☆ 4.7 Article

Data-driven battery state-of-health estimation and prediction using IC based features and coupled model

JOURNAL OF ENERGY STORAGE (2023)

Related references

Note: Only part of the references are listed.

Article Engineering, Electrical & Electronic

Battery Safety Risk Assessment in Real-World Electric Vehicles Based on Abnormal Internal Resistance Using Proposed Robust Estimation Method and Hybrid Neural Networks

Da Li et al.

Summary: Battery safety is a major obstacle for the application of electric vehicles (EVs). Internal resistance (IR) is an important parameter reflecting battery safety and abnormal IR can lead to thermal runaway. A method is proposed to detect unsafe batteries and predict thermal runaway. This method includes IR estimation, normal IR prediction, IR evolution law construction, and safety risk assessment. The proposed methods are effective in predicting IR with low error and classifying unsafe and normal batteries accurately.

IEEE TRANSACTIONS ON POWER ELECTRONICS (2023)

Add to Collection

Article Energy & Fuels

State-of-health estimation by virtual experiments using recurrent decoder-encoder based lithium-ion digital battery twins trained on unstructured battery data

Jakob Schmitt et al.

Summary: A virtual SOH experiment was developed to estimate the battery health of electric vehicles (EVs) based on battery management system (BMS) signals. It successfully estimated the SOH of new and aged batteries and provided a foundation for scalable and robust battery capacity estimation based on data.

JOURNAL OF ENERGY STORAGE (2023)

Add to Collection

Article Energy & Fuels

Stacking regression technology with event profile for electric vehicle fast charging behavior prediction

Dingsong Cui et al.

Summary: The large-scale deployment of electric vehicles presents challenges to the distribution network, but also provides opportunities for power operation. Previous research on EV charging scheduling focused on slow-charging behavior, neglecting fast-charging behavior. This study provides an in-depth understanding of EV user fast-charging behavior in public stations using a Variational-Bayesian Gaussian mixture model. Charging energy, duration, and dwelling duration after charging are considered in the cluster model to support charging recommendation strategy and power allocation decision. Inspired by previous studies, a charging behavior prediction framework is proposed that improves prediction accuracy and priority evaluation.

APPLIED ENERGY (2023)

Add to Collection

Article Energy & Fuels

A multi-fault diagnostic method based on category-reinforced domain adaptation network for series-connected battery packs

Linhui Cai et al.

Summary: Detecting and distinguishing different types of faults in battery packs is crucial for the intelligent development and safe operation of electric vehicles. However, it is difficult to discriminate fault characteristics of lithium-ion battery packs with different types and health conditions. The proposed method integrates Attentional Mechanisms and Domain Adaptation Neural Network to diagnose multiple faults in series-connected battery packs, including voltage imbalance, internal short circuit, sensor faults, sensor drift voltage, and random fluctuation. Experimental validation in real working conditions demonstrates the effectiveness of the combined approach in improving model generalization performance across different battery packs.

JOURNAL OF ENERGY STORAGE (2023)

Add to Collection

Article Energy & Fuels

Novel method for modelling and adaptive estimation for SOC and SOH of lithium-ion batteries

Zuxin Li et al.

Summary: In this study, an improved fractional-order model (IFOM) is presented to describe the performance of lithium-ion batteries. The endogenous immune algorithm (EIA) is used to identify model parameters, and an adaptive dual square root Kalman filtering (ADSRCKF) method is proposed to achieve accurate estimation considering the aging effect. Experimental results demonstrate that the adaptively updated parameters can better match the real-time battery status, and ADSRCKF method achieves high accuracy and strong robustness.

JOURNAL OF ENERGY STORAGE (2023)

Add to Collection

Article Thermodynamics

Lithium-ion battery health estimation with real-world data for electric vehicles

Jiaqiang Tian et al.

Summary: This study proposes a state-of-health (SOH) attenuation model considering driving mileage and seasonal temperature for battery health estimation, which is significant for battery pack management and maintenance. The variable forgetting factor recursive least square (VFFRLS) algorithm is used for battery model parameter identification and the extended Kalman-particle filter (EPF) algorithm is proposed for online capacity estimation. The proposed model and algorithm are verified using actual vehicle data over nine months. The experimental results demonstrate the accurate estimation of model parameters and capacity through the proposed algorithm, and the decrease in average capacity of the battery module with total mileage. The compensation of monthly driving mileage and ambient temperature factors effectively improves the accuracy of the SOH model.

ENERGY (2023)

Add to Collection

Article Automation & Control Systems

A Battery Capacity Estimation Framework Combining Hybrid Deep Neural Network and Regional Capacity Calculation Based on Real-World Operating Data

Qiushi Wang et al.

Summary: This article proposes a battery capacity estimation framework based on real-world EV operating data. A reference capacity calculation method is presented by combining the Coulomb counting method with the incremental capacity analysis method. A hybrid deep neural network model is used for battery capacity estimation, and the validation results show superior performance compared to state-of-the-art methods with a mean absolute percentage error of 2.79% while maintaining low computational cost.

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS (2023)

Add to Collection

Article Engineering, Electrical & Electronic

Data-Driven Lithium-Ion Battery Degradation Evaluation Under Overcharge Cycling Conditions

Yiwen Zhao et al.

Summary: This article proposes a data-driven framework for evaluating degradation of overcharged lithium-ion batteries. It includes a multilevel overcharge cycling experiment to analyze battery degradation behaviors and features, and develops a machine learning and model integration method for evaluation. The proposed method achieves a mean squared error of 1.26 x 10(-4) and effectively identifies overcharged cells.

IEEE TRANSACTIONS ON POWER ELECTRONICS (2023)

Add to Collection

Article Automation & Control Systems

Coestimation of State-of-Charge and State-of-Health for Power Batteries Based on Multithread Dynamic Optimization Method

Tiancheng Ouyang et al.

Summary: This article proposes a multithread dynamic optimization method for accurate estimation of state-of-charge (SOC) and state-of-health (SOH) of power batteries. The method utilizes a fractional-order model and an unscented Kalman filter for SOC estimation, and proposes Gaussian linear models based on parameters of six commonly used open-circuit-voltage models for SOH estimation. Experimental results confirm the effectiveness of the proposed method in improving estimation accuracy.

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS (2022)

Add to Collection

Article Energy & Fuels

An estimation model for state of health of lithium-ion batteries using energy-based features

Li Cai et al.

Summary: Accurate state of health (SOH) estimation is a key but challenging issue in battery health monitoring (BHM) for lithium-ion batteries. Extracting energy-based features becomes a method to achieve accurate and reliable SOH estimation, as complete discharging curves are rarely available in real-world scenarios.

JOURNAL OF ENERGY STORAGE (2022)

Add to Collection

Article Chemistry, Physical

A machine learning-based framework for online prediction of battery ageing trajectory and lifetime using histogram data

Yizhou Zhang et al.

Summary: This study proposes a battery ageing prediction framework that combines global models and individualized models, using histogram data as features. The framework achieves low error rates on laboratory and real-world fleet data, with further improvement through online adaptation.

JOURNAL OF POWER SOURCES (2022)

Add to Collection

Article Engineering, Electrical & Electronic

State-of-Health Estimation for LiFePO4 Battery System on Real-World Electric Vehicles Considering Aging Stage

Litao Zhou et al.

Summary: This research proposes a SOH estimation model based on real-world EV operation data, which can comprehensively and accurately track the health status of batteries. By considering the ohmic resistance and the peak value of the incremental capacity (IC) curve as health features, as well as the mechanism of battery aging, the three stages of SOH degradation can be quantitatively described.

IEEE TRANSACTIONS ON TRANSPORTATION ELECTRIFICATION (2022)

Add to Collection

Article Energy & Fuels

Virtual experiments for battery state of health estimation based on neural networks and in-vehicle data

Felix Heinrich et al.

Summary: This paper presents a novel data-driven approach for estimating the state of health of batteries based on virtual execution of battery experiments. The method learns the electrical behavior of batteries based on driving data and simulates the electric response during battery experiments to determine the state of health. The results show state-of-the-art accuracy in terms of internal resistance and remaining capacity estimation.

JOURNAL OF ENERGY STORAGE (2022)

Add to Collection

Article Thermodynamics

Battery electric vehicle usage pattern analysis driven by massive real-world data

Dingsong Cui et al.

Summary: Electric vehicles play a key role in transportation electrification and reducing pollution. However, their increased usage poses challenges for energy system optimization. This study analyzes a large dataset of charging and travel events in Beijing in 2018, providing valuable insights for large-scale deployment and metropolitan areas.

ENERGY (2022)

Add to Collection

Article Thermodynamics

SOH prediction of lithium battery based on IC curve feature and BP neural network

Jianping Wen et al.

Summary: In this paper, a battery SOH prediction model based on incremental capacity analysis and BP neural network is proposed to predict battery SOH at different ambient temperatures. By analyzing the correlation between the characteristics of IC curve and SOH, the mapping relationship between temperature and IC curve characteristics is established, and the SOH prediction model at different temperatures is obtained. The accuracy of the model is verified by comparing the model test results and experimental results.

ENERGY (2022)

Add to Collection

Article Chemistry, Physical

Prediction of remaining useful life for a composite electrode lithium ion battery cell using an electrochemical model to estimate the state of health

Kaveh Khodadadi Sadabadi et al.

Summary: This paper developed a remaining useful life (RUL) prediction algorithm based on estimation of parameters of an enhanced single particle model (eSPM) that could be implemented using vehicle charging data. The proposed method estimates parameters associated with battery aging, uses them to design a RUL predictor, and validates the algorithm using experimental data collected on LMO-NMC battery cells, demonstrating the feasibility of inferring battery state of health and RUL from readily available charging data in plug-in battery-electric or hybrid vehicles.

JOURNAL OF POWER SOURCES (2021)

Add to Collection

Article Chemistry, Physical

Online capacity estimation of lithium-ion batteries with deep long short-term memory networks

Weihan Li et al.

Summary: There is a growing demand for modern diagnostic systems for batteries in real-world operation, especially for estimating their health status such as remaining capacity. A data-driven capacity estimation model using recurrent neural networks with long short-term memory capability has been developed for cells under real-world working conditions. This model is robust, can handle input noise, adapt to variations in input time series length, and generate viable estimation even with incomplete input data.

JOURNAL OF POWER SOURCES (2021)

Add to Collection

Article Thermodynamics

Estimation and prediction of state of health of electric vehicle batteries using discrete incremental capacity analysis based on real driving data

Zhicheng Xu et al.

Summary: A novel method using discrete incremental capacity analysis based on real-life driving data is proposed to estimate battery SoH and compare the SoH of various types of electric vehicles.

ENERGY (2021)

Add to Collection

Review Chemistry, Physical

The challenge and opportunity of battery lifetime prediction from field data

Valentin Sulzer et al.

Summary: Accurate battery life prediction is crucial for various applications, but existing methods based on lab data need to incorporate field data for a complete understanding of cell aging. Challenges arise due to uncontrolled operating conditions, less accurate sensors, and infrequent validation checks in real-world applications. Combining machine learning with physical models shows promise in estimating battery life, assessing second-life condition, and predicting future usage conditions.

JOULE (2021)

Add to Collection

Article Multidisciplinary Sciences

Closed-loop optimization of fast-charging protocols for batteries with machine learning

Peter M. Attia et al.

NATURE (2020)

Add to Collection

Article Mathematics, Applied

Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) network

Alex Sherstinsky

PHYSICA D-NONLINEAR PHENOMENA (2020)

Add to Collection

Article Automation & Control Systems

Battery Aging Assessment for Real-World Electric Buses Based on Incremental Capacity Analysis and Radial Basis Function Neural Network

Chengqi She et al.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2020)

Add to Collection

Article Chemistry, Physical

Battery life estimation based on cloud data for electric vehicles

Kai Li et al.

JOURNAL OF POWER SOURCES (2020)

Add to Collection

Article Automation & Control Systems

Health Prognosis for Electric Vehicle Battery Packs: A Data-Driven Approach

Xiaosong Hu et al.

IEEE-ASME TRANSACTIONS ON MECHATRONICS (2020)

Add to Collection

Article Engineering, Electrical & Electronic

A Hybrid Method for the Prediction of the Remaining Useful Life of Lithium-Ion Batteries With Accelerated Capacity Degradation

Xinwei Cong et al.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2020)

Add to Collection

Review Chemistry, Physical

Battery Lifetime Prognostics

Xiaosong Hu et al.

JOULE (2020)

Add to Collection

Article Energy & Fuels

Data-driven prediction of battery cycle life before capacity degradation

Kristen A. Severson et al.

NATURE ENERGY (2019)

Add to Collection

Article Energy & Fuels

Aging trajectory prediction for lithium-ion batteries via model migration and Bayesian Monte Carlo method

Xiaopeng Tang et al.

APPLIED ENERGY (2019)

Add to Collection

Article Energy & Fuels

Synchronous estimation of state of health and remaining useful lifetime for lithium-ion battery using the incremental capacity and artificial neural networks

Shuzhi Zhang et al.

JOURNAL OF ENERGY STORAGE (2019)

Add to Collection

Article Computer Science, Hardware & Architecture

Data-Driven Battery Lifetime Prediction and Confidence Estimation for Heavy-Duty Trucks

Sergii Voronov et al.

IEEE TRANSACTIONS ON RELIABILITY (2018)

Add to Collection

Article Engineering, Electrical & Electronic

Long Short-Term Memory Recurrent Neural Network for Remaining Useful Life Prediction of Lithium-Ion Batteries

Yongzhi Zhang et al.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2018)

Add to Collection

Article Electrochemistry

Durability and Reliability of EV Batteries under Electric Utility Grid Operations: Path Dependence of Battery Degradation

Matthieu Dubarry et al.

JOURNAL OF THE ELECTROCHEMICAL SOCIETY (2018)

Add to Collection

Article Computer Science, Information Systems

Remaining Useful Life Prediction for Lithium-Ion Batteries Based on Exponential Model and Particle Filter

Lijun Zhang et al.

IEEE ACCESS (2018)

Add to Collection

Proceedings Paper Energy & Fuels

Battery remaining useful life prediction under coupling stress based on support vector regression

Jingcai Du et al.

CLEANER ENERGY FOR CLEANER CITIES (2018)

Add to Collection

Review Energy & Fuels

State-of-the-art characterization techniques for advanced lithium-ion batteries

Jun Lu et al.

NATURE ENERGY (2017)

Add to Collection

Article Energy & Fuels

A capacity model based on charging process for state of health estimation of lithium ion batteries

Xue Li et al.

APPLIED ENERGY (2016)

Add to Collection

Article Automation & Control Systems

A Framework for Simplification of PDE-Based Lithium-Ion Battery Models

Changfu Zou et al.

IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY (2016)

Add to Collection

Article Chemistry, Physical

Production caused variation in capacity aging trend and correlation to initial cell performance

Thorsten Baumhoefer et al.

JOURNAL OF POWER SOURCES (2014)

Add to Collection

Article Chemistry, Physical

Prognostics of lithium-ion batteries based on Dempster-Shafer theory and the Bayesian Monte Carlo method

Wei He et al.

JOURNAL OF POWER SOURCES (2011)

Add to Collection

Article Chemistry, Physical

Identifying battery aging mechanisms in large format Li ion cells

Matthieu Dubarry et al.

JOURNAL OF POWER SOURCES (2011)

Add to Collection

© Peeref 2019-2024. All rights reserved.