Determination of Melamine Content in Milk Powder Based on Neural Network Algorithm and Terahertz Spectrum Detection

$Refractive index spectra of pure milk powder and pure melamine, and refractive index spectra of mixed samples. (a) Refractive index spectra of pure milk powder and pure melamine; (b) refractive index spectra of mixed samples$

Fig. 4. Refractive index spectra of pure milk powder and pure melamine, and refractive index spectra of mixed samples. (a) Refractive index spectra of pure milk powder and pure melamine; (b) refractive index spectra of mixed samples

Download full size

Fig. 5. Optimized results of number of input vectors and number of hidden layers for BPNN

Download full size

Fig. 6. Predicted accuracy comparison of GRNN model with different numbers of input vectors

Download full size

Fig. 7. Predicted accuracy comparison of GRNN model with different spread values

Download full size

Fig. 8. Predicted results of BPNN and GRNN models for mass concentration of melamine

Download full size

Table 1. True value distribution of modeling and prediction datasets of melamine doped milk powder with different mass concentrations
View table
Table 1. True value distribution of modeling and prediction datasets of melamine doped milk powder with different mass concentrations
Dataset Number ofsamples Mass concentration /%
Minimum Maximum Mean Standard deviation
Total 176 0.043 19.988 9.317 6.261
Modeling 132 0.043 19.988 9.397 6.311
Prediction 44 0.043 19.988 9.069 6.169

Table 2. Results of correction processing for THz absorbance of melamine doped milk powder

View table

Table 2. Results of correction processing for THz absorbance of melamine doped milk powder

Model	Preprocessing method	PC	Calibration		Prediction
Model	Preprocessing method	PC	r_c	RMSEC	r_p	RMSEP
PLS	None	7	0.9881	0.0098	0.9752	0.0127
	Savitzky-Golay	7	0.9889	0.0095	0.9762	0.0124
	MSC	2	0.9901	0.0089	0.9814	0.0112
	Baseline correction	4	0.9797	0.0128	0.9593	0.0165
	Normalization	3	0.9897	0.0091	0.9813	0.0112
	MSC+Normalization	3	0.9912	0.0085	0.9842	0.0103

Tools

Get Citation

Copy Citation Text

Jun Hu, Zhen Xu, Maopeng Li, Yande Liu. Determination of Melamine Content in Milk Powder Based on Neural Network Algorithm and Terahertz Spectrum Detection[J]. Laser & Optoelectronics Progress, 2020, 57(22): 223001

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Spectroscopy

Received: Mar. 13, 2020

Accepted: Apr. 28, 2020

Published Online: Nov. 9, 2020

The Author Email: Yande Liu (jxliuyd@163.com)

DOI:10.3788/LOP57.223001

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology

Table 1. True value distribution of modeling and prediction datasets of melamine doped milk powder with different mass concentrations

Table 1. True value distribution of modeling and prediction datasets of melamine doped milk powder with different mass concentrations

Table 2. Results of correction processing for THz absorbance of melamine doped milk powder

Table 2. Results of correction processing for THz absorbance of melamine doped milk powder