Online detection of soluble solids content and size of crystal pear based on LEDs light source-detector

Online detection method of soluble solids content (SSC) and size of crystal pear using LEDs light source-detector based on near infrared spectroscopy was studied. LEDs light source-detector with wavelengths of 850 nm, 880 nm and 940 nm were used to irradiate crystal pear in this experiment. The crystal pear was homogeneously arranged on conveyor line at the speed of 5 pears per second. Spectra was measured in near infrared diffuse reflectance mode. Three pre-processing methods including average smoothing, first and second derivatives were applied to improve the predictive ability of the models. Partial least squares (PLS) and least squares support vector machine (LS-SVM) were used to develop calibration models. The prediction set was used to evaluate the predictive ability of the models. The results showed that the best model was obtained by PLS with the pre-processing method of average smoothing. The correlation coefficient (R) and root mean square error of prediction (RMSEP) was (0.86, 0.58%) and (0.90, 1.93 mm) for soluble solids content and size, respectively. The results showed that online detection of soluble solids content and size of crystal pear based on near infrared diffuse reflectance spectroscopy combined with LEDs light source-detector was feasible.