Dawei Zhang1,2*, Dongmei Fu2,3， Xiaogang Li1,2，Jintao Shu1
1Beijing Advanced Innovation Center for Materials Genome Engineering, University of Science and Technology Beijing, Beijing 100083, China
2National Materials Corrosion and Protection Data Center, Beijing 100083, China
3School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, China
EXTENDED ABSTRACT: Materials corrosion is a complex failure process affected by many factors and can seriously jeopardize the service safety of infrastructure and major equipment. The estimated cost of corrosion losses adds up to more than 3 trillion yuan in China every year. The evaluation of corrosion resistance and behaviors takes the longest time and the highest cost in the whole chain of materials R&D and application. As such, corrosion evaluation is considered as one of the most challenging topics to study in the U.S. Materials Genome Initiative and is also a key and featured research direction in the field of material genome engineering in China. Materials corrosion processes are often described as high-dimensional functions as they depend on many parameters including material physical and chemical properties and environmental factors and also their complex interactions. To efficiently understand the relationship between high-dimensional corrosion data and influencing parameters, it is necessary to reduce the dimensionality of corrosion data and select some key characteristic parameters; Then the mapping relationship between corrosion data and key characteristic parameters can be established. Based on the data resource and technological foundation of the National Materials Corrosion and Protection Data Center, this study adopts efficient machine learning methods, with comprehensive consideration of the source, structure and internal logical relationship of the corrosion data and the application of different linear, local linear and nonlinear analysis methods. In views of the statistics, trend and combination characteristics, the influence parameters of materials corrosion are effectively selected and the data dimensionality is reduced via correlation and causality analyses. Subsequently, the nonlinear model between the key characteristic parameters and the corrosion process is constructed by using support vector machine, random forest, graph neural network and their optimized algorithms, in order to realize data-driven intelligent corrosion evaluation and prediction. Several case studies related to atmospheric corrosion evaluation and corrosion inhibitor selection are presented.
Keywords: Corrosion and Protection; Corrosion Big Data; Machine Leaming; Corrosion Prediction
Dawei Zhang is a full professor at University of Science and Technology Beijing(USTB). He serves as Director of Office of International Affairs of USTB, Deputy Director of National Materials Corrosion and Protection Data Center and Associate Director of Beijing Advanced Innovation Center for Materials Genome Engineering. He is the Chair of International Advisory Council of Association for Materials Protection and Performance (AMPP). His research interests are intelligent design of corrosion-resistant materials and high-efficiency corrosion evaluation and prediction technology. He has published over 200 papers and is currently an Editor of Corrosion Science. He has received several academic awards including Outstanding Young Scientist Award from Chinese Society for Corrosion and Protection, Science and Technology Research Achievements Award from Ministry of Education, Beijing Tehcnical Invention Award and was also awarded by the Beijing Nova Program.