Optimal pretreatment determination of kiwifruit drying via online monitoring

Integrating Image Analysis and Machine Learning for Moisture Prediction and Appearance Quality Evaluation: A Case Study of Kiwifruit Drying Pretreatment

The appearance of dried fruit clearly influences the consumer's perception of the quality of the product but is a subtle and nuanced characteristic that is difficult to quantitatively measure, especially online. This paper describes a method that combines several simple strategies to assess a suitable surrogate for the elusive quality using imaging, combined with multivariate statistics and machine learning. With such a convenient tool, this study also shows how one can vary the pretreatments and drying conditions to optimize the resultant product quality. Specifically, an image batch processing method was developed to extract color (hue, saturation, and value) and morphological (area, perimeter, and compactness) features. The accuracy of this method was verified using data from a case study experiment on the pretreatment of hot-air-dried kiwifruit slices. Based on the extracted image features, partial least squares and random forest models were developed to satisfactorily predict the moisture ratio (MR) during drying process. The MR of kiwifruit slices during drying could be accurately predicted from changes in appearance without using any weighing device. This study also explored determining the optimal drying strategy based on appearance quality using principal component analysis. Optimal drying was achieved at 60 °C with 4 mm thick slices under ultrasonic pretreatment. For the 70 °C, 6 mm sample groups, citric acid showed decent performance.

Three-dimensional morphological changes of potato slices during the drying process

Hot air drying is a common method for drying potato slices. In this paper, the three-dimensional (3D) morphological changes incurred during hot air drying of potato slices were investigated. The effect of drying on the thickness and diameter of potato slices was of special interest. The results showed that the potato slices underwent stages of regular warping, collapse, and curling during the drying process. After classifying the numerical variation in characteristics into the standard deviation in mean height (SDMH) and the rate of change in mean height (RCMH) of potato slices, the RCMH was selected to describe the 3D morphological changes in the potato drying process. A critical point and a termination point for RCMH of potato slices in the drying process were observed. Samples varied widely after the critical point was reached. A logarithmic function model was used to assess differences in the RCMH at the critical point and the termination point. The R-squared (R2) value of 0.9 suggested a strong correlation between the parameters of the experiment and changes in slice thickness and diameter. The model proposed in this paper could accurately characterize the late-stage changes in potato slice qualities during hot air drying of potato slices.

•

Drying potato slices underwent stages of regular warping, collapse and curling.

•

A correlation between the fitted results and the changes in thickness and diameter.

•

A height change model in the later stage of hot air drying of potato slices.

Thermodynamic and Quality Performance Studies for Drying Kiwi in Hybrid Hot Air-Infrared Drying with Ultrasound Pretreatment

The present study examined the effect of ultrasonic pretreatment at three time the levels of 10, 20 and 30 min on some thermodynamic (effective moisture diffusivity coefficient(Deff), drying time, specific energy consumption (SEC), energy efficiency, drying efficiency, and thermal efficiency) and physical (color and shrinkage) properties of kiwifruit under hybrid hot air-infrared(HAI) dryer at different temperatures (50, 60 and 70 °C) and different thicknesses (4, 6 and 8 mm). A total of 11 mathematical models were applied to represent the moisture ratio (MR) during the drying of kiwifruit. The fitting of MR mathematical models to experimental data demonstrated that the logistic model can satisfactorily describe the MR curve of dried kiwifruit with a correlation coefficient (R2) of 0.9997, root mean square error (RMSE) of 0.0177 and chi-square (χ2) of 0.0007. The observed Deff of dried samples ranged from 3.09 × 10−10 to 2.26 × 10−9 m2/s. The lowest SEC, color changes and shrinkage were obtained as 36.57 kWh/kg, 13.29 and 25.25%, respectively. The highest drying efficiency, energy efficiency, and thermal efficiency were determined as 11.09%, 7.69% and 10.58%, respectively. The results revealed that increasing the temperature and ultrasonic pretreatment time and decreasing the sample thickness led to a significant increase (p < 0.05) in drying efficiency, thermal efficiency, and energy efficiency, while drying time, SEC and shrinkage significantly decreased (p < 0.05).

Recent developments of artificial intelligence in drying of fresh food: A review

Intellectualization is an important direction of drying development and artificial intelligence (AI) technologies have been widely used to solve problems of nonlinear function approximation, pattern detection, data interpretation, optimization, simulation, diagnosis, control, data sorting, clustering, and noise reduction in different food drying technologies due to the advantages of self-learning ability, adaptive ability, strong fault tolerance and high degree robustness to map the nonlinear structures of arbitrarily complex and dynamic phenomena. This article presents a comprehensive review on intelligent drying technologies and their applications. The paper starts with the introduction of basic theoretical knowledge of ANN, fuzzy logic and expert system. Then, we summarize the AI application of modeling, predicting, and optimization of heat and mass transfer, thermodynamic performance parameters, and quality indicators as well as physiochemical properties of dried products in artificial biomimetic technology (electronic nose, computer vision) and different conventional drying technologies. Furthermore, opportunities and limitations of AI technique in drying are also outlined to provide more ideas for researchers in this area.