A health assessment framework of lithium-ion batteries for cyber defense

Hong, Sheng; Zeng, Yining

doi:10.1016/j.asoc.2020.107067

Cited by 37 publications

(7 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To shorten the model training time, the number of health feature selection can be reduced during the experiment. In addition, some dimensionality reduction methods, such as principal component analysis (PCA) ( Fei et al., 2021 ) and local linear embedding (LLE) algorithm ( Hong and Zeng, 2021 ), may also be an effective manner to reduce the dimension of health features and correspondingly shorten the model training time.…”

Section: Challenges and Future Trend Of Machine Learning Methodsmentioning

confidence: 99%

State of health prediction of lithium-ion batteries based on machine learning: Advances and perspectives

Shu

Shen

et al. 2021

iScience

View full text Add to dashboard Cite

Summary Accurate state of health (SOH) prediction is significant to guarantee operation safety and avoid latent failures of lithium-ion batteries. With the development of communication and artificial intelligence technologies, a body of researches have been performed toward precise and reliable SOH prediction method based on machine learning (ML) techniques. In this paper, the conception of SOH is defined, and the state-of-the-art prediction methods are classified based on their primary implementation procedure. As an essential step in ML-based SOH algorithms, the health feature extraction methods reported in the literature are comprehensively surveyed. Next, an exhausted comparison is conducted to elaborate the development of ML-based SOH prediction techniques. Not only their advantages and disadvantages of the application in SOH prediction are reviewed but also their accuracy and execution process are fully discussed. Finally, pivotal challenges and corresponding research directions are provided for more reliable and high-fidelity SOH prediction.

show abstract

Section: Challenges and Future Trend Of Machine Learning Methodsmentioning

confidence: 99%

State of health prediction of lithium-ion batteries based on machine learning: Advances and perspectives

Shu

Shen

et al. 2021

iScience

View full text Add to dashboard Cite

show abstract

“…RUL prediction. The capacity predicted value corresponding to each particle in the mth cycle after the jth cycle was calculated, and then the weighted sum was carried out to obtain the capacity predicted value of the mth cycle after the jth cycle, as shown in Equation (13).…”

Section: Rul Prediction Based On Cuckoo Search Particle Filtering Alg...mentioning

confidence: 99%

“…Therefore, accurate RUL prediction can effectively grasp the operating state of the energy supply system and plays an important reference role in battery health management, 11 to avoid battery aging or failure causing safety accidents, and can alert users to timely maintenance of the battery 12 . Therefore, power battery RUL prediction research has an important value in engineering applications 13 . At present, there are three methods to predict the RUL of lithium‐ion batteries, including the modeling method, data‐driven method, 14 and fusion method.…”

Section: Introductionmentioning

confidence: 99%

A novel cuckoo search particle filtering strategy for the remaining useful life prediction of the lithium‐ion batteries in hybrid electric vehicle

Ren

Wang

Chen

et al. 2022

Intl J of Energy Research

View full text Add to dashboard Cite

Summary The remaining useful life (RUL) is a core parameter of the battery management system. To realize accurately predict the RUL, the paper takes the National Aeronautics and Space Administration battery test data set as the research object, and a battery capacity degradation model based on an exponential growth model is built to characterize the battery aging process. A novel cuckoo search optimization particle filtering algorithm is proposed for the RUL prediction by transferring the particles in the prior distribution region of the particle filtering algorithm to the maximum likelihood region. The initial cycle numbers are set differently, the capacity decay process of the four groups of batteries can be predicted completely, and the RUL of the batteries can be obtained. Compared with the commonly used particle filtering and unscented particle filtering algorithms, the results show that the proposed method has obvious advantages in the relative error of prediction and resampling rate under the four datasets. For the B0005 dataset, the relative errors are 4.8%, 3.2%, and 0.8%, respectively under 30, 50, and 70 cycles, corresponding to the particle filtering algorithm errors are 10.3%, 7.9%, and 4.8%, and the unscented particle filter algorithm errors are 6.3%, 4.8%, and 2.4%, respectively. In addition, the method for RUL prediction present in the paper has a high confidence level, and low resampling rate, which plays an important role in promoting the further application of lithium‐ion batteries. Highlights A novel cuckoo search optimization particle filtering algorithm is proposed. Different battery aging cycle number is distinguished to predict. Multiple battery RUL prediction is realized. RUL prediction has high prediction accuracy and high confidence.

show abstract

“…At this point, the client application can directly interact and transmit data with the corresponding physical storage device (Hong et al 2021).…”

Section: Overview Of Virtual Storage Space Mapping Algorithmmentioning

confidence: 99%

Research on mapping algorithm of distributed virtual storage space based on digital certificate authentication

Zheng¹,

Hong

Wang³

et al. 2021

J Ambient Intell Human Comput

Self Cite

View full text Add to dashboard Cite

With the continuous development of information technology, the amount of data in information systems continues to increase. Big data has become an inevitable trend in the development of information technology, and the problems faced by the secure storage of big data have also become problems that must be solved. On the one hand, the research in this paper meets the storage requirements of unstructured massive data. On the other hand, it applies digital certificate authentication technology to realize storage security identity authentication based on digital certificate, and solves the application problem of high-security identity authentication in distributed storage. The innovation of this paper is to use the corresponding virtual storage space mapping algorithm to realize the unified management of resource pool. And before data transmission, the digital certificate authentication method is used to realize the authority control of the storage resource pool. This paper has completed the design and implementation of the distributed secure storage system, and completed the related testing and verification work, which significantly improved the performance of data storage and solved the problem of big data secure storage.

show abstract

A health assessment framework of lithium-ion batteries for cyber defense

Cited by 37 publications

References 30 publications

State of health prediction of lithium-ion batteries based on machine learning: Advances and perspectives

State of health prediction of lithium-ion batteries based on machine learning: Advances and perspectives

A novel cuckoo search particle filtering strategy for the remaining useful life prediction of the lithium‐ion batteries in hybrid electric vehicle

Research on mapping algorithm of distributed virtual storage space based on digital certificate authentication

Contact Info

Product

Resources

About