Life Prediction Of Lithium-ion Batteries Research Articles

Remaining Useful Life Prediction for Lithium-Ion Batteries Based on the Partial Voltage and Temperature

Remaining useful life (RUL) prediction is vital to provide accurate decision support for a safe power system. In order to solve capacity measurement difficulties and provide a precise and credible RUL prediction for lithium-ion batteries, two health indicators (HIs), the discharging voltage difference of an equal time interval (DVDETI) and the discharging temperature difference of an equal time interval (DTDETI), are extracted from the partial discharging voltage and temperature. Box-Cox transformation, which is data processing, is used to improve the relation grade of HIs. In addition, the Pearson correlation is employed to evaluate the relationship degree between HIs and capacity. On this basis, a local Gaussian function and a global sigmoid function are utilized to improve the multi-kernel relevance vector machine (MKRVM), whose weights are optimized by applying a whale optimization algorithm (WOA). The availability of the extracted HIs as well as the accuracy of the RUL prediction are verified with the battery data from NASA.

Remaining useful life prediction of Lithium-ion batteries based on PSO-RF algorithm

Accurately predicting the Remaining Useful Life (RUL) of lithium-ion batteries is the key to the battery health management system. However, problems of unstable model output and extensive calculation limit the prediction accuracy. This article proposes a Particle Swarm Optimization Random Forest (PSO-RF) prediction method to improve the RUL prediction accuracy. First, the battery capacity extracted from the lithium-ion battery data set of the National Aeronautics and Space Administration (NASA) and the University of Maryland Center for Advanced Life Cycle Engineering (CALCE) is set as the battery life health factor. Then, a PSO-RF prediction model is established based on the optimal parameters for the number of trees and the number of random features to split by the PSO algorithm. Finally, the experiment is verified on the NASA and CALCE data sets. The experiment results indicate that the method predicts RUL with Mean Absolute Error (MAE) less than 2%, Root Mean Square Error (RMSE) less than 3%, and goodness of fit greater than 94%. This method solves the problem of parameter selection in the RF algorithm.

Remaining Useful Life Prediction of Lithium-Ion Batteries Based on Data Preprocessing and Improved ELM

Accurate prediction of the remaining useful life (RUL) of lithium-ion batteries (LIBs) can provide an important reference for the safe operation of LIBs. At present, there are some problems in the prediction of RUL of LIBs, such as redundancy or deficiency of characteristic parameters, local regeneration in degradation characteristics, and poor stability of single model prediction. In this paper, an RUL prediction method combining kernel principal component analysis (KPCA), improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN), whale optimization algorithm (WOA), and extreme learning machine (ELM) is proposed. Firstly, in the data preprocessing stage, the KPCA method is used to reduce the dimension of the extracted indirect health indicators (HI), and then the ICEEMDAN algorithm is introduced to eliminate the local regeneration phenomenon in the fusion HI sequence. Secondly, in the model construction stage, a capacity prediction model based on WOA-ELM and a fusion HI prediction model are built to predict the intrinsic mode functions (IMF) components of the fusion HI sequence. The prediction results are superimposed and then input into the capacity prediction model to realize RUL indirect prediction. Finally, the proposed method is verified by using NASA battery degradation data sets at different temperatures and experimental environments. The results show that the RUL prediction accuracy of the proposed method is greatly improved, and it has good stability and robustness.

Remaining Useful Life Prediction for Lithium-Ion Batteries Based on Improved Variational Mode Decomposition and Machine Learning Algorithm

Remaining useful life (RUL) prediction of batteries is important for the health management and safety evaluation of lithium-ion batteries. Because lithium-ion batteries have capacity recovery and noise interference during actual use, direct use of measured capacity data to predict their RUL generalization ability is not efficient. Aimed at the above problems, this paper proposes an integrated life prediction method for lithium-ion batteries by combining improved variational mode decomposition (VMD) with a long short-term memory network (LSTM) and Gaussian process regression algorithm (GPR). First, the VMD algorithm decomposed the measured capacity dataset of the lithium-ion battery into a residual component and capacity regeneration component, in which the penalty factor α and mode number K in the VMD algorithm were optimized by the whale optimization algorithm (WOA). Second, the LSTM and GPR models were established to predict the residual component and capacity regeneration components, respectively. Last, the predicted components are integrated to obtain the final predicted lithium-ion battery capacity. The experimental results show that the mean absolute error (MAE) and root mean square error (RMSE) of the proposed lithium-ion battery capacity prediction model are less than 0.5% and 0.8%, respectively, and the method outperforms the five compared algorithms and several recently proposed hybrid algorithms in terms of prediction accuracy.

State of health and remaining useful life prediction for lithium-ion batteries based on differential thermal voltammetry and a long and short memory neural network

State of health and remaining useful life prediction for lithium-ion batteries based on differential thermal voltammetry and a long and short memory neural network

Data driven discovery of an analytic formula for the life prediction of Lithium-ion batteries

Predicting the cycle life of Lithium-Ion Batteries (LIBs) remains a great challenge due to their complicated degradation mechanisms. The present work employs an interpretative machine learning of symbolic regression (SR) to discover an analytic formula for LIB life prediction with newly defined features. The novel features are based on the discharging energies under the constant-current (CC) and constant-voltage (CV) modes at every five cycles alternately. The cycle life is affected by the CC-discharging energy at the 15th cycle (E15−CCD) and the difference between the CC-discharging energies at the 45th cycle and 95th cycle (Δ45−95). The cycle life highly correlates with a simple indicator (E15−CCD−3)/Δ45−95 with a Pearson correlation coefficient of 0.957. The machine learning tools provide a rapid and accurate prediction of cycle life at the early stage.

A Bayesian Mixture Neural Network for Remaining Useful Life Prediction of Lithium-Ion Batteries

Remaining useful life (RUL) is one of the essential ingredients in the battery management system. However, due to the characteristic of the dynamic and time-varying electrochemical system with nonlinear and complicated internal mechanisms, the uncertainty of RUL estimation has been expanded, and it is difficult to give an accurate time to reach the end of life. This article proposes the Bayesian mixture neural network (BMNN), a probabilistic deep learning method, to obtain more accurate RUL prediction and provide uncertainty estimation, while the quasi-Gramian angular field (Q-GAF) beneficial to identify prior distribution is utilized to transform time-series sequence into temporal images. BMNN consists of the Bayesian convolutional neural network (BCNN) extracting features in temporal images and Bayesian long short-term memory (B-LSTM) learning correlation between retention capacity and other degradation inducements. After concatenating two terms, the variational Bayesian neural network outputs the distribution of prediction results. In the experimental stage, the performance of the proposed method is validated on four different lithium-ion battery datasets and demonstrates higher stability, lower uncertainty, and more accuracy than other methods.

An Improved Weighting Coefficient Optimization-Particle Filtering Algorithm Based on Gaussian Degradation Model for Remaining Useful Life Prediction of Lithium-ion Batteries

Establishing a capacity degradation model accurately and predicting the remaining useful life of lithium-ion batteries scientifically are of great significance for ensuring safety and reliability throughout the batteries’ whole life cycle. Aiming at the problems of “particle degradation” and “sample poverty” in traditional particle filtering, an improved weighting coefficient optimization - particle filtering algorithm based on a new Gaussian degradation model for the remaining useful life prediction is proposed in this research. The main idea of the algorithm is to weight the selected particles, sort them according to the particle weights, and then select the particles with relatively large weights to estimate the filtering density, thereby improving the filtering accuracy and enhancing the tracking ability. The experimental verification results under the National Aeronautics and Space Administration data show that the improved weighting coefficient optimization - particle filtering algorithm based on the Gaussian degradation model has significantly improved accuracy in predicting the remaining useful life of lithium-ion batteries. The RMSE of the B05 battery can be controlled within 1.40% and 1.17% at the prediction starting point of 40 cycles and 70 cycles respectively, and the RMSE of the B06 battery can be controlled within 2.45% and 1.93% at the prediction starting point of 40 cycles and 70 cycles respectively. It can be seen that the algorithm proposed in this study has strong traceability and convergence ability, which is important for the development of high-reliability battery management systems.

Particle swarm optimized data-driven model for remaining useful life prediction of lithium-ion batteries by systematic sampling

The remaining useful life (RUL) is considered an important health indicator in lithium-ion batteries for evaluating various features such as efficiency, robustness, and accuracy. The RUL investigates the battery reliability for determining the advent of failure and further mitigating battery risk. The effective RUL prediction of a lithium-ion battery can ensure safe operation, avoid internal, external failures, and unwanted catastrophic occurrences. However, the accomplishment of accurate RUL prediction is difficult due to the occurrence of capacity degradation and performance deviation with temperature and aging impacts. Hence, this paper delivers an improved hybrid data-driven model comprising recurrent neural network (RNN) and particle swarm optimization (PSO). A systematic sampling technique is employed to construct a 31-dimensional multi-channel input data framework. Various parameters from NASA battery datasets such as charging profile voltage, temperature, current, and discharge capacity are selected as suitable health indicators to generate a 31-dimensional input framework for RNN-PSO model training. Furthermore, the validation of the presented framework is carried out with other optimized data-driven models and MIT Stanford battery datasets. Compared with other optimized data-driven models, the experimentation conducted with NASA and MIT Stanford battery datasets demonstrates that RNN-PSO delivers higher prediction accuracy with mean square error at 3.7719 × 10−8 for battery B5 and 2.9759 × 10−8 for c33. The results prove the effectiveness of the proposed RNN-PSO model for the RUL prediction of lithium-ion batteries on different battery datasets.

Improved anti-noise adaptive long short-term memory neural network modeling for the robust remaining useful life prediction of lithium-ion batteries

Safety assurance is essential for lithium-ion batteries in power supply fields, and the remaining useful life (RUL) prediction serves as one of the fundamental criteria for the performance evaluation of energy and storage systems. Based on an improved dual closed-loop observation modeling strategy, an improved anti-noise adaptive long short-term memory (ANA-LSTM) neural network with high-robustness feature extraction and optimal parameter characterization is proposed for accurate RUL prediction. Then, an adaptive state parameter feedback correction strategy is constructed through multiple feature collaboration with its internal coupling mechanism characterization, which considers varying current rates, ambient temperatures, and other influencing parameters. Subsequently, a collaborative multi-parameter optimization is carried out along with the model training and meta-structure fine-tuning. Compared with other optimal existing methods, the maximum root mean square error decreases by 51.80%, the mean absolute error reduces by 26.95%, the maximum mean absolute percentage error decreases by 33.87%, and the R-squared increases by 4.11%. The established multiple-feature collaboration model realizes multi-scale parameter optimization and robust RUL prediction, thus advancing the industrial application of lithium-ion batteries.

A novel deep learning-based life prediction method for lithium-ion batteries with strong generalization capability under multiple cycle profiles

Life prediction of lithium-ion batteries is vital for battery system utilization and maintenance. Especially, the accurate life prediction in early cycles can accelerate the battery design, production, and optimization. However, diverse aging mechanisms, various cycle profiles, and negligible capacity degradation in the early cycling stages pose significant challenges. This paper proposes a novel deep learning-based life prediction method for lithium-ion batteries with strong generalization capability under multiple cycle profiles, where the battery lifetime model is formulated by a two-dimensional and one-dimensional parallel hybrid neural network. Firstly, the input data is constructed by a five-step streamlined preprocessing approach. Secondly, two-dimensional and one-dimensional convolutional neural networks are respectively used to extract the underlying associations between the data. Then, the long short-term memory network is employed to learn the time-sequential relationships among the extracted features. Ultimately, the diagnosis for the current cycle life and the prognostic on the remaining useful life of the battery are performed. A well-known dataset is utilized to validate the accuracy and generalization performance of the proposed method. Comparison results with other methods show that the proposed model has strong generalization capability. For the test set composed of data from 31 cells under 25 different cycle profiles, its mean absolute percentage error in early lifetime prediction and remaining useful life prediction is merely 1.47% and 2.85%.

Remaining useful life prediction of lithium-ion batteries based on attention mechanism and bidirectional long short-term memory network

Accurate prediction of the remaining useful life of lithium-ion batteries is beneficial to prolong the battery's life and increase safety. However, there is insufficient historical data available because of the limitation of charge and discharge cycles of lithium-ion batteries. To enhance the prediction accuracy, a hybrid model based on an attention mechanism and a bidirectional long short-term memory network is proposed, which can acquire good prediction results with early data of the target battery. Multiple temporal features, which strongly correlate with the capacity considered the main feature of battery health, are used as input to train and test the proposed model. The attention mechanism is added in the bidirectional long short-term memory network to precisely decide the attention distribution of multiple features to extract useful information. It helps the bidirectional long short-term memory networks to make a better prognosis and overcome the vanishing and exploding gradient problems. The experimental results show that the proposed framework can decrease the uncertainty for multi-step prediction and outperforms other machine learning models in prediction accuracy.

An Adaptive Noise Reduction Approach for Remaining Useful Life Prediction of Lithium-Ion Batteries

Lithium-ion batteries are widely used in the electric vehicle industry due to their recyclability and long life. However, a failure of lithium-ion batteries can cause some catastrophic accidents, such as electric car battery explosion fires and so on. To prevent such harm from occurring, it is essential to monitor the remaining useful life of lithium-ion batteries and give early warning. In this paper, an adaptive noise reduction approach is proposed to predict the RUL (Remaining Useful Life) of lithium-ion batteries, which uses CEEMDAN (Complete Ensemble Empirical Mode Decomposition with Adaptive Noise) combined with wavelet decomposition to achieve adaptive noise reduction decomposition, and then inputs the obtained IMF (Intrinsic Mode Function) components into LS–RVM (Least Square Relevance Vector Machine) for training, prediction, and reconstruction, so as to achieve high-precision prediction of RUL. Moreover, in order to verify the validity of the model, the model in this paper is compared with other common models. The results demonstrate that the RMSE, MAPE, and MAE of the proposed model are 0.008678, 0.005002, and 0.006894, and that it has higher accuracy than the other common prediction models.

Lithium-Ion Battery Degradation and Capacity Prediction Model Considering Causal Feature

Accurate life prediction of lithium-ion batteries is essential for the safety and reliability of smart electronic devices, and data-driven methods are one of the mainstream methods nowadays. However, existing prediction methods suffer from the problems such as lack of practical meaning of features and insufficient interpretability. To address this problem, this article proposes a battery degradation and capacity prediction model based on the Granger causality (GC) test and the long short-term memory network. First, initial health indicators are set from the monitoring data of the battery. Second, the vector autoregressive model and the GC test are used to select causal features that are associated with capacity degradation. Then, the impulse response analysis approach is proposed for the first time to analyze the exact influence of the features on capacity degradation and combine the battery aging mechanism, further clarifying the interpretability of the selected features. Finally, using the causal features as model input, a prediction model based on the long short-term memory network is constructed. The experimental results of the two datasets show that the minimum root mean square error is 0.0093 Ah and 0.9635 mAh with the mean relative errors of 0.25% and 0.13%, which verifies the validity and accuracy of the proposed method.

Remaining useful cycle life prediction of lithium-ion battery based on TS fuzzy model

Accurately predicting the remaining useful cycle life of a lithium-ion battery is essential for health management of battery systems. Aiming at the time-varying and nonlinear problems of lithium-ion batteries, a remaining useful cycle life estimation method based on Takagi-Sugeno fuzzy model is proposed, which not only reduces the amount of data calculation, but also reduces massive data and has high accuracy. First, collect the rate of change of working voltage in the charging process, and analyze the relationship between the position of voltage rate curve and the number of cycles. Second, in order to reduce the amount of historical data, the interval with obvious mapping relationship is selected, and the recursive least square method is used to fit the curve off-line, which reduces the amount of data calculation and is easy to achieve in battery management system engineering. And then, the Takagi-Sugeno fuzzy model is applied to establish the remaining useful cycle life method based on Takagi-Sugeno fuzzy model. Finally, battery management system application shows that the proposed method can achieve high prediction accuracy and also provides a new perspective for remaining useful cycle life prediction.

Remaining useful life prediction of lithium-ion batteries based on wavelet denoising and transformer neural network

It is imperative to accurately predict the remaining useful life (RUL) of lithium-ion batteries to ensure the reliability and safety of related industries and facilities. In view of the noise sequence embedded in the measured aging data of lithium-ion batteries and the strong nonlinear characteristics of the aging process, this study proposes a method for predicting lithium-ion batteries’ RUL based on the wavelet threshold denoising and transformer model. To specify, firstly, the wavelet threshold denoising method is adopted to preprocess the measured discharging capacity data of lithium-ion batteries to eliminate some noise signals. Second, based on the denoised data, the transformer model output’s full connection layer is applied to replace the decoder layer for establishing the RUL prediction model of lithium-ion batteries. Finally, the discharging capacity of each charging–discharging cycle is predicted iteratively, and then the RUL of lithium-ion batteries can be calculated eventually. Two groups of lithium-ion batteries’ aging data from the Center for Advanced Life Cycle Engineering (CALCE) at the University of Maryland and the laboratory at Anqing Normal University (AQNU) are employed to verify the proposed method, individually. The experimental results demonstrate that this method can overcome the impacts of data measurement noise, effectively predict the RUL of lithium-ion batteries, and present a sound generalization ability and high accuracy.

Remaining useful life prediction for lithium-ion batteries in later period based on a fusion model

Lithium-ion batteries are broadly used in many fields. Accurate remaining useful life (RUL) prediction ensures the reliable operation and the safety of battery systems. However, no single model can realize long-term prediction for RUL with the reliable uncertainty management in the later period. To this end, a competitive model based on an improved autoregressive (AR) and particle filter (PF) model is proposed. Specifically, the similarity capacity series is creatively employed in the AR model, while the underlying capacity is introduced as a new approach for the parameter estimation of the observation equation in PF. Then, average weight is used to update the state equation and describe the future system states. After that, the RUL and its probability density function are obtained by PF again. The effectiveness and robustness are verified by the National Aeronautics and Space Administration (NASA) dataset. Results illustrate that the fusion model outperforms others and accurately predicts RUL with narrow uncertainty representation in the later period.

Remaining useful life prediction of Lithium-ion battery using improved support vector regression and fuzzy information granulation

With the widespread use of lithium-ion batteries in various fields, battery Prognostics and Health Management (PHM) technologies are gaining more and more attention. Repeated use of batteries can lead to degradation of battery performance and thus affect battery life. Accurate prediction of the remaining useful life (RUL) of batteries is crucial and is the most central issue in battery PHM. In this paper, a method based on a combination of fuzzy information granulation (FIG) and support vector regression with artificial bee colony optimization (ABC-SVR) is proposed to estimate the RUL of Lithium-ion batteries. First, the capacity degradation data are divided into several windows using the FIG method. Second, the maximum and minimum values of each window are predicted separately using the ABC-SVR algorithm to obtain the information of the prediction window. Finally, the missing values of the prediction windows are complemented by the linear interpolation method to obtain the complete capacity prediction values, and the remaining useful life of the battery can be calculated according to the failure threshold. The results show that the proposed method obtains the RUL value with high accuracy.

Prediction of Remaining Useful Life of the Lithium-Ion Battery Based on Improved Particle Filtering

Remaining useful life (RUL) prediction of lithium-ion batteries plays an important role in battery failure prediction and health management (PHM). By accurately predicting the RUL of the battery, the battery can be replaced accordingly, thereby effectively avoiding the occurrence of an accident and ensuring the normal operation of the entire system. In the prediction of the remaining service life of lithium-ion batteries, it is difficult to ensure accuracy due to the problem of particle degradation and the influence of singular values in the particle filter algorithm. In view of these problems, this article introduces the unscented Kalman algorithm to improve the particle filter algorithm from the perspective of re-weighting the particles, so as to improve the accuracy of the prediction results of the remaining service life of lithium-ion batteries. The improved particle filter is simulated and verified using the battery sample data in the Arbin experimental test platform. Comparing the simulation results with the traditional particle filter method, when the number of reference samples is the same, the PDF width of the prediction results of the improved particle filter algorithm is slightly smaller than that of the particle filter algorithm, indicating that the fluctuation of the prediction result is more accurate. It is proved that the improved particle filter method proposed in this article can provide more accurate battery RUL prediction results and can effectively improve the accuracy and robustness of the remaining service life prediction of lithium-ion batteries.

Life Prediction under Charging Process of Lithium-Ion Batteries Based on AutoML

Accurate online capacity estimation and life prediction of lithium-ion batteries (LIBs) are crucial to large-scale commercial use for electric vehicles. The data-driven method lately has drawn great attention in this field due to efficient machine learning, but it remains an ongoing challenge in the feature extraction related to battery lifespan. Some studies focus on the features only in the battery constant current (CC) charging phase, regardless of the joint impact including the constant voltage (CV) charging phase on the battery aging, which can lead to estimation deviation. In this study, we analyze the features of the CC and CV phases using the optimized incremental capacity (IC) curve, showing the strong relevance between the IC curve in the CC phase as well as charging capacity in the CV phase and battery lifespan. Then, the life prediction model based on automated machine learning (AutoML) is established, which can automatically generate a suitable pipeline with less human intervention, overcoming the problem of redundant model information and high computational cost. The proposed method is verified on NASA’s LIBs cycle life datasets, with the MAE increased by 52.8% and RMSE increased by 48.3% compared to other methods using the same datasets and training method, accomplishing an obvious enhancement in online life prediction with small-scale datasets.