OPTIMISATION WITH AI IN ENGINEERING - 2027/8

Module Overview

How do we find the "perfect" design in a sea of thousands of variables? This module focuses on the transition from conceptual design to high-performance optimisation. You will leverage AI-driven techniques to solve complex engineering challenges, from enhancing structural performance to strategic material selection.

The module is built around two core pillars: a Replication Activity, where you critically reproduce and validate advanced optimisation methods from current research literature, and a Group Optimisation Project, where you will architect and execute a solution for a self-defined, multi-faceted engineering problem. By combining global search algorithms with local refinement and surrogate modelling, you will learn to navigate the trade-offs between computational cost and design fidelity.

Please note that the information detailed within this record is accurate at the time of publishing and may be subject to change. This record contains information for the most up to date version of the programme / module for the 2027/8 academic year.

Module provider

School of Engineering

Module Leader

HAGEN-ZANKER Alex (Sch of Eng)

Number of Credits: 30

ECTS Credits: 15

Framework: FHEQ Level 7

Module cap (Maximum number of students): N/A

Module Availability

Semester 2

Prerequisites / Co-requisites

N/A

Module content

The curriculum is divided into a foundational replication phase and a capstone application phase:

1. The Optimisation Toolbox

• Mathematical Foundations: Parameterization of design spaces and encoding boundary conditions.
• Global Search Algorithms: Mastery of nature-inspired and heuristic methods (e.g., Genetic Algorithms, PSO).
• Local Refinement & Bayesian Methods: Utilizing gradient-based search and probabilistic modelling for fine-tuning solutions.
• Surrogate Modelling (Metamodelling): Using AI to approximate expensive simulation data.

2. Research Replication

• Literature Appraisal: Selecting and dissecting state-of-the-art optimisation studies.
• Methodological Reproduction: Replicating technical workflows to verify research claims and understand algorithm performance.

3. Group Optimization Project

• Problem Definition: Scoping a real-world engineering challenge.
• Collaborative Architecture: Dividing roles (e.g., Data Engineer, Optimisation Lead, Validation Lead) to execute a complex team project.

Assessment pattern

Alternative Assessment

It is not possible to complete the group assignments of the module without substantial participation. Without substantial participation in group work the next opportunity to take part in the assessment is when the module is offered to the next cohort of students. For students who have substantially participated in the group work there is the following alternative assessment: ¿ Participation in Seminars: Alternatively assessed by reflective essay following personalised brief. ¿ Group Project Presentation: Alternatively assessed by video recording of individual presentation following personalised brief. ¿ Group Project Report: Alternatively assessed by individual report following personalised brief.

Assessment Strategy

The assessment strategy is designed to:

• Achieve engagement at technical depth with state-of-the-art in the use of AI in engineering optimization.
• Use challenge lead Problem-Based Learning (PBL) centered on a high-stakes group project.

• Replication Report: A detailed individual report reproducing a published study, including a critical evaluation of the original methodology and results. (LO1, LO2, LO5)
• Group Project Report: A collaborative technical document detailing the architecture and results of the team-defined optimization challenge. (LO1, LO3, LO4)
• Group Presentation & Oral Defense: Teams present their final design solution, with each member defending their individual contribution and the collective engineering logic. (LO5)
• Seminar Participation: Engagement in peer-review and technical discussions throughout the semester (LO5).

Peer review and verbal feedback during tutorials

Module aims

• Equip students to translate physical engineering constraints and challenges into rigorous mathematical optimisation frameworks.
• Develop technical proficiency in deploying and fine-tuning evolutionary algorithms and Bayesian optimisation for design space exploration.
• Cultivate the ability to lead and contribute to specialised subgroups within a structured, multidisciplinary team environment.
• Enable students to critically evaluate AI-generated outputs and seamlessly integrate them into traditional, high-fidelity engineering workflows.

Learning outcomes

Methods of Teaching / Learning

The learning and teaching strategy is designed to:

• Focus, initially, on acquisition of in-depth knowledge in specialised area of optimisation with AI
• Subsequently, learn to apply skills, collaboratively, in the context of an engineering challenge

The learning and teaching methods include:

• Focused Lectures: Covering the theoretical underpinnings of search algorithms and metamodelling.
• Technical Workshops: Hands-on integration of AI optimisation libraries with engineering solvers (e.g., Python integration with CAD/FEA).
• Research Tutorials: Mentored sessions focused on the challenges of reproducing academic literature.
• Project-Based Learning (PBL): Intensive group work where teams apply the "Design-Optimize-Validate" cycle.

Indicated Lecture Hours (which may also include seminars, tutorials, workshops and other contact time) are approximate and may include in-class tests where one or more of these are an assessment on the module. In-class tests are scheduled/organised separately to taught content and will be published on to student personal timetables, where they apply to taken modules, as soon as they are finalised by central administration. This will usually be after the initial publication of the teaching timetable for the relevant semester.

Reading list

https://readinglists.surrey.ac.uk
Upon accessing the reading list, please search for the module using the module code: ENGM327

Other information

The School of Engineering is committed to developing graduates with strengths in Employability, Digital Capabilities, Global and Cultural Capabilities, Sustainability, and Resourcefulness and Resilience. This module is designed to allow students to develop knowledge, skills, and capabilities in the following areas:

Employability: This module mirrors the R&D environment of leading engineering firms, preparing students for roles in advanced simulation, performance engineering, and systems optimisation.

Digital Capabilities: Mastery of high-dimensional optimisation platforms and the ability to bridge AI toolsets with heavy-duty physics solvers.

Global and Cultural Capabilities: Examining algorithmic bias and the ethical impact of automated design across different regulatory frameworks.

Sustainability: Optimisation is the key to sustainability; students learn to minimize material usage and energy consumption through precise algorithmic refinement.

Resourcefulness and Resilience: The Replication Activity builds the resilience needed to troubleshoot "failed" replications¿a common reality in research¿and the resourcefulness to find alternative pathways.