Potassium di-hydrogen phosphate identification based on wide energy X-ray absorption spectrum and an artificial neural network

Abstract

In order to accurately distinguish potassium di-hydrogen phosphate (KH2PO4) from common counterfeit products (NH4H2PO4, KCl, Na2SO4, MgSO4 and white sugar), a wide X-ray absorption spectrum detection system based on photon count detector (PCD) was used to scan six samples leading to wide X-ray absorption spectrum (XAS). Principal component analysis (PCA) was used to extract the main features of XAS (normalized) and an artificial neural network (ANN) was used for automatic identification. The experimental results showed that the absorption of X-rays in the energy range of 12 keV to 40 keV was different among samples. The overall accuracy was 86.67%. The precision, recall and F1-score of potassium di-hydrogen phosphate all reached 100%. Therefore, it is feasible to use the difference of XAS between potassium di-hydrogen phosphate and other counterfeit products to realize product identification, and PCA-ANN algorithm can achieve an ideal automatic recognition result. Wide XAS combined with PCA-ANN automatic classification algorithm provides a new idea for the identification of the potassium di-hydrogen phosphate authenticity.