A Data-Driven Predictive Prognostic Model for Lithium-Ion Batteries based on a 
Deep Learning Algorithm

Prognostic and health management (PHM) can ensure that a lithium-ion battery is working safely and reliably. The main approach of PHM evaluation of the battery is to determine the State of Health (SoH) and the Remaining Useful Life (RUL) of the battery. The advancements of computational tools and big data algorithms have led to a new era of data-driven predictive analysis approaches, using machine learning algorithms. This paper presents the preliminary development of the data-driven prognostic, using a Deep Neural Networks (DNN) approach to predict the SoH and the RUL of the lithium-ion battery. The effectiveness of the proposed approach was implemented in a case study with a battery dataset obtained from the National Aeronautics and Space Administration (NASA) Ames Prognostics Center of Excellence (PCoE) database. The proposed DNN algorithm was compared against other machine learning algorithms, namely, Support Vector Machine (SVM), k-Nearest Neighbors (k-NN), Artificial Neural Networks (ANN), and Linear Regression (LR). The experimental results reveal that the performance of the DNN algorithm could either match or outweigh other machine learning algorithms. Further, the presented results could serve as a benchmark of SoH and RUL prediction using machine learning approaches specifically for lithium-ion batteries application.

Download Full-text

State of Charge Estimation of Lithium-Ion Battery for Electric Vehicles Using Machine Learning Algorithms

World Electric Vehicle Journal ◽

10.3390/wevj12010038 ◽

2021 ◽

Vol 12 (1) ◽

pp. 38

Author(s):

Venkatesan Chandran ◽

Chandrashekhar K. Patil ◽

Alagar Karthick ◽

Dharmaraj Ganeshaperumal ◽

Robbi Rahim ◽

...

Keyword(s):

Machine Learning ◽

Lithium Ion Battery ◽

Electric Vehicles ◽

Learning Algorithms ◽

Gaussian Process Regression ◽

Lithium Ion ◽

Machine Learning Algorithms ◽

State Of Charge ◽

Support Vector ◽

Soc Estimation

The durability and reliability of battery management systems in electric vehicles to forecast the state of charge (SoC) is a tedious task. As the process of battery degradation is usually non-linear, it is extremely cumbersome work to predict SoC estimation with substantially less degradation. This paper presents the SoC estimation of lithium-ion battery systems using six machine learning algorithms for electric vehicles application. The employed algorithms are artificial neural network (ANN), support vector machine (SVM), linear regression (LR), Gaussian process regression (GPR), ensemble bagging (EBa), and ensemble boosting (EBo). Error analysis of the model is carried out to optimize the battery’s performance parameter. Finally, all six algorithms are compared using performance indices. ANN and GPR are found to be the best methods based on MSE and RMSE of (0.0004, 0.00170) and (0.023, 0.04118), respectively.

Download Full-text

A Comparison of Machine Learning Algorithms on Lithium-ion Battery Cycle Life Prediction

10.1109/ubmk52708.2021.9558946 ◽

2021 ◽

Author(s):

Melike Dokgoz ◽

Yusuf Yaslan

Keyword(s):

Machine Learning ◽

Lithium Ion Battery ◽

Life Prediction ◽

Learning Algorithms ◽

Lithium Ion ◽

Machine Learning Algorithms ◽

Cycle Life

Download Full-text

Modeling Lithium-Ion Batteries Using Machine Learning Algorithms for Mild-Hybrid Vehicle Applications

10.1109/sest50973.2021.9543225 ◽

2021 ◽

Author(s):

Daniel Jerouschek ◽

Omer Tan ◽

Ralph Kennel ◽

Ahmet Taskiran

Keyword(s):

Machine Learning ◽

Lithium Ion Batteries ◽

Learning Algorithms ◽

Lithium Ion ◽

Hybrid Vehicle ◽

Machine Learning Algorithms ◽

Mild Hybrid

Download Full-text

Introduction and Implementation of Machine Learning Algorithms in R

Advances in Business Information Systems and Analytics - Sentiment Analysis and Knowledge Discovery in Contemporary Business ◽

10.4018/978-1-5225-4999-4.ch008 ◽

2019 ◽

pp. 126-147

Author(s):

S. R. Mani Sekhar ◽

G. M. Siddesh

Keyword(s):

Machine Learning ◽

Neural Networks ◽

Support Vector Machine ◽

Discriminant Analysis ◽

Computer Science ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Support Vector ◽

Linear Discriminant ◽

The Given

Machine learning is one of the important areas in the field of computer science. It helps to provide an optimized solution for the real-world problems by using past knowledge or previous experience data. There are different types of machine learning algorithms present in computer science. This chapter provides the overview of some selected machine learning algorithms such as linear regression, linear discriminant analysis, support vector machine, naive Bayes classifier, neural networks, and decision trees. Each of these methods is illustrated in detail with an example and R code, which in turn assists the reader to generate their own solutions for the given problems.

Download Full-text

(Invited) Application of High Throughput Experimentation to Machine Learning Algorithms for the Development of Lithium Ion Battery Materials

ECS Meeting Abstracts ◽

10.1149/ma2019-03/1/23 ◽

2019 ◽

Keyword(s):

Machine Learning ◽

Lithium Ion Battery ◽

High Throughput ◽

Learning Algorithms ◽

Lithium Ion ◽

Machine Learning Algorithms ◽

Battery Materials ◽

High Throughput Experimentation

Download Full-text

A Hybrid Prognostic Approach for Remaining Useful Life Prediction of Lithium-Ion Batteries

Shock and Vibration ◽

10.1155/2016/3838765 ◽

2016 ◽

Vol 2016 ◽

pp. 1-15 ◽

Cited By ~ 2

Author(s):

Wen-An Yang ◽

Maohua Xiao ◽

Wei Zhou ◽

Yu Guo ◽

Wenhe Liao

Keyword(s):

Lithium Ion Batteries ◽

Lithium Ion Battery ◽

Learning Algorithm ◽

Lithium Ion ◽

Relevance Vector Machine ◽

Remaining Useful Life ◽

Support Vector ◽

Failure Event ◽

Useful Life ◽

Data Driven Modeling

Lithium-ion battery is a core component of many systems such as satellite, spacecraft, and electric vehicles and its failure can lead to reduced capability, downtime, and even catastrophic breakdowns. Remaining useful life (RUL) prediction of lithium-ion batteries before the future failure event is extremely crucial for proactive maintenance/safety actions. This study proposes a hybrid prognostic approach that can predict the RUL of degraded lithium-ion batteries using physical laws and data-driven modeling simultaneously. In this hybrid prognostic approach, the relevant vectors obtained with the selective kernel ensemble-based relevance vector machine (RVM) learning algorithm are fitted to the physical degradation model, which is then extrapolated to failure threshold for estimating the RUL of the lithium-ion battery of interest. The experimental results indicated that the proposed hybrid prognostic approach can accurately predict the RUL of degraded lithium-ion batteries. Empirical comparisons show that the proposed hybrid prognostic approach using the selective kernel ensemble-based RVM learning algorithm performs better than the hybrid prognostic approaches using the popular learning algorithms of feedforward artificial neural networks (ANNs) like the conventional backpropagation (BP) algorithm and support vector machines (SVMs). In addition, an investigation is also conducted to identify the effects of RVM learning algorithm on the proposed hybrid prognostic approach.

Download Full-text

A Very Large-Scale Bioactivity Comparison of Deep Learning and Multiple Machine Learning Algorithms for Drug Discovery

10.26434/chemrxiv.12781241 ◽

2020 ◽

Author(s):

Thomas R. Lane ◽

Daniel H. Foil ◽

Eni Minerali ◽

Fabio Urbina ◽

Kimberley M. Zorn ◽

...

Keyword(s):

Machine Learning ◽

Neural Networks ◽

Deep Learning ◽

Drug Discovery ◽

Deep Neural Networks ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Support Vector ◽

Learning Methods ◽

Machine Learning Methods

Machine learning methods are attracting considerable attention from the pharmaceutical industry for use in drug discovery and applications beyond. In recent studies we have applied multiple machine learning algorithms, modeling metrics and in some cases compared molecular descriptors to build models for individual targets or properties on a relatively small scale. Several research groups have used large numbers of datasets from public databases such as ChEMBL in order to evaluate machine learning methods of interest to them. The largest of these types of studies used on the order of 1400 datasets. We have now extracted well over 5000 datasets from CHEMBL for use with the ECFP6 fingerprint and comparison of our proprietary software Assay CentralTM with random forest, k-Nearest Neighbors, support vector classification, naïve Bayesian, AdaBoosted decision trees, and deep neural networks (3 levels). Model performance <a>was</a> assessed using an array of five-fold cross-validation metrics including area-under-the-curve, F1 score, Cohen’s kappa and Matthews correlation coefficient. <a>Based on ranked normalized scores for the metrics or datasets all methods appeared comparable while the distance from the top indicated Assay CentralTM and support vector classification were comparable. </a>Unlike prior studies which have placed considerable emphasis on deep neural networks (deep learning), no advantage was seen in this case where minimal tuning was performed of any of the methods. If anything, Assay CentralTM may have been at a slight advantage as the activity cutoff for each of the over 5000 datasets representing over 570,000 unique compounds was based on Assay CentralTMperformance, but support vector classification seems to be a strong competitor. We also apply Assay CentralTM to prospective predictions for PXR and hERG to further validate these models. This work currently appears to be the largest comparison of machine learning algorithms to date. Future studies will likely evaluate additional databases, descriptors and algorithms, as well as further refining methods for evaluating and comparing models.

Download Full-text

Analysis of Data-Driven Prediction Algorithms for Lithium-Ion Batteries Remaining Useful Life

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.717.390 ◽

2013 ◽

Vol 717 ◽

pp. 390-395 ◽

Cited By ~ 4

Author(s):

Lin Jiang ◽

Wei Ming Xian ◽

Bin Long ◽

Hou Jun Wang

Keyword(s):

Lithium Ion Batteries ◽

Particle Filtering ◽

Linear Trend ◽

Lithium Ion ◽

Single Step ◽

Remaining Useful Life ◽

Data Driven ◽

Support Vector ◽

Data Set ◽

Useful Life

As one of the most widely used energy storage systems, lithium-ion batteries are attracting more and more attention, and the estimation of lithium-ion batteries remaining useful life (RUL) becoming a critical problem. Generally, RUL can be predicted in two ways: physics of failure (PoF) method and data driven method. Due to the internal electro-chemical reactions are either inaccessible to sensors or hard to measure; the data-driven method is adopted because it does not require specific knowledge of material properties. In this paper, three data-driven algorithms, i.e., Support Vector Machine (SVM), Autoregressive Moving Average (ARMA), and Particle Filtering (PF) are presented for RUL prediction. The lithium-ion battery aging experiment data set has been trained to implement simulation. Based on the RUL prediction result, we can conclude that: (1) ARMA model achieved better result than SVM, however, the result shows a linear trend, which fail to properly reflect the degradation trend of the battery; (2) SVM often suffers from over fitting problem and is more suitable for single-step prediction; and (3) PF approach achieved a better prediction and reflected the trends of degradation of the battery owing to its combined with specific model.

Download Full-text

State of Health Estimation of Lithium-Ion Batteries Based on Combination of Gaussian Distribution Data and Least Squares Support Vector Machines Regression

Materials Science Forum ◽

10.4028/www.scientific.net/msf.929.93 ◽

2018 ◽

Vol 929 ◽

pp. 93-102

Author(s):

Didik Djoko Susilo ◽

Achmad Widodo ◽

Toni Prahasto ◽

Muhammad Nizam

Keyword(s):

Lithium Ion Batteries ◽

Lithium Ion ◽

Remaining Useful Life ◽

Data Driven ◽

Support Vector ◽

Degradation Data ◽

Starting Point ◽

Capacity Degradation ◽

Battery Capacity ◽

Useful Life

Lithium-ion batteries play a critical role in the reliability and safety of a system. Battery health monitoring and remaining useful life (RUL) prediction are needed to prevent catastrophic failure of the battery. The aim of this research is to develop a data-driven method to monitor the batteries state of health and predict their RUL by using the battery capacity degradation data. This paper also investigated the effect of prediction starting point to the RUL prediction error. One of the data-driven method drawbacks is the need of a large amount of data to obtain accurate prediction. This paper proposed a method to generate a series of degradation data that follow the Gaussian distribution based on limited battery capacity degradation data. The prognostic model was constructed from the new data using least square support vector machine (LSSVM) regression. The remaining useful life prediction was carried out by extrapolating the model until reach the end of life threshold. The method was applied to three differences lithium-ion batteries capacity data. The results showed that the proposed method has good performance. The method can predict the lithium-ion batteries RUL with a small error, and the optimal RUL starting point was found at the point where the battery has experienced the highest capacity recovery due to the self-recharge phenomenon.

Download Full-text