Materials informatics: an intelligent multiscale materials simulation tool for accelerated formulation and in-service life prediction of specialised coatings for defence platforms
Project Leader: Ellie Hajizadeh
Primary Contact: Ellie Hajizadeh (email@example.com)
Keywords: artificial intelligence; computational materials science; defence; polymeric materials
Disciplines: Chemical & Biomolecular Engineering,Mechanical Engineering
Specialised surface coatings provide camouflage in the UV, visible, near-infrared, thermal infrared and microwave portions of the electromagnetic spectrum for Defence platforms such as aircraft, ships, and land vehicles. Apart from these aforementioned threats, these coatings are also essential in providing protection from corrosion and weathering that mars their long-term performance. Therefore, the ability to accurately predict the lifetime performance of these coatings and establish strategies to mitigate or hinder their degradation is vital to ensure the long-term survivability and sustainability of military platforms against environmental and other fast-evolving threats.
The emergence of artificial intelligence (AI) brings a new dawn to the development of materials and coatings science.
The combination and integration of materials science, multiscale simulations, and AI techniques, is such an interdisciplinary field that will assist scientists to effectively
- Guide the chemical synthesis and coatings formulation route and avoid traditional time-consuming trial-and-error material development
- Optimise the process parameters
- Simulate materials systems and obtain the hidden relationship between different variables
- Predict the specific properties of materials
- Upgrade the existing material characterisation methods.
It is this data-intensive science, recently called ‘the fourth paradigm of science’ that combines big data produced by materials simulation and laboratory experimentation and AI to compress vast quantities of known information to uncover unknown theories and guide scientific innovation.
This research program aims to exploit the acceleration offered by experimentally validated high-throughput multiscale simulations (molecular-meso-macro) and AI (particularly, machine learning and neural network) techniques for the development of an autonomous exploratory self-learning materials design system. This will enable DST scientists to:
- Fast-explore the coating materials design space
- Establish the relationship between materials structure-property-process variables
- Investigate the underlying chemical and physical mechanisms responsible for the product performance or failure (degradation) under the operational conditions, and ultimately,
- Optimise and predict the lifetime of the specialised coatings based on existing data.
Related articles on methodologies
 Elnaz Hajizadeh, Shi Yu, Shihu Wang, and Ronald G. Larson, “A novel hybrid population balance—Brownian dynamics method for simulating the dynamics of polymer-bridged colloidal latex particle suspensions”, J. Rheol. 62, 235–247 (2018).
 Elnaz Hajizadeh, Billy Todd, Peter Daivis, Journal of Rheology, 58, 281–305 (2014)
 Elnaz Hajizadeh, Billy Todd, Peter Daivis, J. Chem. Phys, 142, 174911 (2015)
 Elnaz Hajizadeh, Billy Todd, Peter Daivis, J. Chem. Phys, 141, 194905 (2014)
 Guorui Zhu, Hossein Rezvantalab, Elnaz Hajizadeh, Xiaoyi Wang, Ronald G Larson, Journal of Rheology, 60, 327–343 (2016)
 Elnaz Hajizadeh, Ronald G Larson, Soft Matter, 13, 5942–5949 (2017)
 Elnaz Hajizadeh, Hamid Garmabi, International Journal of Chemical and Biomolecular Engineering, 1, 40-44, (2008)