Syllabus

Introduction to AI in Thermal Engineering Data Collection and Preprocessing Error approximation Case studies on thermal systems employing artificial intelligence models such as ANN, KNN and ANFIS – Performance prediction, Performance optimization, Design optimization, Predictive maintenance, and Fault detection.

Module I (2 classes): Introduction to AI in Thermal Engineering
1. Introduction to Python/MATLAB for AI
2. Learning modules on basics of KNN, ANN, ANFIS and Deep Learning

Module II (3 classes): Data Collection, Preprocessing and Error approximation
3. Methods of data collection in thermal systems
4. Hands-on lab: Preprocessing thermal data i.e., Data cleaning, normalization, and feature extraction
5. Error estimation and approximation of AI models

Module III (5 classes): Case studies on thermal systems employing artificial intelligence models
6. Performance prediction of heat exchanger employing KNN
7. Performance optimization of humidifier employing ANN
8. Design optimization of evacuated U-tube solar collector employing ANFIS

Module IV (2 classes): Predictive maintenance and Fault detection
9. Predictive maintenance of vapour compression refrigeration system employing ANN
10. Fault detection of vapour compression refrigeration system employing ANN

To understand the fundamentals of AI algorithms.

To apply AI techniques to solve thermal engineering problems

To develop skills in data preprocessing, feature engineering, and model evaluation

To design and implement AI models for predictive maintenance and optimization of thermal systems

• Understand fundamental AI and machine learning concepts and techniques.
• Develop and evaluate AI models for thermal applications.
• Apply AI algorithms to real-world thermal problems.
• Implement AI/ML models for proactive maintenance and optimization.
• Engage in innovative research in AI/ML for thermal engineering.

Witten, I.H., Frank, E., Hall, M.A., Data Mining: Practical Machine Learning Tools and Techniques, 3rd ed., Morgan Kaufmann, Burlington, MA, 2021 , Reprint

Landkof, Y.D., Guergova, T.Z. (Eds.), Computational Intelligence in Thermal Engineering, Springer, Cham, 2020 , Reprint

Dagli, C.H., Westphal, L.A., Riley, M.F., AI for Engineering Applications, Springer, Boston, MA, 2021. , Reprint

Witten, I.H., Frank, E., Hall, M.A., Data Mining: Practical Machine Learning Tools and Techniques, 3rd ed., Morgan Kaufmann, Burlington, MA, 2023 , Reprint

Priyadarshi, G., Hoang, H. M., Hunlede, R., Paviet-Salomon, Y., Delahaye, A., & Naik, B. K. (2025). Application of artificial intelligence models for assessing the performance of closed vertical refrigerated display cabinet-A comparative study of different operating scenarios. Engineering Applications of Artificial Intelligence, 147, 110332.

Mohapatra, A., Tejes, P. K. S., Gembali, C., & Kiran Naik, B. (2023). Design and performance analyses of evacuated U-tube solar collector using data-driven machine learning models. Journal of Solar Energy Engineering, 145(1), 011007.