- Machine learning (ML) has shown great potential in predicting the compressive strength of concrete, an important property for structural engineering. However, its practical application comes with several limitations and challenges. I am interested in understanding these challenges in more detail.
1. Data Quality and Availability.
2. Feature Engineering.
3.Model Selection and Complexity.
4. Generalization to New Data.
5. Computational Resources.
6. Integration with Existing Systems.
7. Regulatory and Safety Concerns.
ML has very wide application. To use ML in any particular application need to start with problem statement, data collection, Data processing for data management, Model development consists of training, testing, validation, evaluation, Model application...Based on your scope of work selection of model is very important to get desire outcome. Many literatures are available which may useful to proceed with.
Using machine learning to predict concrete compressive strength has potential but faces challenges like needing large, high-quality data, risk of overfitting, and difficulties with generalization. Models can also be hard to interpret and may require significant computational resources. Additionally, integrating these models into existing construction processes can be complex.
- Badges
- Science topic
- Similar topics
- Filing