Time-Frequency Image Analysis and Transfer Learning for Capacity Prediction of Lithium-Ion Batteries

Ma’D El-Dalahmeh,Mo’Ath El-Dalahmeh,Michael Short,Maher Al-Greer

doi:10.3390/en13205447

Ma’D El-Dalahmeh, Mo’Ath El-Dalahmeh + Show 2 more

Open Access

https://doi.org/10.3390/en13205447

Copy DOI

Journal: Energies	Publication Date: Oct 19, 2020
Citations: 23	License type: CC BY 4.0

Affiliation: Teesside University

Abstract

Energy storage is recognized as a key technology for enabling the transition to a low-carbon, sustainable future. Energy storage requires careful management, and capacity prediction of a lithium-ion battery (LIB) is an essential indicator in a battery management system for Electric Vehicles and Electricity Grid Management. However, present techniques for capacity prediction rely mainly on the quality of the features extracted from measured signals under strict operating conditions. To improve flexibility and accuracy, this paper introduces a new paradigm based on a multi-domain features time-frequency image (TFI) analysis and transfer deep learning algorithm, in order to extract diagnostic characteristics on the degradation inside the LIB. Continuous wavelet transform (CWT) is used to transfer the one-dimensional (1D) terminal voltage signals of the battery into 2D images (i.e., wavelet energy concentration). The generated TFIs are fed into the 2D deep learning algorithms to extract the features from the battery voltage images. The extracted features are then used to predict the capacity of the LIB. To validate the proposed technique, experimental data on LIB cells from the experimental datasets published by the Prognostics Center of Excellence (PCoE) NASA were used. The results show that the TFI analysis clearly visualised the degradation process of the battery due to its capability to extract different information on electrochemical features from the non-stationary and non-linear nature of the battery signal in both the time and frequency domains. AlexNet and VGG-16 transfer deep learning neural networks combined with stochastic gradient descent with momentum (SGDM) and adaptive data momentum (ADAM) optimization algorithms are examined to classify the obtained TFIs at different capacity values. The results reveal that the proposed scheme achieves 95.60% prediction accuracy, indicating good potential for the design of improved battery management systems.

Highlights

IntroductionTo optimise the energy performance of the lithium-ion battery (LIB), prolong their life cycle, and reduce their cost, it is critical to monitor the internal state of the battery, such as state-of-charge (SoC), state-of-health (SoH), and remaining useful life (RUL) [2,3]
We demonstrate how the generated
We demonstrate how the generated time-frequency image (TFI) from the measured terminal voltage at different capacities through Continuous wavelet transform (CWT) were fed into AlexNet and Visual Geometry Group (VGG)-16 DL-convolutional neural network (CNN) for capacity classification, after they had been trained for TFI classification

Summary

Introduction

To optimise the energy performance of the LIBs, prolong their life cycle, and reduce their cost, it is critical to monitor the internal state of the battery, such as state-of-charge (SoC), state-of-health (SoH), and remaining useful life (RUL) [2,3]. Over the battery’s lifetime, the capability for LIBs to provide a certain amount of power and store energy is reduced due to internal ageing phenomena [4,5]. When the capacity parameter is utilised as an indicator of the battery’s SoH, the SoH is known as the ratio of the battery capacity at current cycle to its rated capacity at the beginning of life or initial capacity provided by the battery manufacturer [8]

Objectives

Results

Conclusion