Enhancing fatigue life of SS316L via shot peening and machine learning

This study presents a method to improve the fatigue life of SS316L samples fabricated by Laser Powder Bed Fusion (LPBF). Shot peening applied after heat treatment at 900°C for 1 h enhanced fatigue life to 3,829,354 cycles. A key innovation of this work is the investigation of shot peening coverage (C), which reached up to 68%—a critical factor in improving fatigue performance. To understand the role of partial residual stress relief, the same optimized shot peening parameters were applied to as-built samples and those heat-treated at a lower temperature of 600°C. This enabled the evaluation of how residual stress states affect fatigue behavior. Using material condition, peening depth, C, and peening duration as input features, machine learning models (Random Forest and XGBoost) achieved over 90% accuracy, offering a predictive framework for optimizing fatigue life in additively manufactured metals.

Authors

Institutions

Publication Details

Journal
Surface Engineering
Published
2025-08-01
DOI
https://doi.org/10.1177/02670844251365915
Citations
1
Primary Topic
Surface Treatment and Residual Stress
Type
article
Field-Weighted Citation Impact
0.71

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Enhancing fatigue life of SS316L via shot peening and machine learning

Vijay Ravula, Chandan Mondal, U. Chandrasekhar, Hari Krishna Chirala
1 citations
Surface Engineering
Surface Treatment and Residual Stress
0.71
article

Enhancing fatigue life of SS316L via shot peening and machine learning

Vijay Ravula, Chandan Mondal, U. Chandrasekhar, Hari Krishna Chirala
article en
1 citations

Abstract

This study presents a method to improve the fatigue life of SS316L samples fabricated by Laser Powder Bed Fusion (LPBF). Shot peening applied after heat treatment at 900°C for 1 h enhanced fatigue life to 3,829,354 cycles. A key innovation of this work is the investigation of shot peening coverage (C), which reached up to 68%—a critical factor in improving fatigue performance. To understand the role of partial residual stress relief, the same optimized shot peening parameters were applied to as-built samples and those heat-treated at a lower temperature of 600°C. This enabled the evaluation of how residual stress states affect fatigue behavior. Using material condition, peening depth, C, and peening duration as input features, machine learning models (Random Forest and XGBoost) achieved over 90% accuracy, offering a predictive framework for optimizing fatigue life in additively manufactured metals.

Surface EngineeringVol. 41(8-9)
Lahore College for Women University (PK), Defence Metallurgical Research Laboratory (IN), International Advanced Research Centre for Powder Metallurgy and New Materials (IN), Shriram Institute for Industrial Research (IN), Central Tobacco Research Institute (IN)
Science and Engineering Research Board
Openalex Percentile: Top 29%
Surface Treatment and Residual Stress
0.71
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.