SOH and RUL Prediction of Lithium-Ion Batteries Based on Gaussian Process Regression with Indirect Health Indicators

Jia, Jianfang; Liang, Jianyu; Shi, Yuanhao; Wen, Jinyu; Pang, Xiaoqiong; Zeng, Jianchao

doi:10.3390/en13020375

Cited by 148 publications

(58 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The input vector x i and output f ( x i ) in this article are both one-dimensional scalars, where x i is a time series, that is, the number of cycles 26 , 29 , rather than physical features 14 , 27 , 39 , 40 , and the output is the corresponding discharge capacitance. However, when needed, a similar study for obtaining better results can be performed in the case of a high-dimensional input, although it requires some feature engineering.…”

Section: Methodsmentioning

confidence: 99%

High precision implicit function learning for forecasting supercapacitor state of health based on Gaussian process regression

Ren

Cai

2021

Sci Rep

View full text Add to dashboard Cite

State of health (SOH) prediction of supercapacitors aims to provide reliable lifetime control and avoid system failure. Gaussian process regression (GPR) has emerged for SOH prediction because of its capability of capturing nonlinear relationships between features, and tracking SOH attenuations effectively. However, traditional GPR methods based on explicit functions require multiple screenings of optimal mean and covariance functions, which results in data scarcity and increased time consumption. In this study, we propose a GPR-implicit function learning, which is a prior knowledge algorithm for calculating mean and covariance functions from a preliminary data set instead of screening. After introducing the implicit function, the average root mean square error (Average RMSE) is 0.0056 F and the average mean absolute percent error (Average MAPE) is 0.6%, where only the first 5% of the data are trained to predict the remaining 95% of the cycles, thereby decreasing the error by more than three times than previous studies. Furthermore, less cycles (i.e., 1%) are trained while still obtaining low prediction errors (i.e., Average RMSE is 0.0094 F and Average MAPE is 1.01%). This work highlights the strength of GPR-implicit function model for SOH prediction of energy storage devices with high precision and limited property data.

show abstract

Section: Methodsmentioning

confidence: 99%

High precision implicit function learning for forecasting supercapacitor state of health based on Gaussian process regression

Ren

Cai

2021

Sci Rep

View full text Add to dashboard Cite

show abstract

“…In 2020, short-term SOH estimation was completed by adding the Gaussian process regression (GPR) approach with probability prognostics [249]. The SOH value along with three Indirect Health Indicators (IHI) was applied to forecast the RUL of Li-ion cells using the GPR method.…”

Section: ) Gaussianmentioning

confidence: 99%

A Comprehensive Review of Available Battery Datasets, RUL Prediction Approaches, and Advanced Battery Management

et al. 2021

View full text Add to dashboard Cite

Battery ensures power solutions for many necessary portable devices such as electric vehicles, mobiles, and laptops. Owing to the rapid growth of Li-ion battery users, unwanted incidents involving Li-ion batteries have also increased to some extent. In particular, the sudden breakdown of industrial and lightweight machinery due to battery failure causes a substantial economic loss for the industry. Consequently, battery state estimation, management system, and estimation of the remaining useful life (RUL) have become a topic of interest for researchers. Considering this, appropriate battery data acquisition and proper information on available battery data sets may require. This review paper is mainly focused on three parts. The first one is battery data acquisitions with commercially and freely available Li-ion battery data set information. The second is the estimation of the states of battery with the battery management system. And third is battery RUL estimation. Various RUL prognostic methods applied for Li-ion batteries are classified, discussed, and reviewed based on their essential performance parameters. Information on commercially and publicly available data sets of many battery models under various conditions is also reviewed. Various battery states are reviewed considering advanced battery management systems. To that end, a comparative study of Li-ion battery RUL prediction is provided together with the investigation of various RUL prediction algorithms and mathematical modelling.INDEX TERMS Battery datasets, battery data repository, remaining useful life (RUL), battery management, li-ion battery, RUL prediction methods.

show abstract

“…Step 3: Take the best initial adaptation value as the current global optimal value, and its position as the location of the global optimal value. Step 4: Update the flying speed of each particle according to Equation (17) and limit the amplitude, and update the current position of the particle. In the formula,…”

Section: Phase Space Reconstruction Theorymentioning

confidence: 99%

State-of-Health Prediction for Lithium-Ion Batteries Based on a Novel Hybrid Approach

et al. 2020

View full text Add to dashboard Cite

Generally, the State-of-Health (SOH) monitoring and Remaining Useful Life (RUL) prediction and assessment of lithium-ion (Li-ion) batteries need to use sensors to obtain the degradation test data of the same type of batteries and establish the degradation model for reference. However, when the battery type is unknown, a usable reference model cannot be obtained, so its prediction and evaluation may be relatively inconvenient. In this paper, the State of-Health prediction for lithium-ion batteries based on a novel hybrid scheme is proposed. Firstly, historical charge/discharge time series and capacity series are extracted to analyze and construct Health Indicators, then using Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) to decompose the Health Indicator series into the trend and non-trend terms. Among them, the relatively smooth trend item data series uses the Autoregressive Integrated Moving Average model (ARIMA) for prediction; when dealing with the data series of non-trend items which are obviously non-smooth and seemingly random, the residuals predicted by ARIMA and the non-trend items obtained by CEEMDAN decomposition are combined into new non-trend items; then the least square support vector machine (LSSVM) is introduced to build a nonlinear prediction model and make predictions. Finally, combining the prediction results of the trend item data series and the non-trend item data series as a reference for the assessment of the state of health and remaining useful life. The 13 experimental results of 3 batteries verify the effectiveness of the scheme.

show abstract

SOH and RUL Prediction of Lithium-Ion Batteries Based on Gaussian Process Regression with Indirect Health Indicators

Cited by 148 publications

References 35 publications

High precision implicit function learning for forecasting supercapacitor state of health based on Gaussian process regression

High precision implicit function learning for forecasting supercapacitor state of health based on Gaussian process regression

A Comprehensive Review of Available Battery Datasets, RUL Prediction Approaches, and Advanced Battery Management

State-of-Health Prediction for Lithium-Ion Batteries Based on a Novel Hybrid Approach

Contact Info

Product

Resources

About