Specialisation: AI for Engineering

MISCADA’s Artificial Intelligence for Engineering specialisation uniquely combines AI expertise with engineering practice. Unlike general AI programs, this specialisation focuses on integrating AI with physical systems, developing solutions that respect real engineering constraints and requirements. Over the course of the programme, students learn to combine traditional engineering principles with modern AI methods, preparing them to implement machine learning algorithms for engineering tasks such as real-time system optimisation, predictive maintenance, and advanced control systems. The program culminates in a substantial research project that can be conducted in collaboration with industry partners, within specific engineering domains, or as part of ongoing research initiatives. Through hands-on experience with real engineering systems and challenges, graduates develop the ability to bridge the gap between AI theory and practical engineering implementation, preparing them to drive AI-based innovation across engineering R&D and beyond.

Term 1

In term 1, students will study core modules covering essential foundations in programming, scientific computing, and data analysis. Additionally, students take Optimisation and Control for Artificial Intelligence, which covers optimisation theory, Model Predictive Control (MPC), and their implementation in AI-driven engineering systems. This module provides crucial theoretical foundations for AI applications in engineering control and optimisation problems.

Term 2

In term 2, students will take Deep Learning for Engineering, focusing on advanced deep learning techniques integrated with physical models, simulations, and engineering domain knowledge. Students will also select modules from our Core II methodological core to complement their specialisation.

Term 3

Students can choose projects among areas covered in the engineering department, such as:

Digital Twins and Simulation-Driven Design: Using AI to create and optimise virtual replicas of physical systems.
Power Systems and Control: Applying machine learning to power system optimisation and control.
AI-Driven Material Design: Using AI to discover and optimise new energy materials and batteries.
Deep Learning for Engineering Systems: From circuit modeling to fluid dynamics.
Machine Learning for Infrastructure: Applications in satellite imagery analysis.
Computational Engineering: Accelerating engineering simulations using deep learning techniques
Predictive Maintenance: Applying machine learning to sensor data for early fault detection.
AI for Manufacturing: Optimising manufacturing processes and production systems through machine learning.