ARTIFICIAL INTELLIGENCE IN ELECTROMECANICAL ENGINEERING: THE ESPRIT MODEL

ARTIFICIAL INTELLIGENCE IN ELECTROMECANICAL ENGINEERING: THE ESPRIT MODEL

M. Riahi, N. AJAILIA (2024).  ARTIFICIAL INTELLIGENCE IN ELECTROMECANICAL ENGINEERING: THE ESPRIT MODEL.

In response to the surge of artificial intelligence (AI) in the last decade, which now spans across electromechanical sectors like automation, electricity, and maintenance, the ESPRIT approach is introduced. It emphasizes the need for engineers to diversify their skill sets to adapt to the evolving landscape. This educational paradigm integrates an AI module into the electromechanical engineering curriculum, congruent with CDIO standards, to cultivate a broad spectrum of competencies in AI. The curriculum is meticulously crafted to progress from foundational knowledge to advanced application and assessment, employing active learning strategies to enhance students’ technical, problem-solving, and professional skills, ultimately encouraging a well-rounded mastery of AI in engineering. This paper describes the ESPRIT approach, a pedagogical paradigm tailored for equipping electromechanical engineers with the necessary AI competencies. The integration of a dedicated AI module within ESPRIT’s electromechanical engineering curriculum aligns with the CDIO standards, marking a significant stride in engineering education. Our pedagogical contribution is threefold, encapsulating the design, execution, and evaluation of the AI module over a span of three years. The curriculum employs active learning strategies (standard 8) to immerse students in AI problem-solving, fostering an environment of practical engagement. The curriculum unfolds in a structured manner (standard 3), starting with the AI discovery phase in the third year, where students acquaint themselves with Python, AI libraries, and foundational AI concepts, including elementary classification and regression algorithms. The second phase, in the fourth year, pivots on the application and reinforcement of the knowledge acquired, with a focus on the lifecycle of an AI project. Students culminate this stage by undertaking a mini project adhering to AI project conventions. The final phase, in the fifth year, emphasizes practical application and mastery, culminating in an NVIDIA DLI workshop where students have the opportunity to earn a certificate in AI for predictive maintenance. In conclusion, the paper presents a critical analysis of this pedagogical approach, highlighting its pragmatic applications and the well-paced learning trajectory that aligns with student capability. Nonetheless, it underscores the imperative of achieving a symmetrical balance between the theoretical and practical aspects of AI to fully harness its potential in electromechanical engineering.

Authors (New): 
Mohamed Hedi Riahi
Nadia AJAILIA
Affiliations: 
ESPRIT School of Engineering, Tunisia
Keywords: 
Artificial Intelligence
Electromechanical engineering
Engineering education
Predictive maintenance
CDIO Standard 1
CDIO Standard 2
CDIO Standard 3
CDIO Standard 5
CDIO Standard 6
CDIO Standard 8
CDIO Standard 11
Year: 
2024
Reference: 
Cao, R., & Sun, L. (2020). Design and practice of machine learning course based on cdio and student behavior data. In 2020 15th international conference on computer science & education (iccse) (p. 553-556). IEEE.: 
https://doi.org/10.3390/app12083751
Chen, L., Chen, P., & Lin, Z. (2020). Artificial intelligence in education: A review. Ieee Access.: 
https://doi.org/10.1109/ACCESS.2020.2988510
Crawley, E., Malmqvist, J., Ostlund, S., Brodeur, D., & Edstrom, K. (2007). Rethinking engineering education. The CDIO approach, 302(2), 60-62.: 
http://dx.doi.org/10.1007/978-3-319-05561-9
Edström, K., & Kolmos, A. (2014). Pbl and cdio: complementary models for engineering education development. European Journal of Engineering Education, 39(5), 539-555.: 
https://doi.org/10.1080/03043797.2014.895703
Grüner, T., Böllhoff, F., Meisetschläger, R., Vydrenko, A., Bator, M., Dicks, A., & Theissler, A. (2020). Evaluation of machine learning for sensorless detection and classification of faults in electromechanical drive systems. Procedia Computer Science.: 
https://doi.org/10.1016/j.procs.2020.09.170
Humble, N., & Mozelius, P. (2019). Artificial intelligence in education—a promise, a threat or a hype. In Proceedings of the european conference on the impact of artificial intelligence and robotics (p. 149-56).: 
http://dx.doi.org/10.34190/ECIAIR.19.005
Lee, J., Bagheri, B., & Kao, H.-A. (2015). A cyber-physical systems architecture for industry 4.0-based manufacturing systems. Manufacturing letters.: 
https://doi.org/10.1016/j.mfglet.2014.12.001
Malmqvist, J., Knutson Wedel, M., Lundqvist, U., Edström, K., Rosén, A., Fruergaard Astrup, T., . . . others (2019). Towards cdio standards 3.0. In Proceedings of the 15th international cdio conference (p. 512-529).: 
Novatchkov, H., & Baca, A. (2013). Artificial intelligence in sports on the example of weight training. Journal of sports science & medicine, 12(1), 27.: 
NVIDIA. (n.d.). Applications of ai for predictive maintenance. Retrieved from: https://www.nvidia.com/en-us/training/instructor-led-workshops/predictive-maintenance/: 
Tsai, Y.-T., Wang, C.-C., Peng, H.-S., Huang, J. H., & Tsai, C.-P. (2018). Construction of artificial intelligence mechanical laboratory with engineering education based on cdio teaching strategies. In Innovative technologies and learning: First international conference, icitl 2018, Portoroz, Slovenia, august 27–30, 2018, proceedings 1 (p. 81-87).: 
Go to top