Prediction of the Bilinear Stress-Strain Curve of Aluminum Alloys Using Artificial Intelligence and Big Data

Abstract

<jats:p>Aluminum alloys are among the most widely used materials in demanding industries such as aerospace, automotive or food packaging and, therefore, it is essential to predict the behavior and properties of each component. Tools based on artificial intelligence can be used to face this complex problem. In this work, a computer-aided tool is developed to predict relevant mechanical properties of aluminum alloys—Young’s modulus, yield stress, ultimate tensile strength and elongation at break. These predictions are based on the alloy chemical composition and tempers, and are employed to estimate the bilinear approximation of the stress-strain curve, very useful as a decision tool that helps in the selection of materials. The system is based on the use of artificial neural networks supported by a big data collection about technological characteristics of thousands of commercial materials. Thus, the volume of data exceeds 5 k entries. Once the relevant data have been retrieved, filtered and organized, an artificial neural network is defined and, after the training, the system is able to make predictions about the material properties with an average confidence greater than 95 % . Finally, the trained network is employed to show how it can be used to support decisions about engineering applications.</jats:p>

Prediction of Mechanical Properties by Artificial Neural Networks to Characterize the Plastic Behavior of Aluminum Alloys

“…The main alloying elements of aluminum are copper, magnesium, silicon, manganese, nickel, and zinc [ 8 ]. The relatively low hardness of aluminum can sometimes cause abrasive wear of the material [ 9 ]. The low hardness of pure aluminum makes it a non-ideal material for building structures.…”

“…These supplementary elements do not simply improve the hardness of the metal, but also modify other properties [ 11 , 12 ]. Besides, heat-treated aluminum alloys can withstand more load due to the precipitation hardening process of aluminum, even though the hardness is different due to the addition of various alloying agents [ 9 ].…”

“…There is a wide variety of decision support systems focused on materials engineering [ 18 ]; however, very few really take advantage of technologies based on artificial intelligence [ 9 , 10 , 19 , 20 , 21 , 22 ]. Although several studies that use machine learning to address metallotechnics and the properties of metals have been published [ 23 , 24 ], aluminum alloys have hardly been investigated considering their tempers from an industrial perspective using these tools [ 25 ].…”

“…In this study, a computer-aided methodology is developed to predict some fundamental properties of aluminum alloys whose chemical composition and treatments (thermal and mechanical) are known [ 10 ]. The system presented in this work is able to predict accurately the yield stress (YS) and the ultimate tensile strength (UTS) of aluminum alloys based on Brinell hardness data [ 9 , 26 ]. This methodology uses artificial neural networks (ANNs) and technology based on machine learning to carry out the predictions.…”

“…In this study, a third new method is going to be developed, similar to the first one, but with the particularity that the function that relates the tensile properties with Brinell hardness will be obtained using artificial intelligence and machine learning [ 41 ]. This new methodology takes, as input, the chemical composition, the temper, and the Brinell hardness and, then, approximates the yield strength and the ultimate tensile strength [ 9 , 10 ].…”