A Fault Detection System for Power Cells During Capacity Confirmation Test Through a Global One-Class Classifier

• Esteban Jove ^[1] ; José-Luis Casteleiro-Roca ^[1] ; Héctor Quintián ^[1] ; Francisco Zayas-Gato ^[1] ; José Luis Calvo-Rolle ^[1]
  1. [1] Universidade da Coruña

     Universidade da Coruña

     A Coruña, España

     
• Localización: Intelligent Data Engineering and Automated Learning – IDEAL 2020. 21st International Conference: Guimarães, Portugal; November 4–6, 2020. Proceedings / Cesar Analide (ed. lit.), Paulo Novais (ed. lit.), David Camacho Fernández (ed. lit.), Hujun Yin (ed. lit.), Vol. 2, 2020 (Part II), ISBN 978-3-030-62365-4, págs. 477-484
• Idioma: inglés
• Enlaces
  • Texto completo
• Resumen

  • Power cells have presented an increasing popularity during last decades due to its importance in electric mobility, electronic devices and energy management systems. The international expansion of green policies to promote electric cars and renewable energies, has resulted in the need of ensuring their quality and reliability performance. In this context, detecting any early deviation from the correct operation must be addressed. Hence, this work is focused on the fault detection in a Lithium Iron Phosphate – LiFePO4 (LFP) cell. This is achieved by means of different one-class techniques, whose performance is assessed through artificially generated anomalies. After analysing the behaviour of each tested technique, the chosen classifier presents a successful performance.