Development of Effective Corrosion Testing Approaches for Performance Evaluation of Organic Coatings
Lead Research Organisation:
University of Manchester
Department Name: Materials
Abstract
The aim of the PhD is to develop and apply innovative and efficient corrosion testing methods that can generate rapidly corrosion and performance data to support machine learning activities. The PhD activity will focus on designing and implementing corrosion testing approaches exploiting electrochemistry, imaging and other methods, such as reliable, standardized, and representative data can be obtained for a variety of coating systems and correlated to long term performance information. The data obtained will then be used to train machine learning algorithms aiming at optimizing new coatings formulations. One of the key challenges to be addressed is the acceleration in the laboratory of specific processes that are responsible for failure in field applications. To approach the challenge, information from modelling activities and from high-resolution imaging, will be exploited. Once suitable methods for corrosion testing are developed, the data produced and the methodologies developed will also be exploited to enhance fundamental understanding of long-term failure processes.
Organisations
People |
ORCID iD |
Michele Curioni (Primary Supervisor) | |
Vincenzo Bongiorno (Student) |
Publications
Bongiorno V
(2022)
Exploring the use of machine learning for interpreting electrochemical impedance spectroscopy data: evaluation of the training dataset size
in Corrosion Science
Bongiorno V
(2023)
Evaluating organic coating performance by EIS: Correlation between long-term EIS measurements and corrosion of the metal substrate
in Materials and Corrosion
Studentship Projects
Project Reference | Relationship | Related To | Start | End | Student Name |
---|---|---|---|---|---|
EP/R513131/1 | 30/09/2018 | 29/09/2023 | |||
2564044 | Studentship | EP/R513131/1 | 30/09/2020 | 31/03/2024 | Vincenzo Bongiorno |
Description | Machine Learning models can be used to interpret electrochemical tests to assess the performance of organic coatings for corrosion protection. Machine Learning can be trained with simulated data and then used to interpret experimental data with satisfactory accuracy. |
Exploitation Route | This study proved the methodology of using Machine Learning to interpret electrochemical data from organic coatings. This can be used in other fields of application, hence it could be potentially be used by others. |
Sectors | Aerospace Defence and Marine Construction Energy Transport |
Description | My findings will be used to help in the automation of organic coatings testing for corrosion protection using a Machine Learning-based tool. Additionally, this study offers a proof of concept which has been never seen before, which can potentially spread to other fields and be adapted in other applications of corrosion testing and new materials development. |
Title | Automatic EIS Measurement set-up and Machine Learning-based EIS analysis |
Description | The software is at is fist stage, composed of Python codes which call Machine Learning models to interpret Electrochemical Impedance Spectroscopy from organic coatings for corrosion protection. |
Type Of Technology | New/Improved Technique/Technology |
Year Produced | 2022 |
Impact | This software could potentially automate the interpretation of Electrochemical Impedance Spectroscopy, allowing its employment in industrial field. |
Description | Application of Electrochemical Techniques to Organic Coatings |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Other audiences |
Results and Impact | My work was presented for the first time in an international conference to an audience composed of researchers, PGRs and leading academics in the field of electrochemical techniques for organic coatings. The aim was to sponsor my publication and show the potential impact of my research. The audience had some questions and ideas for improvement. |
Year(s) Of Engagement Activity | 2022 |
Description | Corrosion Symposium |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | National |
Primary Audience | Other audiences |
Results and Impact | I presented my initial results in a National Scientific conference about corrosion to an audience composed of PGR students, researchers and academics working in the field. |
Year(s) Of Engagement Activity | 2021 |
Description | Corrosion@Manchester |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | National |
Primary Audience | Other audiences |
Results and Impact | Presentation to a broad audience of students and researchers to show the impact of Machine Learning for the interpretation of electrochemical data for organic coating assessment. |
Year(s) Of Engagement Activity | 2023 |
Description | EUROCORR 2023 |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Other audiences |
Results and Impact | My project was presented in this scientific conference to an audience composed of PGRs, researchers, academics, professional practitioners and industrial sponsors. The final outcome of my project was presented showing how corrosion testing analysis can be automated, limiting the human intervention using Machine Learning-based techniques. The audience showed an increasing interest for this field. |
Year(s) Of Engagement Activity | 2023 |
Description | Electrochem |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | National |
Primary Audience | Postgraduate students |
Results and Impact | My work was shown at this conference composed mainly by PGR students. |
Year(s) Of Engagement Activity | 2023 |
Description | Electrochemical Methods in Corrosion Research |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Other audiences |
Results and Impact | I presented my work to academics, PGRs and researchers. The audience came from the whole Europe and showed an increasing interest in how Machine Learning can be applied for corrosion testing of organic coatings. Following the presentation, a useful debate arose bringing positive critiques and interest. |
Year(s) Of Engagement Activity | 2022 |