FREE PhD study and funding virtual fair REGISTER NOW FREE PhD study and funding virtual fair REGISTER NOW

Exploiting Machine Learning for Automated Interpretation of Corrosion Testing Data

   Department of Materials

This project is no longer listed on and may not be available.

Click here to search for PhD studentship opportunities
  Dr M Curioni  No more applications being accepted  Competition Funded PhD Project (UK Students Only)

About the Project

Most products that enter the market are protected from environmental degradation (corrosion). Forecasting the long-term performance based on short term tests is challenging both experimentally (because it is difficult to accelerate the degradation mechanisms) and theoretically (because failure modes are highly system-dependent). Corrosion tests rely either on exposure to an aggressive environment, followed by evaluation of the surface, or on the application of an electrical signal to the surface, to measure a response. Both approaches rely heavily on human interaction for the interpretation of the results. This constitutes a bottleneck, produces inconsistencies, and limits the number of tests that can be performed due to cost.

 This project aims to exploit machine learning (ML) to reduce the human input in corrosion testing. ML algorithms will be developed interpret corrosion testing data obtained by electrochemical measurements. ML algorithms will also be developed to interpret images of corroded surface such that they can be automatically ranked according to standards.

This project is part of the MADSIM PhD Training Centre. This initiative is a community for PhD students at the University of Manchester whose projects involve mathematical modelling, big data and AI and involve collaboration between supervisors in different departments at the University and/or supervisors are based in external partner organisations.

Students appointed to this position will be expected to play an active role in MADSIM.

At the University of Manchester, we pride ourselves on our commitment to fairness, inclusion and respect in everything we do. We welcome applications from people of all backgrounds and identities and encourage you to bring your whole self to work and study. 

Applicants are expected to hold, or about to obtain, a minimum upper second undergraduate degree (or equivalent / higher qualification) in Engineering, Materials Science, Physics, Computer Science, Statistics or Applied Mathematics, or a closely related discipline. The project has both an experimental and a mathematical component, therefore candidates should demonstrate interest in both aspects. Excellent computer coding skills in R and/or Python are desirable. 

 The successful candidate will work under the joint supervision by the Department of Materials and the Department of Mathematics, and in close collaboration with industrial partners. 

To apply:

 The University’s Equality and Diversity policy

is applicable to all applicants, students and staff.

Funding Notes

MADSIM Interdisciplinary PhD studentships in Modelling, AI and Big Data
The bursary / stipend will follow the EPSRC minimum rate. Unfortunately we don’t know exactly how much this will be each year because EPSRC release the rates each year. The first year’s minimum stipend is in the region of £16,062


Exploring the use of machine learning for interpreting electrochemical impedance spectroscopy data: evaluation of the training dataset size, V Bongiorno, S Gibbon, E Michailidou, M Curioni, Corrosion Science, 2022.
BS EN ISO 9227:2017, Corrosion tests in artificial atmospheres, Salt Spray. tests, Br. Stand. Inst. (2017)
Electrochemical Impedance of Organic‐Coated Steel: Correlation of Impedance Parameters with Long‐Term Coating Deterioration, J.R. Scully, Journal of Electrochemical Society, 1989
Prediction of corrosion behavior using neural network as a data mining tool, M. Kamrunnahar, M. Urquidi-Macdonald, Corrosion Science, 2010.
Search Suggestions
Search suggestions

Based on your current searches we recommend the following search filters.

PhD saved successfully
View saved PhDs