Related Experiment Video
Updated: May 21, 2025
05:36
Production and Analysis of Sporosarcina pasteurii Biocement Bricks Using Custom 3D-Printed Molds for Unconfined Compression Tests
Published on: March 7, 2025
167
Data driven design of ultra high performance concrete prospects and application
Bryan K Aylas-Paredes1, Taihao Han2, Advaith Neithalath3
1Department of Materials Science and Engineering, Missouri University of Science and Technology, 248A V. H. McNutt Hall, 1400 N. Bishop, Rolla, MO, 65409, USA.
Scientific Reports
|March 19, 2025
Summary
Machine learning models accurately predict ultra-high performance concrete (UHPC) compressive strength by identifying key material factors. This optimizes UHPC design and reduces experimental needs for enhanced material development.
Area of Science:
- Civil Engineering
- Materials Science
- Data Science
Background:
- Ultra-high performance concrete (UHPC) offers superior mechanical and durability properties for infrastructure.
- Factors like low water-to-binder ratios, SCMs, and fiber reinforcement significantly influence UHPC performance.
- Machine learning (ML) is increasingly utilized for predicting UHPC performance and optimizing mixture designs.
Purpose of the Study:
- To review ML applications in predicting UHPC workability, mechanical, and thermal properties.
- To explore future research directions, including data crossing, generative AI, and physics-guided ML.
- To develop and evaluate ML models for predicting UHPC compressive strength using a substantial dataset.
Main Methods:
- A comprehensive literature review of ML applications in UHPC.
- Development of ML models using a database of 1300 UHPC records.
- Application of SHapley Additive exPlanations (SHAP) to assess variable importance.
Main Results:
- ML models demonstrated high accuracy in predicting UHPC compressive strength.
- SHAP analysis indicated that chemical compositions had minor impacts on strength prediction for the materials studied.
- Excluding insignificant variables improved model efficiency and predictive accuracy.
Conclusions:
- Optimized ML models can significantly enhance UHPC material design and performance prediction.
- Reducing the experimental workload is achievable through data-driven insights from ML models.
- Expanding the dataset with more diverse data can further improve model generalizability and predictive capabilities.
Related Concept Videos
01:14Design Example: Managing Concrete Workability
67
This example deals with managing the workability of concrete for a raft foundation project under hot weather conditions. Workability is crucial for ensuring the concrete is easy to place, compact, and finish. In this scenario, a slump test — a common method to measure the workability of fresh concrete — initially indicated low workability. This was attributed to the rapid water loss from the concrete mix, exacerbated by the high temperatures causing the course aggregates to heat up.
67
01:22Fiber Reinforced Concrete
65
Fiber-reinforced concrete significantly enhances the structural and nonstructural properties of traditional concrete by incorporating fibers like steel, glass, and polymers. These fibers, varying from natural ones such as sisal and cellulose to manufactured ones like polypropylene and Kevlar, are mixed into hydraulic cement with aggregates. Steel fibers, often preferred for their robustness, contribute to improved ductility, toughness, and post-cracking performance. The concrete is classified...
65
01:20Concrete
299
Concrete is a vital construction material extensively used worldwide, primarily valued for its strength, durability, and versatility, which it provides for various structural designs. Concrete generally comprises ingredients like Portland cement, coarse gravel, fine sand, and water. Concrete can be mixed by simple hand methods or industrially at computer-controlled plants. The mixture consists of aggregates and a paste made from water and Portland cement. This paste coats the aggregates and,...
299
01:26Design Example: Sustainability in Concrete Building
148
As the construction industry moves towards more eco-friendly practices, concrete's adaptability and its ability to incorporate sustainable features make it a key material in the drive towards greener building solutions.
There are multiple approaches to achieve sustainability in a commercial concrete building. For instance, construct a concrete parking area under the building, utilizing pervious concrete paver blocks in open areas to facilitate rainwater collection through an underground...
There are multiple approaches to achieve sustainability in a commercial concrete building. For instance, construct a concrete parking area under the building, utilizing pervious concrete paver blocks in open areas to facilitate rainwater collection through an underground...
148
01:23Abrasion Resistance of Concrete
89
Abrasion resistance is an essential characteristic of concrete that determines its durability and longevity under various wear conditions. Concrete surfaces are vulnerable to different types of abrasion. For instance, surfaces may wear down due to the constant movement of vehicles or be eroded by solids carried in water, as seen in concrete canal linings. Specific tests are conducted to measure the abrasion resistance of concrete.
One such test is the revolving disc test, where three plates...
One such test is the revolving disc test, where three plates...
89
01:28Effects of Air-entrainment in Concrete
77
Air entrainment in concrete significantly enhances the material's durability, especially in environments subjected to freeze-thaw cycles. Introducing small air bubbles into the concrete mix acts as internal voids that accommodate the expansion of water when it freezes, thereby alleviating internal stress and preventing structural cracks. This function is crucial in climates with significant freezing and thawing, as it protects the concrete from repeated stresses that could lead to premature...
77