ENERGY OPTIMIZATION IN AN INDUSTRIAL FOOD DRYING PROCESS USING HYPERSPECTRAL IMAGING (HSI) FOR THE ASSESSMENT OF REAL TIME DRING CONDITIONS

Abstract

Real time data acquisition has become important in food drying which is a highly energy intensive process and needs to be optimized. The use of Hyperspectral imaging (HSI) is getting value due to its short measuring time, chemical-free technique, and can be applied to estimate more than one attribute at the same time. All these factors reduce energy requirements and costs of process. HSI was utilized for the determination of moisture content of potato slices with three thicknesses (5mm, 7mm, 9mm) at three drying temperatures (50oC, 60oC, 70oC) during convective drying in a laboratory hot air dryer. The Page, thin-layer drying model was found suitable to describe the drying process with a fitting accuracy of R2 (0.96-0.99) and lowest reduced Chi-square (0.0002460.000906), RMSE (0.01453-0.02685), and relative percentage error (1.49%-5.07%) under the used drying conditions. Spectral data was analyzed using the partial least squares regression (PLSR) analysis, a multivariate calibration technique, alongside MCUVE-PLS and CARS-PLS. The feasibility of both moisture content and CIELAB co-ordinate prediction with a reduced wavelength set from the VNIR region (400-1010nm) was investigated with these three models. The PLSR model (R2 = 0.93-0.98, RMSE = 0.16-0.36 and the lowest number of optimal wavelengths = 6, for all drying conditions) was found suitable to implement for the moisture visualization procedure. The current study showed that hyperspectral imaging was a useful tool for non-destructively measurement and visualization of the moisture content and chromaticity during the drying process and let the user to know the process end time, thus saving energy consumption and retention of product quality as well.