Experiments detailing the spray drying of fruit and vegetable juices are necessary at the experimental scale in order to determine the optimum drying conditions and to select the most appropriate carriers and solution formulations for drying on the industrial scale. In this study, the spray-drying process of beetroot juice concentrate on a maltodextrin carrier was analyzed at different dryer scales: mini-laboratory (ML), semi-technical (ST), small industrial (SI), and large industrial (LI). Selected physicochemical properties of the beetroot powders that were obtained (size and microstructure of the powder particles, loose and tapped bulk density, powder flowability, moisture, water activity, violet betalain, and polyphenol content) and their drying efficiencies were determined. Spray drying with the same process parameters but at a larger scale makes it possible to obtain beetroot powders with a larger particle size, better flowability, a color that is more shifted towards red and blue, and a higher retention of violet betalain pigments and polyphenols. As the size of the spray dryer increases, the efficiency of the process expressed in powder yield also increases. To obtain a drying efficiency >90% on an industrial scale, process conditions should be selected to obtain an efficiency of a min. of 50% at the laboratory scale or 80% at the semi-technical scale. Designing the industrial process for spray dryers with a centrifugal atomization system is definitely more effective at the semi-technical scale with the same atomization system than it is at laboratory scale with a two-fluid nozzle.

The aim of the study was to develop a neural model enabling classification of fruit spray dried powders, on the basis of graphic data acquired from a bitmap received in the process of spray drying. The neural model was developed with multi-layer perceptron topology. Input variables were expressed in 46 image descriptors based on RGB, YCbCr, HSV (B) and HSL models. Sensitivity analysis of input variables and principal component analysis determined the significance level of each attribute. The optimal model with the lowest error value root mean square, at the level of 0.04 contained 46 neurons in the input layer, 11 neurons in the hidden layer, 10 neurons in the output layer. The results allowed to show that dyeing force (color features) had influence on effective differentiation of the research material consisting of spray-dried powders of rhubarb juice with various dried juice content levels: 30, 40 and 50% as well as high (“H”) and low (“L”) level of saccharification a chosen carrier (potato maltodextrin).

Tenderization based on papain and microwave vacuum drying and puffing (MVDP) as well as adequate processing conditions enabled expansion of slices of the raw meat tissue. The main aim of the study was to use the response surface method and find the conditions of puffing that could maximize the expansion of meat during MVDP. The bound was set on the expansion: the most expanded puffings should be of good quality, including a desirable porous structure. The best combination of values of the MVDP process conditions (e.g., the initial moisture content in meat slices, microwave energy, and the vacuum absolute pressure) was found during experiments using the central composite design. The volume of slices puffed under these conditions was 1.60–1.78 times greater than the volume of slices before MVDP, and the sensory quality index remained acceptable. The research showed that pretreatment reduced the hardness of sample by over 25% and increased its crispiness, which was confirmed in cryo-scanning electron microscopy images.

The study concentrates on researching possibilities of using computer image analysis and neural modeling in order to assess selected quality discriminants of spray-dried chokeberry powder. The aim of the paper is the quality identification of chokeberry powders on account of their highest dying power, the highest bioactivity, as well as technologically satisfying looseness of the powder. The article presents neural models with vision techniques backed up by devices such as digital cameras, as well as an electron microscope. The reduction in size of input variables with PCA has an influence on improving the processes of learning data sets, thus increasing the effectiveness of identifying chokeberry fruit powders included in digital pictures, which is shown in the results of the conducted research. The effectiveness of image recognition is presented by classifying abilities, as well as low Root Mean Square Error (RMSE), for which the best results are achieved with a typology of network type Multi-Layer Perceptron (MLP). The selected networks type MLP are characterized by the highest degree of classification at 0.99 and RMSE at 0.11 at most at the same time.