Implementation of generative adversarial network-CLS combined with bidirectional long short-term memory for lithium-ion battery state prediction
Introduction
The state-of-charge (SOC) of the lithium-ion (Li-ion) battery is an important evaluation index of a battery management system (BMS). Therefore, performing an accurate measurement of the SOC is the main concern in analyzing battery-pack performance. In general, the battery pack is composed of hundreds and thousands of single cells for high voltage and energy storage [1]. The characteristics of batteries are different after undergoing several charge/discharge cycles. The BMS test needs to be executed many times for desired model accuracy, even though the characteristics of batteries are slightly different under the same state-of health (SOH).
Coulomb counting is the basic method to measure SOC. In this method, the current is integrated over time, and the integral is divided by the capacity to obtain the SOC [2,3]. However, Coulomb counting methods highly depend on the initial SOC estimation and the bias in the current sensing. The conventional SOC estimation algorithm is represented by a Kalman filter [4,5]; however, the SOC-open circuit voltage (OCV) characteristics of a battery have strong nonlinearity at the beginning and end of the charge/discharge state [6], [7], [8]. The extended Kalman filter (EKF) [9], [10], [11], [12] is proposed to deal with the problem of predicting the SOC under the linear assumption of the Kalman filter. However, the performance of the Kalman filter and its derivative version depends on an accurate battery model, such as the conventional Thevenin model or second Thevenin model [13]. Both models require offline parameter identification, as well as measurement of the OCV, and a determination of the time elapsed of the model. Jian Chen et al. [14,15] proposed the use of the adaptive neuro-fuzzy and radial basis function neural network as a nonlinear observer. In the experiment of [14], the battery is discharged with a constant current in steps of 5% of capacity and rested; then, the corresponding resistance R can be calculated as the ratio of the instantaneous voltage drop U and current I. Then, the parameters of the RC networks at the corresponding measured SOCs can be determined. Finally, the neural network is used to fit the curve, and the Thevenin model is used to estimate the SOC. This method can yield an accurate estimation if the battery has the same SOH. Han et al. [16] used the genetic algorithm (GA) to identify the battery capacity and analyze the battery age model under different test temperatures. In [17], a radial basis function (RBF) neural network (NN) was used to learn the bounds of the uncertain dynamics of the battery equivalent circuit model. Then, the outputs of the RBF NN were used to estimate the SOC based on a robust sliding-mode observer (RSMO). However, this requires tremendous testing under different temperatures to identify the model parameters. Other SOC estimation methods are established on machine learning strategies, which encompass artificial neural networks (ANNs), fuzzy NNs, back propagation neural networks (BPNNs), and adaptive fuzzy NNs [18], [19], [20], [21], [22]. These data-oriented approaches treat the battery model as a black box, with requiring knowledge of the battery internal structure. The battery model is treated in the weights of NNs. A large amount of experimental data is required to train the NNs for high accuracy. In addition, it is difficult to balance the model precision and generalization performance. Furthermore, it necessitates tremendous computing workload and resource consumption. A summary of the lithium-ion battery state prediction methods is listed in Table 1.
In this study, a method involving the use of GAN-CLS (called as matching-aware discriminator) to generate the required data, rather than running experiments, is adopted [23]. In this method, measured data with different SOH are padded with zeros at the end, such that all data are of the same length. Then, the vectors are reshaped as 2-dimensional images, and convolutional neural network (CNN) is used to extract the rough and detailed features as needed. For the original GAN, the random data with fixed distribution were used to generate the desired distribution. However, battery SOC-OCV characteristics vary with different SOH, which means that the SOC-OCV characteristics exhibit a different distribution. In the GAN-CLS model, the discriminator in GAN receives the generated data and corresponding SOH, such that the input data includes the corresponding SOH information. The performance of the generated data was tested based on a significance test, using the best data to represent the experimental data. The generated data are used to train the bidirectional-LSTM (BLSTM) networks that operate on the input sequence in both directions to facilitate optimal decision-making for the current input [24,25]. As a result, the GAN-CLS generates high-quality pseudo-experimental data, which can be used for BMS or fault-detection simulation. The proposed methods reduce the time cost 50 times in modeling and 20 times in train/test. The results show a predicted mean square error (MSE) smaller than 0.002. The proposed methods significantly reduce the time and resource cost.
Section snippets
Conventional battery model
Equivalent-circuit models of battery cells are widely used in SOC estimation. Among these models, Fig. 1 shows the improved Thevenin model. Eqs. (1) through (3) represents the mathematical expressions of the second order model [26].
Thevenin model has the polarization resistance Rp and polarization capacitor Cp, Up is voltage on capacitance Cp, i(t) is charge/discharge current. Cc and Rc are concentration
Advanced generative adversarial networks (GAN)-conditional latent space (CLS)
To solve the problem that the GAN cannot create the data corresponding to the label, the auxiliary classifier GAN (AC-GAN) is proposed. Fig. 7 shows the GAN-CLS architecture, which is similar to AC-GAN, whereby the discriminator receives the generated data and corresponding information (additional parameters such as SOH, temperature, charge cycles and shocks) instead of only the generated data. The SOC-OCV characteristics have a different distribution under different SOH, thus, in this
Test bench description
This approach used LG Chem. middle-power 18650-HE4 cylindrical lithium-ion batteries that has a rated capacity of 2.5Ah for experiments. Compared to the rated capacity (2.5Ah) and its nominal C-rate (1C=2.5A), this battery has more maximum discharge current (20A, 8C-rate). Namely, because of middle-power/energy characteristics, the cathode material of this battery is basically NiMnCoO2 (NMC). For reference, according to the three different ratios of Ni:Mn:Co, it is possible to produce various
Conclusions
This paper combines the deep learning technologies of GAN-CLS and BLSTM to estimate the state of batteries. The proposed methods only require a few CNN processed experiment datasets to train the GAN-CLS. The trained networks can generate extremely valid data in contrast to the alternative of running many repeated experiments. The generated data with high PCCs are used to train the BLSTM. The analysis is carried out considering both time cost and error. The time cost results suggest that the
CRediT authorship contribution statement
Haoliang Zhang: Investigation, Writing - original draft. Wei Tang: Formal analysis. Woonki Na: Methodology, Investigation. Pyeong-Yeon Lee: Formal analysis. Jonghoon Kim: Writing - review & editing.
Acknowledgements
This material is based upon work supported by the National Science Foundation under Grant No. 1816197.
References (30)
- et al.
A novel method for lithium-ion battery state of energy and state of power estimation based on multi-time-scale filter
Appl. Energy
(2018) - et al.
Enhanced coulomb counting method for estimating state-of-charge and state-of-health of lithium-ion batteries
Appl. Energy
(2009) - et al.
An online framework for state of charge determination of battery systems using combined system identification approach
J. Power Sources
(2014) - et al.
State-of-charge estimation and uncertainty for lithium-ion battery strings
Appl. Energy
(2014) - et al.
State of charge estimation of lithium-ion batteries using the open-circuit voltage at various ambient temperatures
Appl. Energy
(2014) - et al.
Improved extended Kalman filter for state of charge estimation of battery pack
J. Power Sources
(2014) - et al.
Battery state of the charge estimation using Kalman filtering
J. Power Sources
(2013) - et al.
A double-scale and adaptive particle filter-based online parameter and state of charge estimation method for lithium-ion batteries
Energy
(2018) - et al.
A new battery capacity indicator for lithium-ion battery powered electric vehicles using adaptive neuro-fuzzy inference system
Energy Convers. Manage.
(2004) - et al.
A comparative study of commercial lithium ion battery cycle life in electric vehicle: capacity loss estimation
J. Power Sources
(2014)
State of available capacity estimation for lead-acid batteries in electric vehicles using neural network
Energy Convers. Manage.
A review of state-of-charge indication of batteries by means of a.c. impedance measurements
J. Power Sources
Impedance measurements on lead–acid batteries for state-of-charge, state-of-health and cranking capability prognosis in electric and hybrid electric vehicles
J. Power Sources
State of available capacity estimation for lead-acid batteries in electric vehicles using neural network
Energy Convers. Manage.
Building occupancy modeling using generative adversarial network
Energy Build.
Cited by (30)
Revealing the degradation patterns of lithium-ion batteries from impedance spectroscopy using variational auto-encoders
2024, Energy Storage MaterialsSpecialized deep neural networks for battery health prognostics: Opportunities and challenges
2023, Journal of Energy Chemistry