Data Preparation and Training Methodology for Modeling Lithium-Ion Batteries Using a Long Short-Term Memory Neural Network for Mild-Hybrid Vehicle Applications

Applied Sciences

Ömer Tan¹  Daniel Jerouschek¹  Ahmet Taskiran¹  Ralph Kennel² 

[1] Department of System Integration and Energy Management, IAV GmbH, Weimarer Straße 10, 80807 Munich, Germany;Institute for Electrical Drive Systems and Power Electronics, Technical University of Munich, Arcisstrasse 21, 80333 Munich, Germany;

关键词: lithium-ion battery (LIB);    long short-term memories (LSTM);    machine learning (ML);    modeling;    recurrent neural net (RNN);   

DOI  :  10.3390/app10217880

来源: DOAJ

【 摘 要 】

Voltage models of lithium-ion batteries (LIB) are used to estimate their future voltages, based on the assumption of a specific current profile, in order to ensure that the LIB remains in a safe operation mode. Data of measurable physical features—current, voltage and temperature—are processed using both over- and undersampling methods, in order to obtain evenly distributed and, therefore, appropriate data to train the model. The trained recurrent neural network (RNN) consists of two long short-term memory (LSTM) layers and one dense layer. Validation measurements over a wide power and temperature range are carried out on a test bench, resulting in a mean absolute error (MAE) of 0.43 V and a mean squared error (MSE) of 0.40 V². The raw data and modeling process can be carried out without any prior knowledge of LIBs or the tested battery. Due to the challenges involved in modeling the state-of-charge (SOC), measurements are used directly to model the behavior without taking the SOC estimation as an input feature or calculating it in an intermediate step.

【 授权许可】

Unknown