Online diagnosis of state of health for lithium-ion batteries based on short-term charging profiles

et al. 2021

Energy

Self Cite

Accurate state of charge estimation is essential to improve operation safety and service life of lithiumion batteries. This paper proposes a synthetic state of charge estimation method for lithium-ion batteries based on long short-term memory network modeling and adaptive H-infinity filter. Firstly, the long short-term memory network is exploited to roughly estimate state of charge with the input of voltage, current, operating temperature and state of health. Then, to mitigate the output fluctuation and improve the estimation robustness of long shortterm memory network, the adaptive H-infinity filter is employed to flatten the estimation results and further improve the estimation accuracy. A main advantage of the proposed synthetic method lies in that precise battery modeling and burdensome model parameter identification tasks that are imperative in traditional observers or filters can be omitted, thus improving the application efficiency of the proposed algorithm. The proposed method is verified effective on two types of lithium-ion batteries under dynamic working scenarios including the varying temperature and aged conditions. The experimental results highlight that the estimation error of state of charge can be restricted within 2.1% in wide temperature range and different aging states, manifesting its high-precision estimation capacity and strong robustness.

Section: B Synthetic Soc Estimation Methodsmentioning

confidence: 99%

Synthetic state of charge estimation for lithium-ion batteries based on long short-term memory network modeling and adaptive H-Infinity filter

Chen

Zhao

et al. 2021

Energy

Self Cite

“…Battery SOH represents the ratio of maximum discharging capacity over the rated value [8]. Generally, the prediction methods of SOH can be sorted into three groups: direct calibration methods, filter-based methods and machine learning-based methods [9]. Direct calibration methods determine battery SOH via specific experimental operations, such as full discharge of the battery after a complete charge [10].…”

Section: Introductionmentioning

confidence: 99%

A Flexible State-of-Health Prediction Scheme for Lithium-Ion Battery Packs With Long Short-Term Memory Network and Transfer Learning

IEEE Trans. Transp. Electrific.

Shen

et al. 2021

Self Cite

113

The application of machine learning-based state of health (SOH) prediction is hindered by large demand of training data. To conquer this defect, a flexible and easy transferred SOH prediction scheme for lithium-ion battery packs is developed. Firstly, the charging duration for a predefined voltage range is hired as the health feature to quantify capacity degradation. Then, the long short-term memory (LSTM) network and transfer learning (TL) with fine-tuning strategy are incorporated to constitute the cell mean model (CMM) for SOH prediction with partial training data. Next, to evaluate the SOH inconsistencies among cells, the LSTM model is employed as the cell difference model (CDM), and the minimum estimation value of CDM is identified to determine pack SOH. The experimental results reveal that even when the first 360 cycle data, occupying only 40% in the whole 904 cycle data, are chosen and constituted to the dataset for model training, the obtained estimation algorithm can still predict SOH precisely with the error of less than 3%, thus remarkably reducing the training data amount and mitigating the computation burden during model training. In addition, the preferable validation results on different types of lithium-ion batteries further manifest the extendibility of the proposed strategy. Index Terms-Lithium-ion battery pack, long short-term memory (LSTM), transfer learning (TL), state of health (SOH).

“…Transportation electrification represents a promising solution to mitigate greenhouse gas (GHG) emission and environmental pollution; and this provides favorable opportunities for prompting development of electric vehicles (EVs) and electric-scooters (ESs) [1]. Lithium-ion batteries have been dominating the energy storage media of EVs and ESs [2], of which the energy storage systems are usually composed of hundreds to thousands of cells connected in specific topologies [3]. This leads to the increasing demand of designing effective high-performance battery management systems (BMS), of which one critical task is to conduct state of charge (SOC) estimation of batteries.…”

Section: Introductionmentioning

confidence: 99%

Stage of Charge Estimation of Lithium-Ion Battery Packs Based on Improved Cubature Kalman Filter With Long Short-Term Memory Model

IEEE Trans. Transp. Electrific.

Zhang

et al. 2021

Self Cite

Accurate estimation of state of charge (SOC) of lithium-ion battery packs remains challenging due to inconsistencies among battery cells. To achieve precise SOC estimation of battery packs, firstly, a long short-term memory (LSTM) recurrent neural network (RNN)-based model is constructed to characterize the battery electrical performance, and a rolling learning method is proposed to update the model parameters for improving the model accuracy. Then, an improved square root-cubature Kalman filter (SRCKF) is designed together with the multi-innovation technique to estimate battery cell's SOC. Next, to cope with inconsistencies among battery cells, the SOC estimation value from the maximum and minimum cells are combined with a smoothing method to estimate the pack SOC. The robustness and accuracy of the proposed battery model and cell SOC estimation method are verified by exerting the experimental validation under time-varying temperature conditions. Finally, real operation data are collected from an electric-scooter (ES) monitoring platform to further validate the generalization of the designed pack SOC estimation algorithm. The experimental results manifest that the SOC estimation error can be limited within 2% after convergence.