Prediction of buckling damage of steel equal angle structural members using hybrid machine learning techniques
Abstract This article deals with prediction of buckling damage of steel equal angle structural members using a surrogate model combining machine learning and metaheuristic optimization technique. In particular, a hybrid Artificial Intelligence (AI)-based model involving Artificial Neural Network (AN...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-87869-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823862119413579776 |
|---|---|
| author | Nang Xuan Ho Tien-Thinh Le The-Hung Dinh Van-Hai Nguyen |
| author_facet | Nang Xuan Ho Tien-Thinh Le The-Hung Dinh Van-Hai Nguyen |
| author_sort | Nang Xuan Ho |
| collection | DOAJ |
| description | Abstract This article deals with prediction of buckling damage of steel equal angle structural members using a surrogate model combining machine learning and metaheuristic optimization technique. In particular, a hybrid Artificial Intelligence (AI)-based model involving Artificial Neural Network (ANN) and Particle Swarm Optimization (PSO) was developed and calibrated for the problem at hand. For this purpose, a database concerning compression tests of steel equal angle structural members was constructed from available resources with geometry variables such as length, width, thickness, mechanical properties of materials such as yield strength and initial imperfections (i.e. residual peak stress and initial geometric imperfections) and critical buckling load of columns. The hybrid PSOANN model was adopted because its prediction capability is higher than the traditional technique – i.e. scaled conjugate gradient (SCG). Indeed, ANN trained by PSO delivered better performance in terms of RMSE, MAE, ErrorStD, R2 and Slope in comparison to ANN trained by SCG, for instance. RMSE decreases from 0.141 to 0.055; MAE decreases from 0.108 to 0.042; R2 increases from 0.749 to 0.959, when switching from ANN alone to hybrid PSOANN, respectively. Moreover, a Partial Dependence (PD) investigation was performed to interpret the “black-box” PSOANN model. |
| format | Article |
| id | doaj-art-10ae45d27be34e9283576e4a1b8f2a0b |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-10ae45d27be34e9283576e4a1b8f2a0b2025-02-09T12:36:08ZengNature PortfolioScientific Reports2045-23222025-02-0115111110.1038/s41598-025-87869-wPrediction of buckling damage of steel equal angle structural members using hybrid machine learning techniquesNang Xuan Ho0Tien-Thinh Le1The-Hung Dinh2Van-Hai Nguyen3Faculty of Vehicle and Energy Engineering, Phenikaa UniversityFaculty of Mechanical Engineering and Mechatronics, Phenikaa UniversityFaculty of Mechanical Engineering and Mechatronics, Phenikaa UniversityFaculty of Mechanical Engineering and Mechatronics, Phenikaa UniversityAbstract This article deals with prediction of buckling damage of steel equal angle structural members using a surrogate model combining machine learning and metaheuristic optimization technique. In particular, a hybrid Artificial Intelligence (AI)-based model involving Artificial Neural Network (ANN) and Particle Swarm Optimization (PSO) was developed and calibrated for the problem at hand. For this purpose, a database concerning compression tests of steel equal angle structural members was constructed from available resources with geometry variables such as length, width, thickness, mechanical properties of materials such as yield strength and initial imperfections (i.e. residual peak stress and initial geometric imperfections) and critical buckling load of columns. The hybrid PSOANN model was adopted because its prediction capability is higher than the traditional technique – i.e. scaled conjugate gradient (SCG). Indeed, ANN trained by PSO delivered better performance in terms of RMSE, MAE, ErrorStD, R2 and Slope in comparison to ANN trained by SCG, for instance. RMSE decreases from 0.141 to 0.055; MAE decreases from 0.108 to 0.042; R2 increases from 0.749 to 0.959, when switching from ANN alone to hybrid PSOANN, respectively. Moreover, a Partial Dependence (PD) investigation was performed to interpret the “black-box” PSOANN model.https://doi.org/10.1038/s41598-025-87869-wSteel equal angleBuckling damageSurrogate modelArtificial neural networkParticle swarm optimization. |
| spellingShingle | Nang Xuan Ho Tien-Thinh Le The-Hung Dinh Van-Hai Nguyen Prediction of buckling damage of steel equal angle structural members using hybrid machine learning techniques Scientific Reports Steel equal angle Buckling damage Surrogate model Artificial neural network Particle swarm optimization. |
| title | Prediction of buckling damage of steel equal angle structural members using hybrid machine learning techniques |
| title_full | Prediction of buckling damage of steel equal angle structural members using hybrid machine learning techniques |
| title_fullStr | Prediction of buckling damage of steel equal angle structural members using hybrid machine learning techniques |
| title_full_unstemmed | Prediction of buckling damage of steel equal angle structural members using hybrid machine learning techniques |
| title_short | Prediction of buckling damage of steel equal angle structural members using hybrid machine learning techniques |
| title_sort | prediction of buckling damage of steel equal angle structural members using hybrid machine learning techniques |
| topic | Steel equal angle Buckling damage Surrogate model Artificial neural network Particle swarm optimization. |
| url | https://doi.org/10.1038/s41598-025-87869-w |
| work_keys_str_mv | AT nangxuanho predictionofbucklingdamageofsteelequalanglestructuralmembersusinghybridmachinelearningtechniques AT tienthinhle predictionofbucklingdamageofsteelequalanglestructuralmembersusinghybridmachinelearningtechniques AT thehungdinh predictionofbucklingdamageofsteelequalanglestructuralmembersusinghybridmachinelearningtechniques AT vanhainguyen predictionofbucklingdamageofsteelequalanglestructuralmembersusinghybridmachinelearningtechniques |