| Abstrakt: |
Natural fibers are currently highly valued due to the need for environmentally friendly alternatives. With the advancement of technology, natural fibers have substituted steel, polypropylene, carbon, and glass fibers in some applications. The potential for employing Washingtonia mesh waste (WMW) as a reinforcement for sustainable and lightweight building materials is investigated for the first time as per the authors' knowledge. For this purpose, the three-variable process, which included WMW content from 1 to 3%, was treated with an alkaline (NaOH) concentration from 1 to 5% for a time period of 4 to 24 h, with artificial neural network (ANN) techniques and response surface methodology (RSM) being used for optimization purposes. Consequently, the aim of this study is to estimate and optimize the factors that influence the properties of WMW-reinforced bio-mortars. The results showed that the amount of WMWs, the percentage of NaOH, and the duration of immersion have an impact on the mechanical and physical properties. Furthermore, it was shown that replacing 1% cement with its equivalent of WMWs that had been immersed in 2.5% NaOH for 4 h resulted in a good combination that offers improved flexural and compressive strength. Moreover, the ANN and RSM models correlate strongly with the experimental data. It is also noticed that the model accuracy using artificial neural networks is higher. The mathematical models developed to estimate the attributes of the WMW-reinforced bio-mortars were shown to be very pertinent, having better accuracy with fewer than 7% errors by performing MSE, RMSE, and MAPE calculations. [ABSTRACT FROM AUTHOR] |
Full text from SpringerLink