AI-Powered Comprehensive Framework for UHPC: From Material Optimization to Seismic Resilience of Bridges
A multi-scale AI framework spanning UHPC mix optimization, constitutive modeling, performance-based seismic design, and bridge resilience assessment.
- Publications
- 5+
- Top-tier journals
- Objectives
- 19
- Multi-objective optimization
- Milestone
- First
- UHPC drift limit states
- Impact
- #1
- Most popular in journal
Overview
This project develops a comprehensive AI-powered framework that addresses ultra-high-performance concrete (UHPC) across multiple scales, from material optimization to structural resilience.
Novel contributions
- 01
19-objective UHPC optimization
Multi-objective framework simultaneously optimizes compressive strength, cost, and environmental impacts of UHPC mixes.
- 02
Generative AI for constitutive modeling
Hybrid ML with CTGAN for data augmentation enabling accurate peak and ultimate stress-strain prediction of confined UHPC.
- 03
First UHPC drift limit states
Explainable ML-powered drift ratio limit states for UHPC bridge columns, proposed for the first time.
- 04
Bridge-specific vulnerability
Hybrid ML-enabled multivariate probabilistic seismic demand model for bridge-specific fragility and resilience assessment.
Multi-scale research pipeline
- 2026PublishedView article
CompMoE: Compositional Mixture-of-Experts Neural Network for Sustainable Mix Optimization of Fiber-Reinforced Ultra-High-Performance Concrete
Wakjira, T.G. & Goshu, H.L.
Materials Today Advances, 32, 100944
- 2025PublishedView article
Hybrid machine learning-enabled multivariate bridge-specific seismic vulnerability and resilience assessment of UHPC bridges
Wakjira, T.G. & Alam, M.S.
Resilient Cities and Structures, 4(2), 92-102
- 2024PublishedView article
Performance-based seismic design of Ultra-High-Performance Concrete (UHPC) bridge columns with design example – Powered by explainable machine learning model
Wakjira, T.G. & Alam, M.S.
Engineering Structures, 314, 118346
- 2024PublishedView article
Hybrid machine learning model and predictive equations for compressive stress-strain constitutive modelling of confined ultra-high-performance concrete (UHPC) with normal-strength steel and high-strength steel spirals
Wakjira, T.G., Abushanab, A. & Alam, M.S.
Engineering Structures, 304, 117633
- 2024PublishedView article
Peak and ultimate stress-strain model of confined ultra-high-performance concrete (UHPC) using hybrid machine learning model with conditional tabular generative adversarial network
Wakjira, T.G. & Alam, M.S.
Applied Soft Computing, 154, 111353
- 2024PublishedView article
A novel framework for developing environmentally sustainable and cost-effective ultra-high-performance concrete (UHPC) using advanced machine learning and multi-objective optimization techniques
Wakjira, T.G., Kutty, A.A. & Alam, M.S.
Construction and Building Materials, 416, 135114
Interested in this research?
For code access, collaboration or questions about UHPC-AI, contact the principal investigator, Dr. Tadesse Wakjira.