Abstract
The increase in the silos temperature and intergranular relative humidity can alter the equilibrium moisture content of the grains mass causing losses. Thus, the objective was to evaluate the temporal monitoring of temperature, relative humidity, and intergranular carbon dioxide for the prediction of dry matter loss in wheat grains stored in vertical silos, using a mathematical model and machine learning algorithms. Under these conditions, wheat grains had a slight increase in metabolic activity, causing a dry matter loss of 0.035–0.041%. The intergranular temperature, relative humidity, and carbon dioxide results were similar to the measurements on the surface of the grain mass. It was concluded that the monitoring of temperature, relative humidity, and the concentration of carbon dioxide in the intergranular air indirectly and early determined the changes in the quality of wheat grains during storage. Although the metabolic activity of wheat grains was low, as the lots remained in hygroscopic equilibrium with moisture contents close to 12% (w.b.), the temporal detection characterized the loss of dry matter and the reduction of grain weight stored. Finally, the Artificial Neural Networks and Multiple Linear Regression model satisfactorily predicted the dry matter loss of stored wheat grain mass.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have