SELECTION OF SENSORS BY A NEW METHODOLOGY COUPLING A CLASSIFICATION TECHNIQUE AND ENTROPY CRITERIA

Abstract Complex industrial processes invest a lot of money in sensors and automation devices to monitor and supervise the process in order to guarantee the production quality and the plant and operators safety. Fault detection is one of the multiple tasks of process monitoring and it critically depends on the sensors that measure the significant process variables. Nevertheless, most of the work on fault detection and diagnosis found in literature place more emphasis on developing procedures to perform diagnosis given a set of sensors, and less on determining the actual location of sensors for efficient identification of faults. A methodology based on learning and classification techniques and on the information quantity measured by the Entropy concept, is proposed in order to address the problem of sensor location for fault identification. The proposed methodology has been applied to a continuous intensified reactor, the ‘open plate reactor (OPR)’, developed by Alfa Laval and studied at the Laboratory of Chemical Engineering of Toulouse. The different steps of the methodology are explained through its application to the carrying out of an exothermic reaction.

[1]  Paul M. Frank,et al.  Fault diagnosis in dynamic systems: theory and application , 1989 .

[2]  J. E. Jackson A User's Guide to Principal Components , 1991 .

[3]  Joseph Aguilar-Martin,et al.  Controlling selectivity in nonstandard pattern recognition algorithms , 1991, IEEE Trans. Syst. Man Cybern..

[4]  J. Edward Jackson,et al.  A User's Guide to Principal Components. , 1991 .

[5]  Shankar Narasimhan,et al.  Sensor network design for maximizing reliability of linear processes , 1993 .

[6]  I. Jolliffe Principal Component Analysis , 2002 .

[7]  Anil K. Jain,et al.  Data clustering: a review , 1999, CSUR.

[8]  Per Hagander,et al.  Temperature control of a utility system for an Open Plate Reactor , 2004 .

[9]  S. Joe Qin,et al.  Joint diagnosis of process and sensor faults using principal component analysis , 1998 .

[10]  Christos Georgakis,et al.  Disturbance detection and isolation by dynamic principal component analysis , 1995 .

[11]  Joseph Aguilar-Martin,et al.  An Optimization Method for the Data Space Partition Obtained by Classification Techniques for the Monitoring of Dynamic Processes , 2006, CCIA.

[12]  D. M. Himmelblau,et al.  Determination of optimal measuring sites for fault detection of non-linear systems , 1985 .

[13]  Keith Worden,et al.  Optimal sensor placement for fault detection , 2001 .

[14]  Max Donath,et al.  American Control Conference , 1993 .

[15]  N. Rakoto-Ravalontsalama,et al.  Automatic Clustering for Symbolic Evaluation for Dynamic Systems Supervision , 1992, 1992 American Control Conference.

[16]  Stéphane Lecoeuche,et al.  Unsupervised and auto-adaptive neural architecture for on-line monitoring. Application to a hydraulic process , 2003 .

[17]  L. Zadeh Fuzzy sets as a basis for a theory of possibility , 1999 .

[18]  Michel Cabassud,et al.  Performance Evaluation of a Novel Concept “Open Plate Reactor” Applied to Highly Exothermic Reactions , 2005 .

[19]  Tatiana Kempowsky Surveillance de procédés à base de méthodes de classification : conception d'un outil d'aide pour la détection et le diagnostic des défaillances , 2004 .

[20]  Yuhong Yan Sensor Placement and Diagnosability Analysis at Design Stage , 2004 .

[21]  Per Hagander,et al.  Process control of an open plate reactor , 2005 .

[22]  Audine Subias,et al.  Classification Tool Based on Interactivity Between Expertise and Self-Learning Techniques 1 , 2003 .

[23]  Rui J. P. de Figueiredo,et al.  A new neural network for cluster-detection-and-labeling , 1998, IEEE Trans. Neural Networks.

[24]  Raghunathan Rengaswamy,et al.  Locating sensors in complex chemical plants based on fault diagnostic observability criteria , 1999 .

[25]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

[26]  A. Singhal,et al.  Pattern matching in historical batch data using PCA , 2002 .

[27]  Chuei-Tin Chang,et al.  A simple design strategy for fault monitoring systems , 1993 .

[28]  Donald Gustafson,et al.  Fuzzy clustering with a fuzzy covariance matrix , 1978, 1978 IEEE Conference on Decision and Control including the 17th Symposium on Adaptive Processes.

[29]  James C. Bezdek,et al.  Pattern Recognition with Fuzzy Objective Function Algorithms , 1981, Advanced Applications in Pattern Recognition.

[30]  Carl G. Looney,et al.  Pattern recognition using neural networks , 1997 .

[31]  Madan M. Gupta,et al.  Approximate reasoning in decision analysis , 1982 .