 王军军, 等. 复合绝缘子伞套老化状态模糊综合评估[J]. 中国电力, 2021, 54(5): 156–165
WANG Sihua, CHEN Long, WANG Junjun, et al. Fuzzy comprehensive evaluation of aging state of silicone rubber sheds of composite insulators[J]. Electric Power, 2021, 54(5): 156–165
[2] 王思华, 王军军, 赵磊, 等. 污秽成分对复合绝缘子表面电场的影响[J]. 中国电力, 2021, 54(7): 149–157
WANG Sihua, WANG Junjun, ZHAO Lei, et al. Influence of pollution components on surface electric field of composite insulators[J]. Electric Power, 2021, 54(7): 149–157
[3] 黄冬梅, 王玥琦, 胡安铎, 等. 融合多维度特征的绝缘子状态边缘识别方法[J]. 中国电力, 2022, 55(1): 133–141
HUANG Dongmei, WANG Yueqi, HU Anduo, et al. An edge recognition method for insulator state based on multi-dimension feature fusion[J]. Electric Power, 2022, 55(1): 133–141
[4] 张嘉伟, 叶子帆, 王倩, 等. 基于F-P光纤泄漏电流传感器的绝缘子状态监测[J]. 高电压技术, 2022, 48(8): 2915–2923
ZHANG Jiawei, YE Zifan, WANG Qian, et al. Insulator condition monitoring based on F-P optical fiber leakage current sensor[J]. High Voltage Engineering, 2022, 48(8): 2915–2923
[5] 金立军, 田治仁, 高凯, 等. 基于红外与可见光图像信息融合的绝缘子污秽等级识别[J]. 中国电机工程学报, 2016, 36(13): 3682–3691, 3389
JIN Lijun, TIAN Zhiren, GAO Kai, et al. Discrimination of insulator contamination grades using information fusion of infrared and visible images[J]. Proceedings of the CSEE, 2016, 36(13): 3682–3691, 3389
[6] 王晴. 光传感监测绝缘子污秽的成分分析[J]. 电子测量技术, 2018, 41(23): 74–77
WANG Qing. Analysis of natural pollution deposit on optic sensor for monitoring of insulators contamination[J]. Electronic Measurement Technology, 2018, 41(23): 74–77
[7] 律方成, 戴日俊, 王胜辉, 等. 基于紫外成像图像信息的绝缘子表面放电量化方法[J]. 电工技术学报, 2012, 27(2): 261–268
LV Fangcheng, DAI Rijun, WANG Shenghui, et al. Study of insulator surface discharge quantification method based on ultraviolet imaging image information[J]. Transactions of China Electrotechnical Society, 2012, 27(2): 261–268
[8] 李红玲, 文习山. 绝缘子污秽放电声发射的统计指纹分析[J]. 高电压技术, 2010, 36(11): 2705–2710
LI Hongling, WEN Xishan. Statistical fingerprint analysis for contaminated insulator acoustic emission signals[J]. High Voltage Engineering, 2010, 36(11): 2705–2710
[9] 王黎明, 刘霆, 黄睿, 等. 考虑气象、几何参数、大气污染物的绝缘子表面污秽度预测方法[J]. 高电压技术, 2016, 42(3): 876–884
WANG Liming, LIU Ting, HUANG Rui, et al. Contamination prediction on insulators considering of meteorology, geomentric parameters and air pollutant[J]. High Voltage Engineering, 2016, 42(3): 876–884
[10] 周龙武, 龚泽, 上官帖, 等. 基于概率统计与神经网络相结合的绝缘子盐密预测[J]. 水电能源科学, 2015, 33(12): 172–175, 193
ZHOU Longwu, GONG Ze, SHANGGUAN Tie, et al. Prediction of insulator's ESDD based on probability statistics and neural network[J]. Water Resources and Power, 2015, 33(12): 172–175, 193
[11] 吴大伟, 陶汉涛, 张磊, 等. 基于气象参数统计的绝缘子污秽度评估方法[J]. 电瓷避雷器, 2017(4): 194–198
WU Dawei, TAO Hantao, ZHANG Lei, et al. Evaluation method of insulator contamination based on meteorological parameter statistics[J]. Insulators and Surge Arresters, 2017(4): 194–198
[12] 王自立, 卢明, 姜昀芃, 等. 基于遗传神经网络对运行线路绝缘子污秽度的预测[J]. 电瓷避雷器, 2018(2): 172–179
WANG Zili, LU Ming, JIANG Yunpeng, et al. Prediction of contamination degree of line insulators based on genetic neural network[J]. Insulators and Surge Arresters, 2018(2): 172–179
[13] 吴胜磊, 滕松, 刘振华, 等. 数据驱动的绝缘子积污特征量识别与污秽度预测[J]. 电力工程技术, 2019, 38(6): 179–186
WU Shenglei, TENG Song, LIU Zhenhua, et al. Identification of pollution characteristics of transmission line insulator and pollution prediction based on data driven[J]. Electric Power Engineering Technology, 2019, 38(6): 179–186
[14] 高嵩, 刘洋, 曹彬, 等. 自然降雨对绝缘子自然污秽冲洗效果的影响研究[J]. 电瓷避雷器, 2020(6): 159–163, 170
GAO Song, LIU Yang, CAO Bin, et al. Research on the cleaning effect of natural rainfall on the naturally contaminated insulators[J]. Insulators and Surge Arresters, 2020(6): 159–163, 170
[15] 董海燕, 张友鹏, 李少远, 等. 超大伞裙腕臂复合绝缘子积污分布的风洞模拟[J]. 浙江大学学报(工学版), 2019, 53(8): 1563–1571
DONG Haiyan, ZHANG Youpeng, LI Shaoyuan, et al. Wind tunnel simulation on contamination distribution of canti-lever composite insulator with booster sheds[J]. Journal of Zhejiang University (Engineering Science), 2019, 53(8): 1563–1571
[16] 李特, 吴金木, 陈乔, 等. 基于大气环境质量及气象参数的绝缘子积污预测研究现状[J]. 高压电器, 2017, 53(1): 175–180
LI Te, WU Jinmu, CHEN Qiao, et al. Research status of insulator contamination prediction based on air environment quality and meteorological data[J]. High Voltage Apparatus, 2017, 53(1): 175–180
[17] 李恒真. 高压输电线路外绝缘动态积污机理及在线监测研究[D]. 广州: 华南理工大学, 2012.
LI Hengzhen. Study on the mechanism of dynamic contamination accumulating and its on-line monitoring of external insulation of high voltage transmission line[D]. Guangzhou: South China University of Technology, 2012.
[18] 国家电网有限公司. 电力系统污区分级与外绝缘选择标准第1部分交流系统: Q/GDW 1152.1—2014[S]. 北京: 中国电力出版社, 2015.
[19] 李郅琴, 杜建强, 聂斌, 等. 特征选择方法综述[J]. 计算机工程与应用, 2019, 55(24): 10–19
LI Zhiqin, DU Jianqiang, NIE Bin, et al. Summary of feature selection methods[J]. Computer Engineering and Applications, 2019, 55(24): 10–19
[20] 王干军, 李锦舒, 吴毅江, 等. 基于随机森林的高压电缆局部放电特征寻优[J]. 电网技术, 2019, 43(4): 1329–1336
WANG Ganjun, LI Jinshu, WU Yijiang, et al. Random forest based feature selection for partial discharge recognition of HV cables[J]. Power System Technology, 2019, 43(4): 1329–1336
[21] 金颀, 邱志斌, 阮江军, 等. 球隙最短路径电场特征集与特征选择方法[J]. 电力科学与技术学报, 2020, 35(6): 12–20
JIN Qi, QIU Zhibin, RUAN Jiangjun, et al. Study on electric field features for the shortest path of sphere gap and the feature selection methods[J]. Journal of Electric Power Science and Technology, 2020, 35(6): 12–20
[22] 姚锐, 惠萌, 李俊, 等. 基于随机森林的局部放电特征提取和优选研究[J]. 华北电力大学学报(自然科学版), 2021, 48(4): 63–72
YAO Rui, HUI Meng, LI Jun, et al. Feature extraction and optimal selection based on random forest for partial discharges[J]. Journal of North China Electric Power University (Natural Science Edition), 2021, 48(4): 63–72
[23] HUANG G B, ZHU Q Y, SIEW C K. Extreme learning machine: theory and applications[J]. Neurocomputing, 2006, 70(1-3): 489–501.
[24] 孙承意, 谢克明, 程明琦. 基于思维进化机器学习的框架及新进展[J]. 太原理工大学学报, 1999, 30(5): 453–457
SUN Chengyi, XIE Keming, CHENG Mingqi. Mind evolution based machine learning framework and new development[J]. Journal of Taiyuan University of Technology, 1999, 30(5): 453–457
[25] 周子东, 李东伟, 李国胜, 等. 基于逐步回归的AdaBoost-SVR模型在海上风电项目造价预测中的应用[J]. 太阳能学报, 2020, 41(7): 259–264
ZHOU Zidong, LI Dongwei, LI Guosheng, et al. Application of Ada Boost-SVR model based on stepwise regression in cost forecast of offshore wind power[J]. Acta Energiae Solaris Sinica, 2020, 41(7): 259–264
[26] 高阳, 谢丽蓉, 叶家豪, 等. 自适应提升及预测误差修正的风电功率超短期预测[J]. 智慧电力, 2022, 50(8): 14–21
GAO Yang, XIE Lirong, YE Jiahao, et al. Ultra-short-term wind power prediction based on adaptive lifting and prediction error correction[J]. Smart Power, 2022, 50(8): 14–21
[27] 赵建辉, 张晨阳, 闵林, 等. 基于特征选择和GA-BP神经网络的多源遥感农田土壤水分反演[J]. 农业工程学报, 2021, 37(11): 112–120
ZHAO Jianhui, ZHANG Chenyang, MIN Lin, et al. Retrieval for soil moisture in farmland using multi-source remote sensing data and feature selection with GA-BP neural network[J]. Transactions of the Chinese Society of Agricultural Engineering, 2021, 37(11): 112–120
[28] 游文霞, 李清清, 杨楠, 等. 基于多异学习器融合Stacking集成学习的窃电检测[J]. 电力系统自动化, 2022, 46(24): 178–186
YOU Wenxia, LI Qingqing, YANG Nan, et al. Electricity theft detection based on multiple different learner fusion by Stacking ensemble learning[J]. Automation of Electric Power Systems, 2022, 46(24): 178–186