Bahman Ghiassi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Bahman Ghiassi has a total of 160 co-authors. Here are the top co-authors by number of shared publications:
- Daniel Vicentini Oliveira
University of Minho
36 shared publications - Paulo Barbosa Lourenco
University of Minho
30 shared publications - Ali Dalalbashi
University of Leeds
9 shared publications - Hamid Maljaee
Civil Engineering Department, RISCO, Campus Universitário de Santiago, University of Aveiro, 3810-193 Aveiro, Portugal
6 shared publications - Alessio Alexiadis
School of Chemical Engineering, University of Birmingham, Birmingham, UK
5 shared publications Gabriele Milani
5 shared publications
Latest Publications
- 18 May 2026
- Published by Springer Nature
- p. 249-256
Design Framework for Sustainable Textile-Reinforced Concrete Using Laminate Theory and Damage Modeling
- 18 May 2026
- Published by Springer Nature
- p. 249-256
Design Framework for Sustainable Textile-Reinforced Concrete Using Laminate Theory and Damage Modeling
- 2 April 2026
- Published by Springer Nature
- p. 1267-1276
Critical Assessment of ASCE/SEI 7–22 Waterborne Debris Impact Calculations for Masonry Wall Design
- 2 April 2026
- Published by Springer Nature
- p. 1267-1276
Critical Assessment of ASCE/SEI 7–22 Waterborne Debris Impact Calculations for Masonry Wall Design
- 2 April 2026
- Published by Springer Nature
- p. 1287-1297
Modelling Short-Term Mechanical Loading of Masonry Using Particle-Based DEM
- 2 April 2026
- Published by Springer Nature
- p. 1287-1297
Modelling Short-Term Mechanical Loading of Masonry Using Particle-Based DEM
- Open Access
- 19 February 2026
- Published by Elsevier in Engineering Structures
- Vol. 354
Shear strengthening of masonry walls with inorganic-based composites: Quantifying fiber exploitation through a numerical approach
- 19 February 2026
- Published by Elsevier in Engineering Structures
- Vol. 354
Open AccessShear strengthening of masonry walls with inorganic-based composites: Quantifying fiber exploitation through a numerical approach
- 8 February 2026
- Published by Springer Nature
- p. 728-737
The Effect of Reinforcement Layers on the Flexural Performance of Textile Reinforced Concrete (TRC)
- 8 February 2026
- Published by Springer Nature
- p. 728-737
The Effect of Reinforcement Layers on the Flexural Performance of Textile Reinforced Concrete (TRC)
- 8 February 2026
- Published by Springer Nature
- p. 706-716
Mechanical Performance of Mineral-Impregnated TRC
- 8 February 2026
- Published by Springer Nature
- p. 706-716
Mechanical Performance of Mineral-Impregnated TRC
- 8 February 2026
- Published by Springer Nature
- p. 696-705
Prestressed Textile-Reinforced Concrete: A Route to Sustainable Development in Construction
- 8 February 2026
- Published by Springer Nature
- p. 696-705
Prestressed Textile-Reinforced Concrete: A Route to Sustainable Development in Construction
- Open Access
- 14 November 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (22) , 12114
Evaluating the Performance of Large Language Models for Geometry and Simulation File Generation in Physics-Based Simulations
Finite-element simulations and computer-aided design workflows require complex preprocessing, with geometry creation and simulation setup traditionally demanding significant manual expertise. The question emerges: can machine learning, namely large language models, help automate these processes? This study evaluates how well nine large language models can automate finite-element simulations starting from natural language prompts, generating both the geometry files for meshing (using Gmsh, an open-source geometry and mesh generator) and the input files needed for the solver (using Elmer, an open-source multiphysics simulation tool). Two standard test cases, a simple bar and a wheel and axle assembly, are used to evaluate and compare their performance. A set of criteria and a scoring system is introduced to assess performance across geometry and simulation setup, covering aspects such as file completeness, Boolean operations, shape fidelity, and displacement error. Results show that most LLMs excel at generating solver input files, achieving 78–88% success rate with <1% displacement error when executed. Geometry generation proves more challenging, with 70% success for simple shapes but only 56% for assemblies. Critically, no model successfully implemented Boolean operations required for merging components; GPT-4o uniquely attempted these operations but failed due to volume reuse errors. This 0% success rate for Boolean operations represents the primary bottleneck for assembly automation. Notable findings include extreme performance variability in the smallest model (PHI-3 Mini, varying 0–97% between similar tasks) and complete elimination of unit errors when explicitly prompted for SI units. The results reveal a clear capability gap: while LLMs reliably generate physics solver inputs, they cannot produce ready-to-mesh assemblies, requiring manual intervention for Boolean operations. While the study focuses on a Gmsh–Elmer pipeline, the results likely generalise to other simulation software.
- 14 November 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (22) , 12114
Open AccessEvaluating the Performance of Large Language Models for Geometry and Simulation File Generation in Physics-Based Simulations
Finite-element simulations and computer-aided design workflows require complex preprocessing, with geometry creation and simulation setup traditionally demanding significant manual expertise. The question emerges: can machine learning, namely large language models, help automate these processes? This study evaluates how well nine large language models can automate finite-element simulations starting from natural language prompts, generating both the geometry files for meshing (using Gmsh, an open-source geometry and mesh generator) and the input files needed for the solver (using Elmer, an open-source multiphysics simulation tool). Two standard test cases, a simple bar and a wheel and axle assembly, are used to evaluate and compare their performance. A set of criteria and a scoring system is introduced to assess performance across geometry and simulation setup, covering aspects such as file completeness, Boolean operations, shape fidelity, and displacement error. Results show that most LLMs excel at generating solver input files, achieving 78–88% success rate with <1% displacement error when executed. Geometry generation proves more challenging, with 70% success for simple shapes but only 56% for assemblies. Critically, no model successfully implemented Boolean operations required for merging components; GPT-4o uniquely attempted these operations but failed due to volume reuse errors. This 0% success rate for Boolean operations represents the primary bottleneck for assembly automation. Notable findings include extreme performance variability in the smallest model (PHI-3 Mini, varying 0–97% between similar tasks) and complete elimination of unit errors when explicitly prompted for SI units. The results reveal a clear capability gap: while LLMs reliably generate physics solver inputs, they cannot produce ready-to-mesh assemblies, requiring manual intervention for Boolean operations. While the study focuses on a Gmsh–Elmer pipeline, the results likely generalise to other simulation software.