• Energy Research
• 2025-2025close
• Open Access close
• Open Source close
• Embargo close
• CN close
• AU close
• SA close

In optimizing performance and extending the lifespan of lithium batteries, accurate state prediction is pivotal. Traditional regression and classification methods have achieved some success in battery state prediction. However, the efficacy of these data-driven approaches heavily relies on the availability and quality of public datasets. Additionally, generating electrochemical data predominantly through battery experiments is a lengthy and costly process, making it challenging to acquire high-quality electrochemical data. This difficulty, coupled with data incompleteness, significantly impacts prediction accuracy. Addressing these challenges, this study introduces the End of Life (EOL) and Equivalent Cycle Life (ECL) as conditions for generative AI models. By integrating an embedding layer into the CVAE model, we developed the Refined Conditional Variational Autoencoder (RCVAE). Through preprocessing data into a quasi-video format, our study achieves an integrated synthesis of electrochemical data, including voltage, current, temperature, and charging capacity, which is then processed by the RCVAE model. Coupled with customized training and inference algorithms, this model can generate specific electrochemical data for EOL and ECL under supervised conditions. This method provides users with a comprehensive electrochemical dataset, pioneering a new research domain for the artificial synthesis of lithium battery data. Furthermore, based on the detailed synthetic data, various battery state indicators can be calculated, offering new perspectives and possibilities for lithium battery performance prediction.

Lithium-ion batteries (LIBs) have found wide applications in a variety of fields such as electrified transportation, stationary storage and portable electronics devices. A battery management system (BMS) is critical to ensure the reliability, efficiency and longevity of LIBs. Recent research has witnessed the emergence of model-based fault diagnosis methods in advanced BMSs. This paper provides a comprehensive review on the model-based fault diagnosis methods for LIBs. First, the widely explored battery models in the existing literature are classified into physics-based electrochemical models and electrical equivalent circuit models. Second, a general state-space representation that describes electrical dynamics of a faulty battery is presented. The formulation of the state vectors and the identification of the parameter matrices are then elaborated. Third, the fault mechanisms of both battery faults (incl. overcharege/overdischarge faults, connection faults, short circuit faults) and sensor faults (incl. voltage sensor faults and current sensor faults) are discussed. Furthermore, different types of modeling uncertainties, such as modeling errors and measurement noises, aging effects, measurement outliers, are elaborated. An emphasis is then placed on the observer design (incl. online state observers and offline state observers). The algorithm implementation of typical state observers for battery fault diagnosis is also put forward. Finally, discussion and outlook are offered to envision some possible future research directions. Comment: Submitted to Renewable and Sustainable Energy Reviews on 09-Jan-2024

Machine learning's application in solar-thermal desalination is limited by data shortage and inconsistent analysis. This study develops an optimized dataset collection and analysis process for the representative solar still. By ultra-hydrophilic treatment on the condensation cover, the dataset collection process reduces the collection time by 83.3%. Over 1,000 datasets are collected, which is nearly one order of magnitude larger than up-to-date works. Then, a new interdisciplinary process flow is proposed. Some meaningful results are obtained that were not addressed by previous studies. It is found that Radom Forest might be a better choice for datasets larger than 1,000 due to both high accuracy and fast speed. Besides, the dataset range affects the quantified importance (weighted value) of factors significantly, with up to a 115% increment. Moreover, the results show that machine learning has a high accuracy on the extrapolation prediction of productivity, where the minimum mean relative prediction error is just around 4%. The results of this work not only show the necessity of the dataset characteristics' effect but also provide a standard process for studying solar-thermal desalination by machine learning, which would pave the way for interdisciplinary study.

Climate change, along with infectious diseasespathogens notably Batrachochytrium dendrobatidis (Bd), B. salamandrivorans (Bsal), Ranavirus, and PerkinseaPerkinsus, continue to devastate global amphibian populations, contributing to the greatest vertebrate extinctions of the Anthropocene. These pathogens, primarily favoring cooler, subtropical conditions, demonstrate a significant overlap in their climatic niches, thus affecting a broad range species. Here, we aim to explore the role of global warming and other climatic factors in the dispersal and evolution of these pathogens and to predict the future implications for amphibian populations worldwide. Given the limitations of data availability We conducted a thorough analysis of the climatic niche conservatism (NC) and evolution (CNE) of these pathogens using the currently available distributional data, including our own. We used , We engaged in a comprehensive analysis of the climatic niche conservatism (NC) and evolution (CNE) of these pathogens, utilizing predictive models to anticipate potential shifts in their future distribution and evaluate the capacity for CNE in response to climate change. We show that Bd and Bsal are likely to experience a total reduction in their current potential distributions by 2040, while Ranavirus and PerkinseaPerkinsus may expand their distributions. Interestingly, CNE has played a significant role in influencing the climatic niches of Bd and Bsal, with lineage dependent variations. However, there was no strong correlation found between virulence of Bd and its climatic niche. On the contrary, ranaviruses Ranaviruses and PerkinseaPerkinsus showed evidence of sporadic and recent CNE. Moreover, the emergence of lineages adapted to warmer climates suggests an ongoing CNE and a potential evolutionary response to climate change. With increased infection risk, particularly for Asian amphibians (from Ranavirus and PerkinseaPerkinsus), and the vulnerability of the southern hemisphere (except Bsal) due to limited prior exposure, this study underscores the urgent need for close monitoring and preventive measures, including stringent biosecurity protocols such as risk analysis and pre-border pathogen screening. Our study provides a critical framework for international collaboration and guideline development for amphibian trade, while contributing to the deeper dialogue on mitigating impacts of climate change on wildlife diseases.