Data efficient health prognostic for batteries based on sequential information-driven probabilistic neural network

Applied Energy

Published On 2022/10/1

Accurate and reliable prediction of the battery capacity degradation is vital for predictive health management. This paper proposes a novel framework to improve the accuracy and reliability of battery health prognostic. Firstly, sequential information-ensembled health indicators, which have high correlations with battery capacity and lifetime, are proposed based on partial voltage and capacity sequences. Then, the Gaussian mixture model is adopted for lifetime clustering to verify the effectiveness of the proposed health indicators and an automatic reference batteries selection method is proposed to find out the most relative candidates for degradation base model training. A long short-term memory network with probabilistic regression is leveraged for battery health prognostic, which provides the predicted mean value and confidence interval via Bayesian inference. Finally, the model migration is presented to further …

Journal

Applied Energy

Published On

2022/10/1

Volume

323

Page

119663

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

Yue WU - UNC

Yue WU - UNC

University of North Carolina at Chapel Hill

Position

Kenan Distinguished Professor The

H-Index(all)

54

H-Index(since 2020)

31

I-10 Index(all)

0

I-10 Index(since 2020)

0

Citation(all)

0

Citation(since 2020)

0

Cited By

0

Research Interests

nanoporous systems

metallic glasses

glass transition and LLT

NMR

Daniel Stroe

Daniel Stroe

Aalborg Universitet

Position

Head of Battery Storage Systems Research Programme at

H-Index(all)

49

H-Index(since 2020)

46

I-10 Index(all)

0

I-10 Index(since 2020)

0

Citation(all)

0

Citation(since 2020)

0

Cited By

0

Research Interests

Lithium-ion Batteries

Energy Storage

Electric Vehicles

Renewable Energy

Energy Management

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

Xin Sui

Xin Sui

Aalborg Universitet

Position

H-Index(all)

14

H-Index(since 2020)

14

I-10 Index(all)

0

I-10 Index(since 2020)

0

Citation(all)

0

Citation(since 2020)

0

Cited By

0

Research Interests

Li-ion batteries

SOH estimation

RUL prediction

University Profile Page

Pallavi Bharadwaj

Pallavi Bharadwaj

Massachusetts Institute of Technology

Position

Postdoctoral Research Associate

H-Index(all)

10

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

Smart power electronics

Green energy optimization

Net zero transition

Yue Wu (武悦)

Yue Wu (武悦)

Central South University

Position

Chang Sha China.

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

Control and Optimization

Energy Storage System

Electrified Vehicles

Intelligent Transportation

University Profile Page

Other Articles from authors

Yue Wu (武悦)

Yue Wu (武悦)

Central South University

Solar Energy

An adaptive power smoothing approach based on artificial potential field for PV plant with hybrid energy storage system

The increasing quantity of PV installation has brought great challenges to the grid owing to power fluctuations. Hybrid energy storage systems have been an effective solution to smooth out PV output power variations. In order to reduce the required capacity and extend the lifetime of the hybrid energy storage system, a two-stage self-adaptive smoothing approach based on the artificial potential field is proposed to decompose and allocate power among the grid, battery, and supercapacitor dynamically. In the ramp rate control stage, an unsymmetric artificial potential field method is used to regulate the cutoff frequency of a low-pass filter, so as to limit the PV power ramp rate within the prescribed range and allocate the power between the grid and the hybrid energy storage system. In the HESS power distribution stage, a symmetric artificial potential field is adopted to distribute power between the battery and …

Daniel Stroe

Daniel Stroe

Aalborg Universitet

Data in Brief

Dataset of lithium-ion battery degradation based on a forklift mission profile for state-of-health estimation and lifetime prediction

Lithium-ion (Li-ion) batteries are becoming an increasingly integral part of modern society, through consumer electronics, stabilisation of the electric grid, and electric vehicles. However, Lithium-ion batteries degrade in effectiveness over time; a degradation which is extremely dependent on the usage of the battery. Therefore, to study how a battery cell degrades under dynamic conditions, a realistic load profile was constructed based on the operation of forklifts. This profile was used to age three Lithium-ion battery cells at 45, 40, and 35°C and the response of the cells was measured on a second-by-second basis. Periodically the ageing was halted to perform a reference test of the cells allowing for the tracking of their degradation.

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 …

Yue WU - UNC

Yue WU - UNC

University of North Carolina at Chapel Hill

Modelling long COVID using Bayesian networks (preprint)

Motivated by the ambiguity of operational case definitions for long COVID and the impact of the lack of a common causal language on long COVID research, in early 2023 we began developing a research framework on this post-acute infection syndrome. We used directed acyclic graphs (DAGs) and Bayesian networks (BNs) to depict the hypothesised mechanisms of long COVID in an agnostic fashion. The DAGs were informed by the evolving literature and subsequently refined following elicitation workshops with domain experts. The workshops were structured online sessions guided by an experienced facilitator. The causal DAG aims to summarise the hypothesised pathobiological pathways from mild or severe COVID-19 disease to the development of pulmonary symptoms and fatigue over four different time points. The DAG was converted into a BN using qualitative parametrisation. These causal models aim to assist the identification of disease endotypes, as well as the design of randomised controlled trials and observational studies. The framework can also be extended to a range of other post-acute infection syndromes.

Yue WU - UNC

Yue WU - UNC

University of North Carolina at Chapel Hill

Modelling long COVID using Bayesian networks

Motivated by the ambiguity of operational case definitions for long COVID and the impact of the lack of a common causal language on long COVID research, in early 2023 we began developing a research framework on this post-acute infection syndrome. We used directed acyclic graphs (DAGs) and Bayesian networks (BNs) to depict the hypothesised mechanisms of long COVID in an agnostic fashion. The DAGs were informed by the evolving literature and subsequently refined following elicitation workshops with domain experts. The workshops were structured online sessions guided by an experienced facilitator. The causal DAG aims to summarise the hypothesised pathobiological pathways from mild or severe COVID-19 disease to the development of pulmonary symptoms and fatigue over four different time points. The DAG was converted into a BN using qualitative parametrisation. These causal models aim to assist the identification of disease endotypes, as well as the design of randomised controlled trials and observational studies. The framework can also be extended to a range of other post-acute infection syndromes.

Daniel Stroe

Daniel Stroe

Aalborg Universitet

On the Use of Randomly Selected Partial Charges to Predict Battery State-of-Health

As society becomes more reliant on Lithium-ion (Li-ion) batteries, state-of-health (SOH) estimation will need to become more accurate and reliable. Therefore, SOH modelling is in the process of shifting from using simple and continuous charge/discharge profiles, to more dynamic profiles constructed to mimic real operation, when ageing the Li-ion batteries. However, in most cases, when ageing the batteries, the same exact profile is just repeated until the battery reaches its end-of-life. Using data from batteries aged in this fashion to build a model, there is a very real possibility that the model will rely on the built-in repetitiveness of the profile. Therefore, this work will examine the dependence of the performance of a multiple linear regression on the number of charges used to train the model, and their location within the profile used to age the batteries. The investigation shows that it is possible to build models using randomly selected partial charges while still reaching errors as low as 0.5%. Furthermore, it shows that only two randomly sampled partial charges are needed to achieve errors of less than 1%. Lastly, as the number of randomly sampled partial charges used to create the model increases, then the dependence on particular partial charges tends to decrease.

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 …

Daniel Stroe

Daniel Stroe

Aalborg Universitet

Batteries

Lithium-Ion Supercapacitors and Batteries for Off-Grid PV Applications: Lifetime and Sizing

The intermittent nature of power generation from photovoltaics (PV) requires reliable energy storage solutions. Using the storage system outdoors exposes it to variable temperatures, affecting both its storage capacity and lifespan. Utilizing and optimizing energy storage considering climatic variations and new storage technologies is still a research gap. Therefore, this paper presents a modified sizing algorithm based on the Golden Section Search method, aimed at optimizing the number of cells in an energy storage unit, with a specific focus on the unique conditions of Denmark. The considered energy storage solutions are Lithium-ion capacitors (LiCs) and Lithium-ion batteries (LiBs), which are tested under different temperatures and C-rates rates. The algorithm aims to maximize the number of autonomy cycles—defined as periods during which the system operates independently of the grid, marked by intervals between two consecutive 0% State of Charge (SoC) occurrences. Testing scenarios include dynamic temperature and dynamic load, constant temperature at 25 °C, and constant load, considering irradiation and temperature effects and cell capacity fading over a decade. A comparative analysis reveals that, on average, the LiC storage is sized at 70–80% of the LiB storage across various scenarios. Notably, under a constant-temperature scenario, the degradation rate accelerates, particularly for LiBs. By leveraging the modified Golden Section Search algorithm, this study provides an efficient approach to the sizing problem, optimizing the number of cells and thus offering a potential solution for energy storage in off-grid PV systems.

Yue Wu (武悦)

Yue Wu (武悦)

Central South University

Applied Energy

Optimal battery thermal management for electric vehicles with battery degradation minimization

The control of a battery thermal management system (BTMS) is essential for the thermal safety, energy efficiency, and durability of electric vehicles (EVs) in hot weather. To address the battery cooling optimization problem, this paper utilizes dynamic programming (DP) to develop an online rule-based control strategy. Firstly, an electrical–thermal-aging model of the LiFePO 4 battery pack is established. A control-oriented onboard BTMS model is proposed and verified under different speed profiles and temperatures. Then in the DP framework, a cost function consisting of battery aging cost and cooling-induced electricity cost is minimized to obtain the optimal compressor power. By exacting three rules” fast cooling, slow cooling, and temperature-maintaining” from the DP result, a near-optimal rule-based cooling strategy, which uses as much regenerative energy as possible to cool the battery pack, is proposed for …

Yue WU - UNC

Yue WU - UNC

University of North Carolina at Chapel Hill

medRxiv

Applying causal inference and Bayesian statistics to understanding vaccine safety signals---a simulation study

Community perception of the safety of vaccines in the interest of public health influences vaccine uptake. Challenges for active vaccine safety monitoring include survey response rates, unbiased reporting and the balance between specificity and sensitivity of signal detection methods. To address these problems, we used causal DAGs and statistical methods to guide understanding of biological and behavioural factors which may influence vaccine safety signal detection. The DAGs informed the generation of scenarios in which these factors were varied. A posterior predictive analysis (PPA) signal detection method, based upon a Bayesian logistic model, was used to detect signals across the scenarios. In the high probability of severe reaction scenarios, true signals were generated where there was higher survey participation with more survey responder AEFI data available for analysis. In the low probability of severe reaction scenarios, false signals were generated when there was a strong influence of reaction severity on survey participation and reports of severe reactions. Low rates of survey participation reduce the amount of data available to inform the parameters of the statistical model, and therefore reduce the certainty regarding the value of these parameters. We obtained insights into the value of the causal DAG to account for survey non-response, to guide understanding of short-term vaccine safety, interpret the results of the PPA analysis under plausible scenarios, and review implications for future vaccine safety monitoring.

Yue WU - UNC

Yue WU - UNC

University of North Carolina at Chapel Hill

The Lancet Regional Health-Southeast Asia

Coverage gaps in empiric antibiotic regimens used to treat serious bacterial infections in neonates and children in Southeast Asia and the Pacific

BackgroundHigh levels of antimicrobial resistance (AMR) are propagating deaths due to neonatal and paediatric infections globally. This is of particular concern in Southeast Asia and the Pacific, where healthcare resources are constrained and access to newer agents to treat multidrug-resistant pathogens is limited.MethodsTo assess the coverage provided by commonly prescribed empiric antibiotic regimens for children in low- and middle-income countries in Southeast Asia and the Pacific, we built a weighted incidence syndromic combination antibiogram (WISCA), parameterised using data obtained from a systematic review of published literature incorporating WHO-defined SEARO and WPRO regions in Ovid MEDLINE, EMBASE, Global Health and PubMed. Susceptibility data for bacterial pathogens were extracted to provide coverage estimates for pre-specified antibiotics (aminopenicillins, gentamicin, third …

Pallavi Bharadwaj

Pallavi Bharadwaj

Massachusetts Institute of Technology

IEEE Transactions on Industrial Informatics

A Battery Digital Twin From Laboratory Data Using Wavelet Analysis and Neural Networks

Lithium-ion (Li-ion) batteries are the preferred choice for energy storage applications. Li-ion performances degrade with time and usage, leading to a decreased total charge capacity and to an increased internal resistance. In this article, the wavelet analysis is used to filter the voltage and current signals of the battery to estimate the internal complex impedance as a function of state of charge (SoC) and state of health (SoH). The collected data are then used to synthesize a battery digital twin (BDT). This BDT outputs a realistic voltage signal as a function of SoC and SoH inputs. The BDT is based on feedforward neural networks trained to simulate the complex internal impedance and the open-circuit voltage generator. The effectiveness of the proposed method is verified on the dataset from the prognostics data repository of NASA.

Daniel Stroe

Daniel Stroe

Aalborg Universitet

Journal of Energy Storage

Identification of the aging state of lithium-ion batteries via temporal convolution network and self-attention mechanism

Deep learning methods have been widely used for battery aging state estimation with either manual or automatic features, while the contribution of multi-source features is rarely considered. To solve this problem, a hybrid method is proposed to combine the manual and automatic features based on a temporal convolution network (TCN) and a self-attention mechanism (SA). Specifically, the local voltage, capacity, and incremental capacity are manually extracted as battery aging features. Then, for extracting automatic features, TCN employs dilated convolution to capture the capacity regeneration phenomenon during battery degradation. Considering the contribution of multi-source features, we use SA to fuse the obtained manual and automatic features. Finally, the available capacity and remaining useful life of the battery are predicted using a fully connected neural network on one dataset from our lab, the Oxford …

Xin Sui

Xin Sui

Aalborg Universitet

IEEE Transactions on Industry Applications

Small-Sample-Learning-Based Lithium-Ion Batteries Health Assessment: An Optimized Ensemble Framework

Machine Learning is widely studied in battery state of health (SOH) estimation due to its advantage in establishing the non-linear mapping between measurements and SOH. However, the requirement of a big dataset and the lack of robustness limit the practical application, especially in small sample learning. To tackle these challenges, an optimal ensemble framework called BaggELM (bagging extreme learning machine) is proposed for battery SOH estimation. Specifically, the required dataset is reduced by optimizing the input voltage and the hyperparameters of the BaggELM algorithm. Moreover, a statistical post-processing method is used to aggregate multiple ELMs, and the final estimate is determined by the maximum probability density value. As a result, the effects of random parameterization of ELM and the training data size on SOH estimation are suppressed, thus improving the robustness and accuracy of …

Daniel Stroe

Daniel Stroe

Aalborg Universitet

Battery state-of-health estimation using machine learning

Over the years, lithium–ion batteries have developed as a key enabling technology for the green transition. Although many of these batteries’ characteristics, such as energy density, power capability, and cost, have gradually improved, uncertainties remain concerning their performance over their lifetimes. Thus, to ensure reliable and efficient battery operation, the battery's available performance, known as its state of health (SOH), must be known at every moment. This chapter introduces the most common battery SOH estimation methods, from direct measurements to deep neural networks, discussing their key performance metrics, advantages, and drawbacks.

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 …

Yue WU - UNC

Yue WU - UNC

University of North Carolina at Chapel Hill

arXiv preprint arXiv:2402.12887

The practice of qualitative parameterisation in the development of Bayesian networks

The typical phases of Bayesian network (BN) structured development include specification of purpose and scope, structure development, parameterisation and validation. Structure development is typically focused on qualitative issues and parameterisation quantitative issues, however there are qualitative and quantitative issues that arise in both phases. A common step that occurs after the initial structure has been developed is to perform a rough parameterisation that only captures and illustrates the intended qualitative behaviour of the model. This is done prior to a more rigorous parameterisation, ensuring that the structure is fit for purpose, as well as supporting later development and validation. In our collective experience and in discussions with other modellers, this step is an important part of the development process, but is under-reported in the literature. Since the practice focuses on qualitative issues, despite being quantitative in nature, we call this step qualitative parameterisation and provide an outline of its role in the BN development process.

Daniel Stroe

Daniel Stroe

Aalborg Universitet

Advanced Energy Materials

Unravelling the Mechanism of Pulse Current Charging for Enhancing the Stability of Commercial LiNi0.5Mn0.3Co0.2O2/Graphite Lithium‐Ion Batteries

The key to advancing lithium‐ion battery (LIB) technology, particularly with respect to the optimization of cycling protocols, is to obtain comprehensive and in‐depth understanding of the dynamic electrochemical processes during battery operation. This work shows that pulse current (PC) charging substantially enhances the cycle stability of commercial LiNi0.5Mn0.3Co0.2O2 (NMC532)/graphite LIBs. Electrochemical diagnosis unveils that pulsed current effectively mitigates the rise of battery impedance and minimizes the loss of electrode materials. Operando and ex situ Raman and X‐ray absorption spectroscopy reveal the chemical and structural changes of the negative and positive electrode materials during PC and constant current (CC) charging. Specifically, Li‐ions are more uniformly intercalated into graphite and the Ni element of NMC532 achieves a higher energy state with less Ni─O bond length variation …

Yue WU - UNC

Yue WU - UNC

University of North Carolina at Chapel Hill

Biztonságtudományi Szemle

Changes in the crop world market: what will be the food supply without the Russia-Ukraine war?

A 2007/2008-as élelmiszerválságot követően a COVID-19 járvány után a világ a folyamatban levő orosz-ukrán háború idején szenvedi el ismét egy élelmiszer válság következményeit. A háború két résztvevő országa a világ alapvető élelmiszer ellátója. A kialakult élelmiszer krízis is mutatja a háború negatív hatásait. Ebben a kutatásban arra törekedtünk, hogy megjósoljuk Ukrajnában a fő terményexport mennyiségét a 2022-től (a háború kitörésének évétől) 2024-ig tartó időszakra. Kutatási módszertanként idősoros elemzést használtunk. Azt találtuk, hogy Oroszország és Ukrajna a becslések szerint egyre fontosabb szerepet fog játszani a világ élelmiszerellátásában a búza, a kukorica, az árpa és a napraforgómag tekintetében. Ez a kutatási eredmény szilárd alapja lehet annak a jövőbeni összehasonlító vizsgálatnak is, amely az oroszukrán háború világ élelmiszerellátására gyakorolt hatását vizsgálja.

Daniel Stroe

Daniel Stroe

Aalborg Universitet

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 …

Other articles from Applied Energy journal

Linhao Fan (樊林浩)

Linhao Fan (樊林浩)

Tianjin University

Applied Energy

Fabrication of high electrochemical performance ternary lithium battery using LiNi0. 8Co0. 1Mn0. 1O2 with nano-TiO2 coating

With the increase of nickel content and the reduction of cobalt content in the ternary materials, LiNi0.8Co0.1Mn0.1O2 (NCM 811) meets the challenges in poor cycle stability and reduced safety. To address these problems, the coating method is considered as a promising technology to improve the performance of the ternary material. In the current work, NCM811 cathode materials coated with nano-TiO2 are synthesized by using oxalic acid co-precipitation and wet coating with anhydrous ethanol methods. Then, the properties of our prepared ternary cathode material with different coating amounts have been investigated. We found that the nano-TiO2-coated method can weaken the agglomeration phenomenon and particle dispersion in the preparation process, resulting in an improved reversibility of the redox reaction, reduced impedance and stable cycle performance of the battery. When the amount of coated …

Anna Timofiejczuk

Anna Timofiejczuk

Politechnika Slaska

Applied Energy

PiezoTensorNet: Crystallography informed multi-scale hierarchical machine learning model for rapid piezoelectric performance finetuning

Piezoelectric devices offer numerous opportunities for sustainable harvesting of wasted mechanical energy, leading to a significant interest in data-driven research on these materials. This study presents the design of PiezoTensorNet, a comprehensive framework that encompasses a hierarchical classification neural network for crystal point group determination and modular ensembles of regression-based multi-dimensional models for predicting piezoelectric tensors. The machine learning models capable of forecasting tensors for dopant element alloying and various crystallographic transformations is integrated along with finite element analysis for electromechanical performance evaluation. The efficacy of integrated toolkit is demonstrated through the computational design and discovery of a lead-free microelectromechanical system based on AlN. The introduction of Boron and Erbium dopants in AlN enhances its …

Xiufeng Liu

Xiufeng Liu

Danmarks Tekniske Universitet

Applied Energy

Temporal collaborative attention for wind power forecasting

Wind power serves as a clean and sustainable form of energy. However, its generation is fraught with variability and uncertainty, owing to the stochastic and dynamic characteristics of wind. Accurate forecasting of wind power is indispensable for the efficient planning, operation, and grid integration of wind energy systems. In this paper, we introduce a novel forecasting method termed Temporal Collaborative Attention (TCOAT). This data-driven approach is designed to capture both temporal and spatial dependencies in wind power generation data, as well as discern long-term and short-term patterns. Utilizing attention mechanisms, TCOAT dynamically adjusts the weights of each input variable and time step based on their contextual relevance for forecasting. Furthermore, the method employs collaborative attention units to assimilate directional and global information from the input data. It also explicitly models the …

Laurence Stamford

Laurence Stamford

Manchester University

Applied Energy

Integrated sustainability assessment of repurposing onshore abandoned wells for geothermal power generation

As global efforts intensify to mitigate climate change through Net-Zero by 2050, the transition from fossil fuels to renewable energy sources is of utmost importance. Within this context, geothermal power generation is an underestimated yet rapidly developing field with immense potential. A notable opportunity arises from repurposing abandoned oil and gas wells (AOGWs) as alternative sources for geothermal power production. This study employs multi-criteria decision analysis (MCDA) to examine the techno-sustainability of four geothermal power systems: i) a business-as-usual geothermal power plant (GEObau), ii) repurpose two completely AOGWs for geothermal power generation (R-GEOdouble), iii) repurpose a single completely AOGW (R-GEOsingle), iv) repurpose semi-AOGWs (i.e., wells still in operation but with high water cut, R-GEOsemi). We assessed 30 criteria across technical, environmental …

Mohamed E. Zayed (Assistant Professor)

Mohamed E. Zayed (Assistant Professor)

Tanta University

Applied Energy

Energy and economic analysis of building integrated photovoltaic thermal system: Seasonal dynamic modeling assisted with machine learning-aided method and multi-objective …

In this research, the effect of phase change material (PCM) on energy consumption of a typical multistory office building located in five different cities (Shenyang, Zhengzhou, Changsha, Kunming and Hong Kong) representing different climate regions of China, was simulated for a whole year using EnergyPlus. Based on the simulation results, the energy savings resulting from PCM application were evaluated. For economic analysis, the static payback period (SPP) and dynamic payback period (DPP), considering different discount rates, were used to assess the application of PCM in a typical official building. Test results showed that the energy savings resulting from PCM application are more prominent for office building located in cold region such as Shenyang and Zhengzhou as well as in hot summer and cold winter (Changsha). From economic analysis, the application of PCM in Shenyang, Zhengzhou and …

Jinyue Yan

Jinyue Yan

Kungliga Tekniska högskolan

Applied Energy

A compact time horizon compression method for planning community integrated energy systems with long-term energy storage

Long-term energy storage (LTES), such as hydrogen storage, has attracted significant attention due to its outstanding performance in storing energy over extended durations and seasonal balancing of power generation and consumption. However, planning for LTES usually necessitates the comprehensive coverage of its whole operation cycle, spanning from days to months, making the issue complex and intractable. To simplify the planning of a community integrated energy system (CIES) with LTES, this study proposes a time horizon compression (THC) method and formulates a concise long-term planning model for CIES with compressed time horizons. Then, robust optimization method with a budget uncertainty set is employed to develop a robust THC model, aimed at addressing data uncertainties in CIES planning. The proposed robust THC model is implemented in the planning of a CIES with high penetration …

Dominik Franjo Dominković

Dominik Franjo Dominković

Danmarks Tekniske Universitet

Applied Energy

Frigg 2.0: Integrating price-based demand response into large-scale energy system analysis

Transitioning energy systems to renewable sources requires a paradigm shift in system operation: Rather than only dispatching central generators to match volatile demand, the demand side must also be adjusted flexibly to match renewable generation. Electrified heating is one source of such flexibility, via demand response and heat storage.In energy system analysis, demand response is often modelled as a direct control problem, where central decisions set demand levels. We consider this an over-simplification and have previously proposed Frigg, a framework for integrating price-based indirect demand response models in energy system analysis. In this article, a reformulation is proposed that solves central previous shortcomings, such as modelling a larger number of intertemporal constraints. This allows wide application of Frigg in energy system modelling.In this paper, Frigg is applied to soft-link plan4EU, a …

Diego Nieves Avendano

Diego Nieves Avendano

Universiteit Gent

Applied Energy

A novel day-ahead regional and probabilistic wind power forecasting framework using deep CNNs and conformalized regression forests

Regional forecasting is crucial for a balanced energy delivery system and for achieving the global transition to clean energy. However, regional wind forecasting is challenging due to uncertain weather prediction and its high dimensional nature. Most solutions are limited to single-turbine or farm/park forecasting; therefore, this work proposes a day-ahead regional wind power forecasting framework using deep Convolutional Neural Networks (CNN) with context-aware turbine maps and Conformal Quantile Regression (CQR) to generate quantile forecasts with valid coverage.Additionally, this work introduces the use of the Split Conformal Predictive System (SCPS) to generate valid prediction distributions, which has not yet been proposed for wind power forecasting in general. As well as a new method to generate calibrated prediction distributions based on SCPS and Quantile Regression Forests (QRF). This new …

James Flint

James Flint

Loughborough University

Applied Energy

A pendulum-based rotational energy harvester for self-powered monitoring of rotating systems in the era of industrial digitization

Wireless condition monitoring of rotating systems, including vehicle powertrains and wind turbines, is a key for continuously assessing the operational performance in the era of industrial digitization. However, one of their major challenges revolve around the dependence on power supply from batteries. Hence, this paper presents the concept, theoretical model, and experimental study of a pendulum-based energy harvester for high-speed rotational systems. The proposed design harvests energy from rotating shafts by using a suspended eccentric pendulum-based configuration and requires only one anchor point with the host to extract mechanical energy. A numerical model was established to study the dynamics and the electromechanical properties of the harvester. An experimental prototype was developed based on the key parameters determined from the numerical study and mounted on an electric motor …

Morteza Vahid-Ghavidel

Morteza Vahid-Ghavidel

Universidade do Porto

Applied Energy

Integrated energy demand-supply modeling for low-carbon neighborhood planning

As the building stock is projected to double before the end of the half-century and the power grid is transitions to low-carbon resources, planning new construction hand in hand with the grid and its capacity is essential. This paper presents a method that combines urban building energy modeling and local planning of renewable energy sources (RES) using an optimization framework. The objective of this model is to minimize the investment and operational cost of meeting the energy needs of a group of buildings. The framework considers two urban-scale RES technologies, photovoltaic (PV) panels and small-scale wind turbines, alongside energy storage system (ESS) units that complement building demand in case of RES unavailability. The urban buildings are modeled abstractly as “shoeboxes” using the Urban Modeling Interface (umi) software. We tested the proposed framework on a real case study in a …

Chaolong Song

Chaolong Song

China University of Geosciences Wuhan

Applied Energy

Enhancement of hydrogen production via optimizing micro-structures of electrolyzer on a microfluidic platform

Electrochemical water splitting plays a vital role for production of hydrogen (H2). Enhancing the rate of hydrogen separation from the electrode is crucial for improving the performance of water electrolyzers. The water electrolyzers often encounter issues such as air bubble adhesion to the electrode plate, leading to increased electrical resistance, reduced current density, and thus lower hydrogen generation rates. In addition, the compact configuration of electrolyzer and non-transparent electrode plates make it impracticable to observe and analyze the gas-liquid two-phase flow between the anode and cathode plates. Hence, a methodology is in high demand to experimentally investigate the two-phase flow within the electrolyzer, which could be further used to guide the design and optimization of the electrolyzer. In this work, we propose to utilize a microfluidic system as a phantom of electrolyzer. The transparent …

Jihyeok Choi

Jihyeok Choi

Kookmin University

Applied Energy

Computational fluid dynamics simulation of the stacked module in air gap membrane distillation for enhanced permeate flux and energy efficiency

Advancements in membrane distillation (MD) technology require the development of module designs to optimize system performance. This study established a computational fluid dynamics (CFD) model to assess the performance of an air gap membrane distillation (AGMD) system. The CFD model achieved an accuracy of approximately 96.43% through verification under various feed temperatures and flow conditions in an experimental AGMD system. CFD simulations demonstrated the importance of flow and temperature distribution within the module, and the response surface method was employed to investigate the influence of module size on system performance. The thickness of the air gap affected the permeate flux by >7 times the module length. The influence of the module length on the change in the gained output ratio was >11 times that of the feed temperature. In addition, graphical optimization enables …

Yuli Shan (单钰理)

Yuli Shan (单钰理)

Rijksuniversiteit Groningen

Applied Energy

Investigating the fast energy-related carbon emissions growth in African countries and its drivers

Efforts to avoid the acceleration of global warming have tended to focus on countries with high CO2 emissions levels and large populations, with a high level of economic development or industrialization. African countries, which often do not conform to such criteria, are more vulnerable to climate change due to their dependence on climate-sensitive industries and their limited infrastructure and technological capacity to cope with its impacts. The long-term economic growth rates projected for Africa's rapid development period will, further, make Africa a potential emission hotspot in the near future. Here, for the first time, we built an energy-related emissions inventory for 19 African countries for 2010–2019, which addresses emissions from 47 economic sectors and 5 energy types, making it the most comprehensive of its kind. The degree of decoupling of economy and emissions, and drivers of CO2 emission changes …

HE Hongwen 何洪文

HE Hongwen 何洪文

Beijing Institute of Technology

Applied Energy

Towards a fossil-free urban transport system: An intelligent cross-type transferable energy management framework based on deep transfer reinforcement learning

Deep reinforcement learning (DRL) is now a research focus for the energy management of fuel cell vehicles (FCVs) to improve hydrogen utilization efficiency. However, since DRL-based energy management strategies (EMSs) need to be retrained when the types of FCVs are changed, it is a laborious task to develop DRL-based EMSs for different FCVs. Given that, this article introduces transfer learning (TL) into DRL to design a novel deep transfer reinforcement learning (DTRL) method and then innovatively proposes an intelligent transferable energy management framework between two different urban FCVs based on the designed DTRL method to achieve the reuse of well-trained EMSs. To begin, an enhanced soft actor-critic (SAC) algorithm integrating prioritized experience replay (PER) is formulated to be the studied DRL algorithm in this article. Then, an enhanced-SAC based EMS of a light fuel cell hybrid …

RJ BARTHELMIE

RJ BARTHELMIE

Cornell University

Applied Energy

Corrigendum to “Wind shadows impact planning of large offshore wind farms”[Applied Energy 359 (2024) 122755]

This work is supported by the US Department of Energy (DoE)(DE-SC0016605). The research used computing resources from the National Science Foundation: Extreme Science and Engineering Discovery Environment (XSEDE)(allocation award to SCP is TG-ATM170024) and National Energy Research Scientific Computing Center, a DOE Office of Science User Facility supported by the Office of Science of the US Department of Energy under Contract No. DE-AC02-05CH11231. None of the funding agencies have reviewed the information contained here and the opinions in this manuscript do not necessarily reflect those of any of these parties.

Dayong Zhang

Dayong Zhang

Southwestern University of Finance and Economics

Applied Energy

On the interactive effects of climate policies: Insights from a stock-flow consistent model

Climate policies such as carbon tax and green finance policy are critical measures to promote low-carbon transition worldwide. These policies are, however, likely to interact with each other and create unintentional consequences. This paper adopts a stock-flow consistent model to theoretically explore the effects of policy interactions. Specifically, commercial banks, as the key credit creators and critical players in providing source of finance, are included. Based on the numerical simulations of the dynamic model, we find that both carbon tax and green finance policies render positive impacts on low-carbon transition. In addition, green credit incentives, if imposed simultaneously with carbon tax, can enhance the positive effects. Although low-carbon transition could generate higher net government revenues, our results show that banking sector tends to expose to higher financial risks when firms’ debt-equity ratio rises …

Badong Chen

Badong Chen

Xi'an Jiaotong University

Applied Energy

A hybrid PV cluster power prediction model using BLS with GMCC and error correction via RVM considering an improved statistical upscaling technique

Accurate cluster photovoltaic power prediction (CPPP) is crucial for the operation and control of renewable energy grid-connected power systems. The traditional modeling strategies for CPPP such as direct aggregation (DA) and statistical upscaling (SU) have limitations such as error accumulation and upscaling factor uncertainty. To address these issues, this paper proposed a novel hybrid approach for CPPP by combining machine learning models with an improved SU technique. Firstly, a robust broad learning system (BLS) model, in which the Generalized Maximum Correntropy Criterion (GMCC) is used to replace the original mean square error (MSE) loss in BLS, is proposed to solve the problem of multiple outliers affecting the prediction accuracy of regional cluster stations, and it is called GBLS. Then, the Relevance Vector Machine (RVM) as an effective nonlinear regression model is further utilized to …

Xianming Ye

Xianming Ye

University of Pretoria

Applied Energy

Harnessing eXplainable artificial intelligence for feature selection in time series energy forecasting: A comparative analysis of Grad-CAM and SHAP

This study investigates the efficacy of Explainable Artificial Intelligence (XAI) methods, specifically Gradient-weighted Class Activation Mapping (Grad-CAM) and Shapley Additive Explanations (SHAP), in the feature selection process for national demand forecasting. Utilising a multi-headed Convolutional Neural Network (CNN), both XAI methods exhibit capabilities in enhancing forecasting accuracy and model efficiency by identifying and eliminating irrelevant features. Comparative analysis revealed Grad-CAM’s exceptional computational efficiency in high-dimensional applications and SHAP’s superior ability in revealing features that degrade forecast accuracy. However, limitations are found in both methods, with Grad-CAM including features that decrease model stability, and SHAP inaccurately ranking significant features. Future research should focus on refining these XAI methods to overcome these limitations …

Sharifah Rafidah Wan Alwi

Sharifah Rafidah Wan Alwi

Universiti Teknologi Malaysia

Applied Energy

A comparative life cycle assessment of solar combined cooling, heating, and power systems based on RESHeat technology

Switching to renewable energy is key to reducing Greenhouse Gas (GHG) emissions from building energy systems. The Renewable Energy System for Residential Building Heating and Electricity Production (RESHeat) uses solar irradiation, integrating underground thermal energy storage and high-performance heat pumps. This is a new system ongoing prototype demonstration, and its environmental impact has to be evaluated on a life-cycle basis. This study provides a comprehensive analysis of the monthly and annual environmental impacts of RESHeat systems in Limanowa and Cracow, comparing them with traditional gas boilers and Combined Cooling, Heating, and Power system (CCHP) systems. Compared to traditional gas boilers, global warming and fossil resource scarcity are reduced by exceeding 60%. In the end-of-life of systems, reuse decreases mineral resource scarcity by 38.73% in Limanowa …

Chukwuma John Okolie

Chukwuma John Okolie

University of Lagos

Applied Energy

Technical and performance assessments of wind turbines in low wind speed areas using numerical, metaheuristic and remote sensing procedures

The application of innovative technologies in the manufacture of wind turbines (WT) has produced more efficient WT that can operate successfully in low wind speed (LWS) environments. This technology has not been implemented in many LWS parts of the world due to the paucity of enabling technical information (wind resource availability and wind turbine configuration). This study uses ten years wind speed data from twelve Nigerian cities and their population densities, remote sensing, and the configuration of some commercially available LWS turbines in generating technical information suitable for data-backed decision-making on low-speed turbine deployability, operational conditions, and energy yield at 50 and 400 m. Five different numerical and metaheuristic procedures were randomly selected and utilized to estimate Weibull parameters used in computing wind energy development (WEDP) parameters …