Using machine learning and a data-driven approach to identify the small fatigue crack driving force in polycrystalline materials

• Published in: npj computational materials 2018-07, Vol.4 (1), p.1-10, Article 35
• Main Authors: Rovinelli, Andrea, Sangid, Michael D., Proudhon, Henry, Ludwig, Wolfgang
• Format: Article
• Language: English
• Subjects: 639/301/1023/1026; 639/301/1023/303; Artificial intelligence; Bayesian analysis; Characterization and Evaluation of Materials; Chemistry and Materials Science; Computational Intelligence; Computer simulation; Condensed Matter; Crack propagation; Fatigue cracks; Fatigue failure; Fracture mechanics; Learning algorithms; Machine learning; Materials Science; Mathematical and Computational Engineering; Mathematical and Computational Physics; Mathematical Modeling and Industrial Mathematics; Mathematical models; Physics; Polycrystals; Propagation; Service life assessment; Theoretical
• ISSN: 2057-3960; 2057-3960
• DOI: 10.1038/s41524-018-0094-7

The propagation of small cracks contributes to the majority of the fatigue lifetime for structural components. Despite significant interest, criteria for the growth of small cracks, in terms of the direction and speed of crack advancement, have not yet been determined. In this work, a new approach to identify the microstructurally small fatigue crack driving force is presented. Bayesian network and machine learning techniques are utilized to identify relevant micromechanical and microstructural variables that influence the direction and rate of the fatigue crack propagation. A multimodal dataset, combining results from a high-resolution 4D experiment of a small crack propagating in situ within a polycrystalline aggregate and crystal plasticity simulations, is used to provide training data. The relevant variables form the basis for analytical expressions thus representing the small crack driving force in terms of a direction and a rate equation. The ability of the proposed expressions to capture the observed experimental behavior is quantified and compared to the results directly from the Bayesian network and from fatigue metrics that are common in the literature. Results indicate that the direction of small crack propagation can be reliably predicted using the proposed analytical model and compares more favorably than other fatigue metrics. Crack propagation: machine learning identifies micromechanical variables A machine learning technique can identify the complex variables behind the propagation direction of small cracks in a titanium alloy. A team led by Michael Sangid at Purdue University in the U.S.A built two separate Bayesian networks using machine learning to analyse diffraction and tomography data acquired during in situ fatigue cycling of a titanium alloy. The orientation of the first principal stress axis in a specific direction and the maximum resolved shear stress were the most strongly correlated with crack propagation, and were incorporated into an analytical relationship to describe the probability of the crack propagation direction. This analytical expression reproduced experimental results and was more reliable than previous literature predictions. This sort of semi-supervised machine learning methodology may help us identify driving forces in other complex engineering problems.