This course offers an applied overview of key soft computing methodologies—artificial neural networks, genetic algorithms, fuzzy logic, and cluster analysis—with a focus on their application in thermal and energy systems. Emphasis will be placed on coding and implementation of neural networks and genetic algorithms, as applied to data drawn from real-world thermal systems. Students will engage in hands-on projects involving numerical analysis, literature review, and technical presentations, potentially aligned with their own research activities.

The outline for the course is below; however, order and/or content may occur.
• Artificial Neural Networks (ANNs) and Applications
o Definitions and fundamentals
o Types of ANNs: similarities and differences
o Applications to the characterization of thermal systems
• Genetic Algorithms (GAs) and Applications
o Definitions and fundamentals
o Use of GAs as a global optimization technique
o Applications to the characterization of thermal systems
• Fuzzy Logic (FL) and Applications
o Definitions and fundamentals
o Types of inference systems
o Applications to the control of thermal systems
• Cluster Analysis (CA) and Applications
o Classification algorithms
o Mathematical fundamentals
o Applications to characterization of thermal systems

Course Format: The course is structured in a guided, discussion-based format with supplementary lectures. Key components include: • Background lectures on soft computing and thermal system integration.
• Team or individual projects involving data analysis, code development, and literature integration.
• Student presentations on project results, emphasizing communication and critical evaluation.

Reference Materials: There is no required textbook, but selected references will be used throughout the course, including:
• Haykin, S. (2002). Neural Networks: A Comprehensive Foundation (2nd Edition), Pearson Education.
• Mitchell, M. (1996). An Introduction to Genetic Algorithms, MIT Press.
• Additional research papers and technical documents tailored to specific topics.

Active participation is essential. Students are expected to engage in discussions, coding activities, and peer feedback throughout the course.
Coding and Tools: Students are expected to develop code using MATLAB, Fortran 77/90, or another language of their choosing, as long as they are proficient. Projects will involve algorithm implementation and data interpretation.

soft computing methodologies, artificial neural networks, genetic algorithms, fuzzy logic, cluster analysis,thermal and energy systems