Vali-e-Asr University of Rafsanjan · Iran

Advancing Structural Engineering Through Artificial Intelligence

Our lab bridges classical structural mechanics with modern machine learning to solve complex problems in steel structures, concrete, and corrosion engineering.

2,764+
Total Citations
32
h-index
95+
Publications
59
i10-index
View Publications Try Our Calculator ↓

Research Areas

Our work spans four interconnected domains, combining experimental data with AI-driven predictive models.

🏗️

Steel Structures & Buckling

Lateral-torsional and distortional buckling of steel I-beams, castellated and cellular beams, and corroded web plate girders — assessed using ANN, regression, and machine learning.

🧱

Supplementary Cementitious Materials

Recycled glass, copper slag, ceramic waste powder, and metakaolin in self-compacting concrete — evaluating fresh properties, strength, microstructure, and durability.

🤖

AI & Soft Computing in Civil Engineering

Artificial neural networks, XGBoost, gene expression programming, PSO, ANFIS, and hybrid meta-heuristic optimizers applied to structural capacity prediction.

🌊

Corrosion & Structural Reliability

Reliability analysis of corroded steel box-girder bridges, pitting corrosion effects on plate elements, fatigue life estimation, and maintenance strategies.

🏢

Tall Building Systems

Combined framed tube, shear core, outrigger, and belt-truss systems — analytical models, dynamic response to blast loading, and optimum outrigger placement.

FRP-Reinforced Concrete

Shear and flexural capacity of FRP-RC beams, CFRP-confined columns, compressive strength prediction, and innovative GEP equations for design practice.

Our Team

A dedicated group pushing the boundaries of structural engineering and computational methods.

Dr. Yasser Sharifi

Dr. Yasser Sharifi

Principal Investigator
Professor of Structural Engineering
Vali-e-Asr University of Rafsanjan, Iran
vru.ac.ir
Steel Structures Machine Learning Corrosion Concrete
Mohammad Mahdi Karami-Pour

Mohammad Mahdi Karami-Pour

Ph.D. Researcher
Structural Engineering
Vali-e-Asr University of Rafsanjan, Iran
FRP-RC Beams XGBoost PSO MARS
Nematullah Zafarani

Nematullah Zafarani

Ph.D. Researcher
Structural Engineering
Vali-e-Asr University of Rafsanjan, Iran
FRP-RC Beams SFRC Neural Networks Metaheuristics

Publications

95 peer-reviewed articles across structural engineering, AI, and materials science.

FRP-RC Beam Shear Strength Predictor

Predict the nominal shear capacity (Vn) of slender FRP-reinforced concrete beams using our PSO-optimized XGBoost model.

Model

PSO-optimized XGBoost regressor trained on an experimental database of FRP-RC slender beams without stirrups.

Input Parameters

bw mm a mm d mm f'c MPa ρf % Ef GPa Ec GPa

Output

Nominal shear capacity Vn in kN — Developed by Karami-Pour & Sharifi, Vali-e-Asr University of Rafsanjan.

FRP-RC Beam Shear Strength Predictor · PSO-XGBoost · Karami-Pour & Sharifi

Contact

We welcome inquiries from researchers, engineers, and institutions interested in structural engineering, AI-assisted assessment, and sustainable construction materials.

Open to Collaboration

If you are interested in joint research, data exchange, or academic partnership in the areas of structural reliability, machine learning for structural assessment, FRP-reinforced concrete, or sustainable cementitious materials, we would be pleased to hear from you. Please reach out directly to any member of our team.

Principal Investigator

Dr. Yasser Sharifi

y.sharifi@vru.ac.ir

Ph.D. Researcher

Mohammad Mahdi Karami-Pour

m.m.karamipour@stu.vru.ac.ir

Ph.D. Researcher

Nematullah Zafarani

 

Location

Department of Civil Engineering
Vali-e-Asr University of Rafsanjan
Rafsanjan, Kerman, Iran

Online Tools

FRP-RC Shear Strength Predictor
PSO-XGBoost · Karami-Pour & Sharifi

Abstract