基于模糊Petri网的光纤复合低压电缆故障诊断  

Fault diagnosis of optical fiber composite low voltage cable based on fuzzy Petri net

作　　者：王鹤[1] 郑红霞[1] 葛维春[2] 罗桓桓[2] 周桂平[2] 吕旭明[2] 王英杰 WANG He;ZHENG Hong-xia;GE Wei chun;LUO Huan-huan;ZHOU Gui-ping;LV Xu-ming;WANG Ying-jie(School of Electrical Engineering,Northeast Electric Power University,Jilin 132012,China;State Grid Liaoning Electric Power Co.,Ltd.,Shenyang 110006,China;Beijing Guodian Network Technology Co.,Ltd.,Beijing 100070,China)

机构地区：[1]东北电力大学电气工程学院,吉林省吉林市132012 [2]辽宁省电力有限公司,沈阳110006 [3]北京国电通网络技术有限公司,北京100070

出　　处：《吉林大学学报（工学版）》2019年第2期664-672,共9页Journal of Jilin University:Engineering and Technology Edition

基　　金：国家重点研发专项项目(2016YFB0901200)

摘　　要：提出了一种基于动态自适应模糊Petri网(DAFPN)的光纤复合低压电缆(OPLC)故障诊断方法,该方法能计及OPLC中电缆发生故障时发热对光缆产生的影响,准确地进行OPLC故障的诊断与分类。在构建OPLC故障诊断的通用模糊Petri网模型的基础上,利用BP神经网络算法对Petri网模型中的参数进行学习、训练,以减少人为主观因素造成的误差。最后,用DAFPN对OPLC故障进行诊断,结果证明:相比较单独使用模糊Petri网,该方法能更好地动态适应专家系统中模糊知识的更新,有效提高OPLC故障诊断的准确度。An OPLC fault diagnosis method is proposed based on Dynamic Adaptive Fuzzy Petri Net(DAFPN).The method can record the effect of heating on the optical cable when the electric cable fails in OPLC,and accurately diagnose and classify OPLC fault.First,the fuzzy Petri net model of general OPLC fault diagnosis is constructed.Then,the BP neural network algorithm is used to learn and train the parameters in the Petri net model,so as to reduce the error caused by the subjective factors.Finally,the DAFPN is used to diagnose the OPLC fault.Experimental results show that,comparing with using fuzzy Petri net along,the proposed method can better adapt to the dynamic fuzzy knowledge in expert system update,and can effectively improve the accuracy of fault diagnosis.

关 键 词：通信技术 光纤复合低压电缆 故障诊断 模糊PETRI网 神经网络算法 

分 类 号：TM246[一般工业技术—材料科学与工程]