RESEARCH FIELD 04 / 2020–2026

Machine learning for engineering

Predictive and interpretable models for structural composites, concrete strength, nanofluid processing, and biomaterial properties.

6Related publications

2Research threads

Read the publications Explore the themes

Scientific schematic of a concrete specimen and FRP interface connected to input variables, layered neural networks, an optimization loop, and predicted material response. — Conceptual schematic · Machine learning

THE CENTRAL QUESTION

How can experimental and engineering data support reliable predictions of material and structural behavior?

Research approach

Neural networks and extreme learning machines are paired with metaheuristic optimizers for strength, bond, and member-response prediction. More recent experimental studies extend learning to superfinishing nanofluids and use Gaussian process regression with SHAP interpretation for gelatin scaffolds.

Research perspective

The collection follows prediction across structural, manufacturing, and biomaterial settings, with each model interpreted within the data and application examined in its study.

Hybrid neural networksExtreme learning machinesGaussian processesSHAP interpretation

WITHIN THE FIELD

Research threads.

Explore the themes and their associated papers. Full references and publisher links follow below.

014 publications

Structural response & material strength

Steel–concrete behavior, FRP–concrete bond, and concrete compressive strength.

2022Simulation of steel-concrete composite floor system behavior at elevated temperatures via multi-hybrid metaheuristic framework
2022Assessment of composite beam performance using GWO–ELM metaheuristic algorithm
2020Evaluating the bond strength of FRP in concrete samples using machine learning methods
2020Swarm-based hybridizations of neural network for predicting the concrete strength

022 publications

Learning from materials experiments

Nanofluid superfinishing and crosslinked gelatin scaffold properties.

2026Experimental and machine learning analysis of structure–property relationships in GPTMS-crosslinked gelatin scaffolds for bone regeneration
2026Experimental and machine learning evaluation of Al₂O₃ nanofluid lubricants for surface roughness reduction and thermal conductivity enhancement in superfinishing

THE RELATED BIBLIOGRAPHY

6 publications.

Search & export these references →

Each paper is listed once within this field. Related work may also appear in another field where its subject or methods overlap. Years follow the journal citation; earlier online dates are shown separately.

2026

Experimental and machine learning analysis of structure–property relationships in GPTMS-crosslinked gelatin scaffolds for bone regeneration

Aria Ghabussi, Nima Azmi, Fereshteh Beheshti, Hamidreza Azimy

Biomaterials Advances

DOI: 10.1016/j.bioadv.2026.215112

Read at publisher ↗View in complete bibliography →

2026

Experimental and machine learning evaluation of Al₂O₃ nanofluid lubricants for surface roughness reduction and thermal conductivity enhancement in superfinishing

Hamidreza Azimy, Aria Ghabussi, Reza Nosouhi, Mohammad Akbari

The International Journal of Advanced Manufacturing Technology

DOI: 10.1007/s00170-026-17677-7

Read at publisher ↗View in complete bibliography →

2022Online 2021

Simulation of steel-concrete composite floor system behavior at elevated temperatures via multi-hybrid metaheuristic framework

Armin Morasaei, Aria Ghabussi, Soheila Aghlmand, Maziar Yazdani, Shahrizan Baharom, Hamid Assilzadeh

Engineering with Computers

DOI: 10.1007/s00366-020-01228-z

Read at publisher ↗View in complete bibliography →

2022Online 2021

Assessment of composite beam performance using GWO–ELM metaheuristic algorithm

Runqian Ma, Misagh Karimzadeh, Aria Ghabussi, Yousef Zandi, Shahrizan Baharom, Abdellatif Selmi, Nelson Maureira-Carsalade

Engineering with Computers

DOI: 10.1007/s00366-021-01363-1

Read at publisher ↗View in complete bibliography →

2020

Evaluating the bond strength of FRP in concrete samples using machine learning methods

Juncheng Gao, Mohammadreza Koopialipoor, Danial Jahed Armaghani, Aria Ghabussi, Shahrizan Baharom, Armin Morasaei, Ali Shariati, Majid Khorami, Jian Zhou

Smart Structures and Systems

DOI: 10.12989/sss.2020.26.4.403

Read at publisher ↗View in complete bibliography →

2020