Reviewing of prediction of cracks and recognizing its patterns in geopolymer concrete beams using machine learning

Geopolymer concrete, known for its sustainable properties and high strength, has emerged as a viable alternative to traditional Portland cement concrete. However, the prediction of cracks and the recognition of their patterns in geopolymer concrete beams remain critical challenges that impact structural integrity and durability. This review paper explores various machine learning techniques employed in the analysis of crack formation and pattern recognition in geopolymer concrete. We systematically evaluate the effectiveness of different algorithms, including supervised and unsupervised learning methods, and their applications in crack detection and classification. Additionally, we highlight the integration of image processing techniques and sensor data in enhancing predictive accuracy. The findings indicate that machine learning models significantly improve the understanding of crack behavior in geopolymer concrete, facilitating proactive maintenance strategies. This paper concludes with recommendations for future research directions, emphasizing the need for more comprehensive datasets and the exploration of hybrid machine learning models to advance the field.