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

A collaborative network of digital twins for anomaly detection applications of complex systems. Snitch Digital Twin concept

P. Calvo-Báscones, A. Voisin, P. Do, M.A. Sanz-Bobi

Computers in Industry Vol. 144, pp. 103767-1 - 103767-17

Resumen:

This paper proposes a novel anomaly detection methodology for industrial systems based on Digital Twin (DT) ecosystems. In addition to DTs, conceived as a digital representation of a physical entity, this paper proposes a new concept of DT focused on modeling connections between physical behaviors. This new DT concept is called Snitch Digital Twin (SDT). The scope of the SDT is the study of variations between behaviors and support the detection of anomalies between them. The behavior of each physical entity is characterized by three spatiotemporal features computed from each collected measurement. Behavioral anomalies are identified and quantified through modular patterns based on quantile regression and behavioral indexes. Finally, the robustness of the proposed methodology is assessed by comparing it with the other two commonly used algorithms based on Kernel Principal Component Analysis (KPCA) and One-Class Support Vector Machines (OCSVM) in a case study application. The case study is based on the diagnosis of the cooling system of a power-generator diesel engine. The results obtained prove the advantages and goodness of this novel methodology compared to the two traditional algorithms.


Resumen divulgativo:

El concepto de Gemelo Digital se fundamenta en la digitalización del estado de vida y comportamiento activos reales. Este artículo propone un nuevo concepto de Gemelo Digital, llamado Gemelo Digitale Chivato con un gran potencial en aplicaciones de detección de anomalías en sistemas multi-agente.


Palabras Clave: Anomaly detection; Digital Twins; Behavior characterization; Quantile regression; Diesel generator


Índice de impacto JCR y cuartil WoS: 7.635 - Q1 (2020)

Referencia DOI: DOI icon 10.1016/j.compind.2022.103767

Publicado en papel: Enero 2023.

Publicado on-line: Septiembre 2022.



Cita:
P. Calvo-Báscones, A. Voisin, P. Do, M.A. Sanz-Bobi. A collaborative network of digital twins for anomaly detection applications of complex systems. Snitch Digital Twin concept. Computers in Industry. Vol. 144, pp. 103767-1 - 103767-17, Enero 2023. [Online: Septiembre 2022]


    Líneas de investigación:
  • Industria conectada: análisis del ciclo de vida y gestión de activos
  • Analítica de datos avanzada en el sector energético
  • Análisis de datos
  • Industria conectada: mantenimiento, fiabilidad y diagnostico con auto-aprendizaje