MSc Civil Engineering (Full-time) final year Project brief

Project Brief

1.0 Problem Statement

Concrete is central to modern construction due to its versatility, strength, and affordability. However, its production imposes a heavy burden on the environment. Cement manufacturing alone is responsible for nearly 8% of global CO₂ emissions [1], significantly contributing to climate change. Furthermore, the process consumes large volumes of natural resources, including water, sand, and aggregates [2], which raises concerns about resource depletion and ecosystem disruption. Concrete production is also water-intensive, contributing to local and regional water stress [3]. Moreover, conventional production methods often result in inefficiencies, such as material wastage and inconsistent quality, further exacerbating its environmental impact [4]. Given the global push towards sustainable development, exploring innovative strategies to address these challenges holistically is essential.

2.0 Introduction

In response to these urgent challenges, the construction sector is dynamically seeking innovative strategies to reduce its carbon footprint and enhance concrete sustainability. Artificial Intelligence (AI) has recently emerged as a transformative technology, offering powerful tools for optimizing mix designs, predicting performance, and improving production efficiency [4]. However, existing research predominantly focuses on material composition, with limited integration of AI into the concrete processing and curing stages.

This project introduces AIcrete, a unique AI-driven framework that extends optimization beyond traditional boundaries. Integrating ultrasonic mixing and vibration curing techniques with AI-powered decision-making [5]. AIcrete aims to enhance concrete production's sustainability, durability, and cost-efficiency. This integrated approach seeks to contribute to environmental preservation and advance intelligent infrastructure solutions.

3.0 Aim and Objectives

3.1 Aim

To develop a sophisticated system integrating AI with ultrasonic mixing and vibration curing to enhance concrete's strength, sustainability, and durability. Although companies currently utilize AI in the three phases independently, these have yet to be integrated. This new project will promote a shift to ward sustainability in numerous ways.

3.2 Objectives

1. To investigate and analyze the environmental and performance challenges associated with conventional concrete production, which include high CO₂ emissions, significant raw material consumption, and variability in quality.
2. Develop an AI model that identifies the optimal concrete mix with reduced cement while maintaining high performance.
3. Employ ultrasonic mixing to enhance consistency and minimize air voids.
4. Implement and manage vibration curing with AI to accelerate strength development.
5. Carry out laboratory experiments to assess the system’s performance.
6. Evaluate the environmental and cost benefits compared to traditional methods.

4.0 Timeline

4.1 Month 1- Literature review, define scope, initial lab test set up, and choose AI approach.

1. Study AI in concrete, ultrasonic mixing, and vibration curing.
2. Search for similar studies, technologies, and existing AI methods.
3. Selecting AI models for optimizing concrete, ultrasonic mixing, and vibration curing.
4. Secure university laboratory for concrete mixing and testing.
5. Arrange for ultrasonic transducers and vibration devices.
6. Choose several concrete mix designs for testing.

4.2 Month 2- Run experiments on concrete samples and apply data from lab tests to the AI model.

1. Test the concrete samples to measure strength, setting time, and changes in microstructure.
2. Utilize lab data to enhance the mix optimization forecasts.
3. Test the AI model by incorporating lab data into the model.
4. Merge the three AI models into one.

4.3 Month 3- Analyse and compare results, evaluate AI-predicted mix ratios, and write the final dissertation.

1. Compare the test results for compressive strength, microstructure, and curing time.
2. Evaluate whether AI-predicted mix ratios enhance performance.
3. Prepare the final report, including the abstract, introduction, methodology, results, graphs, comparison tables, charts, AI performance data, cost analysis, a discussion of the new model's benefits, and a conclusion.

5.0 Potential Impact of the AIcrete model.

5.1 AI-driven vibration analysis v/s traditional testing.

 5.2 Sustainability and cost-efficiency

• Reduction of material waste through improved mix design generated by AI.
• Reduce carbon footprint by minimizing cement content while maintaining the strength of the structure.
• Reduces workforce and testing costs through automated defect detection.
• The AI model will predict the concrete performance from before mixing to curing.

5.3 Key Innovation

• Identify concrete integrity without breaking samples: a non-destructive approach.
• AI continuously updates and improves predictions- real-time and innovative technology.
• Enhances mix design for durability and strength while minimizing resource use – Sustainable
• AI models optimize recycled materials (e.g., fly ash, slag, recycled aggregates) to minimize environmental impact without compromising performance—material substitution.
• AI analyzes real-time data during production to identify inconsistencies, anticipate failures, and minimize defects - Quality Control & Anomaly Detection

6.0 Conclusion

This integrated approach can significantly contribute to sustainable construction practices and align global objectives for climate resilience and intelligent infrastructure. The findings from this project are expected to provide valuable insights into the practical application of AI in concrete technology and pave the way for future eco-friendly and efficient concrete production methods.