Use of a convolutional neural network to segment signals of motor operated valves

Motor operated valves (MOV) are one of the most numerous classes nuclear power plant components. An important issue concerned with MOV diagnostics is lack in-process (online) automated control for technical condition during full operation NPP unit. In this regard, a vital task that based on signals current and voltage consumed ‘opening’ ‘closing’ operations. The represent time series measured at regular intervals. (and voltage) can be received online contain all necessary information status. Essentially, approach allows active to calculated from signals, characteristics (‘diagnostic signs’) extracted particular portions (segments) using values which MOVs diagnosed. paper deals problem automating segmentation signals. To accomplish this, an algorithm has been developed convolutional neural network.