Machine Learning Applied to Electrified Vehicle Battery State of Charge and State of Health Estimation: State-of-the-Art

Carlos Vidal,Phillip Kollmeyer,Ali Emadi,Pawel Malysz

doi:10.1109/access.2020.2980961

Carlos Vidal, Phillip Kollmeyer + Show 2 more

Open Access

https://doi.org/10.1109/access.2020.2980961

Copy DOI

Abstract

The growing interest and recent breakthroughs in artificial intelligence and machine learning (ML) have actively contributed to an increase in research and development of new methods to estimate the states of electrified vehicle batteries. Data-driven approaches, such as ML, are becoming more popular for estimating the state of charge (SOC) and state of health (SOH) due to greater availability of battery data and improved computing power capabilities. This paper provides a survey of battery state estimation methods based on ML approaches such as feedforward neural networks (FNNs), recurrent neural networks (RNNs), support vector machines (SVM), radial basis functions (RBF), and Hamming networks. Comparisons between methods are shown in terms of data quality, inputs and outputs, test conditions, battery types, and stated accuracy to give readers a bigger picture view of the ML landscape for SOC and SOH estimation. Additionally, to provide insight into how to best approach with the comparison of different neural network structures, an FNN and long short-term memory (LSTM) RNN are trained fifty times each for 3000 epochs. The error is somewhat different for each training repetition due to the random initial values of the trainable parameters, demonstrating that it is important to train networks multiple times to achieve the best result. Furthermore, it is recommended that when performing a comparison among estimation techniques such as those presented in this review paper, the compared networks should have a similar number of learnable parameters and be trained and tested with identical data. Otherwise, it is difficult to make a general conclusion regarding the quality of a given estimation technique.

Highlights

The transportation industry faces many challenges to improve efficiency, expand performance, advance connectivity, increase autonomy, and reduce emissions
Significant design effort is placed on the battery management system (BMS) software design to perform a state of charge (SOC) and state of health (SOH) estimation accurately
Many other parameters besides the number of neurons and learning rates should be considered, e.g., the number of hidden layers, the initial weights distribution values, it will increase complexity and the offline computational burden for the search of the optimal structures. Another unique approach was presented by the authors in [22], where they have trained a model composed of three parallel feedforward neural networks (FNNs), each individually trained with distinct training data from three operation modes, idling, charging, and discharging

Summary

INTRODUCTION

The transportation industry faces many challenges to improve efficiency, expand performance, advance connectivity, increase autonomy, and reduce emissions. For a comprehensive review of the different approaches to the estimation of SOC, SOH, SOP, and other battery states, beyond the machine learning approaches, which are the focus of this paper, readers are referred to [4], [6], [7]. Machine learning data-driven approaches to battery state estimation have been driven by recent advances in artificial intelligence (AI) [8] in fields such as computer vision and autonomous vehicles. To determine the percentage of useful energy left inside the battery, it is necessary to perform an indirect measurement of the SOC via estimation This is done by a great variety of methods and techniques which use measurable signals such as the battery terminal voltage, current, and temperature [4].

FEEDFORWARD ARTIFICIAL NEURAL NETWOR

RADIAL BASIS FUNCTION NEURAL NETWORK

Findings

CONCLUDING REMARKS