Identification of Li-ion battery models through monotonic echo serial networks for coarse data. (15th January 2020)

• Record Type: Journal Article
• Authors: Álvarez-Caballero, Antonio; Blanco, Cecilio; Couso, Inés; Sánchez, Luciano
• Is Part Of: Logic journal of the IGPL. Volume 28:Number 1(2020)
• Page Start: 109
• Page End: 120
• Publication Date: 2020-01-15
• Subjects: Transformation models -- battery model -- monotonic model -- echo state networks; Logic, Symbolic and mathematical -- Periodicals; 511.3
• DOI: 10.1093/jigpal/jzz075
• Languages: English
• ISSNs: 1367-0751

Abstract

Abstract: Monotone transformation models are extended to inaccurate data and are combined with recurrent neural networks in a new battery model that is able to ascertain the health of rechargeable batteries for automotive applications. The presented method exploits the information contained in the vehicle's operational records better than other cutting-edge models and uses a minimum amount of human expert knowledge. The experimental validation of the technique includes a comparative analysis of batteries in different health conditions, comprising first-principles models and different machine learning procedures.