PSI - Issue 56

ScienceDirect Available online at www.sciencedirect.com ScienceDirect Structural Integrity Procedia 00 (2023) 000–000 Available online at www.sciencedirect.com ScienceDirect Structural Integrity Procedia 00 (2023) 000–000 Available online at www.sciencedirect.com Procedia Structural Integrity 56 (2024) 105–110

www.elsevier.com/locate/procedia

www.elsevier.com/locate/procedia

2452-3216 © 2023 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of the SIRAMM23 organizers 10.1016/j.prostr.2024.02.044 2452-3216 © 2023 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of the SIRAMM23 organizers 2452-3216 © 2023 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of the SIRAMM23 organizers * Corresponding author. Tel.:+91 6000585610. E-mail address: ed20d003@smail.iitm.ac.in © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of the SIRAMM23 organizers Abstract The present work is focused on machine learning-assisted predictions of the low cycle fatigue behaviour and fatigue crack growth rate (FCGR) of 17- 4 PH SS processed through L-PBF and post-processing. Various machine learning techniques reported in the literature 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 17-4 PH SS alloy. After optimizing 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 among each other over the training as well as the testing phase based on their mean squared error and R2 scores. Extreme Gradient Boosting model has performed better for the FCGR predictions providing the least mean squared errors and higher R2 scores compared to other models. Abstract The present work is focused on machine learning-assisted predictions of the low cycle fatigue behaviour and fatigue crack growth rate (FCGR) of 17- 4 PH SS processed through L-PBF and post-processing. Various machine learning techniques reported in the literature 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 17-4 PH SS alloy. After optimizing 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 among each other over the training as well as the testing phase based on their mean squared error and R2 scores. Extreme Gradient Boosting model has performed better for the FCGR predictions providing the least mean squared errors and higher R2 scores compared to other models. Keywords: Fatigue; 17-4 PH SS; Machine learning; Additive manufacturing. 1. Introduction In the field of internet of things, data may now be shared and retrieved via cloud-based data storage systems from any location in the globe [1]. Thus, the introduction of advanced data collection and interpretation techniques, such as support vector mechanisms, decision trees, and random forests approaches, can address the shortcomings in the current Structural Integrity and Reliability of Advanced Materials obtained through Additive Manufacturing (SIRAMM23) Fatigue Life and Crack Growth Rate Prediction of Additively Manufactured 17-4 PH Stainless Steel using Machine Learning Structural Integrity and Reliability of Advanced Materials obtained through Additive Manufacturing (SIRAMM23) Fatigue Life and Crack Growth Rate Prediction of Additively Manufactured 17-4 PH Stainless Steel using Machine Learning B. Kalita a, *, R.C. Abhiraaj a , R. Jayaganthan b a Student, Engineering Design Department, IIT Madras, Chennai, India-600036 b Professor, Engineering Design Department, IIT Madras, Chennai, India-600036 B. Kalita a, *, R.C. Abhiraaj a , R. Jayaganthan b a Student, Engineering Design Department, IIT Madras, Chennai, India-600036 b Professor, Engineering Design Department, IIT Madras, Chennai, India-600036 Keywords: Fatigue; 17-4 PH SS; Machine learning; Additive manufacturing. 1. Introduction In the field of internet of things, data may now be shared and retrieved via cloud-based data storage systems from any location in the globe [1]. Thus, the introduction of advanced data collection and interpretation techniques, such as support vector mechanisms, decision trees, and random forests approaches, can address the shortcomings in the current * Corresponding author. Tel.:+91 6000585610. E-mail address: ed20d003@smail.iitm.ac.in