Near-infrared spectroscopic sensing system for online monitoring of milk quality during milking

Abstract

There has been a need in recent years for a method that will enable dairy farmers to monitor milk quality of individual cow during milking. We constructed a near-infrared (NIR) spectroscopic sensing system for online monitoring of milk quality on an experimental basis. This system enables NIR spectra of unhomogenized milk to be obtained during milking over a wavelength range of 600–1050 nm. We developed calibration models for predicting three major milk constituents (fat, protein and lactose), somatic cell count (SCC) and milk urea nitrogen (MUN) of unhomogenized milk, and we validated the precision and accuracy of the models. The coefficient of determination (r 2) and standard error of prediction (SEP) of the validation set were obtained: for fat, r 2 = 0.95, SEP = 0.42%; for protein, r 2 = 0.91, SEP = 0.09%; for lactose, r 2 = 0.94, SEP = 0.05%; for SCC, r 2 = 0.82, SEP = 0.27 log SCC/mL; and for MUN, r 2 = 0.90, SEP = 1.33 mg/dL, respectively. These results indicated that the NIR spectroscopic sensing system developed in this study could be used to monitor milk quality in real-time during milking. The system can provide dairy farmers with information on milk quality and physiological condition of each cow and therefore give them feedback control for producing milk of high quality and for optimizing dairy farm management.