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

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.