148 Int. J. Nuclear Knowledge Management, Vol. 5, No. 2, 2011 Copyright © 2011 Inderscience Enterprises Ltd. A model-based ensemble approach to plant-wide online sensor monitoring Giulio Gola*, Davide Roverso and Mario Hoffmann Institute for Energy Technology, Os Allè 5, 1751, Halden, Norway Email: giulio.gola@hrp.no Email: davide.roverso@hrp.no Email: mario.hoffmann@hrp.no *Corresponding author Abstract: Online sensor monitoring aims at detecting anomalies in sensors and reconstructing their correct signals during operation. Since 1994, research at the OECD Halden Reactor Project has focused on the problem of sensor monitoring, eventually developing the PEANO system for signal validation. PEANO combines fuzzy clustering and auto-associative neural networks and has proved successful in a variety of practical applications. Nevertheless, using one single empirical model sets a limit to the number of signals that can be handled at a time. Recently, PEANO has been extended to cover the validation of all the plant signals. This has entailed shifting from a single-model to a model-ensemble approach. This paper illustrates the plant-wide extension of the PEANO system and its practical application to a real case study. Keywords: sensor monitoring; signal reconstruction; nuclear application; ensemble; evolving clustering method. Reference to this paper should be made as follows: Gola, G., Roverso, D. and Hoffmann, M. (2011) ‘A model-based ensemble approach to plant-wide online sensor monitoring’, Int. J. Nuclear Knowledge Management, Vol. 5, No. 2, pp.148–161. Biographical notes: Giulio Gola is currently working as a Principal Research Scientist at the Institute for Energy Technology (IFE), Halden, Norway, and OECD Halden Reactor Project (HRP) within the Computerized Operations and Support Systems Department. He received his MSc and a PhD in Nuclear Engineering by the Polytechnic of Milan, Italy, in 2005 and 2009, respectively. His research topics deal with the development of artificial intelligence-based methods for online, large-scale signal validation, condition monitoring, instrument calibration, system diagnostics and prognostics. Davide Roverso is a graduate in Information Technology from the University of Torino, Italy, 1990, and a PhD in Computing Science from the University of Aberdeen, Scotland, UK, 1997. He has been a Research Scientist at the Institute for Energy Technology (IFE) and OECD Halden Reactor Project (HRP) since 1998, and has been leading the Department of Computerized Operation Support Systems since 2008. His experience and research interests have ranged from computational intelligence techniques for signal validation,