A Quantum Neural Network Regression for Modeling Lithium-ion Battery Capacity Degradation

TL;DR

This paper introduces a hybrid quantum-classical neural network model to accurately predict lithium-ion battery capacity degradation, leveraging quantum computing principles to potentially outperform classical methods in handling large datasets.

Contribution

It presents a novel quantum neural network framework for modeling battery degradation, demonstrating its effectiveness with NASA data and discussing advantages over classical neural networks.

Findings

Quantum neural networks successfully model nonlinear battery degradation.

Numerical results show promising accuracy with NASA battery data.

Potential for better handling of large datasets in energy storage applications.

Abstract

Given the high power density low discharge rate and decreasing cost rechargeable lithium-ion batteries LiBs have found a wide range of applications such as power grid level storage systems electric vehicles and mobile devices. Developing a framework to accurately model the nonlinear degradation process of LiBs which is indeed a supervised learning problem becomes an important research topic. This paper presents a classical-quantum hybrid machine learning approach to capture the LiB degradation model that assesses battery cell life loss from operating profiles. Our work is motivated by recent advances in quantum computers as well as the similarity between neural networks and quantum circuits. Similar to adjusting weight parameters in conventional neural networks the parameters of the quantum circuit namely the qubits degree of freedom can be tuned to learn a nonlinear function in a supervised learning fashion. As a proof of concept paper our obtained numerical results with the battery dataset provided by NASA demonstrate the ability of the quantum neural networks in modeling the nonlinear relationship between the degraded capacity and the operating cycles. We also discuss the potential advantage of the quantum approach compared to conventional neural networks in classical computers in dealing with massive data especially in the context of future penetration of EVs and energy storage.