An LED-based spectrally tuneable light source for visible and near-infrared spectroscopy analysis: A case study for sugar content estimation of citrus

Abstract

Light source plays an important role in visible and near-infrared (Vis–NIR) spectroscopy detection systems. Traditionally, halogen tungsten lamps are used in most studies and applications. However, halogen tungsten lamps have two main shortcomings: generation of large amount of heat and limited operational lifetime. In this study, a light emitting diode (LED)-based spectrally tuneable light source in a broad Vis–NIR wavelength range (400–1070 nm) using an integrating sphere was designed and developed, as well as the control circuit to control the LEDs conveniently and easily for obtaining tuneable spectra. The Vis–NIR spectroscopy detection system equipped with this LED-based spectrally tuneable light source was applied for estimating sugar content of citrus. Based on stepwise multiple linear regression (SMLR) modelling in the spectral region of 500–900 nm, the calibration results using the LED light source (correlation coefficient ( r c ) = 0.78, root mean square error of calibration (RMSEC) = 0.74 Brix%) were better than those using the halogen tungsten lamp ( r c = 0.74, RMSEC = 0.80 Brix%), while the prediction result was a bit worse (root mean square error of prediction (RMSEP) = 1.09 and 0.95 Brix%, respectively). Generally, the performances of the two kinds of light sources for sugar content estimation of citrus samples were similar, but the energy consumption and heat generation of the LED light source were much lower. Besides, the LED light source could warm up to a stable status much faster than the halogen tungsten lamp. For further research, the method proposed in this study can be applied to online sugar content estimation of citrus and be expanded to other applications.