State-of-Health Identification of Lithium-Ion Batteries Based on Nonlinear Frequency Response Analysis: First Steps with Machine Learning

Harting, Nina; Schenkendorf, René; Wolff, Nicolas; Krewer, Ulrike

doi:10.3390/app8050821

Cited by 38 publications

(23 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to a very diverse range of systems, a wide variety of phenomena can be investigated with nonlinear techniques. Previous works have ranged from detailed studies of electrochemical processes (e.g., determining transfer coefficients α [83] and examining kinetic mechanisms in electrochemical reactions [86] ) to the linkage of important system parameters to nonlinear outcome (e.g., state of health [87] and aging effects of batteries [88] ). Harting et al demonstrated that NL techniques can be used to differentiate between different aging processes in lithium-ion batteries.…”

Section: Nonlinear Electrochemical Methodsmentioning

confidence: 99%

Nonlinear Electrochemical Analysis: Worth the Effort to Reveal New Insights into Energy Materials

Schlüter

Novák

Schröder

2022

Advanced Energy Materials

View full text Add to dashboard Cite

and the effectiveness and durability of the materials applied, researchers always call for reliable and detailed knowledge of the mechanism(s) of both, main and side reactions, and especially for their kinetics. In order to gain the relevant information, a large number of methods have been proposed to characterize battery materials, battery electrodes and their interfaces, and battery cells. But when samples are taken out of the cells and analyzed later, there is a high risk of both, contamination and changes due to possible relaxation processes, and the challenge is to draw sound conclusions in respect to a "living and breathing" battery cell, i.e., to a cell under current flow (cf. Figure 1). Therefore, the so-called in situ and operando (and often online) methods are preferred. Sometimes they are the only option to collect relevant data to understand and improve materials for energy systems. [5] In many cases, results from different techniques need to be combined to obtain sound conclusions. [6,7] The terminology for the aforementioned methods shifted during the last decade and is not always consistent throughout the literature. Nowadays, the general understanding is as follows: An operando experiment means a characterization experiment in an electrochemical cell (e.g., battery, fuel cell, electrolyzer) under current flow, with either the potential or the current controlled. One of the many examples is the operando neutron powder diffraction, a technique analyzing the changes in the structure of battery materials in "real" battery cells under current flow with the help of neutron diffraction. [9] Another example is the operando X-ray photoelectron spectroscopy experiment (normally limited to vacuum-compatible cells with nonvolatile electrolytes) providing information about the changes of the chemical composition of the interfacial species with the potential. [10,11] An in situ experiment is also an experiment in a battery cell, however, the current flow is interrupted when the data are collected. An example here is the in situ X-ray absorption spectroscopy (XAS) experiment in which the cell has to be disconnected for technical reasons during the operation of the detector [7] or the tomography of energy materials by means of neutron or X-ray source. [12,13] Online techniques are understood here as either continuously or periodically analyzed samples that are taken out of the electrochemical cell. A typical example is the online (differential) electrochemical mass spectrometry (often shortened as online electrochemical mass spectrometry (OEMS)/differential electrochemical mass spectrometry (DEMS)) analyzing the volatile products of electrochemical reactions with the help of a mass spectrometer by

show abstract

Section: Nonlinear Electrochemical Methodsmentioning

confidence: 99%

Nonlinear Electrochemical Analysis: Worth the Effort to Reveal New Insights into Energy Materials

Schlüter

Novák

Schröder

2022

Advanced Energy Materials

View full text Add to dashboard Cite

show abstract

“…Thus, predicting the degradation behavior of batteries by ML techniques is also essential for the entire electrification system. [57][58][59] The fundamental goal of ML models in rechargeable batteries is to establish the quantitative structure-activity relationship (QSAR) between conditional attributes and decision attributes through low-cost and accurate predictions. [60] In this section, we will mainly focus on the recent applications of ML models for predicting properties of materials, state of battery, and designing materials for rechargeable LIBs.…”

Section: Applications Of ML In Rechargeable Libmentioning

confidence: 99%

Machine Learning: An Advanced Platform for Materials Development and State Prediction in Lithium‐Ion Batteries

et al. 2021

View full text Add to dashboard Cite

performance and cost are not satisfactory while the energy density of conventional LIBs have almost reached the theoretical maximum. To further advance current LIBs, numerous efforts have been devoted to the exploration of new electrode and electrolyte materials. [3] The historical material research has heavily relied on either "trial-and-error" processes or serendipity, both of which require the vast numbers of tedious experiments (Figure 1a). Such intuition-based approaches are often time-consuming and inefficient, which cannot avoid the consumption of many manpower and material resources. In the past 50 years, computational chemistry, such as firstprinciples (FP) calculations, [4,5] quantum mechanics, [6] molecular dynamics (MD) [7] and Monte Carlo techniques, [8] has become a mature approach to complement and aid experimental studies for predicting and designing new materials. With the rapid development of high-performance computations, density functional theory (DFT) has been widely applied to high-throughput property prediction, which is conducive to the development of materials databases, such as Inorganic Crystal Structure Database (ICSD), [9] Cambridge Structural Database, [10] the Materials Project [11] database, AFLOWLIB consortium, [12] Open Quantum Materials Database, [13] Harvard Clean Energy Project, [14] Electronic Structure Project, [15] MaterialGo, [16] and so on. However, Lithium-ion batteries (LIBs) are vital energy-storage devices in modern society. However, the performance and cost are still not satisfactory in terms of energy density, power density, cycle life, safety, etc. To further improve the performance of batteries, traditional "trial-and-error" processes require a vast number of tedious experiments. Computational chemistry and artificial intelligence (AI) can significantly accelerate the research and development of novel battery systems. Herein, a heterogeneous category of AI technology for predicting and discovering battery materials and estimating the state of the battery system is reviewed. Successful examples, the challenges of deploying AI in real-world scenarios, and an integrated framework are analyzed and outlined. The state-of-the-art research about the applications of ML in the property prediction and battery discovery, including electrolyte and electrode materials, are further summarized. Meanwhile, the prediction of battery states is also provided. Finally, various existing challenges and the framework to tackle the challenges on the further development of machine learning for rechargeable LIBs are proposed.

show abstract

“…The characteristics of accumulator battery depend on the chemical composition of the components, but, despite this, an equivalent selection of the main characteristics for the traction storage battery is required, since they affect the quality and service life of the traction power source as a whole. Table 1 shows the main characteristics that you need to be guided by when choosing the most preferred type of rechargeable batteries [66][67][68]. To determine the most preferred type of TCS, the following characteristics were selected [68,69]:…”

Section: Comparison Of Different Types Of Batteriesmentioning

confidence: 99%

Degradation of Lithium-Ion Batteries in an Electric Transport Complex

et al. 2021

View full text Add to dashboard Cite

The article provides an overview and comparative analysis of various types of batteries, including the most modern type—lithium-ion batteries. Currently, lithium-ion batteries (LIB) are widely used in electrical complexes and systems, including as a traction battery for electric vehicles. Increasing the service life of the storage devices used today is an important scientific and technical problem due to their rapid wear and tear and high cost. This article discusses the main approaches and methods for researching the LIB resource. First of all, a detailed analysis of the causes of degradation was carried out and the processes occurring in lithium-ion batteries during charging, discharging, resting and difficult operating conditions were established. Then, the main factors influencing the service life are determined: charging and discharging currents, self-discharge current, temperature, number of cycles, discharge depth, operating range of charge level, etc. when simulating a real motion process. The work considers the battery management systems (BMS) that take into account and compensate for the influence of the factors considered. In the conclusion, the positive and negative characteristics of the presented methods of scientific research of the residual life of LIB are given and recommendations are given for the choice of practical solutions to engineers and designers of batteries. The work also analyzed various operating cycles of electric transport, including heavy forced modes, extreme operating modes (when the amount of discharge and discharge of batteries is greater than the nominal value) and their effect on the degradation of lithium-ion batteries.

show abstract

State-of-Health Identification of Lithium-Ion Batteries Based on Nonlinear Frequency Response Analysis: First Steps with Machine Learning

Cited by 38 publications

References 48 publications

Nonlinear Electrochemical Analysis: Worth the Effort to Reveal New Insights into Energy Materials

Nonlinear Electrochemical Analysis: Worth the Effort to Reveal New Insights into Energy Materials

Machine Learning: An Advanced Platform for Materials Development and State Prediction in Lithium‐Ion Batteries

Degradation of Lithium-Ion Batteries in an Electric Transport Complex

Contact Info

Product

Resources

About