£6,000 PhD Scholarship | APPLY NOW £6,000 PhD Scholarship | APPLY NOW

Data-driven structural health monitoring through AI-enhanced stochastic model updating and parametrisation


   Department of Mechanical and Aerospace Engineering

  , Dr Andrew Hamilton  Friday, September 30, 2022  Funded PhD Project (Students Worldwide)

About the Project

The department of Mechanical and Aerospace Engineering at the University of Strathclyde is inviting applications for the following fully funded PhD project (for international students it will be partially funded), expected to commence in October 2022.

Special Note: This project belongs to the Strathclyde International Strategic Partner (ISP) Joint PhD Cluster. It hence will be implemented with close connection with a partner project at Tsinghua University. The successful candidate is expected to be keen on international collaboration including several months visiting to Tsinghua in China.

 

Background:

 Model updating [1] has been developed as a typical topic to calibrate the parameters or the model itself to turn the model prediction towards the experimental measurements. However, it is widely recognised that the unavoidable uncertainties in both experiments and simulations must be understood in model updating. Non-deterministic modelling approaches enable characterisation, propagation, and quantification of uncertainties, providing predictions over a possible range of outcomes rather than a unique solution with maximum fidelity to a single experimental observation.

Structural Health Monitoring (SHM) plays a significant role in providing insight into the structural properties in the life-circle of produces. Model updating has a natural connection with the topic System Identification, implying the inherent properties of the physical system can be identified (or predicted) from the numerical modelling. This brings SHM and model updating together in this project: to develop a reliable numerical model with a precise indicator to support decision-making in SHM.  

For uncertainty treatment, a significant aspect is the advanced data technology to extract as much as possible uncertainty information from the available experimental data, to enhance the data-driven decision-making process. From the applicant’s recently organised special issue on advances of model updating , it is surprising to find that Artificial Intelligence (AI) techniques are absent. This has been caused by two challenges: 1) how to avoid non-unique solutions when the AI-based agent model is employed in model updating; 2) how to implement AI in the presence of gross data with multi-source of uncertainties. This project is consequently aimed at filling the gap between the popular AI techniques and their application to SHM and model updating with novel approaches of uncertainty treatment.

Overall aim:

 Overall Aim of this project is a complete framework of SHM with the aid of precise and robust models calibrated by stochastic model updating, whereby the robust and real-time features will be ensured by the AI techniques based on a database of various damage data.

Student experience and training

 Scientific training through research:

Scientific independence. The student will be trained to 1) gain a deep understanding of how the uncertainties influence the outcome of numerical simulation, and then reduce them during model updating; 2) design a complete SHM framework making full use of the robust prediction of numerical models; and to 3) develop an AI-based deep learning diagnosis network to ensure precise and real-time SHM.

Programming skills. Sensor placement optimisation, uncertainty quantification/propagation, and deep learning diagnosis network are three key aspects for the student to train the programming skills.

On-site experimental skills. Ground vibration tests with different types and configurations of sensors in various structural health states.

Transferrable skills training: Scientific writing, knowledge exchange, and international collaboration (through working together with the group at Tsinghua).

Desirable features of the candidates:

Mathematic background (especially probabilistic and statistical approaches)

Engineering mechanics and structural dynamics

Computational intelligence techniques

Finite element analysis and software skills

Familiar with MATLAB and other programming tools such as C++ or Python.

Keywords:

Model updating, uncertainty quantification, artificial intelligence, mechanical engineering, aerospace engineering, Aeronautical, Maritime and Transport Engineering, Civil & Structural Engineering


Funding Notes

The successful candidate will be funded for 3 years with UK home fee and stipend at the UKRI Doctoral Stipend rate (approx. £16,000 annually). The international student can also apply but please note the gap between the UK fee and international fee (approx. £56,000) must be filled by the applicant’s own funding.

References

[1] S. Bi, M. Beer, Overview of Stochastic Model Updating in Aerospace Application Under Uncertainty Treatment, in: L.J.M. Aslett, F.P.A. Coolen, J. De Bock (Eds.), Uncertain. Eng. Introd. to Methods Appl., Springer International Publishing, Cham, 2022: pp. 115–129. https://doi.org/10.1007/978-3-030-83640-5_8.

How good is research at University of Strathclyde in Engineering?


Research output data provided by the Research Excellence Framework (REF)

Click here to see the results for all UK universities

Email Now


PhD saved successfully
View saved PhDs