Neural network-based Raman spectral recognition model for milk powder and wheat flour

Abstract

The problem of counterfeit milk powder has occurred in recent years, and one of the standard techniques is to adulterate milk powder with wheat flour to reduce the cost. Since the morphology and colour of wheat flour are similar to that of milk powder, it is not easy to distinguish it from the naked eye, so a rapid method for detecting wheat flour adulteration in milk powder is urgently needed. This study used Raman spectral analysis as a novel and efficient screening technique. With the advantages of high sensitivity, non-destructive detection, low cost, no contamination, and online analysis, this method can play an essential role in rapid food detection and production control. By processing and analyzing the spectral data, a neural network model for identifying milk powder and wheat flour based on Raman spectroscopy has been developed in this study, and the model's performance has been evaluated. The results show that the model can quickly and accurately identify the proportion of wheat flour in milk powder to determine whether milk powder is adulterated or not. The results of this study are of great significance in ensuring the safety of infant milk powder. In the future, the method can be further optimized, for example, to improve detection speed and accuracy and to provide a more reliable quality control method for the milk powder industry.