EV battery health estimator

The brief

An electric-scooter company needs to know when a battery pack is wearing out. Using battery ageing data, estimate state of health (remaining capacity) from cycle measurements and predict when it will fall below 80%. Good looks like: capacity estimated within a few percent, and a clear view of how fast each battery is ageing.

What you will build

1. Extract features from each charge and discharge cycle
2. Plot capacity fade per battery
3. Train a model to estimate state of health
4. Predict the cycle at which capacity reaches 80%
5. Summarise what speeds up ageing

Free, open data to build it with

• NASA Battery Dataset ↗ Kaggle (NASA data)

Check each dataset's licence before you publish your work. Your mentor gives your team its own version of the brief (data, scope or region), so every team's project is its own.