Statistical Study and Modeling of the Effect of Phosphoric Acid Impurities on the Physical Quality of Ammonium Phosphate Determined from the Production Data Using Artificial Neural Network
Keywords:Ammonium phosphates fertilizers, Impurities, Granulation yield, Principal Components Analysis (PCA), Artificial Neural Network (ANN).
The monitoring of the physical properties of fertilizers presents a lot of interest at different levels. All the problems related to the behavior of the granules (segregation, spreading, granulation, hardness…) need a better characterization of the fertilizers in order to understand and/or predict them.
The scientific community is led to develop a variety of modeling approaches for, on the one hand, the understanding of the dynamics of impurities originating from phosphoric acid during the manufacture of fertilizers, and on the other hand, the evaluation of the effectiveness of measurements and data monitoring from production and the fluctuations in the physical quality of the fertilizers that follow.
In this investigation of the influence of elements such as Fe, Al, Mg, F-, Si, Na, K and Cl on fertilizer quality, we gathered and followed-up data from production lines of Ammonium phosphate fertilizers for several months. The aim of the current work is the statistical study and modeling of the phosphoric acid impurities effect on the physical quality of fertilizers such as granulation yield, grain size, and the average diameter of granules D50, based on the analysis of data from different production lines by applying the Artificial Neural Network (ANN) approach. In addition models, were constructed using Multiple Linear Regression (MLR) and Principal Components Analysis (PCA).
How to Cite
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.