Article
Energy & Fuels
Friedrich von Buelow, Joshua Mentz, Tobias Meisen
Summary: The study presents a machine learning method for predicting the state of health of batteries in electric vehicles, which can be applied in real-world applications. It was found that combining different cycle window widths into one training dataset improves the generalization of the model, and the granularity of the operational ranges of the signals does not limit the model's performance.
JOURNAL OF ENERGY STORAGE
(2021)
Article
Energy & Fuels
Friedrich von Buelow, Markus Wassermann, Tobias Meisen
Summary: This study surpasses existing battery state of health (SOH) forecasting methods by using battery pack data from real-world vehicle operation. The results show that a state-of-the-art SOH forecasting method based on histogram features works not only on laboratory battery cell data, but also on real-world battery system data.
JOURNAL OF ENERGY STORAGE
(2023)
Article
Chemistry, Physical
Xiaopeng Tang, Kailong Liu, Qi Liu, Qiao Peng, Furong Gao
Summary: This paper focuses on obtaining referenced SoP values for battery systems by designing a novel equivalent discharging test and a flexible softmax neural network, which successfully reduce the peak discharging current and achieve reliable SoP values with errors lower than 0.5%. The obtained SoP values can serve as a highly accurate benchmark to evaluate the accuracy of other onboard battery SoP estimators.
JOURNAL OF POWER SOURCES
(2021)
Article
Energy & Fuels
Litao Zhou, Zhaosheng Zhang, Peng Liu, Yang Zhao, Dingsong Cui, Zhenpo Wang
Summary: In this study, a novel data-driven framework is proposed to improve the accurate estimation and prediction of the state of health (SOH) of lithium-ion batteries. The proposed method, based on incremental capacity (IC) analysis and battery operation characteristics, is more suitable for practical applications and achieves a 12.89% improvement in reflecting SOH compared to the IC peak method. Additionally, a correction model is proposed to remedy deviations due to battery individual adaptivity. The method is validated on laboratory and EV datasets, showing significantly lower mean absolute percentage errors than conventional methods. The study highlights the adaptability of health features in real-world scenarios and the potential of combining group-based and individual-based models for optimized predictions.
JOURNAL OF ENERGY STORAGE
(2023)
Article
Energy & Fuels
Tae -Won Noh, Dong Hwan Kim, Byoung Kuk Lee
Summary: In this study, a novel online state-of-health (SOH) estimation algorithm for electric vehicles (EVs) is proposed based on the compression ratio of open circuit voltage (OCV)-to-charged capacity curve. The proposed algorithm estimates the degraded capacity at every sampling time during the driving operation through a first-order low-pass filter, which does not require complex mathematical tools and numerous offline data.
JOURNAL OF ENERGY STORAGE
(2023)
Article
Energy & Fuels
Carlos Vidal, Pawel Malysz, Mina Naguib, Ali Emadi, Phillip J. Kollmeyer
Summary: This study compares the performance of recurrent and non-recurrent neural networks in estimating battery state of charge, and finds that a non-recurrent feedforward neural network with filtered inputs has higher accuracy, requires less training time, and executes faster.
JOURNAL OF ENERGY STORAGE
(2022)
Review
Energy & Fuels
Pedro H. Camargos, Pedro H. J. dos Santos, Igor R. dos Santos, Gabriel S. Ribeiro, Ricardo E. Caetano
Summary: This article discusses various lithium-ion battery technologies, including nickel cobalt aluminum, nickel manganese cobalt, lithium iron phosphate, and lithium titanate. It also compares niobium batteries, indicating niobium as a promising metal for use in lithium-ion batteries.
INTERNATIONAL JOURNAL OF ENERGY RESEARCH
(2022)
Review
Energy & Fuels
Tahmineh Raoofi, Melih Yildiz
Summary: The paper introduces the battery-powered propulsion system as a solution for aviation-induced CO2 emissions. It emphasizes the importance of an effective Battery Management System (BMS) for ensuring safety and reliability. The study analyzes various methods of battery state estimation and highlights the emerging data-driven approach as a potential solution. However, challenges in implementing AI in the EPS and gaps in current airworthiness certification regulations are identified.
JOURNAL OF ENERGY STORAGE
(2023)
Article
Energy & Fuels
Guangzhong Dong, Yuyao Feng, Yifei Wang, Jingwen Wei
Summary: This paper presents a probabilistic scheme for accurately predicting the end-of-discharge time of lithium-ion batteries. It proposes a robust observer design and statistical characterization of future loading profiles for state-of-charge estimation and uncertainty quantification. Experimental results demonstrate the effectiveness of the proposed scheme in accurately predicting the end-of-discharge time.
JOURNAL OF ENERGY STORAGE
(2023)
Article
Energy & Fuels
Alireza Rastegarpanah, Jamie Hathaway, Rustam Stolkin
Summary: A model-free, convolutional-neural-network-based estimation scheme for the state of health of high-power lithium-ion batteries is proposed in this study, outperforming the model-based approach without the need for dataset-specific adaptations.
Article
Thermodynamics
Xiong Feng, Junxiong Chen, Zhongwei Zhang, Shuwen Miao, Qiao Zhu
Summary: This paper presents a novel neural network structure called CWRNN, which effectively addresses long-term dependencies, reduces training and computation costs, and is validated under different temperature conditions.
Article
Chemistry, Physical
Nikolaos Wassiliadis, Johannes Kriegler, Kareem Abo Gamra, Markus Lienkamp
Summary: The increasing sales of battery electric vehicles have led to their wider use under demanding conditions, such as frequent fast charging and operation under low temperatures. To prevent battery aging and failure, a health-aware fast charging strategy based on a model of reduced order is proposed, which can significantly reduce charging time while prolonging the cycle life of lithium-ion batteries.
JOURNAL OF POWER SOURCES
(2023)
Article
Energy & Fuels
Xiang Zhang, Peng Liu, Ni Lin, Zhaosheng Zhang, Zhenpo Wang
Summary: This study developed a novel data-driven framework for abnormality detection using a neural network with interpretable modules on top of an Autoencoder. The proposed algorithm achieved higher accuracy, shorter training time, and lower computational cost compared to existing algorithms when validated with real EV data.
Article
Chemistry, Physical
Rui Xiong, Yue Sun, Chenxu Wang, Jinpeng Tian, Xiang Chen, Hailong Li, Qiang Zhang
Summary: In this study, a novel method combining four algorithms was proposed to select the most important features for estimating the state of health (SOH) of lithium-ion batteries (LiBs). The selected features improved the accuracy of SOH estimation by 63.5% and 71.1% for NCA and LFP batteries, respectively, compared to using all features. Additionally, the method allowed the use of data obtained in partial voltage ranges, resulting in minimum root mean square errors of 1.2% and 1.6% for NCA and LFP batteries, respectively, demonstrating its capability for onboard applications.
ENERGY STORAGE MATERIALS
(2023)
Article
Chemistry, Physical
Jinpeng Tian, Rui Xiong, Weixiang Shen, Fengchun Sun
Summary: The proposed method in this paper utilizes offline OCV test results to estimate aging diagnosis of lithium ion batteries at an electrode level, achieving fast diagnosis. The estimated aging parameters are close to the results obtained by offline tests, enabling reconstruction of OCV-Q curves for battery capacity estimation with high accuracy. The influence of voltage ranges on estimation results is also discussed in the study.
ENERGY STORAGE MATERIALS
(2021)
Article
Automation & Control Systems
Yannik Steiniger, Dieter Kraus, Tobias Meisen
Summary: This paper provides a comprehensive overview of the application of deep learning in the analysis of sonar images. The focus is on feature extraction, classification, detection, and segmentation using convolutional neural networks (CNN). The research in this field has shown that even small CNNs outperform traditional methods. The purpose of this work is to introduce researchers to the recent achievements in this field and to identify research gaps for further exploration.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2022)
Article
Chemistry, Multidisciplinary
Nils Hutten, Richard Meyes, Tobias Meisen
Summary: Artificial intelligence has been considered as an approach to visual inspection in industrial applications for decades. Recent advances in deep learning, particularly in attention-based vision transformer architectures, have the potential to enable automated visual inspection even in complex environmental conditions. However, the application of vision transformers to real world visual inspection is still limited, possibly due to the assumption that they require large amounts of data to be effective.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Information Systems
Rebecca Braken, Alexander Paulus, Andre Pomp, Tobias Meisen
Summary: Semantic models are used to add context information to datasets, and automating the process of creating these models is a challenge. This study evaluated the performance of link prediction algorithms in few-shot scenarios, where only a small amount of training data is available. The results showed that two out of three selected algorithms performed well in this task.
Review
Business
Miguel Alves Gomes, Tobias Meisen
Summary: The importance of customer-oriented marketing has increased in recent decades, especially in e-commerce. Traditional mass marketing in this area is becoming obsolete as customer-specific targeting becomes realizable. This paper aims to provide a structured overview of different segmentation methods and their current state of the art.
INFORMATION SYSTEMS AND E-BUSINESS MANAGEMENT
(2023)
Article
Social Sciences, Interdisciplinary
Maike Jansen, Tobias Meisen, Christiane Plociennik, Holger Berg, Andre Pomp, Waldemar Windholz
Summary: The Digital Product Passport (DPP) is essential for creating a resource-efficient circular economy by collecting and sharing product-related information. However, there is currently little attention and consensus on the digital infrastructure and system requirements for DPPs.
Article
Multidisciplinary Sciences
Yannik Hahn, Tristan Langer, Richard Meyes, Tobias Meisen
Summary: Deep learning models have revolutionized research fields like computer vision and natural language processing. However, time series analysis, especially time series forecasting, has not seen a similar revolution. This is due to the lack of large, domain-independent benchmark datasets and a competitive research environment. The focus of time series forecasting research is primarily domain-driven, resulting in slow progress and a lack of comparability across models.
Article
Energy & Fuels
Friedrich von Buelow, Yannik Hahn, Richard Meyes, Tobias Meisen
Summary: This paper compares different machine learning models and deep neural network models, and proposes a new method for visualizing battery operational states. The method is shown to be effective in adding transparency and interpretability to the forecasting results while maintaining superior performance.
INTERNATIONAL JOURNAL OF ENERGY RESEARCH
(2023)
Article
Energy & Fuels
Friedrich von Buelow, Markus Wassermann, Tobias Meisen
Summary: This study surpasses existing battery state of health (SOH) forecasting methods by using battery pack data from real-world vehicle operation. The results show that a state-of-the-art SOH forecasting method based on histogram features works not only on laboratory battery cell data, but also on real-world battery system data.
JOURNAL OF ENERGY STORAGE
(2023)
Article
Engineering, Marine
Johannes Benkert, Robert Maack, Tobias Meisen
Summary: In recent years, there has been a steady increase in maritime business and container throughput, leading terminal operators to seek automated container handling solutions. This paper explores the possibility of replacing LiDAR sensors with cameras in automated container terminals and provides a comprehensive review of camera-based container automation, a relatively unexplored field.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2023)
Article
Business
Miguel Alves Gomes, Mark Wonkhaus, Philipp Meisen, Tobias Meisen
Summary: Real-time customer purchase prediction aims to predict what products a customer will buy next by using data such as past purchases, search queries, time spent on product pages, age, gender, and other demographic information. Embedding-based approaches have shown that customer representations can be effectively learned, but the current state-of-the-art does not consider activity time. This work proposes an extended embedding approach that includes activity time to represent customer behavior, and it outperforms current approaches in terms of prediction performance.
JOURNAL OF THEORETICAL AND APPLIED ELECTRONIC COMMERCE RESEARCH
(2023)
Proceedings Paper
Engineering, Marine
Yannik Steiniger, Jannis Stoppe, Dieter Kraus, Tobias Meisen
Summary: This study focuses on the analysis of sonar images using deep learning methods and investigates the impact of data augmentation and image complexity reduction on model performance.
2022 OCEANS HAMPTON ROADS
(2022)
Article
Engineering, Multidisciplinary
Constantin Waubert de Puiseau, Dimitri Tegomo Nanfack, Hasan Tercan, Johannes Loebbert-Plattfaut, Tobias Meisen
Summary: This paper presents a real-world use case of using deep reinforcement learning to solve the dynamic storage location assignment problem in the warehousing industry. The study found that this method can decrease transportation costs compared to traditional manual classification methods.
Article
Energy & Fuels
M. Ahmadifar, K. Benfriha, M. Shirinbayan, A. Aoussat, J. Fitoussi
Summary: This study investigates the impact of innovative polymer-metal interface treatment on the reliability and robustness of hydrogen storage technology. A scaled-down demonstrator was fabricated using rotomolding to examine the mechanical characteristics, damage, and fatigue behaviors of the metal-polymer interface. The findings reveal that sandblasting treatment enhances the resilience of the interface.
JOURNAL OF ENERGY STORAGE
(2024)
Article
Energy & Fuels
A. A. Kandil, Mohamed M. Awad, Gamal I. Sultan, Mohamed S. Salem
Summary: This paper proposes a novel hybrid system that splits solar radiation into visible and thermal components using a beam splitter and integrates a phase change material (PCM) packed bed with a PV cell. Experimental and theoretical analyses show that the hybrid configuration significantly increases the net power output of the system compared to using a PV system alone.
JOURNAL OF ENERGY STORAGE
(2024)
Article
Energy & Fuels
Jinchao Li, Ya Xiao, Shiqiang Lu
Summary: The combination of energy storage and microgrids is crucial in addressing the uncertainty of distributed wind and solar resources. This article proposes a multi microgrid interaction system with electric-hydrogen hybrid energy storage, which optimizes the system's capacity configuration to improve its economy and reliability.
JOURNAL OF ENERGY STORAGE
(2024)
Review
Energy & Fuels
Shri Hari S. Pai, Sarvesh Kumar Pandey, E. James Jebaseelan Samuel, Jin Uk Jang, Arpan Kumar Nayak, HyukSu Han
Summary: This review discusses the structure-property relationship of nickel oxide nanostructures as excellent supercapacitive materials and provides an overview of various preparation methods and strategies to enhance specific capacitance. It comprehensively analyzes the current status, challenges, and future prospects of nickel oxide electrode materials for energy storage devices.
JOURNAL OF ENERGY STORAGE
(2024)
Article
Energy & Fuels
Xiaowei Wu, Xin Dong, Ziqin Liu, Xinyi Wang, Pu Hu, Chaoqun Shang
Summary: The growth of Li dendrites in lithium metal batteries is effectively controlled by constructing a three-dimensional framework on the surface of Li using Ni(OH)2 nanosheets modified Prussian blue tubes. This method provides a homogenous Li+ flux and sufficient space to accommodate the volume change of Li, resulting in suppressed dendrite growth and improved cycling performance.
JOURNAL OF ENERGY STORAGE
(2024)
Article
Energy & Fuels
Yan-Jie Liao, Yi-Yen Hsieh, Yi-Chun Yang, Hsing-Yu Tuan
Summary: We present two-dimensional AgInP2Se6 (AIPSe) bimetallic phosphorus trichalcogenides nanosheets as anodes for advanced alkali metal ion batteries (AMIBs). The introduction of bimetallic components enhances the electronic/ionic conductivity and optimizes the redox dynamics, resulting in superior electrochemical performance. The AIPSe@G anodes achieve high specific capacity, excellent cycle stability, and rate capability in both lithium-ion (LIBs) and potassium-ion batteries (PIBs). The comprehensive full cell tests further demonstrate the stability of AIPSe@G anodes under diverse current regimes.
JOURNAL OF ENERGY STORAGE
(2024)
Article
Energy & Fuels
Chenghu Wu, Weiwei Li, Tong Qian, Xuehua Xie, Jian Wang, Wenhu Tang, Xianfu Gong
Summary: In the context of increasing global environmental pollution and constant increase of carbon emission, hydrogen production from surplus renewable energy and hydrogen transportation using existing natural gas pipelines are effective means to mitigate renewable energy fluctuation, build a decarbonized gas network, and achieve the goal of carbon peak and carbon neutral in China. This paper proposes a quasi-steady-state modeling method of a hydrogen blended integrated electricity-gas system (HBIEGS) considering gas linepack and a sequential second-order cone programming (S-SOCP) method to solve the developed model. The results show that the proposed method improves computational efficiency by 91% compared with a general nonlinear solver.
JOURNAL OF ENERGY STORAGE
(2024)
Article
Energy & Fuels
Jingcen Zhang, Zhi Guo, Yazheng Zhu, Haifeng Zhang, Mengjie Yan, Dong Liu, Junjie Hao
Summary: In this study, a new type of sensible heat storage material was prepared using low-cost steel slag as the main component, providing an effective way of recycling steel slag. By analyzing the effects of different pretreatment steel slag content and sintering temperatures on the organization and properties of heat storage materials, the study found that the steel slag heat storage material exhibited excellent performance and stability under certain conditions.
JOURNAL OF ENERGY STORAGE
(2024)
Article
Energy & Fuels
D. Carrillo-Pena, G. Pelaz, R. Mateos, A. Escapa
Summary: Methanogenic biocathodes have the potential to convert CO2 and electricity into methane, making them suitable for long-term electrical energy storage. They can also function as biological supercapacitors for short-term energy storage, although this aspect has received less attention. In this study, carbon-felt-based MB modified with graphene oxide were investigated for their electrical charge storage capabilities. Results showed that the potential of the electrode during discharging plays a significant role in determining the charge storage capacity.
JOURNAL OF ENERGY STORAGE
(2024)
Article
Energy & Fuels
Marco Gambini, Federica Guarnaccia, Michele Manno, Michela Vellini
Summary: This paper presents an analytical assessment of the energy-power relationship for different material-based hydrogen storage systems. It explores the impact of power demand on the amount of discharged hydrogen and the utilization factor. The results show that metal hydrides have higher specific power compared to liquid organic hydrogen carriers. The study provides insights into the discharge duration and energy utilization of hydrogen storage systems.
JOURNAL OF ENERGY STORAGE
(2024)
Article
Energy & Fuels
Shujahadeen B. Aziz, Rebar T. Abdulwahid, Pshko A. Mohammed, Srood O. Rashid, Ari A. Abdalrahman, Wrya O. Karim, Bandar A. Al-Asbahi, Abdullah A. A. Ahmed, M. F. Z. Kadir
Summary: This study investigates a novel biodegradable green polymer electrolyte for energy storage. Results show that the sample with added glycerol has the highest conductivity. The primary conduction species in the electrolyte are ions. Testing confirms that the sample can withstand a voltage suitable for practical applications.
JOURNAL OF ENERGY STORAGE
(2024)
Article
Energy & Fuels
Binit Kumar, Abhishek Awasthi, C. Suresh, Yongseok Jeon
Summary: This study presents a new numerical model for effective thermal conductivity that overcomes the limitations of previous models. The model can be applied to various shapes and phase change materials, using the same constants. By incorporating the natural convection effect, the model accurately calculates the thermal conductivity. The results of the study demonstrate the effectiveness of the model for different shapes and a wide range of alkanes.
JOURNAL OF ENERGY STORAGE
(2024)
Article
Energy & Fuels
Supak Pattaweepaiboon, Wisit Hirunpinyopas, Pawin Iamprasertkun, Katechanok Pimphor, Supacharee Roddecha, Dirayanti Dirayanti, Adisak Boonchun, Weekit Sirisaksoontorn
Summary: In this study, electrode powder from spent zinc-carbon/alkaline batteries was upcycled into LiMn2O4 cathode and carbon anode for rechargeable lithium-ion batteries. The results show that the upcycled LiMn2O4 exhibits improved electrochemical performance, with higher discharge capacity compared to pristine LiMn2O4. Additionally, the recovered carbon materials show superior cycling performance. This research provides great potential for upcycling waste battery electrodes to high-value cathode and anode materials for lithium-ion battery applications.
JOURNAL OF ENERGY STORAGE
(2024)
Article
Energy & Fuels
Pan Yang, H. D. Yang, X. B. Meng, C. R. Song, T. L. He, J. Y. Cai, Y. Y. Xie, K. K. Xu
Summary: This paper introduces a novel multi-task learning data-driven model called GBLS Booster for accurately assessing the state of health (SOH) and remaining useful life (RUL) of lithium batteries. The model combines the strengths of GBLS and the CNN-Transformers algorithm-based Booster, and the Tree-structured Parzen Estimator (TPE) algorithm is used for optimization. The study devises 10 healthy indicators (HIs) derived from readily available sensor data to capture variations in battery SOH. The random forest method (RF) is employed for feature refinement and data dimension reduction, while the complete empirical mode decomposition (CEEMDAN) method and the Pearson correlation coefficient are used for noise reduction and data point elimination in RUL prediction. The proposed model demonstrates exceptional accuracy, robustness, and generalization capabilities.
JOURNAL OF ENERGY STORAGE
(2024)
Article
Energy & Fuels
M. Arrinda, M. Oyarbide, L. Lizaso, U. Osa, H. Macicior, H. J. Grande
Summary: This paper proposes a robust aging model generation methodology for lithium-ion batteries with any kind of lab-level aging data availability. The methodology involves four phases and ensures the robustness of the aging model through a verification process.
JOURNAL OF ENERGY STORAGE
(2024)
