Neuro-fuzzy approach to diagnosis of electrical networks operation

This paper presents a neuro-fuzzy approach to power quality assessment. From the end user perspective it is important, that power quality indicia are held in certain limits. However, electrical equipment susceptibility to disturbances varies from type to type. Additionally, not only one physical phenomenon (e.g. harmonics) can cause equipment malfunctioning or damage, but more likely a superposition of some different disturbances. On the contrary, some disturbance levels higher than indicated in standards can be harmless to certain equipment. The authors propose an automated neuro-fuzzy approach to power quality assessment incorporating equipment susceptibility. This helps to predict damages or abnormal functioning of devices and implement adequate countermeasures.