Academic CV · Structural Health Monitoring

Structural damage detection through FEM, modal analysis and machine learning.

Civil and structural engineering researcher focused on vibration-based SHM, finite element modelling, structural dynamics, and data-driven damage location and severity prediction in frame structures.

Research output Thesis abstract Download CV

Core field Civil / Structural Engineering

Research tools FEM · MATLAB · Modal Analysis

Current focus SHM · ML Damage Detection

Research Profile

Practical, interpretable SHM for civil structures

My research connects engineering mechanics with data-driven prediction, aiming to support safer, more reliable and more sustainable structural assessment.

Structural Health Monitoring

Vibration-based damage detection, modal features, sensor-informed assessment, anomaly detection and condition monitoring.

Finite Element Modelling

MATLAB-based modelling, semi-rigid connections, eigenvalue analysis, stiffness-reduction scenarios and model-updating concepts.

Machine Learning

ANN, SVM, Random Forest, LSBoost, optimization-based modelling, regression workflows and damage severity prediction.

Research Output

Accepted and ongoing research

Machine-Learning-Based Damage Detection in Beam-Column Connections Using Modal Features

Accepted Conference Paper · SMAR 2026
Accepted for the 8th International Conference on Smart Monitoring, Assessment and Rehabilitation of Civil Structures. The study compares ANN, SVM, Random Forest and LSBoost for damage prediction using natural frequencies and mode-shape features in benchmark and numerical frame studies.

SMAR 2026 Modal features ANN SVM RF LSBoost

Search-Optimized Support Vector Machines for Vibration-Based Structural Damage Location and Severity Prediction

Manuscript Ready for Submission
This manuscript focuses on optimized SVM-based prediction of damage location and severity using vibration-based features, extending the research direction toward experimental and numerical frame benchmarks.

SVM Optimization Damage location Severity prediction

Master’s Thesis Abstract

Damage Identification in Beam-to-Column Connections Using Artificial Neural Networks

Damage to beam-to-column connections can have serious consequences for the safety and performance of structures. This thesis investigates the use of artificial neural networks as an advanced method for damage identification in beam-to-column connections within the framework of structural health monitoring. Although structural connections are commonly assumed to be perfectly rigid in finite-element models, the connections in this study were modelled as semi-rigid using the finite-element method.

Connection damage was simulated through reductions in connection stiffness. The resulting modal characteristics, including natural periods and mode shapes, were used as input parameters for the artificial neural network. By modifying the structural stiffness matrices and extracting eigenvalues and eigenvectors, the datasets required to train the network were generated. The severity of connection damage was defined as the network output.

The results demonstrate that artificial neural networks can effectively identify damage in semi-rigid beam-to-column connections. The proposed approach shows promise as a data-driven method for SHM and condition assessment of framed structures.

Damage identification Semi-rigid connections ANN Modal analysis Thesis grade: 19/20

Education

Academic background

Sep 2021 – Sep 2023

Master’s Degree in Civil Engineering – Earthquake Engineering

Azarbaijan Shahid Madani University, Tabriz, Iran · Thesis grade: 19/20

Sep 2011 – Jun 2017

Bachelor’s Degree in Civil Engineering

Islamic Azad University of Tabriz, Tabriz, Iran

Technical Skills

Research toolkit

Structural Engineering SHM, modal analysis, structural dynamics, damage detection, steel structures, beam-column connections, RC/steel frame behaviour.

Computational Modelling Finite element methods, MATLAB modelling, eigenvalue analysis, numerical data generation, vibration-based assessment.

Machine Learning ANN, SVM, search/optimization-based modelling, Random Forest, LSBoost, regression metrics, training/validation/test workflows.

Engineering Practice ETABS, technical office work, quantity surveying, site supervision, project coordination, resource optimization.

Updated academic CV

Download the full PDF CV with education, research output, technical skills, professional experience and references.

Download CV

Keep CV.pdf in the same folder as this HTML file so the download button works correctly.

Download CV.pdf Contact me