Machine Learning for Mechanical & Energy Systems
Machine Learning for Mechanical & Energy Systems
Level: Intermediate
Duration: 16 recorded sessions (~32 hours)
Language: Persian
Format: On-demand
Instructor: Erfan Haghighat
Course Fee (Certificate included): €30
This course covers the fundamentals and applications of machine learning in mechanical and energy systems.
Topics include renewable energy modeling, HVAC and chiller optimization, pumping systems, energy storage,
and real-world engineering case studies using Python.
Intermediate · On-Demand · Persian
Course Overview
This course introduces core machine learning concepts with a focus on mechanical and energy system applications.
The content is project-oriented and designed for engineers seeking practical, real-world understanding.
What You’ll Learn
- Apply basic machine learning models to engineering problems
- Understand data-driven modeling in energy systems
- Analyze real-world datasets using Python
- Build practical engineering workflows
Course Details
Level: Intermediate
Duration: 16 recorded sessions (~32 hours)
Language: Persian
Format: On-demand
Instructor: Erfan Haghighat
Certificate
Upon successful completion of the course requirements, learners are eligible to receive a professional certificate
issued by Owtana Tech .
The certificate verifies practical skills in applying machine learning techniques to mechanical and energy systems,
including renewable energy modeling, HVAC optimization, and data-driven engineering analysis.
Course Syllabus
Session 1 — Introduction to Machine Learning
- Introduction to artificial intelligence and machine learning fundamentals
- Supervised vs. unsupervised learning (conceptual overview)
- Basic concepts of neural networks and an introduction to deep learning architectures
Session 2 — Machine Learning Applications in Renewable Energy Systems
- Performance analysis of wind turbines using data-driven methods
- Modeling and power output prediction of photovoltaic systems
- Review of machine learning applications in solar thermal collectors
Session 3 — Energy Systems: Cogeneration, Trigeneration, and Storage
- Overview of CHP and CCHP systems
- Efficiency and performance analysis of hybrid energy systems
- Machine learning approaches for energy storage optimization
Session 4 — Cooling Systems and Chillers
- Overview of chiller technologies (compression, absorption, adsorption, etc.)
- Performance indicators and efficiency metrics (COP, EER, etc.)
- Application of machine learning for chiller performance optimization
Session 5 — Air Handling Units (AHU): Fundamentals
- Structure and main components of AHU systems
- Operating principles and temperature–humidity control strategies
Session 6 — Mathematical Foundations and Python for Data Engineering
- Linear algebra, probability, and statistics
- Differential and integral calculus for data modeling
- Introduction to Python programming and algorithmic thinking
Session 7 — Energy Applications in the Aluminum and Steel Industries
- Analysis of energy consumption in industrial aluminum processes
Session 8 — Air Handling Units (AHU): Advanced Analysis
- Performance analysis and system-level evaluation of AHU systems
Session 9 — Fundamentals of Machine Learning (Advanced Concepts)
- Review of supervised learning fundamentals
- Numerical problem-solving and engineering-oriented exercises
Session 10 — Pumping Systems and Piping Networks
- Hydraulic network analysis
- Energy consumption modeling and pump curve prediction
Session 11 — Supervised Learning Algorithms
- From classical algorithms to deep learning (Part I)
- Regression and classification techniques
- Overfitting, underfitting, and cross-validation
- Introduction to neural networks for energy engineering applications
Session 12 — Air Handling Units (AHU): System Integration
- Integrated analysis and optimization of AHU systems
Session 13 — Supervised Learning (Practical Applications – Free Session)
- Hands-on Python exercises
- Analysis and comparison of algorithm performance using real datasets
Session 14 — Python Implementation and Case Studies
- Step-by-step data analysis and model development
- Real-world case studies in thermal and energy systems
Session 15 — Optimization of Energy Systems with Phase Change Materials (PCM)
- System modeling of renewable energy applications with PCM
- Machine learning–based prediction and optimization techniques
Session 16 — Final Project and Course Wrap-Up
- Data extraction from simulations
- Development of a complete machine learning project
- Final optimization of a mechanical or energy system
Special Course Features
- Sessions 5, 7, 8, 10, and 12 are free and publicly accessible
- Remaining sessions are part of the structured learning program
- Optional assessment and certification available