A Data-Driven Learning-Based Continuous-Time Estimation and Simulation Method for Energy Efficiency and Coulombic Efficiency of Lithium Ion Batteries

Abstract

Lithium ion (Li-ion) batteries work as the basic energy storage components in modern railway systems, hence estimating and improving battery efficiency is a critical issue in optimizing the energy usage strategy. However, it is difficult to estimate the efficiency of lithium ion batteries accurately since it varies continuously under working conditions and is unmeasurable via experiments. This paper offers a learning-based simulation method that employs experimental data to estimate the continuous-time energy efficiency and coulombic efficiency of lithium ion batteries, taking lithium titanate batteries as an example. The state of charge (SOC) regions and discharge current rates are considered as the main variables that may affect the efficiencies. Over eight million empirical datasets are collected during a series of experiments performed to investigate the efficiency variation. A back propagation (BP) neural network efficiency estimation and simulation model is proposed to estimate the continuous-time energy efficiency and coulombic efficiency. The empirical data collected in the experiments are used to train the BP network model, which reveals a test error of 10 −4 . With the input of continuous SOC regions and discharge currents, continuous-time efficiency can be estimated by the trained BP network model. The estimated and simulated result is proven to be consistent with the experimental results.

Effect of Current Rate and Prior Cycling on the Coulombic Efficiency of a Lithium-Ion Battery

“…Coulombic efficiency and continuous-time energy efficiency of several lithium titanate batteries were investigated according to dissimilar discharge current rates and state of charge sections. The experimental outcomes demonstrated the coulombic efficiency and energy efficiency discrepancy in dissimilar state of charge sections and changing discharge rates [7].…”

A comprehensive review on the state of charge estimation for lithium‐ion battery based on neural network

“…In the recent years, BPNN has been widely used to train lithium-ion batteries with nonlinear characteristics. 24 Wu et al, in 2018, incorporated the firefly algorithm into BPNN for SOC prediction of lithium iron phosphate battery with good error results using voltage and discharge current as input variables. 35 In Reference 30, BPNN was trained at temperatures of 0 C, 25 C, and 45 C, demonstrating that BPNN can work effectively at different temperatures (T) while still having high accuracy.…”

“…[20][21][22] Neural networks have been widely used for image recognition and result prediction based on input data. [23][24][25] Compared with other SOC estimation methods, the neural network method does not need to accurately consider the electrochemical state inside the battery to estimate the SOC by self-learning capability. 26 With the continuous development of artificial intelligence, neural network methods have received increasing attention from researchers in the battery field.…”

Toward Commercially Viable Li-S Batteries: Overall Performance Improvements Enabled by a Multipurpose Interlayer of Hyperbranched Polymer-Grafted Carbon Nanotubes

“…With a theoretical cathode capacity of 1675 mAh g –1 and battery energy density of 2600 Wh kg –1 , Li-S battery (LSB) is considered one of the most promising future secondary batteries. , Moreover, the environmental friendliness, low cost, and inherent safety of sulfur are also the prerequisites for large-scale stationary and mobile applications. , However, the practicability of LSB is still hindered by its poor rate and cycle performance, low sulfur utilization, and poor cathode robustness. The technical issues originated from the low conductivity of sulfur, its structure and volume change upon cycling, and the sluggish kinetics and shuttle effect of the soluble lithium polysulfide (LiPS) intermediates. − Another crucial but often overlooked performance parameter for batteries is the energy efficiency, which is a function of Coulombic efficiency and polarization loss. , A high Coulombic efficiency does not guarantee high energy efficiency in the presence of a considerable polarization loss.…”