Fault diagnosis for an MSF desalination plant by using Bayesian networks

This work outlines the development of a fault diagnostic system for an MSF (multi-stage flash) desalination plant by using BNs (Bayesian networks). This diagnostic system processes the plant data to determine whether the process state is normal or not. In the latter case, the diagnostic system determines the cause of the abnormal process state; i.e., it finds out which is the fault that is affecting the supervised process. ABN is a graphical model that encodes probabilistic relationships among variables of interest. When used in conjunction with statistical techniques, the graphical model has several advantages for data analysis. A BN readily handles situations where some data entries are missing. This paper determines both the structure and parameters of a BN intended for a diagnostic system. The implemented system is evaluated by using a dynamic simulator, which was developed for a real MSF desalination plant. Besides, the diagnostic system performance is compared with the performances of two other diag...

[1]  Simon X. Yang,et al.  A Multi-Fault Diagnosis Method for Sensor Systems Based on Principle Component Analysis , 2009, Sensors.

[2]  Nicolás J. Scenna,et al.  Fault diagnosis for a MSF using a SDG and fuzzy logic , 2003 .

[3]  Jose Emmanuel Ramirez-Marquez,et al.  Using Bayesian Approach for sensitivity Analysis and Fault Diagnosis in Complex Systems , 2009, Trans. SDPS.

[4]  Haiying Dong,et al.  Transformer fault diagnosis based on reasoning integration of rough set and fuzzy set and Bayesian optimal classifier , 2009 .

[5]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part III: Process history based methods , 2003, Comput. Chem. Eng..

[6]  Michael J. Pazzani,et al.  Searching for Dependencies in Bayesian Classifiers , 1995, AISTATS.

[7]  David A. Bell,et al.  Learning Bayesian networks from data: An information-theory based approach , 2002, Artif. Intell..

[8]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part I: Quantitative model-based methods , 2003, Comput. Chem. Eng..

[9]  Harry Zhang,et al.  Exploring Conditions For The Optimality Of Naïve Bayes , 2005, Int. J. Pattern Recognit. Artif. Intell..

[10]  Nicolás J. Scenna,et al.  A dynamic simulator for MSF plants , 2001 .

[11]  Nicolás J. Scenna,et al.  Fault diagnosis for a MSF using neural networks , 2003 .

[12]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part II: Qualitative models and search strategies , 2003, Comput. Chem. Eng..

[13]  Peter Zoeteweij,et al.  A New Bayesian Approach to Multiple Intermittent Fault Diagnosis , 2009, IJCAI.