STTEWS: A sequential-transformer thermal early warning system for lithium-ion battery safety

Li, Marui; Dong, Chaoyu; Xiong, Binyu; Mu, Yunfei; Yu, Xiaodan; Xiao, Qian; Jia, Hongjie

doi:10.1016/j.apenergy.2022.119965

Cited by 15 publications

(6 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cai et al [3] and Lipu et al [4] constructed SOH estimation algorithms from an optimization perspective. Li et al [5] and Lin et al [6] are committed to exploring input indicators that can be effective for SOH. In addition, most researchers study SOC as an independent task and optimize the estimation accuracy with the similar idea.…”

Section: Battery State Estimationmentioning

confidence: 99%

“…Many researchers have conducted relevant investigations on thermal early warning applying multiple methodologies. Li et al [5] proposed a sequential-transformer thermal early warning system (STTEWS) for prismatic LiFePO4-Graphite battery composed by a new allied temporal convolutionrecurrent diagnosis network (TCRDN) and a complete transformer thermal diagnosis network (TTDN), which managed to reach the thermal diagnosis accuracy of 95%. To predict the thermal runaway (TR) of the battery pack, Zhang et al [8] established a data-driven fusion model named Multi-Mode and Multi-Task Thermal Propagation Forecasting Neural Network (MMTPFNN) applying the thermal image and the discrete operating data of 18650 cells.…”

Section: Early Battery Thermal Warningmentioning

confidence: 99%

See 1 more Smart Citation

Comprehensive battery monitoring and warning system based on hierarchical temporal convolutional network (HTCN)

Wang,

Ye,

et al. 2024

Preprint

View full text Add to dashboard Cite

Battery management system (BMS) is crucial to ensure the efficiency and safety of the Lithium-ion battery pack by monitoring the real-time voltage, current, and temperature. In particular, the monitoring and warning system of the BMS is especially vital and demanding. However, most researchers separate the battery states as individual tasks and discuss them respectively, while state of charge (SOC), state of health (SOH), and state of temperature (SOT) are coupled and should be estimated simultaneously in one model. To satisfy the demand for the online monitoring and warning system, this paper proposed an integrated estimation model based on temporal convolution network (TCN) and multi-task learning taking the mutuality of the SOC, SOH and SOT into consideration. Specifically, four assessing indexes were obtained by analyzing the relationship, tendency and characteristic of the temperature and capacity during the battery aging process. Then, a multi-timescale model was built combined with the conception of multi-task learning, namely the hierarchical temporal convolutional network (HTCN), and the temperature varying tendency is predicted along with the battery states as different output tasks. At last, the model was transferred to test datasets to validate the generality, accuracy and robustness. Results show that the mean average error (MAE) of the SOC, SOH and SOT estimation are 1.37%, 0.95% and 1.01%, respectively. This paper provided a novel, practical and reliable route for the comprehensive BMS construction.

show abstract

Section: Battery State Estimationmentioning

confidence: 99%

Section: Early Battery Thermal Warningmentioning

confidence: 99%

Comprehensive battery monitoring and warning system based on hierarchical temporal convolutional network (HTCN)

Wang,

Ye,

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Ojo et al [93] presented an improved LSTM to estimate the battery surface temperature. Li et al [94] proposed a convolution recursive diagnostic network for LIB temperature estimation by using an adaptive thinning algorithm combined with LSTM and time convolution network. Ding et al [95] developed a metathermal runaway forecasting neural network for LIB.…”

Section: A) Overheating Diagnosticmentioning

confidence: 99%

Multilevel Data-Driven Battery Management: From Internal Sensing to Big Data Utilization

Wei,

Liu,

Liu

et al. 2023

IEEE Trans. Transp. Electrific.

View full text Add to dashboard Cite

Battery management system (BMS) is essential for the safety and longevity of lithium-ion battery (LIB) utilization. With the rapid development of new sensing techniques, artificial intelligence and the availability of huge amounts of battery operational data, data-driven battery management has attracted ever-widening attention as a promising solution. This review article overviews the recent progress and future trend of datadriven battery management from a multi-level perspective. The widely-explored data-driven methods relying on routine measurements of current, voltage, and surface temperature are reviewed first. Within a deeper understanding and at the microscopic level, emerging management strategies with multidimensional battery data assisted by new sensing techniques have been reviewed. Enabled by the fast growth of big data technologies and platforms, the efficient use of battery big data for enhanced battery management is further overviewed. This belongs to the upper and the macroscopic level of the data-driven BMS framework. With this endeavor, we aim to motivate new insights into the future development of next-generation data-driven battery management.

show abstract

“…Emerging techniques, such as transfer learning and self-supervised learning, are applied to lithium battery RUL prediction to provide better prediction performance with limited data [17]. Various deep learning models, such as convolutional neural network (CNN), and recurrent neural network [18], long short-term memory network (LSTM) [19], and transformer [20], are utilized to learn the complex relationship between battery state and RUL. Deep learning models require a large amount of data for training and lithium batteries usually take a long time to test, therefore, the research also includes effective model training and optimization strategies to reduce training time and improve the generalization ability of the models [21].…”

Section: Introductionmentioning

confidence: 99%

Remaining useful life prediction of lithium-ion batteries using EM-PF-SSA-SVR with gamma stochastic process

Keshun,

Guangqi,

Yingkui

2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Due to the complex changes in physicochemical properties of lithium-ion batteries during the process from degradation to failure, it is difficult for methods based on physical or data-driven models to fully characterize this nonlinear process, and existing methods that hybridize physical and data-driven models suffer from ambiguous hybridization, which results in the vast majority of existing methods for predicting the RUL of lithium-ion batteries suffering from a lack of accuracy and robustness. In this study, a novel hybrid approach based on empirical modeling and data-driven techniques is proposed for predicting the remaining useful life (RUL) of lithium-ion batteries. To better capture its complexity, stochasticity, and state transition, and improve the modeling accuracy and RUL prediction precision, Gamma stochasticity and state-space modeling are used to empirically model the complex Li-ion battery degradation process. Moreover, the expectation maximization (EM) method of particle filtering (PF) was used to estimate the hidden parameters of the empirical model, and the estimated parameters were corrected using an optimized support vector regression (SVR) method to enhance the generalization performance and robustness of the data-driven model. The results show that the gamma state-space model is effective in capturing the inherent stochastic properties of the battery degradation and the proposed hybrid method outperforms the existing prediction methods in RUL prediction. The experiments show that the Sparrow Search Algorithm (SSA) optimized SVR is considered to be the most effective correction method for the estimated parameters, while the new EM-PF-SSA-SVR hybrid method provides better performance for state assessment and RUL prediction of lithium-ion batteries. It is indicated that the proposed EM-PF-SSA-SVR method with Gamma stochastic process has hybrid validity and superior performance with equal performance and less parameter computation relative to the existing state-of-the-art deep learning RUL prediction methods.

show abstract

STTEWS: A sequential-transformer thermal early warning system for lithium-ion battery safety

Cited by 15 publications

References 37 publications

Comprehensive battery monitoring and warning system based on hierarchical temporal convolutional network (HTCN)

Comprehensive battery monitoring and warning system based on hierarchical temporal convolutional network (HTCN)

Multilevel Data-Driven Battery Management: From Internal Sensing to Big Data Utilization

Remaining useful life prediction of lithium-ion batteries using EM-PF-SSA-SVR with gamma stochastic process

Contact Info

Product

Resources

About