Development of Highly Accurate Lifetime Prediction Models for Lithium-ion Batteries Using Machine Learning and Physics of Failure

Projektdetaljer

Beskrivelse

Abstract:
Lithium-ion batteries (LIBs) have excellent application potential in portable instruments, aerospace, road transportation, power grid, and defence industry. Their tremendous advantages include high working voltage, high specific energy, and long cycle life. However, lithium-ion battery operation in any of these applications will inevitably lead to the ageing-induced degradation (capacity fade and power decrease), which reduces the service life of the equipment and even creates some safety hazards. Therefore, it is necessary to study LIBs ageing mechanisms for establishing the correlation between the battery's external characteristics (i.e. capacity and internal resistance/power) and the internal side reactions and provide a reliable solution for predicting its lifetime, evaluating the state of health (SOH), and ensuring the equipment's safe operations. This research describes a methodology for establishing accurate lifetime prediction models for LIBs, based on accelerated degradation tests (ADTs) design, machine learning (ML) techniques and physics of failure (PoF) theory.

Funding: CSC Scholarship
StatusIgangværende
Effektiv start/slut dato01/12/202130/04/2024

Fingerprint

Udforsk forskningsemnerne, som dette projekt berører. Disse etiketter er oprettet på grundlag af de underliggende bevillinger/legater. Sammen danner de et unikt fingerprint.