Multi-model deep learning-based state of charge estimation for shipboard lithium batteries with feature extraction and Spatio-temporal dependency
Source abstract
Abstract
The state of charge (SOC) is a key indicator for measuring the remaining battery capacity. However, the different charging and discharging behaviors, as well as the topology connections, may lead to undesirable estimation errors, affecting the battery output performance. This paper proposes a novel method to estimate the SOC of shipboard lithium batteries. This method combines spatial-temporal graph convolutional networks (STGCNs) with Transformer deep learning networks. Furthermore, the STGCN is utilized to construct graph structures, simulating the complex interconnectivity of battery energy storage systems. The Transformer is used for estimating the SOC sequence windows. Additionally, a recurrent neural network is employed as an additional encoder and decoder architecture to enhance multiscale time series processing and capture the nonlinear battery characteristics to reduce fluctuations in the SOC. A principal component analysis is used to eliminate redundant battery features to improve the computational efficiency of the estimation model further. The experimental results indicate that the proposed deep learning network model can effectively estimate the SOC of shipboard lithium batteries with high accuracy and stability.
Source: expertdata · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Advanced Battery Technologies Research · Advancements in Battery Materials · Advanced Battery Materials and Technologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (38)
Show source-provided references
1. Decarbonising inland ship power system: alternative solution and assessment method10.1016/j.energy.2021.120266 ↗
2. All-electric ship operations and management: Overview and future research directions10.1016/j.etran.2023.100251 ↗
3. Intelligent control for rapidity and security of all-electric ships gas turbine under complex mutation load using optimized neural network10.1016/j.applthermaleng.2024.123120 ↗
4. A probabilistic risk-averse approach for energy storage sizing in all-electric ship10.1016/j.est.2022.105392 ↗
5. An online SOC and capacity estimation method for aged lithium-ion battery pack considering cell inconsistency10.1016/j.est.2020.101250 ↗
6. State-of-Charge (SOC)-Balancing control of a battery energy storage system based on a cascade PWM converter10.1109/TPEL.2009.2014868 ↗
7. Lithium-ion battery state-of-charge estimation for small target sample sets using the improved GRU-based transfer learning10.1016/j.energy.2022.123178 ↗
8. Co-estimation of state of charge and capacity for lithium-ion batteries with multi-stage model fusion method10.1016/j.eng.2020.10.022 ↗
9. Time-efficient identification of lithium-ion battery temperature-dependent OCV-SOC curve using multi-output Gaussian process10.1016/j.energy.2023.126724 ↗
10. Differential current in constant-voltage charging mode: a novel tool for state-of-health and state-of-charge estimation of lithium-ion batteries10.1016/j.energy.2023.129826 ↗
11. Electric vehicle battery state of health estimation using Incremental Capacity Analysis10.1016/j.est.2023.107110 ↗
12. State of health and remaining useful life prediction of lithium-ion batteries based on a disturbance-free incremental capacity and differential voltage analysis method10.1016/j.est.2023.107161 ↗
13. Open circuit voltage and state of charge online estimation for lithium ion batteries10.1016/j.egypro.2017.12.388 ↗
14. Efficient estimation of state of charge of lithium-ion batteries10.1016/j.measurement.2023.114026 ↗
15. Modelling of modular battery systems under cell capacity variation and degradation10.1016/j.apenergy.2020.116360 ↗
16. New method for acquisition of impedance spectra from charge/discharge curves of lithium-ion batteries10.1016/j.jpowsour.2022.231483 ↗
17. Lithium-ion battery SOC/SOH adaptive estimation via simplified single particle model10.1002/er.5374 ↗
18. System identification and state estimation of a reduced-order electrochemical model for lithium-ion batteries10.1016/j.etran.2023.100295 ↗
19. Electrochemical modeling and parameterization towards control-oriented management of lithium-ion batteries10.1016/j.conengprac.2022.105176 ↗
20. Development of equivalent circuit model for thermal runaway in lithium-ion batteries10.1016/j.est.2023.109318 ↗
21. An intelligent fusion estimation method for state of charge estimation of lithium-ion batteries10.1016/j.energy.2023.129462 ↗
22. State of charge estimation method based on linearization of voltage hysteresis curve10.1016/j.est.2023.108481 ↗
23. State-space modeling for electrochemical performance of Li-ion batteries with physics-informed deep operator networks10.1016/j.est.2023.109244 ↗
24. Lithium-ion battery ageing behavior pattern characterization and state-of-health estimation using data-driven method10.1109/ACCESS.2021.3092743 ↗
25. State-of-charge estimation of lithium-ion battery using an improved neural network model and extended Kalman filter10.1016/j.jclepro.2019.06.273 ↗
26. Predicting the state of charge and health of batteries using data-driven machine learning10.1038/s42256-020-0156-7 ↗
27. Deep learning framework for lithium-ion battery state of charge estimation: recent advances and future perspectives
28. Influence of the connection topology on the performance of lithium-ion battery pack under cell-to-cell parameters variations10.1016/j.est.2021.102896 ↗
29. Experimental analysis of lithium-ion cell procurement: quality differences, correlations, and importance of cell characterization10.1016/j.est.2023.107430 ↗
30. A framework for joint SOC and SOH estimation of lithium-ion battery: eliminating the dependency on initial states
31. Vaswani
32. End to end multi-task learning with attention for multi-objective fault diagnosis under small sample10.1016/j.jmsy.2021.12.003 ↗
33. Kipf · 2017
34. MVMA-GCN: multi-view multi-layer attention graph convolutional networks10.1016/j.engappai.2023.106717 ↗
35. Rethinking the ST-GCNs for 3D skeleton-based human action recognition10.1016/j.neucom.2021.05.004 ↗
36. DRAW: a recurrent neural network for image generation
37. Dynamic multiobjective optimization with varying number of objectives assisted by dynamic principal component analysis10.1016/j.ins.2024.120398 ↗
38. An a priori analysis on principal component analysis based conditional source-term estimation model for Sandia jet flames10.1016/j.combustflame.2023.113274 ↗