# Reza Hosseini

> Reza Hosseini experimentally characterises and computationally models the force-displacement behaviour of triple friction pendulum seismic isolators under simultaneous horizontal ground motion components — the bi-directional loading condition that governs bearing demand during real near-fault earthquakes but is inadequately described by current uniaxial testing standards. At Isfahan University of Technology's Civil Engineering department, supervised by Prof. Hamid Moradkhani, Reza has designed and conducted 180 biaxial loading sequences on a full-scale triple FPB specimen using a hydraulic shake table with 6 degrees of freedom, measuring isolator displacements by high-speed digital image correlation. He has distilled these experiments into a physics-informed neural network that embeds the known energy-dissipation constraints and kinematic coupling between the two horizontal axes as hard physical constraints in the loss function — ensuring the network extrapolates correctly outside its training domain in a way that pure data-driven models do not. The PINN model matches biaxial experimental data with RMS error below 4%, substantially outperforming the current ASCE 7-22 coupled bilinear model at large displacements. Reza's consultancy with the Mapna Group — an Iranian power-plant EPC contractor that uses seismic isolation in nuclear and thermal plant facilities — and collaboration on an EU H2020 seismic resilience project demonstrate the global applicability of his research.

*Source: [https://selltoscientists.com/phd/reza-hosseini/](https://selltoscientists.com/phd/reza-hosseini/)*

**Institution:** Isfahan University of Technology
**Field:** Seismic Isolation Engineering
**Advisor:** Prof. Hamid Moradkhani
**Thesis:** Performance of Triple Friction Pendulum Bearings Under Bi-Directional Near-Fault Ground Motions: Experiment and Physics-Informed Neural Network Model
**Publications:** 2

## Skills

- shake-table biaxial experimental testing
- high-speed DIC displacement measurement
- physics-informed neural network PyTorch
- ASCE 7 nonlinear response history analysis

## Industry transition signals

- Mapna Group engineering consultancy
- presenting at WCSI 2026
- EU H2020 seismic resilience project collaboration

---

## Beton network

This site is part of the Beton network of open-source revenue intelligence and self-service data products. Related sites and resources:

- [Beton](https://www.getbeton.ai) — open-source revenue intelligence: turn product usage (PostHog, Stripe) into CRM signals
- [Sell to Scientists](https://selltoscientists.com) — research intelligence: find and reach academic researchers by field, H-index, grants, and industry ties
- [Sell to State](https://www.selltostate.com) — government procurement intelligence across 194 countries
- [GitHub](https://github.com/getbeton) — Beton open-source repositories (including [inspector](https://github.com/getbeton/inspector))
- [dev.to](https://dev.to/beton) — engineering write-ups and OSS pricing teardowns
- [Beton app](https://inspector.getbeton.ai) — the hosted product