Application of Machine Learning to Predict the Mechanical Characteristics of Concrete Containing Recycled Plastic-Based Materials

One of the practical ways to overcome adverse environmental effects plastic bottle waste is implement bottles into concrete, one most widely used materials in construction industry. Plastic are mainly made polyethylene terephthalate (PET) and can be as a fiber reinforce concrete. In recent years, PET fiber-reinforced concrete (PFRC) has attracted researcher attention, several experimental studies have been conducted. This paper aims present benefits using reinforcing element machine learning approach. By considering effect fibers engineers stakeholders may encouraged further use these recycled materials. The proposed network was successfully able capture response PFRC with high accuracy (mean squared error (MSE) 7.11 MPa R coefficient 98%). results show that amount usage significant on compressive strength PFRC. Moreover, PFRC’s variation mechanical geometrical properties depends fiber’s shape. effective shapes deformation, followed by embossed irregular shapes.