Li-ion battery degradation modes diagnosis via Convolutional Neural Networks

Costa, Nahuel; Sánchez, Luciano; Anseán, David; Dubarry, Matthieu

doi:10.1016/j.est.2022.105558

Cited by 33 publications

(22 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mayilvahanan et al 31 proposed an ML framework, training by the physics‐based synthetic data, 28 to simultaneously quantitatively predict the values of three degradation modes and classify the limiting electrode with the input of preprocessing the low‐rate charging curves. Leveraging the same synthetic dataset, cycle‐to‐cycle evolution of capacity (

∆ Q (V)

) 119 /IC curves 120 images represented as input features, diagnosis models embedded with NN were trained to quantify the three degradation modes of real‐world LIBs. Kim et al 121 presented a synthetic–data‐based deep learning framework for two‐step classifying dominant aging modes and quantifying the corresponding LLI as well as LAM, with the input of capacity fade and features derived from IC curves.…”

Section: Tasks In Battery Healthmentioning

confidence: 99%

Feature–target pairing in machine learning for battery health diagnosis and prognosis: A critical review

Huang

Sugiarto

2023

EcoMat

View full text Add to dashboard Cite

Lithium‐ion batteries (LIBs) have been dominating the markets of electric vehicles and grid energy storage. Accurate monitoring of battery health status has been one of the most critical challenges of the battery industry. Machine learning (ML) has been widely applied to battery health estimation as well as prediction. Here, by investigating the specific features and targets, we comprehensively discuss task‐oriented ML implementation in various application scenarios in the field of battery health. This review explores the tasks assisted by ML based on multi‐level cell degradation. We highlight opportunities and significance of considering the potential feature–target pair during the ML model training to identify more health information about LIBs as well as shed light into designing tasks for new application scenarios.

show abstract

∆ Q (V)

Section: Tasks In Battery Healthmentioning

confidence: 99%

Feature–target pairing in machine learning for battery health diagnosis and prognosis: A critical review

Huang

Sugiarto

2023

EcoMat

View full text Add to dashboard Cite

show abstract

“…Convolutional networks use in the CNN method to extract complex features from parameters such as temperature, current, and voltage [13]. Among the networks used in battery SOC estimation are Conv2D and Conv1D in addition [14]. Although models such as ResNet and VGG from convolutional-based networks have proven their success on image datasets, they are also used in studies such as regression estimation [15].…”

Section: Related Workmentioning

confidence: 99%

Performance Comparison of Lithium Polymer Battery SOC Estimation Using GWO-BiLSTM and Cutting-Edge Deep Learning Methods

Taş

Bal

Uysal

2023

Preprint

View full text Add to dashboard Cite

In this study, the GWO-BiLSTM method has been proposed by successfully estimating the SOC with the BiLSTM deep learning method using the hyper-parameter values determined by the GWO method of the lithium polymer battery. In studies using deep learning methods, it is important to solve the problems of underfitting, overfitting, and estimation error by determining the hyper-parameters appropriately. EV, HEV, and robots are used more healthily with the successful, reliable, and fast SOC estimation, which has an important place in the Battery Management System. The success of the proposed method was verified by comparing the cutting-edge data-based deep learning methods and the BiLSTM method with the SOC estimation MAE, MSE, RMSE, and Runtime(s) metrics. In the comparison, the prediction successes of the BiLSTM method, which was trained with the optimal hyper-parameter values obtained by the GWO method, with the cutting-edge deep learning methods trained with the hyper-parameter values obtained through trial and error were compared. The GWO-BiLSTM method was the most successful method with RMSE of 0.09244% and R2 of 0.9987 values according to the average results of SOC estimation made with the lithium polymer battery data set, which was created by experiments performed at different discharge levels and is new in the literature.

show abstract

“…Decision trees are deterministic models that rely on multiple conditionals while neural networks follow a probabilistic approach in which they seek to learn by activating arti cial neurons. For this work, Random Forest (RF) [21] and Gradient Boosting Trees (XGB) [22] algorithms were selected for the decision trees and Feed-forward neural network (FNN) [23], 1D-CNN (1DConv) [16], and the DTW-CNN approach [24] were selected as neural networks. It is important to note that in all cases the models use the raw derivative voltage curves as input except for DTW-CNN, which uses images created from the DTW matrix between the pristine and the degraded derivative curves.…”

Section: Diagnosis Algorithmsmentioning

confidence: 99%

“…It is important to note that in all cases the models use the raw derivative voltage curves as input except for DTW-CNN, which uses images created from the DTW matrix between the pristine and the degraded derivative curves. This allows to transform voltage changes into images that re ect the degradation and enables the use of 2D CNNs, which are widely known in the literature to work remarkable well with images [24].…”

Section: Diagnosis Algorithmsmentioning

confidence: 99%

“…This dataset is then used to train, test, and compare selected ML algorithms for diagnosis, including a Random Forest regressor (RF) [21], an Extreme Gradient Boosting regressor (XGB) [22], a Feed-forward neural network (FNN) [23], a 1 dimensional Convolutional Neural Network (1D-Conv) [16], and a dynamic time warping 2-D Convolutional Neural Network (DTW)-CNN [24].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Data-Driven Direct Diagnosis of PV Connected Batteries

Dubarry¹,

Costa²,

Matthews³

2022

Meet. Abstr.

View full text Add to dashboard Cite

Photovoltaic systems are providing a growing share of power to the electric grid worldwide. As more and more of these systems are tied with battery energy storage to balance their intermittency, being able to ensure long and safe operation of these batteries will become critical. Because of their sporadic usage, far from the typical constant current or constant power, diagnosability without having to perform lengthy maintenance cycles will be a key factor to accelerate deployment. This work proposes a new methodology to enable the training of machine learning algorithms so they could be applied directly to photovoltaic (PV) battery charging data for opportunistic diagnosis. This is done by training the algorithms on synthetic voltage data under different degradations calculated from clear-sky model irradiance data. Validation was performed on synthetic voltage responses calculated from plane of array irradiance observations for a PV system located in Maui, HI, USA. Herein, we will present the result of our proof-of-concept study where we investigated the diagnosability of the voltage response of PV charged batteries under 18 different cloud coverages scenarios and for more than 10,000 different degradations. We also evaluated the effect of training conditions on clear-sky irradiance data by analyzing the resulting differences from training on 700,000 different voltage curves for a single day vs. 45,000 different voltage curves for of each of the 18 days used for cloud coverage estimation. In addition, we considered and quantified the effect of cell-to-cell variations. Training was performed on five state-of-the-art machine learning algorithms for battery diagnosis which included decision tree ensemble methods and neural networks. Finally, because the diagnosis was done outside of constant current, the capacity- and time-based information were decorrelated and compared. While time-base diagnosis is the most interesting for deployed systems, it was shown to be less accurate than its capacity counterpart for the tested algorithms. Yet, the accuracy of the diagnosis is still satisfactory for days where cloud effect is limited (average RMSE of 2.5% compared to 1.3% for capacity based if 50% or more clear skies). Summarizing, we will show that the degradation of PV-connected batteries could be diagnosed opportunistically without the need for maintenance cycles using well-trained state-of-art machine learning algorithms. Calculated RMSEs were below 2% for days with 50% or more clear skies considering more than 10,000 different degradation paths with 25% or less of the three thermodynamic degradation modes. In addition to the results themselves, and before real PV battery degradation data becomes available, this work is showing the significant benefits of using synthetic data to understand the expected variations and to start preparing adapted tools for when data become available.

show abstract

Li-ion battery degradation modes diagnosis via Convolutional Neural Networks

Cited by 33 publications

References 68 publications

Feature–target pairing in machine learning for battery health diagnosis and prognosis: A critical review

Feature–target pairing in machine learning for battery health diagnosis and prognosis: A critical review

Performance Comparison of Lithium Polymer Battery SOC Estimation Using GWO-BiLSTM and Cutting-Edge Deep Learning Methods

Data-Driven Direct Diagnosis of PV Connected Batteries

Contact Info

Product

Resources

About