No products in the cart.
USD $0.00
Cart
● Recorded Workshop
Predicting Efficiency (Exergy + Machine Learning)
“Optimizing Energy Systems with Exergy and Machine Learning: Predicting Efficiency for a Sustainable Future”
Registration Closes In
00Days
00Hours
00Mins
00Secs
About This Course
- Energy & Exergy: Combining traditional engineering with AI.
- Energy is conserved (First Law), but Exergy (useful energy) is lost as heat and friction.
- This workshop blends mechanical engineering with AI, using Machine Learning to predict and prevent energy waste in thermal power systems.
- Explore AI integration in thermal power plants to enhance efficiency and avoid failures.
AIM
- AI for Exergy Destruction Detection: Merging process engineering with data science.
- We show how AI can understand physics and detect hidden patterns in sensor data.
- Using historical data (temperatures, pressures, flow rates), we train a Machine Learning model to identify Exergy Destruction and inefficiencies.
- Learn how data science enhances traditional engineering by uncovering unnoticed inefficiencies.
Workshop Objectives
- Machine Learning for Predicting Efficiency: Building a working model with scikit-learn and XGBoost.
- Build a model that predicts efficiency in real-time for boilers or turbines over the next 24 hours.
- Learn to use CoolProp for automatic thermodynamic calculations in Python.
- This course will guide you through applying machine learning to real-world energy systems.
Workshop Structure
Day 1: The Physics – Sensors, Steam, and Exergy
- Energy vs. Exergy: First vs. Second Law of Thermodynamics.
- Power Cycle Anatomy: Boilers, turbines, and condensers.
- CoolProp Intro: Using Python to calculate thermodynamic properties.
Hands On:
- Setup: Google Colab environment and install libraries.
- Data Ingestion: Load turbine_sensor_data.csv.
- Physics Engine: Use CoolProp to calculate Enthalpy (h) and Entropy (s) for each sensor row.
- Target Calculation: Create a column for Exergy Destruction.
Day 2: The Algorithm – Intro to Machine Learning
- Machine Learning: Features vs. Targets.
- Supervised Learning: Algorithm learning from data.
- Decision Trees/Random Forests: Data splitting for predictions.
Hands On:
- Data Pre-processing: Split data into training/testing sets.
- Build AI Model: Use RandomForestRegressor, train on data.
- Evaluate: Predict efficiency, calculate Mean Absolute Error.
Day 3: The Insight – Advanced AI & Predictive Maintenance
- XGBoost: Powerful algorithm for forecasting.
- Feature Importance: Analyze why AI makes specific predictions.
- Prediction to Action: Use AI insights for predictive maintenance.
Hands On:
- Upgrade to XGBoost: Install and train the model.
- Visualization: Plot Actual vs. Predicted Exergy Destruction.
- Insights: Feature importance chart (e.g., temperature vs. pressure).
- Wrap-up: Save the AI model (model.pkl) for deployment.
Who Should Enroll?
- Workshop for Engineers and Data Scientists: Learning AI in the Energy Sector.
- Perfect for engineers wanting to learn AI or data scientists entering the energy sector. A basic understanding of thermodynamics and Python is required. This hands-on workshop bridges traditional engineering with AI techniques for the energy industry.
Join Our Hall of Fame
Take your research to the next level with NanoSchool.
Publication
Get published in prestigious open-access journals.
Excellence
Become part of an elite research community.
Networking
Connect with global researchers and mentors.
Recognition
Worth ₹20,000 in academic value.
Student Feedback
★★★★★
AI and Ethics: Governance and Regulation
Sandra Wingender •