Some new results on neural network approximation
Neural Networks
Hi-index | 0.00 |
Sea salt contamination of overhead medium voltage insulators is the most common cause to outages in power systems installed in coastal regions. The contamination level of insulators is generally expressed by the equivalent salt deposit density (ESDD), which is the parameter that is taken into account, from almost every electric utility to diagnose the sea salt pollution severity on insulators. The periodic maintenance of insulators, which means the insulator washing, can reduce or even prevent the outages caused by the sea salt contamination. The maintenance scheduling is planned based on ESDD measurements, a process quite expensive and time consuming. The current work presents a new approach for the ESDD assessment based on artificial intelligence and more specifically artificial neural networks (ANN). A new ANN model capable to predict with accuracy the ESDD values is developed and is applied on operating medium voltage insulators presented results similar to the experimental ones. The proposed approach can be useful in the work of electrical maintenance engineers reducing maintenance time and cost.