ASISTO: An integrated intelligent assistant system for power plant operation and training

In this paper we present ASISTO, an intelligent assistant system for power plant operation and training based on probabilistic graphical models. Its main advantage is that it provides on-line guidance in the form of ordered recommendations, sensor validation capabilities, and explanation features, all for uncertain environments. The system allows dealing with abnormal situations, non-expected events, or the occurrence of process transients. The different modules of the system are based on Markov decision processes, Bayesian networks, and knowledge representation using the object-oriented paradigm. Functional results for each component of ASISTO using a power plant simulator are also presented.

[1]  Elvira: An Environment for Creating and Using Probabilistic Graphical Models , 2002, Probabilistic Graphical Models.

[2]  Claudio Gentile,et al.  SART: A system for supporting operators with contextual knowledge , 1997 .

[3]  Luis Enrique Sucar,et al.  Integrating Probabilistic and Knowledge-Based Systems for Explanation Generation , 2008, ExaCt.

[4]  Sunil Vadera,et al.  A Probabilistic Model for Information and Sensor Validation , 2006, Comput. J..

[5]  Agnar Aamodt,et al.  Different Roles and Mutual Dependencies of Data, Information, and Knowledge - An AI Perspective on their Integration , 1995, Data Knowl. Eng..

[6]  Matthijs T. J. Spaan,et al.  An Intelligent Assistant for Power Plants Based on Factored MDPs , 2009, 2009 15th International Conference on Intelligent System Applications to Power Systems.

[7]  Patrick Brézillon,et al.  Cooperating for assisting intelligently operators , 1995 .

[8]  F. Elizalde,et al.  Policy Explanation in Factored Markov Decision Processes , 2008 .

[9]  Pablo H. Ibargüengoytia,et al.  Online Diagnosis Using Influence Diagrams , 2004, MICAI.

[10]  U. Rieder,et al.  Markov Decision Processes , 2010 .

[11]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .

[12]  Alberto Reyes,et al.  On-line diagnosis of a power generation process using probabilistic models , 2011, 2011 16th International Conference on Intelligent System Applications to Power Systems.

[13]  Leslie Pack Kaelbling,et al.  Planning and Acting in Partially Observable Stochastic Domains , 1998, Artif. Intell..

[14]  Craig Boutilier,et al.  Decision-Theoretic Planning: Structural Assumptions and Computational Leverage , 1999, J. Artif. Intell. Res..

[15]  Ian Witten,et al.  Data Mining , 2000 .

[16]  Martin L. Puterman,et al.  Markov Decision Processes: Discrete Stochastic Dynamic Programming , 1994 .