AI Blocks › Build and ship software
Battery health feature extractor
Give it battery test data. Get health and wear features ready for life prediction.
Battery health feature extractor is a free AI skill for the job "Build and ship software". Give the instructions to an AI assistant that supports the required files and tools, then review its output.
Free · No account · BSD 2 Clause licence · Made by MathWorks · Level: advanced
Made by MathWorks. See the original on GitHub; we copied it as it is, with its licence.
What it does
Health and wear numbers pulled out of battery test data, ready for models that estimate state of health or predict remaining life. Give it cycling files and it produces more than 165 features, from simple statistics per charge or discharge segment to differential curves that show electrode aging. These curves are incremental capacity (dQ/dV), differential voltage (dV/dQ) and differential temperature (dT/dV), and the skill also pulls peak features from them. It uses five functions from MATLAB's Predictive Maintenance Toolbox, handles segmenting the data, and can process many files in a batch. It asks whether to stop or continue before moving to the next stage. You need MATLAB and that toolbox.
You give it
- Battery cycling or test data
- Which cycling phase to use
- Batch of files (optional)
- Your prediction goal, such as SOH or RUL
You get
- A table of battery features
- Differential curves
- Peak features from the curves
- A batch pipeline for many files
Use it when
- You have months of cycling data and need inputs for a life prediction model.
- You want to see capacity fade through differential curves.
- You must process fifty test files the same way.
- You need statistics from a partial charge segment.
How to use it
- Add it to your AI once: download it and add the folder to Claude, ChatGPT or Codex as a skill.
- Ask for the job in your own words. Your AI opens the skill when it fits.
- It works best when your AI can run MATLAB with the Predictive Maintenance Toolbox.