Batteries

Apply predictive maintenance development tools to battery systems that range from individual cells to battery packs

Apply predictive maintenance development tools to lithium-ion battery cells and battery packs. Specialized features and algorithms use knowledge of charge, discharge profiles, and cycle-to-cycle and cell-to-cell variations to enable detection of anomalies and to identify remaining cycle life.

Functions

expand all

Evaluate Battery Degradation

`meanDifferenceModel`	Identify most degraded cell in serially connected lithium-ion battery pack (Since R2022b)
`adjacentPairCorrelationModel`	Identify worst cell relative to other cells in serially connected lithium-ion battery pack (Since R2023a)

Extract Features from Battery Test Data

`batteryTestDataParser`	Convert data produced by battery lab testing into a format that is compatible with analysis and feature extraction (Since R2024b)
`segmentData`	Classify and organize raw battery measurement data by identifying cycling phase, cycling mode, and data validity (Since R2024b)
`batteryTestFeatureExtractor`	Specify feature set to extract from parsed battery cycling data (Since R2024b)
`extract`	Extract selected battery features from parsed and segmented battery test data (Since R2024b)
`computeDifferentialCurves`	Compute incremental capacity, differential voltage, and differential temperature curves that can be used to analyze battery behavior under constant-current conditions (Since R2024b)

Topics

Characterize Battery Health Using Cycler-Based Test Data
Use specialized battery data parsing and feature extraction tools to organize test measurements and extract features from Lithium-Ion battery test data to evaluate battery health status.
Data Analysis and Feature Extraction for Battery Raw Cycling Data
Extract features from raw battery data using a workflow that includes data preprocessing, data organization and analysis, and feature extraction and visualization.

Featured Examples

Nonlinear State Estimation of a Degrading Battery System

Estimate the states of a nonlinear system using an unscented Kalman filter in Simulink.

Open Script

Battery Cycle Life Prediction from Initial Operation Data

Predict the remaining cycle-life of a fast charging Li-ion battery using a supervised machine learning algorithm.

Open Live Script

Battery Cycle Life Prediction Using Deep Learning

Predict the remaining cycle-life of a fast charging Li-ion battery by training a deep neural network.

Open Live Script

Battery Second-Life Application State of Health (SoH) Estimation of Li-Ion Batteries

Estimate battery state of health (SoH) for second-life application using measurements from first life and terminal voltage during second life.

Open Live Script

Data Analysis and Feature Extraction for Battery Raw Cycling Data

Extract features from raw battery data using a workflow that includes data preprocessing, data organization and analysis, and feature extraction and visualization.

Open Live Script