A CRITIC-BPNN APPROACH TO FRICTION STIR WELDING PARAMETRIC SELECTION AND PREDICTION USING AA6082-T6 MATERIAL
The uncontrolled friction stir welding heat generation impacts the quality of welds. However, the intuition and experience of the engineer fail to regulate the effects of excessive heat generation on the weld quality and research has not addressed this aspect yet. This paper fills the gap by introdu...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Faculty of Engineering, University of Kufa
2025-02-01
|
| Series: | Mağallaẗ Al-kūfaẗ Al-handasiyyaẗ |
| Subjects: | |
| Online Access: | https://journal.uokufa.edu.iq/index.php/kje/article/view/16934 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832087047309885440 |
|---|---|
| author | Mufutau Adeniyi Abolarin Adeyinka Oluwo John Rajan Swaminathan Jose Sunday Ayoola Oke | Alexander Iwodi Agada Ayomide Sunday Ibitoye |
| author_facet | Mufutau Adeniyi Abolarin Adeyinka Oluwo John Rajan Swaminathan Jose Sunday Ayoola Oke | Alexander Iwodi Agada Ayomide Sunday Ibitoye |
| author_sort | Mufutau Adeniyi Abolarin |
| collection | DOAJ |
| description | The uncontrolled friction stir welding heat generation impacts the quality of welds. However, the intuition and experience of the engineer fail to regulate the effects of excessive heat generation on the weld quality and research has not addressed this aspect yet. This paper fills the gap by introducing an integrated CRITIC-BPNN (CRiteria Importance Through Intercriteria Correlation-Back Propagation Neural Network) method to investigate the selection and optimisation characteristics of the friction stir welding process for AA6082-T6 material. In this study, two major performance characteristics i.e. ultimate tensile strength (UTS) and percentage elongation (%EL), were chosen for analysis. The input parameters for the machining were the tool rotational speed, welding speed, tool pin profile and tool shoulder diameter. For the back propagation neural network model, a four-layer network with sigmoid hidden neurons and output neurons was selected. The weight estimates of the friction stir welding parameters are determined by the CRITIC method. For further weight determination between the nodes and edges of the neural networks, the Poisson distribution model was introduced. This stochastic-based method was used to calculate the weights at the edges, between the inputs, hidden layers and outputs of the neural network. The forward pass and backward passes are then used for updating and error minimisation. The welding speed has the highest weight with a contribution of 49.72% using the CRITIC method, implying that welding speed is the best and most influential parameter of the friction stir welding process. For the 4-1-2 neural network architecture, the values of the ultimate tensile strength and percentage elongation at the optimal thresholds are 0.6457 and 0.6019, respectively, for the first forward pass and 0.6123 and 0.6356, respectively, for the second forward pass. The predicted tensile strength is 320.64 MPa and the prediction for the percentage elongation is 18.83%. The results obtained from the proposed method could be useful for planning purposes during the friction welding process.
|
| format | Article |
| id | doaj-art-aef0eed737a147c5af849e88893f1e45 |
| institution | Kabale University |
| issn | 2071-5528 2523-0018 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Faculty of Engineering, University of Kufa |
| record_format | Article |
| series | Mağallaẗ Al-kūfaẗ Al-handasiyyaẗ |
| spelling | doaj-art-aef0eed737a147c5af849e88893f1e452025-02-06T07:59:50ZengFaculty of Engineering, University of KufaMağallaẗ Al-kūfaẗ Al-handasiyyaẗ2071-55282523-00182025-02-01160142144910.30572/2018/KJE/160123 A CRITIC-BPNN APPROACH TO FRICTION STIR WELDING PARAMETRIC SELECTION AND PREDICTION USING AA6082-T6 MATERIAL Mufutau Adeniyi Abolarin0Adeyinka Oluwo1John Rajan2Swaminathan Jose3Sunday Ayoola Oke |4https://orcid.org/0000-0002-0914-8146Alexander Iwodi Agada5 Ayomide Sunday Ibitoye6University of Lagos, Lagos, NigeriaUniversity of Lagos, Lagos, NigeriaVellore Institute of Technology, Vellore, IndiaUniversity of Lagos, Lagos, NigeriaUniversity of Lagos, Lagos, NigeriaUniversity of Lagos, Lagos, NigeriaUniversity of Lagos, Lagos, NigeriaThe uncontrolled friction stir welding heat generation impacts the quality of welds. However, the intuition and experience of the engineer fail to regulate the effects of excessive heat generation on the weld quality and research has not addressed this aspect yet. This paper fills the gap by introducing an integrated CRITIC-BPNN (CRiteria Importance Through Intercriteria Correlation-Back Propagation Neural Network) method to investigate the selection and optimisation characteristics of the friction stir welding process for AA6082-T6 material. In this study, two major performance characteristics i.e. ultimate tensile strength (UTS) and percentage elongation (%EL), were chosen for analysis. The input parameters for the machining were the tool rotational speed, welding speed, tool pin profile and tool shoulder diameter. For the back propagation neural network model, a four-layer network with sigmoid hidden neurons and output neurons was selected. The weight estimates of the friction stir welding parameters are determined by the CRITIC method. For further weight determination between the nodes and edges of the neural networks, the Poisson distribution model was introduced. This stochastic-based method was used to calculate the weights at the edges, between the inputs, hidden layers and outputs of the neural network. The forward pass and backward passes are then used for updating and error minimisation. The welding speed has the highest weight with a contribution of 49.72% using the CRITIC method, implying that welding speed is the best and most influential parameter of the friction stir welding process. For the 4-1-2 neural network architecture, the values of the ultimate tensile strength and percentage elongation at the optimal thresholds are 0.6457 and 0.6019, respectively, for the first forward pass and 0.6123 and 0.6356, respectively, for the second forward pass. The predicted tensile strength is 320.64 MPa and the prediction for the percentage elongation is 18.83%. The results obtained from the proposed method could be useful for planning purposes during the friction welding process. https://journal.uokufa.edu.iq/index.php/kje/article/view/16934normalizationcorrelationtoola measure of conflictoutput weights |
| spellingShingle | Mufutau Adeniyi Abolarin Adeyinka Oluwo John Rajan Swaminathan Jose Sunday Ayoola Oke | Alexander Iwodi Agada Ayomide Sunday Ibitoye A CRITIC-BPNN APPROACH TO FRICTION STIR WELDING PARAMETRIC SELECTION AND PREDICTION USING AA6082-T6 MATERIAL Mağallaẗ Al-kūfaẗ Al-handasiyyaẗ normalization correlation tool a measure of conflict output weights |
| title | A CRITIC-BPNN APPROACH TO FRICTION STIR WELDING PARAMETRIC SELECTION AND PREDICTION USING AA6082-T6 MATERIAL |
| title_full | A CRITIC-BPNN APPROACH TO FRICTION STIR WELDING PARAMETRIC SELECTION AND PREDICTION USING AA6082-T6 MATERIAL |
| title_fullStr | A CRITIC-BPNN APPROACH TO FRICTION STIR WELDING PARAMETRIC SELECTION AND PREDICTION USING AA6082-T6 MATERIAL |
| title_full_unstemmed | A CRITIC-BPNN APPROACH TO FRICTION STIR WELDING PARAMETRIC SELECTION AND PREDICTION USING AA6082-T6 MATERIAL |
| title_short | A CRITIC-BPNN APPROACH TO FRICTION STIR WELDING PARAMETRIC SELECTION AND PREDICTION USING AA6082-T6 MATERIAL |
| title_sort | critic bpnn approach to friction stir welding parametric selection and prediction using aa6082 t6 material |
| topic | normalization correlation tool a measure of conflict output weights |
| url | https://journal.uokufa.edu.iq/index.php/kje/article/view/16934 |
| work_keys_str_mv | AT mufutauadeniyiabolarin acriticbpnnapproachtofrictionstirweldingparametricselectionandpredictionusingaa6082t6material AT adeyinkaoluwo acriticbpnnapproachtofrictionstirweldingparametricselectionandpredictionusingaa6082t6material AT johnrajan acriticbpnnapproachtofrictionstirweldingparametricselectionandpredictionusingaa6082t6material AT swaminathanjose acriticbpnnapproachtofrictionstirweldingparametricselectionandpredictionusingaa6082t6material AT sundayayoolaoke acriticbpnnapproachtofrictionstirweldingparametricselectionandpredictionusingaa6082t6material AT alexanderiwodiagada acriticbpnnapproachtofrictionstirweldingparametricselectionandpredictionusingaa6082t6material AT ayomidesundayibitoye acriticbpnnapproachtofrictionstirweldingparametricselectionandpredictionusingaa6082t6material AT mufutauadeniyiabolarin criticbpnnapproachtofrictionstirweldingparametricselectionandpredictionusingaa6082t6material AT adeyinkaoluwo criticbpnnapproachtofrictionstirweldingparametricselectionandpredictionusingaa6082t6material AT johnrajan criticbpnnapproachtofrictionstirweldingparametricselectionandpredictionusingaa6082t6material AT swaminathanjose criticbpnnapproachtofrictionstirweldingparametricselectionandpredictionusingaa6082t6material AT sundayayoolaoke criticbpnnapproachtofrictionstirweldingparametricselectionandpredictionusingaa6082t6material AT alexanderiwodiagada criticbpnnapproachtofrictionstirweldingparametricselectionandpredictionusingaa6082t6material AT ayomidesundayibitoye criticbpnnapproachtofrictionstirweldingparametricselectionandpredictionusingaa6082t6material |