Li-Ion Batteries Parameter Estimation With Tiny Neural Networks Embedded on Intelligent IoT Microcontrollers

Crocioni, Giulia; Pau, Danilo; Delorme, Jean Michel; Gruosso, Giambattista

doi:10.1109/access.2020.3007046

Cited by 60 publications

(26 citation statements)

References 29 publications

(40 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The weak extrapolability of these empirical models leads to the requirement of extensive experimental tests in order to cover full operating ranges for practical use. In the past five years, the data-driven methods have received rapidly growing research attention, because their model-free and easy-to-implement natures are in favor of real-world applications in view of recent advances in big data and artificial intelligence [11]- [13]. Among many datadriven techniques, incremental capacity analysis (ICA) is one of the most extensively investigated methods.…”

Section: Introductionmentioning

confidence: 99%

Offline and Online Blended Machine Learning for Lithium-Ion Battery Health State Estimation

She

Zou

et al. 2022

IEEE Trans. Transp. Electrific.

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Offline and Online Blended Machine Learning for Lithium-Ion Battery Health State Estimation

She

Zou

et al. 2022

IEEE Trans. Transp. Electrific.

View full text Add to dashboard Cite

“…ECM model estimated voltage and SoC data were validated using experimental data mean absolute error (MAE), mean square error (MSE), root mean square error (RMSE), and mean absolute percentage error were calculated by Equations (12) to (15). 31,72,73

MAE = \sum_{k = 1}^{n} (||, a_{k} - b_{k})

MSE = \frac{1}{n} \sum_{i = 1}^{n} {(a_{k} - b_{k})}^{2}

RMSE = \sqrt{\frac{1}{n} \sum_{i = 1}^{n} {(a_{k} - b_{k})}^{2}}

MAPE = ((), \frac{1}{n} \sum_{k = 1}^{n} \frac{|a_{k} - b_{k}|}{a_{k}}) * 100

…”

Section: Methodsmentioning

confidence: 99%

Investigation on lithium ion battery equivalent circuit models for dynamic load profiles

2021

View full text Add to dashboard Cite

To achieve accurate prediction of the nonlinear behavior of lithium‐ion battery, parameters of the lithium‐ion battery model play a key role for dynamic performance, hence the parameters of the investigated battery model have been estimated. In this work, the electrical equivalent circuit (ECM) models have been used to simulate INR18650‐20R lithium‐ion battery response at 0°C, 25°C, and 45°C, respectively. The ECM model parameters are estimated using incremental open‐circuit voltage (OCV) profile and Trust‐Region Reflective algorithm by the Non‐Linear Least Squares method. The estimated parameters of the ECM model experimentally validated using independent dynamic current profiles including Dynamic Stress Test (DST), Federal urban driving schedule (FUDS), Beijing Dynamic Stress test (BJDST), and US06 at 0°C, 25°C, and 45°C, respectively. Coulomb‐counting based algorithms are implemented for model‐based online SoC estimation. The investigated ECM model with three parallel RC branches exhibits accuracy below 1.8% for different temperature levels and seems suitable to capture the nonlinear dynamics of lithium‐ion batteries for EV application. It is confirmed that the errors resulting from the investigated ECM model are significantly reduced comparatively existing published models.

show abstract

“…Many studies have used the time-based data sampling, in which data are collected by constant time interval [31,33,39]. Their approach seemed reasonable, as typical equipment is measuring data at constant time interval.…”

Section: Time-based Data Samplingmentioning

confidence: 99%

Battery State-of-Health Estimation Using Machine Learning and Preprocessing with Relative State-of-Charge

Jung

Roh

2021

Energies

View full text Add to dashboard Cite

Because lithium-ion batteries are widely used for various purposes, it is important to estimate their state of health (SOH) to ensure their efficiency and safety. Despite the usefulness of model-based methods for SOH estimation, the difficulties of battery modeling have resulted in a greater emphasis on machine learning for SOH estimation. Furthermore, data preprocessing has received much attention because it is an important step in determining the efficiency of machine learning methods. In this paper, we propose a new preprocessing method for improving the efficiency of machine learning for SOH estimation. The proposed method consists of the relative state of charge (SOC) and data processing, which transforms time-domain data into SOC-domain data. According to the correlation analysis, SOC-domain data are more correlated with the usable capacity than time-domain data. Furthermore, we compare the estimation results of SOC-based data and time-based data in feedforward neural networks (FNNs), convolutional neural networks (CNNs), and long short-term memory (LSTM). The results show that the SOC-based preprocessing outperforms conventional time-domain data-based techniques. Furthermore, the accuracy of the simplest FNN model with the proposed method is higher than that of the CNN model and the LSTM model with a conventional method when training data are small.

show abstract

Li-Ion Batteries Parameter Estimation With Tiny Neural Networks Embedded on Intelligent IoT Microcontrollers

Cited by 60 publications

References 29 publications

Offline and Online Blended Machine Learning for Lithium-Ion Battery Health State Estimation

Offline and Online Blended Machine Learning for Lithium-Ion Battery Health State Estimation

Investigation on lithium ion battery equivalent circuit models for dynamic load profiles

Battery State-of-Health Estimation Using Machine Learning and Preprocessing with Relative State-of-Charge

Contact Info

Product

Resources

About