A pattern recognition approach based on DTW for automatic transient identification in nuclear power plants

摘要: Automatic identification of transients in nuclear power plants (NPPs) allows monitoring the fatigue damage accumulated by critical components during plant operation, and is therefore great importance for ensuring that usage factors remain within original design bases postulated designer. Although several schemes to address this important issue have been explored literature, there still no definitive solution available. In present work, a new method automatic transient proposed, based on Dynamic Time Warping (DTW) algorithm, largely used other related areas such as signature or speech recognition. The novel system evaluated real operational data following rigorous pattern recognition protocol. Results show high accuracy proposed approach, which combined with interesting features its low complexity very limited requirements training data.