ILBAY YUPA, DANIEL JEFFERSON
Preferred name
ILBAY YUPA, DANIEL JEFFERSON
Main Affiliation
MCIAA - Mecánica Computacional e Inteligencia Artificial Aplicada
Web Site
Scopus Author ID
60093556900
3 results
Now showing 1 - 3 of 3
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Toward Responsible AI in High-Stakes Domains: A Dataset for Building Static Analysis with LLMs in Structural Engineering(MDPI AG, 2025-10-24); ; - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Human–AI Teaming in Structural Analysis: A Model Context Protocol Approach for Explainable and Accurate Generative AI(MDPI AG, 2025-09-04); ; The integration of large language models (LLMs) into structural engineering workflows presents both a transformative opportunity and a critical challenge. While LLMs enable intuitive, natural language interactions with complex data, their limited arithmetic reasoning, contextual fragility, and lack of verifiability constrain their application in safety-critical domains. This study introduces a novel automation pipeline that couples generative AI with finite element modelling through the Model Context Protocol (MCP)—a modular, context-aware architecture that complements language interpretation with structural computation. By interfacing GPT-4 with OpenSeesPy via MCP (JSON schemas, API interfaces, communication standards), the system allows engineers to specify and evaluate 3D frame structures using conversational prompts, while ensuring computational fidelity and code compliance. Across four case studies, the GPT+MCP framework demonstrated predictive accuracy for key structural parameters, with deviations under 1.5% compared to reference solutions produced using conventional finite element analysis workflows. In contrast, unconstrained LLM use produces deviations exceeding 400%. The architecture supports reproducibility, traceability, and rapid analysis cycles (6–12 s), enabling real-time feedback for both design and education. This work establishes a reproducible framework for trustworthy AI-assisted analysis in engineering, offering a scalable foundation for future developments in optimisation and regulatory automation. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Beyond Prescriptive Codes: A Validated Linear–Static Methodology for Seismic Design of Soft-Storey RC Structures(MDPI AG, 2025-12-23); ; Reinforced concrete buildings with masonry-induced soft-storey irregularities exhibit extreme seismic vulnerability, a critical risk often underestimated by conventional code-based design. Standard equivalent static methods typically fail to capture the intense concentration of seismic demand at the flexible ground level, leading to unconservative designs that do not meet performance objectives. This research proposes a corrective linear–static methodology to address this deficiency. A new Equivalent Lateral Force profile (ELFi1) was developed, derived from modal analyses of 235 representative soft-storey archetypes to accurately account for stiffness heterogeneity. This profile was integrated with a realistic response modification coefficient (Ri1 = 5.04), determined to be 37% lower than the normative R-factor (R = 8) prescribed by code. Nonlinear static analyses confirmed that conventional design resulted in “irreparable” damage (mean Global Damage Index = 0.82). In contrast, redesigning the structure using the proposed ELFi1 and Ri1 methodology successfully mitigated damage concentration, upgrading structural performance to a “repairable” state (mean Global Damage Index = 0.52). Finally, Incremental Dynamic Analysis validated the approach; the redesigned structure satisfied FEMA P695 collapse prevention criteria, achieving an Adjusted Collapse Margin Ratio (ACMR) of 2.10. This study confirms the proposed method is a robust and practical design alternative for soft-storey mechanisms within a simplified linear framework.