A Predictive Model for Weld Properties in AA-7075-FSW: A Heterogeneous AMIS-Ensemble Machine Learning Approach
This study addresses the research gap in materials science by developing an integrated predictive model for Ultimate Tensile Strength (UTS), Maximum Hardness (MH), and Heat Input (HI) in AA-7075 Friction Stir Welding (FSW). The aim is to enhance welding procedures, particularly in high-precision ind...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2023-09-01
|
Series: | Intelligent Systems with Applications |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2667305323000844 |
_version_ | 1797742630241566720 |
---|---|
author | Surasak Matitopanum Peerawat Luesak Somphop Chiaranai Rapeepan Pitakaso Thanatkij Srichok Worapot Sirirak Ganokgarn Jirasirilerd |
author_facet | Surasak Matitopanum Peerawat Luesak Somphop Chiaranai Rapeepan Pitakaso Thanatkij Srichok Worapot Sirirak Ganokgarn Jirasirilerd |
author_sort | Surasak Matitopanum |
collection | DOAJ |
description | This study addresses the research gap in materials science by developing an integrated predictive model for Ultimate Tensile Strength (UTS), Maximum Hardness (MH), and Heat Input (HI) in AA-7075 Friction Stir Welding (FSW). The aim is to enhance welding procedures, particularly in high-precision industries like aerospace and automotive. By incorporating four control parameters (Tilt Angle, Rotation Speed, Welding Speed, and Shoulder Diameter) and utilizing a Long Short-Term Memory (LSTM) machine learning model, a Heterogeneous Ensemble Machine Learning (He-EM) approach is developed. The Artificial Multiple Intelligence System (AMIS) optimizes the decision fusion strategy of each technique, ensuring the model's effectiveness. Validated using diverse experimental design methods and three datasets, the proposed AMIS He-EM model outperforms existing techniques (GPR, SVM, HE-UWE, and HE-WEDE) by significant margins (35.12%, 24.92%, 22.31%, and 15.48% respectively). The model's robustness is demonstrated, as its performance remains consistent across different experimental design methods. The key finding of this research is the remarkable improvement in accuracy for predicting UTS, MH, and HI in AA7075 FSW. This study highlights the importance of incorporating four control parameters and utilizing the D-optimal design for efficient exploration of the input parameter space. The implications of this research are profound, offering opportunities to optimize welding procedures, improve product performance, and streamline manufacturing processes in industries relying on AA7075 FSW. |
first_indexed | 2024-03-12T14:43:22Z |
format | Article |
id | doaj.art-c961f1c52c974a13a9e519ab6ae32800 |
institution | Directory Open Access Journal |
issn | 2667-3053 |
language | English |
last_indexed | 2024-03-12T14:43:22Z |
publishDate | 2023-09-01 |
publisher | Elsevier |
record_format | Article |
series | Intelligent Systems with Applications |
spelling | doaj.art-c961f1c52c974a13a9e519ab6ae328002023-08-16T04:27:30ZengElsevierIntelligent Systems with Applications2667-30532023-09-0119200259A Predictive Model for Weld Properties in AA-7075-FSW: A Heterogeneous AMIS-Ensemble Machine Learning ApproachSurasak Matitopanum0Peerawat Luesak1Somphop Chiaranai2Rapeepan Pitakaso3Thanatkij Srichok4Worapot Sirirak5Ganokgarn Jirasirilerd6Department of Industrial Engineering, Faculty of Engineering and Technology, Rajamangala University of Technology Isan, Nakhon Ratchasima, ThailandDepartment of Industrial Engineering, Rajamangala University of Technology Lanna, Chiang Rai, ThailandDepartment of Industrial Engineering, Ubon Ratchathani University, Ubon Ratchathani 34190, ThailandDepartment of Industrial Engineering, Ubon Ratchathani University, Ubon Ratchathani 34190, ThailandDepartment of Industrial Engineering, Ubon Ratchathani University, Ubon Ratchathani 34190, Thailand; Corresponding author.Department of Industrial Engineering, Rajamangala University of Technology Lanna, Chiang Rai, ThailandDepartment of Industrial Management Technology, Faculty of Liberal Arts and Sciences, Sisaket Rajabhat University, Sisaket 33000, ThailandThis study addresses the research gap in materials science by developing an integrated predictive model for Ultimate Tensile Strength (UTS), Maximum Hardness (MH), and Heat Input (HI) in AA-7075 Friction Stir Welding (FSW). The aim is to enhance welding procedures, particularly in high-precision industries like aerospace and automotive. By incorporating four control parameters (Tilt Angle, Rotation Speed, Welding Speed, and Shoulder Diameter) and utilizing a Long Short-Term Memory (LSTM) machine learning model, a Heterogeneous Ensemble Machine Learning (He-EM) approach is developed. The Artificial Multiple Intelligence System (AMIS) optimizes the decision fusion strategy of each technique, ensuring the model's effectiveness. Validated using diverse experimental design methods and three datasets, the proposed AMIS He-EM model outperforms existing techniques (GPR, SVM, HE-UWE, and HE-WEDE) by significant margins (35.12%, 24.92%, 22.31%, and 15.48% respectively). The model's robustness is demonstrated, as its performance remains consistent across different experimental design methods. The key finding of this research is the remarkable improvement in accuracy for predicting UTS, MH, and HI in AA7075 FSW. This study highlights the importance of incorporating four control parameters and utilizing the D-optimal design for efficient exploration of the input parameter space. The implications of this research are profound, offering opportunities to optimize welding procedures, improve product performance, and streamline manufacturing processes in industries relying on AA7075 FSW.http://www.sciencedirect.com/science/article/pii/S2667305323000844ultimate tensile Strength (UTS)maximum hardness (MH)heat input (HI)machine learningfriction stir welding (FSW), AMIS, decision fusion strategy |
spellingShingle | Surasak Matitopanum Peerawat Luesak Somphop Chiaranai Rapeepan Pitakaso Thanatkij Srichok Worapot Sirirak Ganokgarn Jirasirilerd A Predictive Model for Weld Properties in AA-7075-FSW: A Heterogeneous AMIS-Ensemble Machine Learning Approach Intelligent Systems with Applications ultimate tensile Strength (UTS) maximum hardness (MH) heat input (HI) machine learning friction stir welding (FSW), AMIS, decision fusion strategy |
title | A Predictive Model for Weld Properties in AA-7075-FSW: A Heterogeneous AMIS-Ensemble Machine Learning Approach |
title_full | A Predictive Model for Weld Properties in AA-7075-FSW: A Heterogeneous AMIS-Ensemble Machine Learning Approach |
title_fullStr | A Predictive Model for Weld Properties in AA-7075-FSW: A Heterogeneous AMIS-Ensemble Machine Learning Approach |
title_full_unstemmed | A Predictive Model for Weld Properties in AA-7075-FSW: A Heterogeneous AMIS-Ensemble Machine Learning Approach |
title_short | A Predictive Model for Weld Properties in AA-7075-FSW: A Heterogeneous AMIS-Ensemble Machine Learning Approach |
title_sort | predictive model for weld properties in aa 7075 fsw a heterogeneous amis ensemble machine learning approach |
topic | ultimate tensile Strength (UTS) maximum hardness (MH) heat input (HI) machine learning friction stir welding (FSW), AMIS, decision fusion strategy |
url | http://www.sciencedirect.com/science/article/pii/S2667305323000844 |
work_keys_str_mv | AT surasakmatitopanum apredictivemodelforweldpropertiesinaa7075fswaheterogeneousamisensemblemachinelearningapproach AT peerawatluesak apredictivemodelforweldpropertiesinaa7075fswaheterogeneousamisensemblemachinelearningapproach AT somphopchiaranai apredictivemodelforweldpropertiesinaa7075fswaheterogeneousamisensemblemachinelearningapproach AT rapeepanpitakaso apredictivemodelforweldpropertiesinaa7075fswaheterogeneousamisensemblemachinelearningapproach AT thanatkijsrichok apredictivemodelforweldpropertiesinaa7075fswaheterogeneousamisensemblemachinelearningapproach AT worapotsirirak apredictivemodelforweldpropertiesinaa7075fswaheterogeneousamisensemblemachinelearningapproach AT ganokgarnjirasirilerd apredictivemodelforweldpropertiesinaa7075fswaheterogeneousamisensemblemachinelearningapproach AT surasakmatitopanum predictivemodelforweldpropertiesinaa7075fswaheterogeneousamisensemblemachinelearningapproach AT peerawatluesak predictivemodelforweldpropertiesinaa7075fswaheterogeneousamisensemblemachinelearningapproach AT somphopchiaranai predictivemodelforweldpropertiesinaa7075fswaheterogeneousamisensemblemachinelearningapproach AT rapeepanpitakaso predictivemodelforweldpropertiesinaa7075fswaheterogeneousamisensemblemachinelearningapproach AT thanatkijsrichok predictivemodelforweldpropertiesinaa7075fswaheterogeneousamisensemblemachinelearningapproach AT worapotsirirak predictivemodelforweldpropertiesinaa7075fswaheterogeneousamisensemblemachinelearningapproach AT ganokgarnjirasirilerd predictivemodelforweldpropertiesinaa7075fswaheterogeneousamisensemblemachinelearningapproach |