Civil Engineering Structural

Hamed Bolandi

East Lansing, MI ***** Cell: 517-***-**** ********@***.*** LinkedIn Webpage Google scholar

EDUCATION

Michigan State University, East Lansing, MI Jan 2023

Dual major Ph.D. in Structural Engineering and Computer Science

Islamic Azad University, Iran Sep 2010

Master’s degree in Structural Engineering

Islamic Azad University, Iran Sep 2008

Bachelor’s degree in Civil Engineering

PROFESSIONAL EXPERIENCES

Human Analysis Lab (HAL), Michigan State University, East Lansing, MI Jan 2018 - present

Machine Learning Scientist, graduate student

Implemented a deep learning algorithm to predict dynamic stress using forward Physics Informed Neural Network (PINN), which is generalizable and 60000 times faster than conventional FE solvers.

Implemented an inverse PINN algorithm using deep learning techniques to identify unknown parameters of Partial Differential Equations.

Predict dynamic stress using deep learning, reducing the computational cost of FE solvers by about 10000 times.

Implemented a deep anomaly detection neural network using compressed sensor data, which can accurately localize the anomalies in structural components.

Predict static stress distribution in intact and damaged structural components using deep learning methods to capture damages with the size of 1 mm.

Introduce data reduction for the SHM systems, leading to over 2500% reduction in storage requirement.

Teaching Assistant, graduate student

Teaching Assistant for Python programming language and static Jan 2018 - present

No. 621 Engineering Consulting Group, Iran, Mashhad Jan 2010 - Jan 2018

CEO, Machine Learning Scientist

Predict the compressive strength of concrete using genetic programming leading to eliminating sophisticated and time-consuming laboratory tests.

Implement an evolutionary machine learning algorithm for predicting the shear resistance of steel fiber-reinforced concrete beam, significantly outperforming conventional equations.

Propose multigene genetic programming (MGGP) approach for estimating the elastic modulus of concrete which performs superior to the existing traditional models.

Structural analysis, cost-effective design, and optimization of more than 100 concrete and steel structures, leading to about 500 tons of saving in steel and concrete.

RESEARCH INTERESTS

Machine Learning, Deep Learning, Finite Element Analysis, Physics Informed Neural Network.

SKILLS

Programming: Python, PyTorch, TensorFlow, Julia, MATLAB, SQL

Simulation: ABAQUS, ANSYS, MATLAB PDE solver

Algorithm and tools: CNN, LSTM, MLP, Transformers, matplotlib, Numpy, Scipy, Pandas, Scikit-learn, Regression, Classification, Cloud Computing, Linux OS,

LICENSES

SQL for Data Science, UC DAVIS.

Convolutional Neural Network in TensorFlow, deep learning.

Research Mentor, National Research Mentor Network.

HONORS

Best paper award at the 2022 SMASIS conference.

Top reviewer award for the Cogent Engineering journal.

COURSEWORK

Deep Learning

Design and Theory of Algorithms

Data Mining

Evolutionary Computations

Distributed Systems

Finite element Analysis

Smart Materials and structures

Continuum Mechanics.

SELECTED PUBLICATIONS

Bolandi, H., Sreekumar, G., Li, X., Lajnef, N., Boddeti, V.: Physics informed Neural Network for Prediction of Dynamic Stress (under review).

Bolandi, H., Sreekumar, G., Li, X., Lajnef, N., Boddeti, V.: FE-LstmNET:Predicting Dynamic Stress Distributions in Structural Components (under review).

Bolandi, H., Li, X., Salem, T., Boddeti, V., Lajnef, N.: Bridging finite element and deep learning: High-resolution stress distribution prediction in structural components. Frontiers of Structural and Civil Engineering (2022).

Bolandi, H., Li, X., Salem, T., Boddeti, V., Lajnef, N.: Deep learning paradigm for prediction of stress distribution in damaged structural components with stress concentrations. Advances in Engineering Software (2022).

Bolandi, H., Banzhaf, W., Lajnef, N., Barri, K., Alavi, A.H.: An intelligent model for the prediction of bond strength of frp bars in concrete: A soft computing approach. Technologies 7(2), 42 (2019).

Bolandi, H., Pengcheng, j., Lajnef, N., Barri, K., Hasni, H., Alavi, A.H.: A Novel Data Reduction Approach for Structural Health Monitoring Systems (2019).

Li, X., Bolandi, H., Salem, T., Lajnef, N., Boddeti, V.:NeuralSI: Structural Parameter Identification in Nonlinear Dynamical Systems (2022).

Contact this candidate