Application of Machine Learning to Predict the Mechanical Properties of High Strength Steel at Elevated Temperature

Abstract

AbstractHigh strength steels are increasingly used in several areas of construction offering structural solutions with a high strength‐to‐weight ratio. Safe fire design of these structures relies heavily on accurate predictions of mechanical properties of the material with temperature. This paper presents the results obtained using Machine Learning (ML) algorithms to predict the mechanical properties, including ultimate tensile strength, yield strength and elastic modulus, of high strength steel plate material. The mechanical properties collected from the literature experimental tests show a high degree of scatter, implying that they are influenced significantly by various factors such as the testing method, manufacturing process and chemical composition. However, the current methods for predicting the mechanical properties of high strength steels at elevated temperatures by using ‘reduction factors’ adopted by the structural design codes do not consider these effects and may lead to inaccurate predictions. These deficiencies are overcome by using a ML‐based prediction method, where the effects of the chemical composition on these reduction factors are considered. Deep Neural Networks is trained to predict the mechanical properties with temperatures. The ML‐based method together with the obtained results are presented where it is shown that the trained algorithm gives an excellent correlation coefficient with very small error value.