Predicting the Tensile Behaviour of Cast Alloys by a Pattern Recognition Analysis on Experimental Data

• Published in: Metals (Basel ) 2019-05, Vol.9 (5), p.557
• Main Authors: Fragassa, Cristiano, Babic, Matej, Bergmann, Carlos Perez, Minak, Giangiacomo
• Format: Article
• Language: English
• Subjects: Algorithms; Alloys; Artificial intelligence; Artificial Neural Network (NN); Cast iron; Casting alloys; Clustering; compact graphite cast iron (CGI); Composite materials; Data analysis; Datasets; ductile/spheroidal cast iron (SGI); experimental data analysis; Graphite; Image analysis; Iron constituents; k-nearest neighbours (kNN); Machine learning; Machine Learning (RF); material properties prediction; Mechanical properties; Metal fatigue; Modulus of elasticity; Nodular cast iron; Nodular iron; Pattern analysis; Pattern recognition; Perlite; Photomicrographs; Process parameters; Quality control; Random Forest (RF); Strain; Ultimate tensile strength
• ISSN: 2075-4701; 2075-4701
• DOI: 10.3390/met9050557

The ability to accurately predict the mechanical properties of metals is essential for their correct use in the design of structures and components. This is even more important in the presence of materials, such as metal cast alloys, whose properties can vary significantly in relation to their constituent elements, microstructures, process parameters or treatments. This study shows how a machine learning approach, based on pattern recognition analysis on experimental data, is able to offer acceptable precision predictions with respect to the main mechanical properties of metals, as in the case of ductile cast iron and compact graphite cast iron. The metallographic properties, such as graphite, ferrite and perlite content, extrapolated through macro indicators from micrographs by image analysis, are used as inputs for the machine learning algorithms, while the mechanical properties, such as yield strength, ultimate strength, ultimate strain and Young’s modulus, are derived as output. In particular, 3 different machine learning algorithms are trained starting from a dataset of 20–30 data for each material and the results offer high accuracy, often better than other predictive techniques. Concerns regarding the applicability of these predictive techniques in material design and product/process quality control are also discussed.