Remaining useful life (RUL) prediction of lithium-ion batteries can assess the battery reliability to determine the advent of failure and mitigate battery risk. The existing RUL prediction techniques for lithium-ion batteries are inefficient for learning the long-term dependencies among the capacity degradations. This paper investigates deep-learning-enabled battery RUL prediction. The long short-term memory (LSTM) recurrent neural network (RNN) is employed to learn the long-term dependencies among the degraded capacities of lithium-ion batteries. The LSTM RNN is adaptively optimized using the resilient mean square back-propagation method, and a dropout technique is used to address the overfitting problem. The developed LSTM RNN is able to capture the underlying long-term dependencies among the degraded capacities and construct an explicitly capacity-oriented RUL predictor, whose long-term learning performance is contrasted to the support vector machine model, the particle filter model, and the simple RNN model. Monte Carlo simulation is combined to generate a probabilistic RUL prediction. Experimental data from multiple lithium-ion cells at two different temperatures are deployed for model construction, verification, and comparison. The developed method is able to predict the battery's RUL independent of offline training data, and when some offline data is available, the RUL can be predicted earlier than in the traditional methods.

This paper developed an effective health indicator to indicate lithium-ion battery state of health and moving-window-based method to predict battery remaining useful life. The health indicator was extracted based on the partial charge voltage curve of cells. Battery remaining useful life was predicted using a linear aging model constructed based on the capacity data within a moving window, combined with Monte Carlo simulation to generate prediction uncertainties. Both the developed capacity estimation and remaining useful life prediction methods were implemented based on a real battery management system used in electric vehicles. Experimental data for cells tested at different current rates, including 1 and 2 C, and different temperatures, including 25 and 40 °C, were collected and used. The implementation results show that the capacity estimation errors were within 1.5%. During the last 20% of battery lifetime, the root-mean-square errors of remaining useful life predictions were within 20 cycles, and the 95% confidence intervals mainly cover about 20 cycles.

The OHC shows superior performance as an anode material for LIBs with a high reversible capacity (1181 mA h g ⁻¹ at 0.1 A g ⁻¹ ) and an excellent rate capability (304 mA h g ⁻¹ at 5 A g ⁻¹ ).

In order for the battery management system (BMS) in an electric vehicle to function properly, accurate and robust indication of the energy state of the lithium-ion batteries is necessary. This robustness requires that the energy state can be estimated accurately even when the working conditions of batteries change dramatically. This paper implements battery remaining available energy prediction and state-of-charge (SOC) estimation against testing temperature uncertainties, as well as inaccurate initial SOC values. A double-scale particle filtering method has been developed to estimate or predict the system state and parameters on two different time scales. The developed method considers the slow time-varying characteristics of the battery parameter set and the quick time-varying characteristics of the battery state set. In order to select the preferred battery model, the Akaike information criterion (AIC) is used to make a tradeoff between the model prediction accuracy and complexity. To validate the developed double-scale particle filtering method, two different kinds of lithium-ion batteries were tested at three temperatures. The experimental results show that, with 20% initial SOC deviation, the maximum remaining available energy prediction and SOC estimation errors are both within 2%, even when the wrong temperature is indicated. In this case, the developed double-scale particle filtering method is expected to be robust in practice.

The current lithium-ion battery remaining useful life (RUL) prediction techniques are mainly developed dependent on offline training data. The loaded current, temperature, and state of charge of lithium-ion batteries used for electric vehicles (EVs) change dramatically under the working conditions. Therefore, it is difficult to design acceleration aging tests of lithium-ion batteries under similar working conditions as those for EVs and to collect effective offline training data. To address this problem, this paper developed an RUL prediction method based on the Box-Cox transformation (BCT) and Monte Carlo (MC) simulation. This method can be implemented independent of offline training data. In the method, the BCT was used to transform the available capacity data and to construct a linear model between the transformed capacities and cycles. The constructed linear model using the BCT was extrapolated to predict the battery RUL, and the RUL prediction uncertainties were generated using the MC simulation. Experimental results showed that accurate and precise RULs were predicted with errors and standard deviations within, respectively, [-20, 10] cycles and [1.8, 7] cycles. If some offline training data are available, the method can reduce the required online training data and, thus, the acceleration aging test time of lithium-ion batteries. Experimental results showed that the acceleration time of the tested cells can be reduced by 70%-85% based on the developed method, which saved one to three months' acceleration test time compared to the particle filter method.

An adaptive H infinity filter approach is proposed to estimate the multistates including state of charge (SOC) and state of energy (SOE) for a lithium-ion battery pack. In the proposed approach, the covariance matching technique is used to adaptively update the covariance of system and observation noises and the recursive least square method is used to identify the battery model parameters in real time. The hardware-in-the-loop (HIL) platform for battery charge/discharge is set up to evaluate the accuracy and robustness of the SOC and the SOE estimation and compare the proposed approach with the multistate estimators using an extended Kalman filter and an H infinity filter. The experimental results indicate that the adaptive H infinity filter-based estimator is able to estimate the battery states in real time with the highest accuracy among the three filters.