Unified fatigue life modelling and uncertainty estimation of Ni-based superalloy family with a supervised machine learning approach. (November 2022)

• Record Type: Journal Article
• Authors: Tan, L.; Yang, X.G.; Shi, D.Q.; Hao, W.Q.; Fan, Y.S.
• Is Part Of: Engineering fracture mechanics. Volume 275(2022)
• Publication Date: 2022-11
• Subjects: Machine learning -- SVR -- Fatigue life -- Uncertainty estimation -- Ni-based superalloys; Fracture mechanics -- Periodicals; Rupture, Mécanique de la -- Périodiques; Fracture mechanics; Periodicals; 620.112605
• DOI: 10.1016/j.engfracmech.2022.108813
• Languages: English
• ISSNs: 0013-7944

Abstract

Highlights: A unified SVR fatigue life model with 17 dimensionless inputs is developed to for Ni-based superalloy family. The proposed model achieves a good prediction accuracy for both LCF and HCF regimes under wide loading conditions. An evaluation method for model generalization based on the model uncertainty and data dependence is established. Dimensionality reduced SVR models that trained with key features reorganized remains the acceptable life prediction accuracy. Abstract: Machine learning (ML) approaches, especially the supervised learning methods, show enormous advantages in fatigue investigation, whereas few works follow the interest in the generalization and uncertainty estimation of these data-drive approaches. Within this content, a supervised ML method based on the support vector regression (SVR) for key features identification of fatigue life is presented for the Ni-based superalloy family. The unified SVR model is effective at predicting lives for the Ni-based superalloy family under wide loading conditions and fatigue regimes compared with the classical fatigue life models. In addition, a model fusion method is employed to estimate the uncertainty and data dependency of the SVR model, with which the training strategy produces an important effect on the accuracy and stability of the predicted results. It is found that the coefficient of the uncertainty achieves the optimum where the training percentage is 70% of the modelling samples. After input variable selection by the pairwise Pearson correlation and key feature reorganization, the dimensionality reduced SVR model remains an acceptable accuracy. Predictably, the total strain range and the test frequency are recognized as the highly correlated variables with the fatigue life investigating from the perspective of datasets. The trained ML model and uncertainty estimation approach provide potential tools for fatigue investigation under complex loading conditions. Going forwards, it would be beneficial to generalization ability and uncertainty estimation of a ML model for unified fatigue life modelling.