Hidden Markov model‐based real‐time transient identifications in nuclear power plants

In this article, a transient identification method based on a stochastic approach with the hidden Markov model(HMM) has been suggested and evaluated experimentally for the classification of nine types of transientsin nuclear power plants (NPPs). A transient is defined as when a plant proceeds to an abnormal state froma normal state. Identification of the types of transients during an early accident stage in NPPs is crucial forproper action selection. The transient can be identified by its unique time‐dependent patterns related tothe principal variables. The HMM, a double‐stochastic process, can be applied to transient identificationthat is a spatial and temporal classification problem under a statistical pattern‐recognition framework. Thetrained HMM is created for each transient from a set of training data by the maximum‐likelihood estimationmethod which uses a forward‐backward algorithm and the Baum‐Welch re‐estimation algorithm. Thetransient identification is determined by calculating which model has the highest probability for given test datausing the Viterbi algorithm. Several experimental tests have been performed with normalization methods, clusteringalgorithms, and a number of states in HMM. There are also a few experimental tests that have been performed,including superimposing random noise, adding systematic error, and adding untrained transients to verify itsperformance and robustness. The proposed real‐time transient identification system has been proven to havemany advantages, although there are still some problems that should be solved before applying it to an operatingNPP. Further efforts are being made to improve the system performance and robustness in order to demonstratereliability and accuracy to the required level. © 2002 Wiley Periodicals, Inc.