SoP Estimation based on Maximum Discharge Current using BiLSTM
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
An accurate SoC(state-of-charge) to estimate SoP(state-of-power) is the most remarkable technique for electric vehicles (EV). Hence, the estimation of battery state-of-charge prior to estimation of battery state-of-power requires more computation cost and time. This paper makes two contributions: (1) a data-driven SoP estimation method has been proposed to accurately capture the characteristics of the battery through the bidirectional long-short term memory algorithm, (2) the estimation of maximum discharge current based on voltage and SoC constraints using BiLSTM. The robustness of the proposed method has been verified by comparing the method with co-estimation and conventional method. The results show higher accuracy (approximately 24%) compared to the conventional state-of-power estimation method with 15.54 root-mean-square-error and faster computing time (approximately 66%) compared to co-estimation method with 2015 seconds calculation time, which made the proposed SoP estimation more efficient and reliable for the electric vehicles application.
Abstract
An accurate SoC(state-of-charge) to estimate SoP(state-of-power) is the most remarkable technique for electric vehicles (EV). Hence, the estimation of battery state-of-charge prior to estimation of battery state-of-power requires more computation cost and time. This paper makes two contributions: (1) a data-driven SoP estimation method has been proposed to accurately capture the characteristics of the battery through the bidirectional long-short term memory algorithm, (2) the estimation of maximum discharge current based on voltage and SoC constraints using BiLSTM. The robustness of the proposed method has been verified by comparing the method with co-estimation and conventional method. The results show higher accuracy (approximately 24%) compared to the conventional state-of-power estimation method with 15.54 root-mean-square-error and faster computing time (approximately 66%) compared to co-estimation method with 2015 seconds calculation time, which made the proposed SoP estimation more efficient and reliable for the electric vehicles application.
참고문헌 (17)
- F. Sun, "Model-based dynamic multi-parameter method for peak power estimation of lithiumion batteries", Appl. Energy, 96, pp.378~386 (2012)
- X. Liu, "An improved state of charge and state of power estimation method based on genetic particle filter for lithium-ion batteries", Energies, 13(2) (2020)
- C. Zhang, "A generalized SOC-OCV model for lithium-ion batteries and the SOC estimation for LNMCO battery", Energies, 9(11) (2016)
- Z. Yu, "State-of-charge estimation for lithium-ion batteries using a Kalman filter based on local linearization", Energies, 8(8), pp.7854~7873 (2015)
- 최수봉, "딥러닝 모델을 사용한 게임 봇 탐지 시스템에서 판단 근거 분석을 위한 기법", 한국차세대컴퓨팅학회 논문지, 16(3), pp.7~15 (2020), 한국차세대컴퓨팅학회[DOI]
- J. Guo, "ARIMA-based road gradient and vehicle velocity prediction for hybrid electric vehicle energy management", IEEE Trans. Veh. Technol, 68(6), pp.5309~5320 (2019)
- P. Shen, "The co-estimation of state of charge, state of health, and state of function for lithium-ion batteries in electric vehicles", IEEE Trans. Veh. Technol, 67(1), pp.92~103 (2018)
- H. He, "State-of-charge estimation of the lithium-ion battery using an adaptive extended Kalman filter based on an improved Thevenin model", IEEE Trans. Veh. Technol, 60(4), pp.1461~1469 (2011)
- 윤예진, "회귀 분석을 이용한 Intel SGX 상의 안전한 전력 수요 예측", 한국차세대컴퓨팅학회 논문지, 13(4), pp.7~18 (2017), 한국차세대컴퓨팅학회
- 손남례, "발전변동량을 고려한 SVR기반 제주도지역의단기풍력발전량예측", 한국차세대컴퓨팅학회 논문지, 14(2), pp.7~15 (2018), 한국차세대컴퓨팅학회
- W. J. Jiang, "A Temperature-Based Peak Power Capability Estimation Method for Lithium-Ion Batteries", Procedia Eng, 187, pp.249~256 (2017)
- K. L. Muh, "Estimation of State-of-Power for Li-ion Battery", Korea Institute Of Communication Sciences, 362, pp.106~107 (2019)
- R. Xiong, "A data-driven adaptive state of charge and power capability joint estimator of lithiumion polymer battery used in electric vehicles", Energy, 63, pp.295~308 (2013)
- W. Wang, "Unscented kalman filter-based battery SOC estimation and peak power prediction method for power distribution of hybrid electric vehicles", IEEE Access, 6, pp.35957~35965 (2018)
- J. Xie, "Self-Attention-Based BiLSTM Model for Short Text Fine-Grained Sentiment Classification", IEEE Access, 7, pp.180558~180570 (2019)
- Y. Dong, "A sentiment analysis method of capsule network based on BiLSTM", IEEE Access, 8, pp.37014~37020 (2020)
- S. Eger, "Is it time to swish? Comparing Deep Learning Activation Functions across NLP tasks", Proc. 2018 Conf. Empir. Methods Nat. Lang. Process. EMNLP 2018, pp.4415~4424 (2020)