单类学习下基于VSAPSO-BP的掘进机异常检测方法

详细信息    查看全文 | 推荐本文 |

英文篇名：Roadheader Anomaly Detection Method Based on VSAPSO-BP Under the Single Category Learning 作者：杨健健 ; 唐至威 ; 王晓林 ; 王子瑞 ; 吴淼 英文作者：YANG Jianjian;TANG Zhiwei;WANG Xiaolin;WANG Zirui;WU Miao;School of Mechanical Electronic and Information Engineering,China University of Mining and Technology(Beijing); 关键词：掘进机回转台 ; 异常检测 ; 支持向量数据描述 ; 粒子群优化算法 ; BP神经网络 英文关键词：roadheader rotary table;;anomaly detection;;support vector data description(SVDD);;particle swarm optimization algorithm;;BP neural network 中文刊名：ZDCS 英文刊名：Journal of Vibration,Measurement & Diagnosis 机构：中国矿业大学(北京)机电与信息工程学院; 出版日期：2019-02-15 出版单位：振动.测试与诊断 年：2019 期：v.39;No.189 基金：国家重点基础研究发展计划(“九七三”计划)资助项目(2014CB046306);; 国家自然科学基金资助项目(51874308) 语种：中文; 页：ZDCS201901021 页数：7 CN：01 ISSN：32-1361/V 分类号：136-141+232

摘要

针对掘进机回转台异常检测中故障数据缺失以及故障程度划分的问题,提出一种单类学习下基于VSAP-SO-BP的掘进机异常检测方法。使用支持向量数据描述(support vector data description,简称SVDD)方法对回转台健康数据进行单类学习,根据现场经验构造非健康样本数据集,以SVDD对非健康样本数据集的识别率为依据,把非健康样本数据分为故障临界数据与故障数据,提出变异自适应粒子群优化(variation self-adapting particleswarm optimization,简称VSAPSO)算法,构建VSAPSO-BP神经网络对健康、故障临界与故障3类数据进行检测,检测准确率为91.7%,与传统PSO-BP方法相比具有更高的准确性与稳定性。实验结果表明,采用单类学习下基于VSAPSO-BP的掘进机异常检测方法可以准确有效地检测掘进机回转台异常,具有较高的应用价值。
        To solve the problem of missing fault data and dividing fault degree in roadheader rotary table anomaly detection,a novel anomaly detection method based on variation self-adapting particle swarm optimization(VSAPSO)BP neural network under the single category learning is proposed.Using support vector data description(SVDD)to train the healthy data,constructing a non-healthy sample dataset based on the experience in the field,the non-healthy sample data is divided into fault critical data and fault data based on the recognition rate of SVDD for non-healthy sample datasets,and the variation self-adapting particle swarm optimization algorithm is proposed,the VSAPSO-BP neural network is constructed to detect healthy data,fault critical data and fault data,the detection accuracy is 91.7%,compared with the traditional PSO-BP neural network,VSAPSO-BP neural network has a higher accuracy and stability.The results show that the abnormal of roadheader rotary table can be detected accurately and effectively by using anomaly detection method based on VSAPSO-BP neural network under single learning,this method has a high application value.

引文

[1]张天瑞,于天彪,赵海峰,等.数据挖掘技术在全断面掘进机故障诊断中的应用[J].东北大学学报:自然科学版,2015,36(4):527-531,541.Zhang Tianrui,Yu Tianbiao,Zhao Haifeng,et al.Application of data mining technology in fault diagnosis of tunnel boring machine[J].Journal of Northeastern U-niversity:Natural Science,2015,36(4):527-531,541.(in Chinese)
    [2]邵晋敏.EBZ160TY型掘进机故障诊断专家系统的研究[J].煤矿机械,2013,34(6):265-267.Shao Jinmin.Research of fault diagnosis expert system on EBZ160TY roadheader[J].Coal Mine Machinery,2013,34(6):265-267.(in Chinese)
    [3]尹同舟,唐至威,杨健健,等.基于多传感器BP网络掘进机截割部故障诊断研究[J].煤炭科学技术,2016,44(9):134-139.Yin Tongzhou,Tang Zhiwei,Yang Jianjian,et al.Study on failure diagnosis of cutting unit in roadheader based on BP network of multi sensor[J].Coal Science and Technology,2016,44(9):134-139.(in Chinese)
    [4]罗慧,王友仁.基于GSM-SVDD的模拟电路故障诊断方法[J].电机与控制学报,2013,17(1):108-113.Luo Hui,Wang Youren.A GSM-SVDD method for analog circuits fault diagnosis[J].Electric Machines and Control,2013,17(1):108-113.(in Chinese)
    [5]付文龙,周建中,李超顺,等.基于模糊K近邻支持向量数据描述的水电机组振动故障诊断研究[J].中国电机工程学报,2014,34(32):5788-5795.Fu Wenlong,Zhou Jianzhong,Li Chaoshun,et al.Vibrant fault diagnosis for hydro-electric generating unit based on support vector data description improved with fuzzy K nearest neighbor[J].Proceedings of the CSEE,2014,34(32):5788-5795.(in Chinese)
    [6]张玲玲,廖红云,贾继德,等.基于SVDD与D-S证据理论的发动机故障诊断研究[J].汽车工程,2013,35(1):23-26,50.Zhang Lingling,Liao Hongyun,Jia Jide,et al.A research on engine fault diagnosis based on SVDD and D-S evidence theory[J].Automotive Engineering,2013,35(1):23-26,50.(in Chinese)
    [7]张敏龙,王涛,王旭平,等.带故障样本的弹性双阈值SVDD在线故障诊断算法及其应用[J].振动工程学报,2016,29(3):555-560.Zhang Minlong,Wang Tao,Wang Xuping,et al.Online fault diagnosis algorithm based on variable dualthreshold SVDD with negative samples and its application[J].Journal of Vibration Engineering,2016,29(3):555-560.(in Chinese)
    [8]陈喜阳,闫海桥,孙建平.基于PSO-BP与组合矩的水电机组轴心轨迹识别[J].振动、测试与诊断,2016,36(1):108-114.Chen Xiyang,Yan Haiqiao,Sun Jianping.Research on the identification of axis orbit in hydro-generator unit base on PSO-BP and combined moment invariants[J].Journal of Vibration,Measurement&Diagnosis,2016,36(1):108-114.(in Chinese)
    [9]王东风,孟丽,赵文杰.基于自适应搜索中心的骨干粒子群算法[J].计算机学报,2016,39(12):2652-2667.Wang Dongfeng,Meng Li,Zhao Wenjie.Improved bare bones particle swarm optimization with adaptive search center[J].Chinese Journal of Computers,2016,39(12):2652-2667.(in Chinese)
    [10]徐卫亚,徐飞,刘大文.位移时序预测的APSO-WLSS-VM模型及应用研究[J].岩土工程学报,2009,31(3):313-318.Xu Weiya,Xu Fei,Liu Dawen.Study and application of displacement time series forecast based on APSO-WLSSVM[J].Chinese Journal of Geotechnical Engineering,2009,31(3):313-318.(in Chinese)
    [11]高保龙,李景灿,韩力,等.基于改进PSO的无刷双馈风力发电机优化设计[J].太阳能学报,2015,36(8):1833-1840.Gao Baolong,Li Jingcan,Han Li,et al.Design optimization of burshless doubly-fed wind power generator based on improved PSO algorithm[J].Acta Energiae Solaris Sinica,2015,36(8):1833-1840.(in Chinese)
    [12]李冠男,胡云鹏,陈焕新,等.基于SVDD的冷水机组传感器故障检测及效率分析[J].化工学报,2015,66(5):1815-1820.Li Guannan,Hu Yunpeng,Chen Huanxin,et al.SVDD-based chiller sensor fault detection method and its detection efficiency[J].Journal of Chemical Industry and Engineering(China),2015,66(5):1815-1820.(in Chinese)