Master of Engineering (UAS), AI-Driven Computational Engineering and Design

About this programme

The AI-Driven Computational Engineering and Design programme is aimed at engineers who want to deepen their expertise in modern 3D physics-based computational design methods. The programme focuses on applying advanced computer-aided engineering simulations, statistical design of experiments, and artificial intelligence to the design and optimization of industrial products, equipment, and processes. Upon completion, you will earn a Master of Engineering (M.Eng.) degree from Turku University of Applied Sciences . Computational engineering is transforming the way industrial systems are designed. Instead of relying primarily on physical prototypes and costly, time-consuming experimental testing, engineers can increasingly create, optimize, and validate design candidates in realistic 3D physics-based simulation environments before manufacturing. This approach — the engineering equivalent of agile methods in software development — has been shown to significantly shorten product development cycles, reduce development and prototyping costs, improve product performance, and allow design engineers to efficiently consider more design candidates than is possible with traditional methods. At the same time, the proliferation of artificial intelligence facilitates workflow automation and surrogate-based design optimization, making engineering design processes faster, more systematic, and more intelligent. This leads to substantially increased efficiency in design, and, ultimately, better products. This degree programme combines proven computer-aided engineering (CAE) methods with emerging AI-driven design approaches . You will build competence in carrying out industrial computational fluid dynamics (CFD) simulations , finite element analysis (FEA) simulations, and computational design optimization using workflow automation, design of experiments, and surrogate modelling. The emphasis is on using computational methods as an integral part of engineering design optimization and decision-making, and on using design of experiments and workflow automation to maximize the efficiency of the engineering design process. During the studies, you will learn to apply CFD to the analysis and design of fluid and thermal systems and FEA to the design of structural systems . You will also learn how computational workflows can be automated and connected with numerical optimization using AI-based methods. Design of experiments and surrogate modelling will provide tools for efficiently exploring complex design spaces, identifying the most influential design parameters, and developing computationally efficient approximations of demanding simulation models. These capabilities are valuable in modern industrial applications where engineers must balance performance, reliability, cost, energy efficiency, manufacturability, time available for the design process and other competing design requirements. This degree programme is targeted at engineers who are motivated to work with technically demanding engineering design optimization problems. CFD, FEA, and surrogate modelling require a strong foundation in engineering mathematics and physics, and experience in one or more of the following: CAD design, structural mechanics, fluid flow, and/or heat transfer . The studies also require the ability to work independently when learning to use leading engineering simulation software (ANSYS). Computational engineering is powerful precisely because it combines theoretical methods, application-specific engineering skills, and advanced numerical 3D simulations: obtaining a simulation result is not enough—the engineer must also understand the underlying assumptions, assess the quality of the computational model, and interpret the results critically. Graduates of the programme will be able to contribute to the development of more efficient, high-performance industrial products and processes. The combination of physics-based simulation, computational design, automation, and artificial