Exit Menu

Intelligent, Interpretable and Adaptive Design of Steel Structures using Deep Learning and NLP

The overall aim of this research is to develop a smart design assistant which is able to intuitively perform the design of complex steel structures to Eurocode Standards. Design errors are common, costing the UK economy 100’s of £M each year and occasionally leading to loss of life.

The most common cause is human error through:

  1. misinterpretation of the design code;
  2. poor QA;
  3. insufficient experience.

This research will develop a robust method for automatically assembling design calculations using adaptive AI by implementing natural language processing (NLP) to understand the semantic meaning of the code clauses and their mathematical representation. This enables clauses to be chained together to form multi-step calculations which adapt to the structure at hand whereby only checking relevant clauses, in the order that is necessary to verify the structure.

An aspect of the research will focus on the interpretability of the calculations so that all outputs are both human and machine readable, enabling a high degree of reliability to be developed in the system.

The initial focus will be on Eurocode 3 for steel structures and the following development stages are proposed:

  1. NLP model to interpret clauses from Eurocode 3 as mathematical equations and hierarchies and relationships between variables;
  2. An adaptive algorithm that can apply the relevant clauses required for the design of an arbitrary steel structure to ensure a code-based design check;
  3. Development of the human and machine readable output format.

This may be written in Markdown for interpretability. Please contact Dr Michael Rustell at Michael.rustell@brunel.ac.uk to find out more about the project.

Skills and Experience

Due to the technical nature of this project, you will either be a computer science, a computer engineering or a civil engineering graduate with an object-oriented programming background. Comprehensive training in deep learning will be provided. You should be a highly motivated individual and possess a strong sense of curiosity. The ability to study independently, think critically and collaborate with others is essential.

When applying to this project please state your funding source and include a description of your programming capability

How to apply

If you are interested in applying for the above PhD topic please follow the steps below:

  1. Contact the supervisor by email or phone to discuss your interest and find out if you woold be suitable. Supervisor details can be found on this topic page. The supervisor will guide you in developing the topic-specific research proposal, which will form part of your application.
  2. Click on the 'Apply here' button on this page and you will be taken to the relevant PhD course page, where you can apply using an online application.
  3. Complete the online application indicating your selected supervisor and include the research proposal for the topic you have selected.

Good luck!

This is a self funded topic

Brunel offers a number of funding options to research students that help cover the cost of their tuition fees, contribute to living expenses or both. See more information here: https://www.brunel.ac.uk/research/Research-degrees/Research-degree-funding. The UK Government is also offering Doctoral Student Loans for eligible students, and there is some funding available through the Research Councils. Many of our international students benefit from funding provided by their governments or employers. Brunel alumni enjoy tuition fee discounts of 15%.

Meet the Supervisor(s)


Michael Rustell - Michael is a chartered civil engineer (CEng MICE) who holds an Engineering Doctorate (EngD) in artificial intelligence in design automation of civil infrastructure. He has spent the past 8 years in industry working in ports and marine, oil & gas and nuclear industries and was a lead data scientist for the Europe, Middle East and Africa (EMEA) region at AECOM prior to joining Brunel.  Michaels interests include: deep learning, machine learning and data science in civil engineering, natural language processing, design automation and stochastic design methods.

Tatiana Kalganova -

DEGREES AWARDED

  • PhD Napier University
  • Research-engineer degree Belarusian State University of Informatics and Radio-electronics, Minsk, Belarus
  • MSc (distinction) Belarusian State University of Informatics and Radio-electronics, Minsk, Belarus

ACADEMIC POSTS

  • 2000-present Lecturer Brunel University London
  • 2003-2011 Business Fellow London Technology Network, LTN Link between research activities at Brunel University London and industry
  • 1997-2000 PhD student Napier University
  • 1994-1997 Research Assistant Belarusian State University of Informatics and Radio-electronics