A review of artificial intelligence techniques for optimizing friction stir welding processes and predicting mechanical properties
The implementation of artificial intelligence (AI) has been instrumental in the optimization of friction stir welding (FSW) parameters. Artificial intelligence (AI) techniques, including artificial neural networks (ANN) and adaptive neuro-fuzzy inference systems (ANFIS), were utilized to predict mec...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-02-01
|
| Series: | Engineering Science and Technology, an International Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2215098625000047 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832087541442936832 |
|---|---|
| author | Roosvel Soto-Diaz Mauricio Vásquez-Carbonell Jose Escorcia-Gutierrez |
| author_facet | Roosvel Soto-Diaz Mauricio Vásquez-Carbonell Jose Escorcia-Gutierrez |
| author_sort | Roosvel Soto-Diaz |
| collection | DOAJ |
| description | The implementation of artificial intelligence (AI) has been instrumental in the optimization of friction stir welding (FSW) parameters. Artificial intelligence (AI) techniques, including artificial neural networks (ANN) and adaptive neuro-fuzzy inference systems (ANFIS), were utilized to predict mechanical properties such as ultimate tensile strength (UTS) and optimize pivotal welding parameters, such as rotational speed, feed rate, axial force, and tilt angle. These methodologies enabled precise real-time control, thus improving the quality and consistency of the resulting welded joints. The objective of this study was to conduct a comprehensive review of the application of artificial intelligence (AI) techniques in friction stir welding (FSW). The objective of the study was to synthesize existing research using AI to predict mechanical properties and optimize welding parameters. Furthermore, the study aimed to illustrate how artificial intelligence has improved the caliber and dependability of FSW joints through real-time observation and defect identification. A systematic literature review was conducted according to the PRISMA guidelines to identify relevant studies on the utilization of AI in FSW. A search algorithm was applied to databases such as ScienceDirect and Web of Science, resulting in the identification of 27 relevant scientific papers. The selection criteria were designed to identify studies that employed AI techniques for the prediction and optimization of FSW parameters. The principal findings indicated the pervasive deployment of 34 distinct AI techniques, with ANN being the most prevalent. Hybrid models combining AI with optimization algorithms, such as particle swarm optimization (PSO) and genetic algorithms, were particularly effective. These models demonstrated high precision in predicting tensile strength and detecting internal defects, significantly improving joint quality. In conclusion, AI applications in FSW have proven essential for optimizing welding processes, with hybrid AI models showing superior performance. The continued integration of AI in FSW is expected to enhance the efficiency and reliability of welding operations, offering significant industrial advantages. |
| format | Article |
| id | doaj-art-8c147c9b8549407bacb3cdaa2b12fab4 |
| institution | Kabale University |
| issn | 2215-0986 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Engineering Science and Technology, an International Journal |
| spelling | doaj-art-8c147c9b8549407bacb3cdaa2b12fab42025-02-06T05:11:52ZengElsevierEngineering Science and Technology, an International Journal2215-09862025-02-0162101949A review of artificial intelligence techniques for optimizing friction stir welding processes and predicting mechanical propertiesRoosvel Soto-Diaz0Mauricio Vásquez-Carbonell1Jose Escorcia-Gutierrez2Biomedical Engineering Program, Universidad Simón Bolívar, Barranquilla 080002, Colombia; Corresponding authors.System Engineering Program, Universidad Simón Bolívar, Barranquilla 080002, Colombia; Corresponding authors.Department of Computational Science and Electronic, Universidad de la Costa, CUC, Barranquilla 080002, ColombiaThe implementation of artificial intelligence (AI) has been instrumental in the optimization of friction stir welding (FSW) parameters. Artificial intelligence (AI) techniques, including artificial neural networks (ANN) and adaptive neuro-fuzzy inference systems (ANFIS), were utilized to predict mechanical properties such as ultimate tensile strength (UTS) and optimize pivotal welding parameters, such as rotational speed, feed rate, axial force, and tilt angle. These methodologies enabled precise real-time control, thus improving the quality and consistency of the resulting welded joints. The objective of this study was to conduct a comprehensive review of the application of artificial intelligence (AI) techniques in friction stir welding (FSW). The objective of the study was to synthesize existing research using AI to predict mechanical properties and optimize welding parameters. Furthermore, the study aimed to illustrate how artificial intelligence has improved the caliber and dependability of FSW joints through real-time observation and defect identification. A systematic literature review was conducted according to the PRISMA guidelines to identify relevant studies on the utilization of AI in FSW. A search algorithm was applied to databases such as ScienceDirect and Web of Science, resulting in the identification of 27 relevant scientific papers. The selection criteria were designed to identify studies that employed AI techniques for the prediction and optimization of FSW parameters. The principal findings indicated the pervasive deployment of 34 distinct AI techniques, with ANN being the most prevalent. Hybrid models combining AI with optimization algorithms, such as particle swarm optimization (PSO) and genetic algorithms, were particularly effective. These models demonstrated high precision in predicting tensile strength and detecting internal defects, significantly improving joint quality. In conclusion, AI applications in FSW have proven essential for optimizing welding processes, with hybrid AI models showing superior performance. The continued integration of AI in FSW is expected to enhance the efficiency and reliability of welding operations, offering significant industrial advantages.http://www.sciencedirect.com/science/article/pii/S2215098625000047Artificial intelligence (AI)Friction stir-welding (FSW)Ultimate tensile strength (UTS)PRISMA |
| spellingShingle | Roosvel Soto-Diaz Mauricio Vásquez-Carbonell Jose Escorcia-Gutierrez A review of artificial intelligence techniques for optimizing friction stir welding processes and predicting mechanical properties Engineering Science and Technology, an International Journal Artificial intelligence (AI) Friction stir-welding (FSW) Ultimate tensile strength (UTS) PRISMA |
| title | A review of artificial intelligence techniques for optimizing friction stir welding processes and predicting mechanical properties |
| title_full | A review of artificial intelligence techniques for optimizing friction stir welding processes and predicting mechanical properties |
| title_fullStr | A review of artificial intelligence techniques for optimizing friction stir welding processes and predicting mechanical properties |
| title_full_unstemmed | A review of artificial intelligence techniques for optimizing friction stir welding processes and predicting mechanical properties |
| title_short | A review of artificial intelligence techniques for optimizing friction stir welding processes and predicting mechanical properties |
| title_sort | review of artificial intelligence techniques for optimizing friction stir welding processes and predicting mechanical properties |
| topic | Artificial intelligence (AI) Friction stir-welding (FSW) Ultimate tensile strength (UTS) PRISMA |
| url | http://www.sciencedirect.com/science/article/pii/S2215098625000047 |
| work_keys_str_mv | AT roosvelsotodiaz areviewofartificialintelligencetechniquesforoptimizingfrictionstirweldingprocessesandpredictingmechanicalproperties AT mauriciovasquezcarbonell areviewofartificialintelligencetechniquesforoptimizingfrictionstirweldingprocessesandpredictingmechanicalproperties AT joseescorciagutierrez areviewofartificialintelligencetechniquesforoptimizingfrictionstirweldingprocessesandpredictingmechanicalproperties AT roosvelsotodiaz reviewofartificialintelligencetechniquesforoptimizingfrictionstirweldingprocessesandpredictingmechanicalproperties AT mauriciovasquezcarbonell reviewofartificialintelligencetechniquesforoptimizingfrictionstirweldingprocessesandpredictingmechanicalproperties AT joseescorciagutierrez reviewofartificialintelligencetechniquesforoptimizingfrictionstirweldingprocessesandpredictingmechanicalproperties |