Adaptive Predictive Simulation Modelling Using the Digital Twin Paradigm

Structural integrity management (SIM) involves the application of qualified standards, by competent people, using appropriate processes and procedures throughout the structure’s life cycle, from design through to decommissioning, to ensure that through an ongoing process of risk management the structure’s continued fitness-for-purpose (FFP) is maintained.

In undertaking the structural integrity management task, engineers use simulation tools to predict the risk to the structure from degradation mechanisms such as corrosion and cracking. Sophisticated three dimensional computer simulation models derived from the simulation tools are used to predict the location of the damage and its severity. However the accuracy of the predictions is very much dependent upon the input data describing the properties of the materials and the environmental conditions the structure experiences.
The constantly evolving nature of the properties of the materials and the environmental conditions of the structure make keeping the accuracy of the predictions of the structure’s FFP challenging. Furthermore, material science and the changing nature of material engineering has brought about the requirement that structures have lower mass while being subjected to higher loads and more extreme service conditions over longer time periods than ever before.

Conventional approaches such as survey methods which are used to make measurements which are then used to infer changes in the material or environmental properties are expensive, time consuming and provided insight into the structure and model behaviour that is likely to be out of sync with the measured operational structure.

To address the shortcomings of conventional approaches, a fundamental paradigm shift is needed. This paradigm shift, the Digital Twin, integrates ultra-high fidelity simulation with the structure’s on-board integrated structure health management system, maintenance history and all available historical and structural data to mirror the life of its physical twin and enable unprecedented levels of safety and reliability.
This project will investigate the application of data twinning to predict simulated models for large real-world structures. Using digital twin modelling, we aim to develop algorithms that update model predictors online. This will make it possible to investigate methods of adapting and changing simulation models online as the nature of the monitored structure changes. Adaptation helps to prolong the useful life of learned predictive/inference models which is an important part of making models more useful to non-expert users.

The developed methods will be tested and verified using the simulation models generated based on the current heuristics of using survey data collected from the machine systems of industrial partners.

The successful PhD candidate will be expected to investigate and develop methods for efficient and robust simulation model analytics and predictions that enable manufacturers to edit a virtual prototype throughout the production process and maintain the physical twin’s continued fitness-for-purpose (FFP). The goal is to provide more accurate predicted structural models that reduce development and maintenance time and costs. Therefore, in this position, understanding of physical modelling and creation of these models is essential together with the analytics skills, i.e. combining mechanical/process engineering with data analytics.

How to apply:

Applications are made via our website using the Apply Online button below. If you have an enquiry about this project please contact us via the Email NOW button below, however your application will only be processed once you have submitted an application form as opposed to emailing your CV to us.

Candidates for funded PhD studentship must demonstrate outstanding qualities and be motivated to complete a PhD in 3 years.

The PhD Studentships are open to UK, EU and international students. Candidates for a PhD Studentship should demonstrate outstanding qualities and be motivated to complete a PhD in 3 years and must demonstrate:

• A 1st class honours degree and/or a relevant Master’s degree with distinction or equivalent. If English is not your first language you’ll need IELTS (Academic) score of 6.5 minimum (with a minimum 6.0 in each component).

Additional Eligibility Criteria:

The candidate should hold MSc degree in a suitable field (Automation, Signal Processing, Information Sciences, Computational Intelligence, Computational Mechanics, etc.).

A theoretically oriented, problem-solving mind with experience of data analytics, and simulation and modelling of physical systems will be an added advantage on this PhD. Moreover, a good command in programming with R, Python, C/C++/Fortran is a necessity. Good team working skills will be expected.