To equip participants with the knowledge and practical skills to use AI and machine learning for analyzing, modeling, and predicting degradation in energy storage systems, helping improve battery health assessment, reliability, and lifetime prediction.
New Year Offer End Date: 30th April 2024
Program
AI for Degradation Modeling in Energy Storage Systems
Predicting Battery Lifetimes with the Power of Artificial Intelligence
Skills you will gain:
About Program:
The workshop “AI for Degradation Modeling in Energy Storage Systems” explores how AI and machine learning can be used to understand, predict, and model degradation in batteries and other energy storage devices. It covers key concepts such as battery aging, SOH, RUL, predictive analytics, and AI-driven prognostics, with insights inspired by recent MDPI research trends. Designed for researchers, academicians, and industry professionals, the workshop also includes hands-on sessions in Google Colab/Jupyter Notebook to help participants apply intelligent modeling techniques to real degradation data.
Aim:
Program Objectives:
-
To introduce the fundamentals of degradation mechanisms in energy storage systems.
-
To understand key battery health indicators such as SOC, SOH, and RUL.
-
To explore AI and machine learning techniques for degradation prediction.
-
To develop skills in analyzing battery datasets and building predictive models.
-
To provide hands-on experience using Python in Google Colab/Jupyter Notebook for energy storage data analysis.
What you will learn?
Day 1: Battery Aging Data, Health Indicators and Degradation Diagnostics
Topics Covered
- Lithium-ion battery aging: calendar aging vs cycle aging
- Major degradation mechanisms: capacity fade, resistance growth and thermal stress
- Understanding charge–discharge curves and battery cycling data
- Battery health indicators: SOC, SOH, RUL and End-of-Life
- Extracting capacity, energy, temperature and cycle-based health features
- Detecting degradation trends, anomalies and the battery “knee point”
- Data quality challenges: missing cycles, noise and irregular measurements
- Data-driven, physics-based and hybrid degradation modeling approaches
Hands-On: Build a Battery Health Diagnostic Dashboard
- Import and structure NASA battery-aging data in Google Colab
- Visualize voltage, current, temperature and capacity across cycles
- Calculate cycle-wise SOH and identify the End-of-Life threshold
- Generate capacity-fade and degradation-rate plots
Day 1 Output: Cleaned battery health dataset, SOH trajectory and degradation diagnostic dashboard.
Day 2: Machine Learning for Explainable SOH Estimation
Topics Covered
- Converting charge–discharge signals into predictive health features
- Feature engineering from voltage, current, temperature and cycle duration
- Incremental capacity and curve-derived degradation indicators
- Baseline modeling using Linear Regression
- Nonlinear SOH prediction using Random Forest and XGBoost
- Battery-aware train–test splitting and prevention of data leakage
- Model evaluation using MAE, RMSE and R2
- Feature importance and explainable battery AI using SHAP
- Comparing accuracy, interpretability and computational cost
Hands-On: Train and Explain an SOH Prediction Model
- Build Linear Regression, Random Forest and XGBoost models
- Compare model performance on unseen battery cycles
- Identify the most influential degradation features using SHAP
- Generate predicted-vs-actual SOH and error-analysis plots
Day 2 Output: Validated SOH prediction model, model-comparison report and SHAP-based degradation interpretation.
Day 3: Remaining Useful Life Prediction and AI-Enabled Battery Prognostics
Topics Covered
- Formulating RUL as a time-series forecasting problem
- Defining End-of-Life and generating cycle-wise RUL labels
- Early-cycle prediction of long-term battery degradation
- Sequence preparation using sliding windows
- LSTM-based modeling of nonlinear degradation trajectories
- Prediction uncertainty and confidence-aware maintenance decisions
- Physics-informed constraints for reliable battery prognostics
- Model generalization across cells and operating conditions
- Deployment pathway for BMS, predictive maintenance and battery digital twins
- Translating model results into research figures and publication workflows
Hands-On: Develop an End-to-End Battery RUL Predictor
- Prepare time-series sequences from battery cycling data
- Train a compact LSTM model for RUL prediction
- Compare predicted and actual End-of-Life trajectories
- Estimate the maintenance-alert cycle from predicted RUL
- Test the model on an unseen battery cell
Day 3 Output: Colab-based RUL prediction pipeline, End-of-Life forecast and maintenance decision plot
Mentor Profile
Fee Plan
INR 1999 /- OR USD 50
Get an e-Certificate of Participation!
Intended For :
-
Students interested in renewable energy, sustainability, and energy analytics
-
PhD scholars, researchers, and academicians in energy, environment, and climate studies
-
Industry professionals in renewables, utilities, grid systems, and decarbonization
-
Policy analysts and government professionals working on energy transition strategies
-
Data scientists and AI/ML practitioners applying analytics in the energy sector
-
Entrepreneurs and climate-tech innovators building energy-focused solutions
Career Supporting Skills
Program Outcomes
-
Understand key degradation mechanisms in energy storage systems.
-
Analyze battery health indicators such as SOC, SOH, and RUL.
-
Apply AI and machine learning techniques for degradation prediction.
-
Build basic predictive models using Python in Google Colab/Jupyter Notebook.
-
Interpret degradation data to support reliability and lifetime assessment of energy storage systems.