Artificial neural network based fatigue life assessment of riveted joints in AA2024 aluminum alloy plates and optimization of riveted joints parameters

Reza Masoudi Nejad; Nima Sina; Wenchen Ma; Wei Song; S. P. Zhu; Ricardo Branco; Wojciech Macek; Aboozar Gholami

doi:10.1016/j.ijfatigue.2023.107997

Artificial neural network based fatigue life assessment of riveted joints in AA2024 aluminum alloy plates and optimization of riveted joints parameters

Reza Masoudi Nejad
, Nima Sina
, Wenchen Ma
, Wei Song
, S. P. Zhu
, Ricardo Branco
, Wojciech Macek
, Aboozar Gholami

School of Human Settlements and Civil Engineering

Iowa State University
Tesla Inc
Xuzhou Institute of Technology
University of Electronic Science and Technology of China
University of Coimbra
Gdańsk University of Technology
Foolad Institute of Technology

Research output: Contribution to journal › Article › peer-review

25 Scopus citations

Abstract

The objective of this paper is to provide the fatigue life of riveted joints in AA2024 aluminum alloy plates and optimization of riveted joints parameters. At first, the fatigue life of the riveted joints in AA2024 aluminum alloy plates is obtained by experimental tests. Then, an artificial neural network is applied to estimate the fatigue life of riveted lap joints based on the number of lateral and longitudinal holes, punch pressure, gap between the edge of hole and rivet, rivet shank diameter, and rivet shank length. Also, meta heuristic optimization algorithm is applied to calculate the riveting process parameters. Finally, sensitivity analysis is used to obtain the influence of parameters affecting the riveting process on the fatigue life.

Original language	English
Article number	107997
Journal	International Journal of Fatigue
Volume	178
DOIs	https://doi.org/10.1016/j.ijfatigue.2023.107997
State	Published - Jan 2024

Keywords

AA2024 aluminum alloy
Artificial Neural Network
Fatigue life
Riveted lap joint
Structure

Access to Document

10.1016/j.ijfatigue.2023.107997

Cite this

@article{bd49ec9bbc1742949455c1250c9d002d,

title = "Artificial neural network based fatigue life assessment of riveted joints in AA2024 aluminum alloy plates and optimization of riveted joints parameters",

abstract = "The objective of this paper is to provide the fatigue life of riveted joints in AA2024 aluminum alloy plates and optimization of riveted joints parameters. At first, the fatigue life of the riveted joints in AA2024 aluminum alloy plates is obtained by experimental tests. Then, an artificial neural network is applied to estimate the fatigue life of riveted lap joints based on the number of lateral and longitudinal holes, punch pressure, gap between the edge of hole and rivet, rivet shank diameter, and rivet shank length. Also, meta heuristic optimization algorithm is applied to calculate the riveting process parameters. Finally, sensitivity analysis is used to obtain the influence of parameters affecting the riveting process on the fatigue life.",

keywords = "AA2024 aluminum alloy, Artificial Neural Network, Fatigue life, Riveted lap joint, Structure",

author = "\{Masoudi Nejad\}, Reza and Nima Sina and Wenchen Ma and Wei Song and Zhu, \{S. P.\} and Ricardo Branco and Wojciech Macek and Aboozar Gholami",

note = "Publisher Copyright: {\textcopyright} 2023 Elsevier Ltd",

year = "2024",

month = jan,

doi = "10.1016/j.ijfatigue.2023.107997",

language = "英语",

volume = "178",

journal = "International Journal of Fatigue",

issn = "0142-1123",

publisher = "Elsevier Ltd",

}

TY - JOUR

T1 - Artificial neural network based fatigue life assessment of riveted joints in AA2024 aluminum alloy plates and optimization of riveted joints parameters

AU - Masoudi Nejad, Reza

AU - Sina, Nima

AU - Ma, Wenchen

AU - Song, Wei

AU - Zhu, S. P.

AU - Branco, Ricardo

AU - Macek, Wojciech

AU - Gholami, Aboozar

PY - 2024/1

Y1 - 2024/1

N2 - The objective of this paper is to provide the fatigue life of riveted joints in AA2024 aluminum alloy plates and optimization of riveted joints parameters. At first, the fatigue life of the riveted joints in AA2024 aluminum alloy plates is obtained by experimental tests. Then, an artificial neural network is applied to estimate the fatigue life of riveted lap joints based on the number of lateral and longitudinal holes, punch pressure, gap between the edge of hole and rivet, rivet shank diameter, and rivet shank length. Also, meta heuristic optimization algorithm is applied to calculate the riveting process parameters. Finally, sensitivity analysis is used to obtain the influence of parameters affecting the riveting process on the fatigue life.

AB - The objective of this paper is to provide the fatigue life of riveted joints in AA2024 aluminum alloy plates and optimization of riveted joints parameters. At first, the fatigue life of the riveted joints in AA2024 aluminum alloy plates is obtained by experimental tests. Then, an artificial neural network is applied to estimate the fatigue life of riveted lap joints based on the number of lateral and longitudinal holes, punch pressure, gap between the edge of hole and rivet, rivet shank diameter, and rivet shank length. Also, meta heuristic optimization algorithm is applied to calculate the riveting process parameters. Finally, sensitivity analysis is used to obtain the influence of parameters affecting the riveting process on the fatigue life.

KW - AA2024 aluminum alloy

KW - Artificial Neural Network

KW - Fatigue life

KW - Riveted lap joint

KW - Structure

UR - https://www.scopus.com/pages/publications/85173580083

U2 - 10.1016/j.ijfatigue.2023.107997

DO - 10.1016/j.ijfatigue.2023.107997

M3 - 文章

AN - SCOPUS:85173580083

SN - 0142-1123

VL - 178

JO - International Journal of Fatigue

JF - International Journal of Fatigue

M1 - 107997

ER -

Artificial neural network based fatigue life assessment of riveted joints in AA2024 aluminum alloy plates and optimization of riveted joints parameters

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this