Doctoral project: RUL prediction based on historical battery cycle logs
This project aims to create a workflow with diverse machine learning algorithms to simulate battery remaining useful life (RUL) curve and its corresponding range according to historical battery cycle logs at Micropower.
Project information
Doctoral student
Zijie Feng
Supervisor
Welf Löwe
Assistant supervisors
Per Ranstad, Roger Pettersson och Håkan Grahn (BTH)
Participant organizations
Linnéuniversitetet, Micropower Group
Financiers
Micropower Group, The Knowledge Foundation (Industrial Research School for Data Intensive Applications (DIA))
Timetable
November 2023 – November 2028
Subject
Computer and information science (Department of Computer Science and Media Technology, Faculty of Technology)
Research group
Data Intensive Software Technologies and Applications (DISTA)
Linnaeus University Centre
Linnaeus University Centre for Data Intensive Sciences and Applications (DISA)
Graduate School
The industry graduate school Data Intensive Applications (DIA)
More about the project
As technology advances, battery usage has become increasingly prevalent in daily life. Many traditional fuel-powered mechanical devices, such as forklifts and AGVs, are now powered by battery. Concurrently, concerns about safety and efficiency have heightened the focus on monitoring the condition of batteries in these large devices.
During usage, the battery's actual capacity diminishes gradually. When the capacity falls to a certain threshold, the battery becomes unusable. In general, we can measure the remaining useful life of a battery (i.e., RUL) in two ways: directly by measuring the physical and chemical characteristics of the battery, and indirectly by using data-driven models. Since direct measurement of batteries is very inconvenient, RUL prediction based on data models is a promising research direction. RUL is typically estimated, considering the battery's condition and the customer's usage. However, both factors are influenced by numerous variables, introducing uncertainty into the estimated RUL, and consequently significant fluctuations in the RUL curve.
We utilized different Machine Learning algorithms to build and optimize a workflow from historical battery cycle data to battery RUL prediction with corresponding confidence intervals. The results will help battery owners and suppliers to manage the maintenance and to plan the replacement of batteries ahead of time.
The doctoral project is performed within Data Intensive Software Technologies and Applications (DISTA), Linnaeus University Centre for Data Intensive Sciences and Applications (DISA) and is part of The industry graduate school Data Intensive Applications (DIA).