A custom power protection device controlled by a neural network relay

Voltage dips are becoming an increasing concern to many industrial and commercial customers, due to the problems they cause on several types of equipment. In industrial plants equipped with private generating systems, in case of a fault in the supply feeder, the protection device will disconnect the customer plant from the utility system, preserving sensitive loads from interruptions, but exposing the equipment to a voltage dip due to its intervention delay. This paper describes a high speed protection device based on solid-state breakers, intelligently controlled by an artificial neural network, which is able to considerably reduce this voltage dip duration. It is shown that it is possible to predict with good accuracy the value of the RMS voltage, in order to recognise, within a few μs, the kind of abnormal event that is about to occur on the network. The behaviour of this protection device for several system states and with different types of faults has been analysed