In this paper, it is proved that the direction of the node-voltage difference vector, which is the difference between the node-voltage vector at faulty state and the one at the nominal state, is determined only by the...In this paper, it is proved that the direction of the node-voltage difference vector, which is the difference between the node-voltage vector at faulty state and the one at the nominal state, is determined only by the location of the faulty clement in linear analog circuits. Considering that the direction of the node-voltage sensitivity vector is the same as the one of the node-voltage difference vector and also considering that the module of the node-voltage sensitivity vector presents the weight of the parameter of faulty element deviation relative to the voltage difference, fault dictionary is set up based on node-voltage sensitivity vectors. A decision algorithm is proposed concerned with both the location and the parameter difference of the faulty element. Single fault and multi-fault can be diagnosed while the circuit parameters deviate within the tolerance range of 10 %.展开更多
为实现对节点进行实时有效的故障诊断,提出一种基于SOM自组织网映射算法和免疫遗传神经网络的故障诊断方法。首先,设计节点故障诊断的通用模型;然后采用自组织网映射(self organize mapping,SOM)算法对故障特征数据进行离散化以提高诊...为实现对节点进行实时有效的故障诊断,提出一种基于SOM自组织网映射算法和免疫遗传神经网络的故障诊断方法。首先,设计节点故障诊断的通用模型;然后采用自组织网映射(self organize mapping,SOM)算法对故障特征数据进行离散化以提高诊断模型的泛化性能,并通过主成分分析法(principal component analysis,PCA)对特征数据属性进行约简以减少数据量;最后,建立三层的BP神经网络节点故障诊断模型,并通过免疫遗传算法(immune gene algorithm,IGA)对BP神经网络优化从而得到最终优化的节点故障诊断模型。仿真实验证明该法能有效进行故障诊断,且与其他方法相比,具有诊断效率高和精度高的优点。展开更多
基金supported by Program for New Century Excellent Talents in University under Grant No.NCET-05-0804
文摘In this paper, it is proved that the direction of the node-voltage difference vector, which is the difference between the node-voltage vector at faulty state and the one at the nominal state, is determined only by the location of the faulty clement in linear analog circuits. Considering that the direction of the node-voltage sensitivity vector is the same as the one of the node-voltage difference vector and also considering that the module of the node-voltage sensitivity vector presents the weight of the parameter of faulty element deviation relative to the voltage difference, fault dictionary is set up based on node-voltage sensitivity vectors. A decision algorithm is proposed concerned with both the location and the parameter difference of the faulty element. Single fault and multi-fault can be diagnosed while the circuit parameters deviate within the tolerance range of 10 %.
