Investigation of mechanical, thermal, and acoustic performance of insulation materials containing microwave and ultrasound pretreated coffee wastes and estimation of thermal parameters using artificial neural network

As a result of increasing coffee consumption in the world, the amount of coffee waste, which is an important environmental problem, is increasing. Due to their complex organic properties, they should not be discharged to landfills. At the same time, these wastes with a porous and cellulosic structure, have high acoustic and heat insulation performances in the building material they are used. In this study, commercial coffee wastes were evaluated without pre-treatment (CW) and with microwave (MCW) and ultrasound (UCW) pre-treatment in insulation plaster containing boron. First, the morphological, thermal, and chemical properties of coffee wastes were determined by SEM, TGA, and FTIR analyzes. CW, MCW, and UCW wastes were replaced with insulation plaster at rates of 10%, 20%, and 30%. The physical, mechanical, thermal, and acoustic properties of insulation plasters produced from coffee waste were determined by the analysis methods given in Turkish Standards. According to the results, insulation plasters obtained from pre-treated wastes were more efficient in terms of mechanical and thermal properties. In terms of thermal and acoustic insulation, UCW30 insulation plasters showed the best performance. Thermal conductivity values were estimated by entering dosage, density, water absorption, bond strength, compressive strength, and moisture values as input dataset to artificial neural network (ANN). The developed ANN model and the experimentally obtained data were compared and it was observed that the results were in harmony. As a result, with this study, a new generation green insulation material was produced by recycling coffee wastes. In this way, a different solution has been found for an important environmental problem.