Pesticide Residues Detection by Fluorescence Spectral Analysis Based on BP Neural Network

At present, it is a difficulty to achieve rapid and accurate detection to pesticide residues. In the paper, an overlapped spectrum in fluorescence spectroscopy measurements of acetamiprid residues was separated using artificial neural networks. By means of artificial neural network principle and back-propagation training algorithm, acetamiprid concentration were determined in mixed component of residues and filter paper with overlapped fluorescence spectrum. In the range of 340-400 nm, the fluorescence intensities corresponding to 20 wavelengths were used as character parameters, while the neural network was trained and tested. The mean recoveries of 40 mg/kg and 90 mg/kg acetamiprid were 102% and 97 % respectively. The RSDs of the results were 1.4% and 1.9%. A kind of model is given by detection method and results of this paper, the results have shown that the method to using BP network in fluorescence spectral analysis of acetamiprid residue has good performance such as shorter measuring time, faster training speed and higher accuracy than the other means. It provides an effective method for the detection of pesticide residues.