Recognition method of the squeezing force of shearer dragging cable based on improved deep forest
-
摘要: 采煤机拖拽电缆在运行中常受到外部挤压力作用，致使电缆绝缘发生局部放电，影响电缆使用寿命。现有研究侧重于局部放电规律和严重程度的分析，无法评估乙丙橡胶绝缘电缆所承受应力的大小，导致无法掌握矿用乙丙橡胶绝缘电缆的运行状态。针对该问题，提出一种基于改进深度森林（S−DF）的采煤机拖拽电缆挤压力识别方法。通过实验测量了不同挤压力下采煤机拖拽电缆的局部放电，分析了局部放电谱图、平均放电电流、最大放电量和击穿场强随所施挤压力和电压的变化规律，计算了局部放电的统计特征参量。基于统计特征参量，采用S−DF模型对挤压力大小进行识别。S−DF模型在深度森林（DF）中引入Stacking集成算法，以提升识别准确率。研究结果表明：不同电压下，最大放电量和平均放电电流均随着挤压力的增大而减小；击穿场强随着挤压力的增大呈先增大后减小的趋势，挤压力大于2 000 N时的击穿场强小于未挤压时的击穿场强；不同挤压力下的局部放电统计特征参量可作为放电指纹，S−DF模型能准确地识别电缆所受挤压力的大小，且识别率高于其他传统分类算法。Abstract: The dragging cable of shearer is often subjected to external squeezing pressure during operation, which causes partial discharge of the cable insulation and affects the service life of the cable. The existing research focuses on the analysis of partial discharge law and severity, and cannot evaluate the magnitude of stress borne by ethylene propylene rubber insulated cables. This results in the inability to grasp the operating status of mining ethylene propylene rubber insulated cables. In order to solve the above problems, a method based on improved Stacking-deep forest (S-DF) is proposed for recognizing the squeezing force of shearer dragging cables. The partial discharge of shearers dragging cables under different squeezing pressures is measured through experiments. The variation law of partial discharge spectra, average discharge current, maximum discharge amount, and breakdown field strength with the applied squeezing pressure and voltage are analyzed. The statistical feature parameters of partial discharge are calculated. Based on statistical feature parameters, the S-DF model is used to recognize the magnitude of squeezing pressures. The S-DF model introduces Stacking ensemble algorithm in deep forest (DF) to improve recognition accuracy. The research results indicate that under different voltages, the maximum discharge capacity and average discharge current decrease with the increase of extrusion pressure. The breakdown field strength shows a trend of first increasing and then decreasing with the increase of squeezing pressure. When the squeezing pressure is greater than 2 000 N, the breakdown field strength is lower than that of the non squeezing one. The statistical feature parameters of partial discharge under different squeezing pressures can be used as discharge fingerprints. The S-DF model can accurately recognize the magnitude of squeezing pressure on cables, and the recognition rate is higher than other traditional classification algorithms.
-
图 3 不同挤压力下乙丙橡胶绝缘电缆的PRPD图
Figure 3. PRPD diagram of ethylene propylene rubber cable under different extrusion pressures
图 4 击穿场强与挤压力的关系
Figure 4. Relationship between puncture core field intensity and extrusion pressure
图 5 最大放电量和平均放电电流与挤压力的关系
Figure 5. Relationship between maximum discharge, average discharge current and extrusion pressure
图 6 不同挤压力下的统计特征参量柱状图
Figure 6. Histograms of statistical characteristic parameters under different extrusion pressures
表 1 PRPD图统计特征参量
Table 1. Statistical characteristic parameters of PRPD diagram
参数 Hqmax（φ） Hqn（φ） Hn（φ） Hn（q） + − + − + − Sk √ √ √ √ √ √ √ Ku √ √ √ √ √ √ √ Peak √ √ √ √ √ √ √ Assy √ √ √ — Cc √ √ √ — 
下载: 导出CSV
表 2 S−DF模型与DF模型识别准确率对比
Table 2. Comparison of recognition accuracy between S-DF model and DF model
训练集与
验证集之比识别准确率/% S−DF DF 0.8∶0.2 94.27 87.65 0.5∶0.5 93.55 86.85 0.2∶0.8 88.65 80.95
下载: 导出CSV
表 3 S−DF模型与随机森林、SVM识别准确率对比
Table 3. Comparison of recognition accuracy between S-DF model and random forest and SVM
挤压力/N 识别准确率/% S−DF 随机森林 SVM 0 85.20 87.54 85.52 500 96.20 73.42 76.72 1 000 95.60 78.12 74.73 1 500 97.40 65.00 70.52 2 000 96.20 85.83 86.73 2 500 95.20 81.33 88.45 平均值 94.27 78.54 80.46
下载: 导出CSV
-
[1] 刘志华,崔彦捷,汲胜昌,等. 热机联合应力对油浸纸板绝缘及机械特性影响研究[J]. 电力工程技术,2020,39(5):126-132. doi: 10.12158/j.2096-3203.2020.05.018LIU Zhihua,CUI Yanjie,JI Shengchang,et al. Influence of thermo-mechanical combined stress on insulation and mechanical characteristics of oil-impregnated paperboard[J]. Electric Power Engineering Technology,2020,39(5):126-132. doi: 10.12158/j.2096-3203.2020.05.018 [2] 彭倩,吴广宁,张星海,等. 机械应力对聚丙烯薄膜局部放电性能的影响[J]. 高电压技术,2008,34(6):1261-1266. doi: 10.13336/j.1003-6520.hve.2008.06.024PENG Qian,WU Guangning,ZHANG Xinghai,et al. Influence of mechanical stress on polypropylene film partial discharge[J]. High Voltage Engineering,2008,34(6):1261-1266. doi: 10.13336/j.1003-6520.hve.2008.06.024 [3] 邹林,涂扬,孟永鹏,等. 界面压强和表面粗糙度对聚乙烯与硅橡胶界面的局部放电的影响[J]. 绝缘材料,2014,47(3):94-98,102. doi: 10.3969/j.issn.1009-9239.2014.03.024ZOU Lin,TU Yang,MENG Yongpeng,et al. Effects of interface pressure and surface roughness on the partial discharge between polyethylene and silicone rubber[J]. Insulating Materials,2014,47(3):94-98,102. doi: 10.3969/j.issn.1009-9239.2014.03.024 [4] 路士杰. 温度和机械应力对环氧树脂绝缘件沿面闪络特性的影响[D]. 北京:华北电力大学,2020.LU Shijie. Effects of temperature and mechanical stress on surface flashover characteristics of epoxy resin insulation parts[D]. Beijing:North China Electric Power University,2020. [5] 崔彦捷,汲胜昌,祝令瑜,等. 机械应力对油浸绝缘纸板局部放电影响[J]. 电工技术学报,2021,36(12):2659-2666. doi: 10.19595/j.cnki.1000-6753.tces.191720CUI Yanjie,JI Shengchang,ZHU Lingyu,et al. Effect of mechanical stress on partial discharge of oil-impregnated pressboard[J]. Transactions of China Electrotechnical Society,2021,36(12):2659-2666. doi: 10.19595/j.cnki.1000-6753.tces.191720 [6] 罗家成,高存法,戴相花. 机−电载荷对含裂纹介电材料局部放电的影响[C]. 2009年全国压电和声波理论及器件技术研讨会暨2009年全国频率控制技术年会,武汉,2009.LUO Jiacheng,GAO Cunfa,DAI Xianghua. The influence of mechanical-electric loads on partial discharge in dielectric material containing a crack[C]. 2009 National Piezoelectric and Acoustic Theory and Device Technology Seminar and 2009 National Frequency Control Technology Annual Conference,Wuhan,2009. [7] 林晨,吝伶艳,雷志鹏,等. 基于PDC的多应力老化乙丙橡胶电缆绝缘状态评估[J]. 绝缘材料,2020,53(1):70-75. doi: 10.16790/j.cnki.1009-9239.im.2020.01.013LIN Chen,LIN Lingyan,LEI Zhipeng,et al. State evaluation of multi-stress aged EPR cable insulation based on PDC[J]. Insulating Materials,2020,53(1):70-75. doi: 10.16790/j.cnki.1009-9239.im.2020.01.013 [8] 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. doi: 10.13335/j.1000-3673.pst.2018.2652WANG 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. doi: 10.13335/j.1000-3673.pst.2018.2652 [9] 唐炬,王静,李剑,等. 统计参数用于局部放电模式识别的研究[J]. 高电压技术,2002,28(8):4-6,37. doi: 10.3969/j.issn.1003-6520.2002.08.002TANG Ju,WANG Jing,LI Jian,et al. Statistical parameter method for PD pattern recognition[J]. High Voltage Engineering,2002,28(8):4-6,37. doi: 10.3969/j.issn.1003-6520.2002.08.002 [10] 刘维功,王昊展,时振堂,等. 基于改进XGBoost算法的XLPE电缆局部放电模式识别研究[J]. 电测与仪表,2022,59(4):98-106. doi: 10.19753/j.issn1001-1390.2022.04.015LIU Weigong,WANG Haozhan,SHI Zhentang,et al. Research on partial discharge pattern recognition of XLPE cable based on improved XGBoost algorithm[J]. Electrical Measurement & Instrumentation,2022,59(4):98-106. doi: 10.19753/j.issn1001-1390.2022.04.015 [11] 苏审言,张建德. 基于概率神经网络的变压器局部放电模式识别[J]. 电气自动化,2022,44(3):91-93. doi: 10.3969/j.issn.1000-3886.2022.03.028SU Shenyan,ZHANG Jiande. Pattern recognition of partial discharge of transformer based on probabilistic neural network[J]. Electrical Automation,2022,44(3):91-93. doi: 10.3969/j.issn.1000-3886.2022.03.028 [12] 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. doi: 10.3969/j.ISSN.1007-2691.2021.04.08YAO 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. doi: 10.3969/j.ISSN.1007-2691.2021.04.08 [13] 马良玉,耿妍竹,梁书源,等. 基于Stacking多模型融合的风电机组齿轮箱油池温度异常预警[J/OL]. 中国电机工程学报:1-11[2023-09-25]. http://kns.cnki.net/kcms/detail/11.2107.TM.20230919.1048.004.html.MA Liangyu,GENG Yanzhu,LIANG Shuyuan,et al. Anomaly warning of wind turbine gearbox oil pool temperature based on Stacking fusion of multiple models[J/OL]. Proceedings of the CSEE:1-11[2023-09-25]. http://kns.cnki.net/kcms/detail/11.2107.TM.20230919.1048.004.html. [14] 霍晓占,刘延泉,周兴华,等. 基于改进灰色关联分析和Stacking算法的配电网线损预测研究[J/OL]. 华北电力大学学报(自然科学版):1-8[2023-10-18]. http://kns.cnki.net/kcms/detail/13.1212.tm.20231017.0853.002.html.HUO Xiaozhan,LIU Yanquan,ZHOU Xinghua,et al. Research on distribution network line loss prediction based on improved grey relational analysis and Stacking algorithm[J/OL]. Journal of North China Electric Power University(Natural Science Edition) :1-8[2023-10-18]. http://kns.cnki.net/kcms/detail/13.1212.tm.20231017.0853.002.html. [15] 孙林,郭嘉琪,朱雨晨,等. 基于Stacking集成和偏探索贝叶斯优化的特征选择[J/OL]. 山西大学学报(自然科学版):1-11[2023-10-18]. https://doi.org/10.13451/j.sxu.ns.2023143.SUN Lin,GUO Jiaqi,ZHU Yuchen,et al. Feature selection using Stacking integration and partial exploration Bayesian optimization[J/OL]. Journal of Shanxi University(Natural Science Edition) :1-11[2023-10-18]. https://doi.org/10.13451/j.sxu.ns.2023143. [16] 唐振浩,隋梦璇,曹生现. 基于组合时域特征提取和Stacking集成学习的燃煤锅炉NOx排放浓度预测[J/OL]. 中国电机工程学报:1-16[2023-10-18]. DOI: 10.13334/j.0258-8013.pcsee.230940.TANG Zhenhao,SUI Mengxuan,CAO Shengxian. Prediction of NOx emission concentration from coal-fired boilers based on combined time-domain feature extraction and Stacking ensemble learning[J/OL]. Proceedings of the CSEE:1-16 [2023-10-18]. DOI: 10.13334/j.0258-8013.pcsee.230940. [17] 金秀章,乔鹏,史德金. 基于mRMR-BO优化Stacking集成模型的NO_x浓度动态软测量[J]. 热力发电,2023,52(10):122-128. doi: 10.19666/j.rlfd.202302378JIN Xiuzhang,QIAO Peng,SHI Dejin. Dynamic soft measurement of NO_x concentration based on mRMR-BO Stacking ensemble model[J]. Thermal Power Generation,2023,52(10):122-128. doi: 10.19666/j.rlfd.202302378 [18] 缪智伟,韦才敏. 基于多模型融合Stacking集成学习保险欺诈预测[J]. 汕头大学学报(自然科学版),2023,38(3):13-24. doi: 10.3969/j.issn.1001-4217.2023.03.003MIAO Zhiwei,WEI Caimin. Learning insurance fraud prediction based on multi-model fusion Stacking integration[J]. Journal of Shantou University(Natural Science Edition),2023,38(3):13-24. doi: 10.3969/j.issn.1001-4217.2023.03.003 [19] 丁家满,吴晔辉,罗青波,等. 基于深度森林的轴承故障诊断方法[J]. 振动与冲击,2021,40(12):107-113. doi: 10.13465/j.cnki.jvs.2021.12.014DING Jiaman,WU Yehui,LUO Qingbo,et al. A fault diagnosis method of mechanical bearing based on the deep forest[J]. Journal of Vibration and Shock,2021,40(12):107-113. doi: 10.13465/j.cnki.jvs.2021.12.014 [20] 窦希杰,王世博,刘后广,等. 基于EMD特征提取与随机森林的煤矸识别方法[J]. 工矿自动化,2021,47(3):60-65. doi: 10.13272/j.issn.1671-251x.2020100038DOU Xijie,WANG Shibo,LIU Houguang,et al. Coal and gangue identification method based on EMD feature extraction and random forest[J]. Industry and Mine Automation,2021,47(3):60-65. doi: 10.13272/j.issn.1671-251x.2020100038 [21] 王艺霏,祝继华,刘新媛等. 联合深度森林与异质集成的标记分布学习方法[J/OL]. 软件学报:1-18[2023-10-18]. DOI: 10.13328/j.cnki.jos.006936.WANG Yifei,ZHU Jihua,LIU Xinyuan,et al. Label distribution learning based on deep forest and heterogeneous ensemble[J/OL]. Journal of Software:1-18[2023-10-18]. DOI: 10.13328/j.cnki.jos.006936. [22] 周政雷,陈俊,潘俊涛,等. 基于并行深度森林的配用电通信网络异常流量检测[J]. 华东师范大学学报(自然科学版),2023(5):122-134. doi: 10.3969/j.issn.1000-5641.2023.05.011ZHOU Zhenglei,CHEN Jun,PAN Juntao,et al. Parallel deep-forest-based abnormal traffic detection for power distribution communication networks[J]. Journal of East China Normal University(Natural Science),2023(5):122-134. doi: 10.3969/j.issn.1000-5641.2023.05.011 [23] 毛伊敏,周展,陈志刚. 基于Spark和三路交互信息的并行深度森林算法[J]. 通信学报,2023,44(8):228-240.MAO Yimin,ZHOU Zhan,CHEN Zhigang. Parallel deep forest algorithm based on Spark and three-way interactive information[J]. Journal on Communications,2023,44(8):228-240. [24] 卢喜东,段哲民,钱叶魁,等. 一种基于深度森林的恶意代码分类方法[J]. 软件学报,2020,31(5):1454-1464. doi: 10.13328/j.cnki.jos.005660LU Xidong,DUAN Zhemin,QIAN Yekui,et al. Malicious code classification method based on deep forest[J]. Journal of Software,2020,31(5):1454-1464. doi: 10.13328/j.cnki.jos.005660 [25] 刘东超,熊慕文,高森,等. 基于深度森林模型的GIS局部放电模式识别[J]. 电气传动,2022,52(9):12-18.LIU Dongchao,XIONG Muwen,GAO Sen,et al. Partial discharge pattern recognition of GIS based on deep forest model[J]. Electric Drive,2022,52(9):12-18. -
点击查看大图
图(11) / 表(3)
计量
- 文章访问数: 215
- HTML全文浏览量: 67
- PDF下载量: 26
- 被引次数: 0
