Discriminant covariate deep learning model for projecting of structural characteristics of hybrid fiber incorporated concrete beam retrofitted using GFRP

Devi M. S., Kumar M. V., Chandar S. P., Kirgiz M. S., Nagaprasad N., Ramaswamy K.

DISCOVER APPLIED SCIENCES, cilt.7, sa.10, 2025 (ESCI, Scopus) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 7 Sayı: 10
  • Basım Tarihi: 2025
  • Doi Numarası: 10.1007/s42452-025-07152-5
  • Dergi Adı: DISCOVER APPLIED SCIENCES
  • Derginin Tarandığı İndeksler: Emerging Sources Citation Index (ESCI), Scopus
  • İstanbul Üniversitesi-Cerrahpaşa Adresli: Hayır

Özet

Advanced techniques for retrofitting reinforced concrete structures have emerged in response to the increasing demand for durable and environmentally friendly infrastructure. Previous studies have demonstrated that Hybrid Fiber Reinforced Concrete retrofitted with Glass Fiber Reinforced Polymers exhibits enhanced structural characteristics, including improved flexural strength, shear strength, and ductility. Despite several Finite Element Analysis studies, there remains a research gap in developing a machine learning model to predict these structural characteristics. For this research, a dataset was collected containing 27 attributes, comprising 18 independent variables and 9 dependent variables. The dataset was subjected to exploratory and prescriptive data analysis. The results indicate that the proposed Fused Learning Classifier Model achieves a high accuracy of 99% in predicting the structural characteristics of beams.