The course aims to provide students with the necessary tools to understand how Machine Learning techniques can be used for the analysis of energy systems and components. To this, in the first part of the course, the basic equations governing fluid flows and the tools for thermodynamic and heat transfer analysis are recalled. Building on these foundations, the fundamental concepts for reactive systems (combustion) are introduced. A showcase of how modern Artificial Intelligence (Machine Learning) techniques can be effectively used to analyze fluid flows, heat transfer, and combustion processes is then provided (e.g. Physics-Informed Neural Networks, PINNs). In the second part of the course, the main characteristics of solid, liquid, and gaseous fuels, along with their associated pollutant emissions are discussed. Particular attention is given to the impact of carbon dioxide (CO2) on global warming, and some aspects on renewable fuels are introduced along with their potential applications. The key components for optimal use of thermal energy systems are described and analyzed. The course features practical exercises on Machine Learning methods, and laboratory experiments on a complex thermo-technical system, equipped with a thermal energy storage system relying on Phase Change Materials (PCM).

Upon completion of the course, students are expected to understand the main mechanisms governing fluid flows, heat transfer and combustion in energy components, as well as their analysis within the context of the considered components and systems. Students are also expected to understand the basic principles of the presented Machine Learning techniques, and how they can be used for the analysis of the considered energy applications.

Basic knowledge of thermodynamics and heat transfer. Basic knowledge of mathematical analysis and chemistry. Willingness to learn how to use the Python programming language.

The course is structured according to the following program: FLUID FLOWS: recalls on the fluid motion for continuous systems; basics on the phenomenon of turbulence and boundary layers; Machine Learning techniques for solving fluid flow equations; practical exercises on Machine Learning methods for data analysis using Python notebooks THERMAL ANALYSIS: recalls on thermodynamic analysis tools; recalls on heat transfer mechanisms and dimensional analysis; Machine Learning techniques for heat transfer; practical exercises on Machine Learning methods for thermal analysis using Python notebooks REACTIVE SYSTEMS: basic principles of combustion; theoretical combustion, excess air, unburned components, flame temperature; Machine Learning techniques for reactive systems; practical exercises on Machine Learning methods for image analysis using Python notebooks FUELS: characteristics of solid, liquid and gaseous fuels; the problem of pollutant emissions and the impact of CO2 on global warming; basics on fuels from renewable sources and their use ENERGY DEVICES: heat generators; heat exchangers; heat storages; characteristics and operating principles of the components; practical exercises on thermodynamic analysis and performance evaluation of the considered devices and their components PRACTICE IN THE LABORATORY: experimental measurements on a complex thermo-technical system located at the Energy Center (https://www.energycenter.polito.it/), with thermodynamic analysis and performance evaluation of the different components of the system.

The course includes lectures and practical exercises. The exercises cover the theoretical topics presented in the lectures, and include exercises with numerical solution as well as exercises on the Machine Learning techniques using Python notebooks. The course also includes laboratory practices, with experimental measurements on a complex thermo-technical system.

• Teaching material uploaded by the teachers on the students’ portal • Géron, Aurélien. Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow. O'Reilly Media Inc., 2022 • Incropera, Frank P., et al. Fundamentals of heat and mass transfer. Vol. 6. New York: Wiley, 1996 • Cengel, Yunus A., Michael A. Boles, and Mehmet Kanoğlu. Thermodynamics: an engineering approach. Vol. 5. New York: McGraw-hill, 2011 • Mahajan, Sanjoy. The art of insight in science and engineering: mastering complexity. The MIT Press, 2014

Slides; Esercitazioni di laboratorio;

Modalità di esame: Prova scritta (in aula); Elaborato scritto prodotto in gruppo;

Exam: Written test; Group essay;

... The written test is intended to assess the knowledge acquired by the students on the content of the course; therefore, it is organized in the form of open questions on theoretical and/or application concepts. During the test, it is not possible to consult teaching materials. The duration of the written test is approximately 1.5 hours, and allows to obtain a maximum score of 28/30. To integrate the score, it is possible (but not mandatory) to submit a brief report on the experimental activities carried out in the laboratory during the course. The report can be prepared in small working groups, must be handed in before the written exam, and allows to obtain up to 4 points. The overall grade is then determined by the sum of the score obtained in the written test and that of the laboratory report, if any. Cum laude is assigned for any total score above 30.

Gli studenti e le studentesse con disabilità o con Disturbi Specifici di Apprendimento (DSA), oltre alla segnalazione tramite procedura informatizzata, sono invitati a comunicare anche direttamente al/la docente titolare dell'insegnamento, con un preavviso non inferiore ad una settimana dall'avvio della sessione d'esame, gli strumenti compensativi concordati con l'Unità Special Needs, al fine di permettere al/la docente la declinazione più idonea in riferimento alla specifica tipologia di esame.