Estimating battery state of charge using recurrent and non-recurrent neural networks. (March 2022)

• Record Type: Journal Article
• Authors: Vidal, Carlos; Malysz, Pawel; Naguib, Mina; Emadi, Ali; Kollmeyer, Phillip J.
• Is Part Of: Journal of energy storage. Volume 47(2022)
• Publication Date: 2022-03
• Subjects: LSTM -- Li-ion -- SOC -- Machine learning -- Electric vehicles -- Battery; Energy storage -- Periodicals; Energy storage -- Research -- Periodicals; 621.3126
• DOI: 10.1016/j.est.2021.103660
• Languages: English
• ISSNs: 2352-152X

Abstract

Highlights: Developed feedforward & recurrent neural network state of charge estimators. Memory effectively added to feedforward network through filtered inputs. Performance evaluated from -10°C to 25°C for automotive drive cycles. Microprocessor execution time measured for both network types. Datasets and neural network training code freely available to download. Abstract: Battery state of charge estimation is critical for determining the remaining range of electrified vehicles and the runtime of battery-powered equipment. Neural network algorithms which learn the relation between battery measurements and state of charge are a promising alternative to estimators based on models with adaptive filters. In this work, two types of neural networks are studied: recurrent networks, which have inherent memory of the past, and non-recurrent networks, which can effectively have memory added through exogenous filtered inputs. An extensive and comprehensive study is performed for these network types, with learnable parameters ranging from 20 to 3000. Network performance is compared for two different battery types, multiple temperatures, drive cycles, and training repetitions. Compared to a recurrent neural network, a non-recurrent feedforward neural network with filtered inputs is found to be up to 23% more accurate, require less training time (76% less using a CPU and 60% less using a GPU), and execute in about 1/3 the amount of time on an NXP S32K142 microprocessor.