Real-Time Parameter Estimation of an Electrochemical Lithium-Ion Battery Model Using a Long Short-Term Memory Network

Abstract

An electrochemical lithium-ion battery model is well known to be suited for effectively describing the microstructure evolution in charging and discharging processes of a lithium-ion battery with practically realizable complexity. This paper presents a neural network-based parameter estimation scheme to identify the parameters of an electrochemical lithium-ion battery model in a near-optimal and real-time manner in order to consistently observe the electrochemical states of batteries. The network is first trained to learn the dynamics of the electrochemical lithium-ion battery model, and then, it is applied to estimate the parameters with available finite-time measurements of voltage, current, temperature, and state of charge. In order to efficiently learn the dynamic characteristics of a lithium-ion battery, a well-known recurrent neural network, called a long short-term memory model, is employed with other techniques such as batch normalization, dropout, and stochastic gradient descent with warm restarts for learning speed enhancement and regularization. Using synthetic and experimental data, we show that the proposed estimation scheme works well, finding parameters and recovering the voltage profiles within the root-mean-square error of 0.43% and 26 mV, respectively, even with measurements obtained within a sufficiently short interval of time. INDEX TERMS Electrochemical battery model, lithium-ion battery, long short-term memory, real-time parameter estimation, recurrent neural network, synthetic data generation.

Electric Vehicles Charging Technology Review and Optimal Size Estimation

“…This, hence, motivates the development and the research of innovative charging algorithms which tackle the issue of the charging impact on battery state-of-health (SoH) and aging [76,80]. In fact, recently, many researches are focusing on develop new charging methods which minimize the charging time and extend the battery life at the same time [75,[80][81][82][83]. This new category of charging strategies employs the electrochemical lithium-ion battery models to calculate quantitatively and almost precisely the amount of battery aging and to directly minimize the aging in a given charge time.…”

“…The electrochemical battery model estimates the internal states of a battery in a more accurate way since it is built starting from the internal microstructure of the lithium-ion battery. However, it is very arduous to precisely estimate the parameters because the electrochemical model is composed of complicated coupled partial differential equations (PDEs), and involving a large number of parameters and boundary conditions it requires a large computation burden [82]. Therefore the complexity of these models often leads to the necessity for more memory and computational effort and thus they may not be practically implemented in the fast and real-time computations of EV BMS [86].…”

“…The full description of this model can be found in [85]. Finally, in [82], the authors present an effective method to estimate the parameters of the P2D model using a neural network-based estimation scheme.…”

Real Time Adaptive Estimation of Li-ion Battery Bank Parameters

“…Therefore, Chen and Mora's battery model [1] has been utilized for this and our previous work [2]- [4]. Different strategies are available in the literature for extracting Li-ion battery model parameters [5]- [16].…”

Multi-step ahead thermal warning network for energy storage system based on the core temperature detection

“…Deep learning has been widely used in various fields, because even novices are easy to carry out end-to-end learning without human intervention 22 . If there are enough reliable data, an excellent prediction network can be trained.…”