• Plataforma de vídeos del IIT
  • Twitter
  • LinkedIn
  • Asociación de Ingenieros del ICAI
  • Intranet
  • English
Ir arriba
Información del artículo

Auto-regressive processes explained by self-organized maps: application to the detection of abnormal behavior in industrial processes

C. Brighenti, M.A. Sanz-Bobi

IEEE Transactions on Neural Networks Vol. 22, nº. 12, pp. 2078 - 2090

Resumen:
This paper analyzes the expected time evolution of an auto-regressive (AR) process using self-organized maps (SOM). It investigates how a SOM captures the time information given by the AR input process and how the transitions from one neuron to another one can be understood under a probabilistic perspective. In particular, regions of the map into which the AR process is expected to move are identified. This characterization allows detecting anomalous changes in the AR process structure or parameters. On the basis of the theoretical results, an anomaly detection method is proposed and applied to a real industrial process.


Palabras Clave: Anomaly detection, auto-regressive processes, process quantization, self-organizing maps


Índice de impacto JCR y cuartil WoS: 2.952 (2011)

Referencia DOI: DOI icon 10.1109/TNN.2011.2169810

Publicado en papel: Diciembre 2011.



Cita:
C. Brighenti, M.A. Sanz-Bobi. Auto-regressive processes explained by self-organized maps: application to the detection of abnormal behavior in industrial processes. IEEE Transactions on Neural Networks. Vol. 22, nº. 12, pp. 2078 - 2090 Diciembre 2011.


    Líneas de investigación:
  • *Predicción y Análisis de Datos
  • *Modelado, Simulación y Optimización

pdf Previsualizar
pdf Solicitar el artículo completo a los autores