Transfer learning for battery smarter state estimation and ageing prognostics: Recent progress, challenges, and prospects

Published On 2023/2/1

With the advent of sustainable and clean energy transitions, lithium-ion batteries have become one of the most important energy storage sources for many applications. Battery management is of utmost importance for the safe, efficient, and long-lasting operation of lithium-ion batteries. However, the frequently changing load and operating conditions, the different cell chemistries and formats, and the complicated degradation patterns pose challenges for traditional battery management. The data-driven solutions that have emerged in recent years offer great opportunities to uncover the underlying data mapping within a battery system. In particular, transfer learning improves the performance of data-driven strategies by transferring existing knowledge from different but related domains, and if properly applied, would be a promising approach for smarter battery management. To this end, this paper presents a systematic …

Published On

2023/2/1

Volume

9

Page

100117

Authors

Remus Teodorescu

Remus Teodorescu

Aalborg Universitet

Position

Professor at

H-Index(all)

104

H-Index(since 2020)

72

I-10 Index(all)

0

I-10 Index(since 2020)

0

Citation(all)

0

Citation(since 2020)

0

Cited By

0

Research Interests

Power Electronics

Smart Batteries

AI

University Profile Page

Kang Li

Kang Li

University of Leeds

Position

H-Index(all)

55

H-Index(since 2020)

41

I-10 Index(all)

0

I-10 Index(since 2020)

0

Citation(all)

0

Citation(since 2020)

0

Cited By

0

Research Interests

electrical and electronic engineering

smart energy systems

University Profile Page

Yunhong Che

Yunhong Che

Chongqing University

Position

H-Index(all)

16

H-Index(since 2020)

16

I-10 Index(all)

0

I-10 Index(since 2020)

0

Citation(all)

0

Citation(since 2020)

0

Cited By

0

Research Interests

Energy Storage Systems

Transportation electrification

Prognostics and Health Management

Battery

University Profile Page

Qiao Peng

Qiao Peng

Queen's University Belfast

Position

PhD in Finance

H-Index(all)

9

H-Index(since 2020)

9

I-10 Index(all)

0

I-10 Index(since 2020)

0

Citation(all)

0

Citation(since 2020)

0

Cited By

0

Research Interests

Machine learning

Data science

Carbon finance

Energy system management

University Profile Page

Other Articles from authors

Kang Li

Kang Li

University of Leeds

International Journal of Electrical Power & Energy Systems

A simplified consensus-based distributed secondary control for battery energy storage systems in DC microgrids

DC microgrids have become a promising solution for efficient and reliable integration of renewable energy sources (RESs), battery energy storage systems (BESSs) and loads. To simultaneously achieve average voltage regulation, accurate current-sharing and state-of-charge (SoC) balance, at least two state variables need to be transmitted between neighboring BESS nodes in conventional distributed secondary control. In this paper, a simplified consensus-based distributed secondary control for BESSs in DC microgrids is proposed with only one virtually defined state variable being transmitted, where a cascaded control framework consisting of an SoC controller and a voltage controller is used to regulate DC bus voltages. This virtual state variable combines BESS SoC and its converter output current, there is no need to change the control law when BESSs switch between charging/discharging modes. Once …

Qiao Peng

Qiao Peng

Queen's University Belfast

Energy

Battery calendar degradation trajectory prediction: Data-driven implementation and knowledge inspiration

—Batteries are acknowledged as an important carrier for next-generation energy and future electrification. Capacity degradation is an inevitable process that will eventually lead to a decline in battery performance. This paper presents a battery degradation trajectory prognostics approach under storage conditions based on the data-driven method with necessary knowledge inspiration. This data-driven approach is based on Support Vector Regression (SVR), incorporating mechanisms and empirical knowledge of battery calendar aging as the kernel. The developed data-driven approach is evaluated using two real but different capacity degradation datasets: Dataset A has two storage temperatures (25 °C and 45 °C) and storage SoCs (50% and 90%), while Dataset B has the same storage temperatures but four different storage SoCs (20%, 50%, 70% and 95%). The illustrative results show that the developed …

Yunhong Che

Yunhong Che

Chongqing University

IEEE Transactions on Industrial Electronics

Health Prediction for Lithium-Ion Batteries Under Unseen Working Conditions

Battery health prediction is significant while challenging for intelligent battery management. This article proposes a general framework for both short-term and long-term predictions of battery health under unseen dynamic loading and temperature conditions using domain-adaptive multitask learning (MTL) with long-term regularization. First, features extracted from partial charging curves are utilized for short-term state of health predictions. Then, the long-term degradation trajectory is directly predicted by recursively using the predicted features within the multitask framework, enhancing the model integrity and lowering the complexity. Then, domain adaptation (DA) is adopted to reduce the discrepancies between different working conditions. Additionally, a long-term regularization is introduced to address the shortcoming that arises when the model is extrapolated recursively for future health predictions. Thus, the short …

Kang Li

Kang Li

University of Leeds

Deep Learning-based EMI and IEMI Classification in 5G-R High-Speed Rail Wireless Communications

The proliferation of high-speed rail (HSR) networks and railway electrification has advanced the integration of the latest wireless communication networks with railway systems. Ensuring a reliable bidirectional communication link between moving trains and base stations is crucial to maintaining the safety of real-time rail operations. However, the growing complexity of railway systems and increased exposure to electromagnetic emissions present substantial challenges. In particular, railway wireless communication networks are vulnerable to various kinds of electromagnetic interference (EMI) and intentional EMI (IEMI), which could cause operational disruptions and safety hazards. This paper proposes a real-time classification method for EMI and IEMI, using deep learning-based bidirectional long-short-term memory (BiLSTM) networks. By employing multivariate time-series characteristics, the method can simultaneously learn both time and frequency information at a finer resolution, offering better performance than existing methods. The simulation results demonstrate a high accuracy of 93.4% and adaptability at different speeds and in various scenarios.

Yunhong Che

Yunhong Che

Chongqing University

IEEE/ASME Transactions on Mechatronics

Online Sensorless Temperature Estimation of Lithium-Ion Batteries Through Electro-Thermal Coupling

Owing to the nonnegligible impacts of temperature on the safety, performance, and lifespan of lithium-ion batteries, it is essential to regulate battery temperature to an optimal range. Temperature monitoring plays a fundamental role in battery thermal management, yet it is still challenged by limited onboard temperature sensors, particularly in large-scale battery applications. As such, developing sensorless temperature estimation is of paramount importance to acquiring the temperature information of each cell in a battery system. This article proposes an estimation approach to obtain the cell temperature by taking advantage of the electrothermal coupling effect of batteries. An electrothermal coupled model, which captures the interactions between the electrical and the thermal dynamics, is established, parameterized, and experimentally validated. A closed-loop observer is then designed based on this coupled model …

Kang Li

Kang Li

University of Leeds

Applied Energy

Distributed security state estimation-based carbon emissions and economic cost analysis for cyber–physical power systems under hybrid attacks

Sustainable cyber–physical power systems (CPPSs) significantly reduce carbon emissions due to climate change. However, when the data exchange in CPPSs suffers from hybrid attacks, the distributed state estimation and optimal power flow (OPF) analysis will inevitably be compromised, leading to inadequate or faulty scheduling of clean energy and thermal power generations and further affecting the total carbon emissions and economic cost. To address these problems, this paper proposes a novel consensus-based distributed security state estimation (DSSE) method for CPPSs, which is used to analyze the impact of hybrid attacks on carbon emissions and economic cost. Firstly, the incomplete and non-authentic data features caused by hybrid attacks are described, and their influence on distributed state estimation model is analyzed. A new residual-based attack detection method is then constructed in each …

Qiao Peng

Qiao Peng

Queen's University Belfast

Journal of Energy Chemistry

Characterization and identification towards dynamic-based electrical modeling of lithium-ion batteries

Lithium-ion batteries are widely recognized as a crucial enabling technology for the advancement of electric vehicles and energy storage systems in the grid. The design of battery state estimation and control algorithms in battery management systems is usually based on battery models, which interpret crucial battery dynamics through the utilization of mathematical functions. Therefore, the investigation of battery dynamics with the purpose of battery system identification has garnered considerable attention in the realm of battery research. Characterization methods in terms of linear and nonlinear response of lithium-ion batteries have emerged as a prominent area of study in this field. This review has undertaken an analysis and discussion of characterization methods, with a particular focus on the motivation of battery system identification. Specifically, this work encompasses the incorporation of frequency domain …

Kang Li

Kang Li

University of Leeds

IEEE Transactions on Power Electronics

Real-time Diagnosis of Open Circuit Faults in Three-Phase Voltage Source Inverters

This paper investigates the real-time diagnosis of single and double open circuit faults (OCFs) in three-phase voltage source inverters (VSI). The method analyzes the phase current waveforms continuously in real-time, and abnormal patterns of the current waves due to the corresponding switch OCFs are extracted to define as the fault detection waveforms (FDW). The current values of the FDWs are analyzed and a new scheme is developed to distinguish current waveform patterns from those of normal to unbalanced loads situations and switch OCFs. The scheme detects the starting zero crossing point first and then checks the magnitudes of the FDW. Periodic detections are applied to identify whether the collected data samples are within the FDW current range. The OCFs of the inverter switches are identified by counting the fault points within the predicted samplings of FDWs. The method has been verified through …

Kang Li

Kang Li

University of Leeds

Energy and AI

Distributed scheduling for multi-energy synergy system considering renewable energy generations and plug-in electric vehicles: A level-based coupled optimization method

Multi-energy synergy systems integrating high-penetration large-scale plug-in electric vehicles, distributed renewable energy generations, and battery energy storage systems have great potential to reduce the reliance of the grid on traditional fossil fuels. However, the random charging characteristics of plug-in electric vehicles and the uncertainty of photovoltaics may impose an additional burden on the grid and affect the supply–demand equilibrium. To address this issue, judicious scheduling optimization offers an effective solution. In this study, considering charge and discharge management of plug-in electric vehicles and intermittent photovoltaics, a novel Multi-energy synergy systems scheduling framework is developed for solving grid instability and unreliability issues. This formulates a large-scale mixed-integer problem, which calls for a powerful and effective optimizer. The new binary level-based learning …

Yunhong Che

Yunhong Che

Chongqing University

Thermal state monitoring of lithium-ion batteries: Progress, challenges, and opportunities

Transportation electrification is a promising solution to meet the ever-rising energy demand and realize sustainable development. Lithium-ion batteries, being the most predominant energy storage devices, directly affect the safety, comfort, driving range, and reliability of many electric mobilities. Nevertheless, thermal-related issues of batteries such as potential thermal runaway, performance degradation at low temperatures, and accelerated aging still hinder the wider adoption of electric mobilities. To ensure safe, efficient, and reliable operations of lithium-ion batteries, monitoring their thermal states is critical to safety protection, performance optimization, as well as prognostics, and health management. Given insufficient onboard temperature sensors and their inability to measure battery internal temperature, accurate and timely temperature estimation is of particular importance to thermal state monitoring. Toward …

Kang Li

Kang Li

University of Leeds

Energy and Buildings

Transformer Based Day-ahead Cooling Load Forecasting of Hub Airport Air-Conditioning Systems with Thermal Energy Storage

The air conditioning system constitutes more than half of the total energy demand in hub airport buildings. To enhance the energy efficiency and to enable intelligent energy management, it is vital to build an accurate cold load prediction model. However, the current models face challenges in dealing with dispersed load patterns and lack interpretability when black box approaches are adopted. To tackle these challenges, we propose a novel k-means-Temporal Fusion Transformer (TFT) based hybrid load prediction model. Specifically, the daily load patterns are grouped using an improved k-means clustering method that considers both input feature weights and dynamic time warping (DTW) distances. Additionally, the statistical features of the clustering output are inputted into the TFT. By further incorporating context information, the integration of data between different schema categories is achieved, thus reducing …

Qiao Peng

Qiao Peng

Queen's University Belfast

Transportation Research Part A: Policy and Practice

Transportation resilience under Covid-19 Uncertainty: A traffic severity analysis

Transportation systems are critical lifelines and vulnerable to various disruptions, including unforeseen social events such as public health crises, and have far-reaching social impacts such as economic instability. This paper aims to determine the key factors influencing the severity of traffic accidents in four different stages during the pre- and the post Covid-19 pandemic in Illinois, USA. For this purpose, a Random Forest-based model is developed, which is combined with techniques of explainable machine learning. The results reveal that during the pandemic, human perceptual factors, notably increased air pressure, humidity and temperature, play an important role in accident severity. This suggests that alleviating driver anxiety, caused by these factors, may be more effective in curbing crash severity than conventional road condition improvements. Further analysis shows that the pandemic leads notable shifts in …

Kang Li

Kang Li

University of Leeds

IEEE Access

Mitigating the Inrush Current of V/V Transformers using Railway Conditioners

Inrush current is high-magnitude current drawn by power transformers upon energization. The severity of inrush current depends on factors such as the transformer’s residual flux and the voltage phase angle at the energization instant. This paper proposes a flux matching method for the energization of V/V traction transformers to mitigate inrush current. This is achieved by adjusting the residual flux of the core to an appropriate reference value and then obtaining the proper energization instant. To this end, the method only requires knowledge of nominal voltage and excitation current, eliminating the need to acquire transformer’s parameters/design information. The railway power conditioner, typically present at the low voltage side of the V/V transformer, is used as a current source to inject sinusoidal current into the transformer windings before its energization. The reference residual flux is calculated based on the …

Yunhong Che

Yunhong Che

Chongqing University

Reliability Engineering & System Safety

Predictive health assessment for lithium-ion batteries with probabilistic degradation prediction and accelerating aging detection

Predictive health assessment is of vital importance for smarter battery management to ensure optimal and safe operations and thus make the most use of battery life. This paper proposes a general framework for battery aging prognostics in order to provide the predictions of battery knee, lifetime, state of health degradation, and aging rate variations, as well as the assessment of battery health. Early information is used to predict knee slope and other life-related information via deep multi-task learning, where the convolutional-long-short-term memory-bayesian neural network is proposed. The structure is also used for online state of health and degradation rate predictions for the detection of accelerating aging. The two probabilistic predicted boundaries identify the accelerating aging regions for battery health assessment. To avoid wrong and premature alarms, the empirical model is used for data preprocessing and …

Kang Li

Kang Li

University of Leeds

Energies

Reliability Assessment of Integrated Power and Road System for Decarbonizing Heavy-Duty Vehicles

With the continual expansion of urban road networks and global commitments to net zero, electric vehicles (EVs) have been considered to be the most viable solution to decarbonize the transportation sector. In recent years, the electric road system (ERS) has been introduced and piloted in a few countries and regions to decarbonize heavy-duty vehicles. However, little research has been carried out on its reliability. This paper fills the gap and investigates the reliability of electric truck power supply systems for electric road (ETPSS–ER), which considers both the power system and truck traffic networks. First, a brief introduction of electric roads illustrates the working principle of EV charging on roads. Then, an optimized electric truck (ET) travel pattern model is built, based on which the corresponding ET charging load demand, including both static charging and dynamic charging, is conducted. Then, based on the new ET travel pattern model, a daily travel-pattern-driven Monte Carlo simulation-based reliability assessment method for ETPSS–ER system is presented. Case studies based on the IEEE RBTS system shows that ETs driving on ERS systems can meet the daily travel demands. The case studies also examine the impacts of increasing number of ETs, extra wind power, and battery energy storage systems (BESS) on the reliability of ERS power systems.

Qiao Peng

Qiao Peng

Queen's University Belfast

Multi-objective electricity generation expansion planning towards renewable energy policy objectives under uncertainties

Conventional petrol vehicles emit a substantial quantity of greenhouse gases, leading to increasingly serious global warming problems. The expansion and development of renewable power generation technologies is conducive in promoting the use of electric vehicles, which are more environmentally friendly. This paper proposes a multi-objective power expansion model considering renewable energy policy objectives. The model regards the problem as a multi-period optimisation task, taking the newly installed capacity and the power generation capacity of each power generation technology as decision variables, and simulating the uncertain factors in the planning process using Geometric Brownian Motion and Monte Carlo approaches. The optimisation objective of the model is to minimise expected costs, reduce risk and environmental impacts, and incorporate changing policy objectives into the constraints to …

Qiao Peng

Qiao Peng

Queen's University Belfast

IEEE Transactions on Evolutionary Computation

Evolutionary multi-objective optimisation for large-scale portfolio selection with both random and uncertain returns

With the advent of Big Data, managing large-scale portfolios of thousands of securities is one of the most challenging tasks in the asset management industry. This study uses an evolutionary multi-objective technique to solve large-scale portfolio optimisation problems with both long-term listed and newly listed securities. The future returns of long-term listed securities are defined as random variables whose probability distributions are estimated based on sufficient historical data, while the returns of newly listed securities are defined as uncertain variables whose uncertainty distributions are estimated based on experts’ knowledge. Our approach defines security returns as theoretically uncertain random variables and proposes a three-moment optimisation model with practical trading constraints. In this study, a framework for applying arbitrary multi-objective evolutionary algorithms to portfolio optimisation is …

Kang Li

Kang Li

University of Leeds

IEEE Transactions on Instrumentation and Measurement

Fast Linear State Estimation for Unbalanced Distribution Systems Using Hybrid Measurements

Distribution system state estimation (DSSE) is traditionally solved iteratively using unsynchronized measurements provided by the SCADA system and/or smart meters. This paper puts forward a decoupled linear state estimation method for unbalanced distribution systems. Contrary to conventional methods, the proposed linear DSSE (LDSSE) method can function with purely unsynchronized or hybrid synchronized/unsynchronized measurements. In the case of purely unsynchronized measurements, the voltage phase angles of the reference bus are acquired through local measurements. In the first stage, the proposed LDSSE method estimates the voltage phase angles in terms of network parameters and available measurements. These are referred to as pseudo-synchronized voltage phase angles, which establish a basis for deriving pseudo-synchronized voltage/current phasors. In the second stage, a set of …

Remus Teodorescu

Remus Teodorescu

Aalborg Universitet

IEEE Transactions on Industrial Electronics

Health Prediction for Lithium-Ion Batteries Under Unseen Working Conditions

Battery health prediction is significant while challenging for intelligent battery management. This article proposes a general framework for both short-term and long-term predictions of battery health under unseen dynamic loading and temperature conditions using domain-adaptive multitask learning (MTL) with long-term regularization. First, features extracted from partial charging curves are utilized for short-term state of health predictions. Then, the long-term degradation trajectory is directly predicted by recursively using the predicted features within the multitask framework, enhancing the model integrity and lowering the complexity. Then, domain adaptation (DA) is adopted to reduce the discrepancies between different working conditions. Additionally, a long-term regularization is introduced to address the shortcoming that arises when the model is extrapolated recursively for future health predictions. Thus, the short …

Remus Teodorescu

Remus Teodorescu

Aalborg Universitet

IEEE/ASME Transactions on Mechatronics

Online Sensorless Temperature Estimation of Lithium-Ion Batteries Through Electro-Thermal Coupling

Owing to the nonnegligible impacts of temperature on the safety, performance, and lifespan of lithium-ion batteries, it is essential to regulate battery temperature to an optimal range. Temperature monitoring plays a fundamental role in battery thermal management, yet it is still challenged by limited onboard temperature sensors, particularly in large-scale battery applications. As such, developing sensorless temperature estimation is of paramount importance to acquiring the temperature information of each cell in a battery system. This article proposes an estimation approach to obtain the cell temperature by taking advantage of the electrothermal coupling effect of batteries. An electrothermal coupled model, which captures the interactions between the electrical and the thermal dynamics, is established, parameterized, and experimentally validated. A closed-loop observer is then designed based on this coupled model …