Machine Learning Based Predictions of Fatigue Crack Growth Rate of Additively Manufactured Ti6Al4V

Abstract

The present work focusses on machine learning assisted predictions of the fatigue crack growth rate (FCGR) of Ti6Al4V (Ti64) processed through laser powder bed fusion (L-PBF) and post processing. Various machine learning techniques have provided a flexible approach for explaining the complex mathematical interrelationship among processing-structure-property of the materials. In the present work, four machine learning (ML) algorithms, such as K- Nearest Neighbor (KNN), Decision Trees (DT), Random Forests (RF), and Extreme Gradient Boosting (XGB) algorithms are implemented to analyze the Fatigue Crack growth rate (FCGR) of Ti64 alloy. After tuning the hyper parameters for these algorithms, the trained models were found to estimate the unseen data as equally well as the trained data. The four tested ML models are compared with each other over the training as well as testing phase, based on their mean squared error and R2 scores. Extreme Gradient Boosting has performed better for the FCGR predictions providing least mean squared errors and higher R2 scores compared to other models.

Predictability of Different Machine Learning Approaches on the Fatigue Life of Additive-Manufactured Porous Titanium Structure

“…In this work, the ML-based method was used to predict the fatigue life of AM titanium. However, it is important to acknowledge that other factors such as microstructure and various process parameters [36][37][38][39][40] can also potentially influence the fatigue life. To further enhance the accuracy and robustness of the prediction model, it is recommended that future research considers incorporating as many influencing variables as possible.…”

Recent developments and future trends in fatigue life assessment of additively manufactured metals with particular emphasis on machine learning modeling

“…Konda et al 164 used decision trees and extreme gradient boosting (XGB) algorithms to predict fatigue crack growth behavior of SLM Ti‐6Al‐4V under different post‐processing conditions. The results were compared by mean squared error (MSE) and coefficient of determination, which indicated that the XGB has better generalization ability on this problem.…”

Review on machine learning techniques for the assessment of the fatigue response of additively manufactured metal parts

“…Single source [21][22][23][24]27,[30][31][32][34][35][36] Multi-source [16][17][18][19][20][28][29][30]33 the model, allowing the user to easily consider and implement confidence level bands in the stress life plots. 24 Nonetheless, in, 28 the mean and standard deviation of N f are estimated by using a PINN layout instead of a GPR, with a properly designed custom loss function that uses probability density function and cumulative distribution function with location parameter μ and scale parameter σ.…”

“…If the training database includes specimens coming from more experimental campaigns, where different thermal and surface post treatments were applied, their accountancy is recommended to assess their effect, either with a Boolean 17 or classification strategy. 20,24…”

“…20 Decision trees (DT) is also a rather basic technique that divides the feature space into regions as the decision tree is run and outputs predictions based on the average value, for regression tasks, or the majority class, for classification. 20 Random Forest (RF) on the other hand, uses multiple DTs to generalize and improve even more the prediction by reducing overfitting. 21 Support vector machines (SVM) tries to find a hyperplane that separates in the best manner the classes to be distinguished by maximizing the distance between the hyperplane and those classes; it can also be used for regression purposes.…”