Monitoring industrial processes with SOM-based dissimilarity maps

Today's large scale availability of data from industrial plants is an invaluable resource to monitor industrial processes. Data-based methods can lead to better understanding, optimization or detection of anomalies. As a particular case, batch processes have attracted special interest due to their widespread presence in the industry. The aim of monitoring, in this case, is to compare different runs or implementations of a process with the baseline or normal operating one. On the other hand, visual exploration tools for process monitoring have been a prolific application field for self-organizing maps (SOM). In this paper, we exploit data-based models, obtained by means of SOM, for the visual comparison of industrial processes. For that purpose, we propose a method that defines a new visual exploration tool, called dissimilarity map. We also expose the need to consider dynamic information for effective comparison. The method is assessed in two industrial pilot plants that implement the same process. The results are discussed.

[1]  I. Diaz,et al.  Visualizing knowledge for data mining using dimension reduction mappings , 2004, Proceedings of the 2004 IEEE International Conference on Information Reuse and Integration, 2004. IRI 2004..

[2]  Alfred Ultsch,et al.  Self Organized Feature Maps for Monitoring and Knowledge Aquisition of a Chemical Process , 1993 .

[3]  John F. MacGregor,et al.  Multivariate SPC charts for monitoring batch processes , 1995 .

[4]  Tadao Murata,et al.  Petri nets: Properties, analysis and applications , 1989, Proc. IEEE.

[5]  Guilherme De A. Barreto,et al.  Time Series Prediction with the Self-Organizing Map: A Review , 2007, Perspectives of Neural-Symbolic Integration.

[6]  Ignacio Díaz Blanco,et al.  Visual dynamic model based on self-organizing maps for supervision and fault detection in industrial processes , 2010, Eng. Appl. Artif. Intell..

[7]  Abel A. Cuadrado,et al.  Internet-based remote supervision of industrial processes using self-organizing maps , 2007 .

[8]  Teuvo Kohonen,et al.  The self-organizing map , 1990 .

[9]  J. Príncipe,et al.  Local dynamic modeling with self-organizing maps and applications to nonlinear system identification and control , 1998, Proc. IEEE.

[10]  Abel A. Cuadrado,et al.  A new approach to exploratory analysis of system dynamics using SOM. Applications to industrial processes , 2008 .

[11]  Erkki Oja,et al.  Engineering applications of the self-organizing map , 1996, Proc. IEEE.

[12]  Janos Gertler,et al.  Fault detection and diagnosis in engineering systems , 1998 .

[13]  O. Simula,et al.  The Self-organizing map as a tool in knowledge engineering , 2000 .

[14]  P. Reguera,et al.  Maqueta Industrial para Docencia e Investigación , 2004 .

[15]  VARUN CHANDOLA,et al.  Anomaly detection: A survey , 2009, CSUR.

[16]  Sameer Singh,et al.  Novelty detection: a review - part 1: statistical approaches , 2003, Signal Process..

[17]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[18]  Olli Simula,et al.  Process Monitoring and Modeling Using the Self-Organizing Map , 1999, Integr. Comput. Aided Eng..

[19]  Robert P. W. Duin,et al.  Novelty Detection Using Self-Organizing Maps , 1997, ICONIP.

[20]  J. Hollmen,et al.  Residual generation and visualization for understanding novel process conditions , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[21]  Ignacio Díaz Blanco,et al.  Fuzzy inference maps for condition monitoring with self-organizing maps , 2001, EUSFLAT Conf..

[22]  Daniel A. Keim,et al.  Information Visualization and Visual Data Mining , 2002, IEEE Trans. Vis. Comput. Graph..