Accelerated alloy discovery using synthetic data generation and data mining. (15th April 2023)

• Record Type: Journal Article
• Authors: Kannan, Rangasayee; Nandwana, Peeyush
• Is Part Of: Scripta materialia. Number 228(2023)
• Publication Date: 2023-04-15
• Subjects: Alloy design -- Data Mining -- Synthetic Data -- Machine Learning -- CALPHAD; Materials -- Periodicals; Metallurgy -- Periodicals; Metalen; Legeringen; Materiaalkunde; Metals, metalworking and machinery industries; Metals; Electronic journals; 620.11
• DOI: 10.1016/j.scriptamat.2023.115335
• Languages: English
• ISSNs: 1359-6462

Abstract

Abstract: The search for new alloys with improved properties is never ending with infinite combinations and amounts of alloying elements in the alloy. Advancements in machine learning have made navigating this enormous search space feasible. However, training the machine learning models and tuning their hyper-parameters to make accurate predictions can be time-consuming and often require high-performance computing resources. Furthermore, the quality of the predictions depend on the availability of sufficient training data. Here, we present a generic approach to accelerate alloy discovery by coupling high throughput CALPHAD calculations, synthetic data generation, and data mining. As a demonstration of the approach, we design super bainitic steels that form bainite at 200 ∘ C in lower transformation times. Graphical abstract: