 | |
Project Overview | Project Code: ED 19 |
|---|---|
| Project name: | State-of-health estimation of lithium-ion batteries by deep learning |
| TUM Department: | ED - Mechanical Engineering |
| TUM Chair / Institute: | Institute of Automotive Technology |
| Research area: | Electric Vehicle Powertrains |
| Student background: | Computer EngineeringComputer ScienceMechanical Engineering |
| Further disciplines: | |
Planned project location: | Either home office or student office at the lab |
Project Supervisor - Contact Details | |
|---|---|
| Title: | |
| Given name: | Philip |
| Family name: | Bilfinger |
| E-mail: | philip.bilfinger@tum.de |
| Phone: | +49.89.289.15883 |
Additional Project Supervisor - Contact Details | |
|---|---|
| Title: | Prof. Dr.-Ing. |
| Given name: | Markus |
| Family name: | Lienkamp |
| E-mail: | |
| Phone: |
Additional Project Supervisor - Contact Details | |
|---|---|
| Title: | |
| Given name: | |
| Family name: | |
| E-mail: | |
| Phone: |
Project Description | |
|---|---|
| Project description: | The lithium-ion traction battery is the most expensive single component in the electric vehicle. In order to achieve similar ranges as vehicles with combustion engines battery systems tend to be large and heavy. A major disadvantage of electro-chemical systems is irreversible aging, which reduces the usable energy and power over time, and therefore the vehicle’s range. The goal of this student project is to estimate the State-of-Health (SOH) of batteries by deep learning methods on two datasets. Within the scope of the work, an entire deep learning pipeline should be implemented in Python. This includes data cleaning and filtering, feature engineering, further preprocessing steps and modeling of deep learning methods, such as neural networks & LSTMs. More complex architectures can also be explored. The student can also bring in their own interests and adapt the topic accordingly. Finally, the project will be summarized in a poster and there will be an opportunity to present it to the entire research group. There might be the opportunity to contribute to a paper with the student’s findings. |
| Working hours per week planned: | 40 |
Prerequisites | |
|---|---|
Required study level minimum (at time of TUM PREP project start): | 2 years of bachelor studies completed |
| Subject related: | |
| Other: |