This paper presents a detailed analysis of the relation between physical characteristics and defects of green coffee beans and the sensory profile that influence the sensory notes of fragrance, aroma, flavor, and aftertaste of coffee. Machine learning models were used to identify the variables of importance and identify the ways in which these variables affect the sensory note of coffee, to determine which algorithm and its hyperparameters have greater precision in determining the sensory values of coffee such as floral, fruity, herbal, nutty, caramel, chocolate, spicy, resinous, pyrolytic, earthy, fermented, and phenolic. The result indicates the relationship and importance that exist between the physical variables, defects, and size of the green coffee bean, with respect to their respective sensory notes. The data of the proposed system demonstrate that by combining the scores of several experts, a precision can be achieved analogously to that obtained by cupping experts; therefore, the possibility of errors induced by human concerns such as fatigue or subjectivity is reduced.

A sugar solution measurement system was developed based on the dielectric properties of the sucrose molecule. An ac conductivity and tan δ study as a function of the frequency was performed to find the suitable frequency range for the measuring system. The results indicate that it is possible to obtain a better response of the sensor using the frequencies as the maxima peak in tan δ appears. Developed setup for sucrose solution was appropriate to measure in a 0.15 to 1 g/mL range with an experimental error of about 3%. The proposed system improves the measurement time over some other methods.

Currently, emerging technologies such as digital twins, through the application of frontier techniques, have achieved physics-based simulations that reduce time and costs. Hence, its application is of the utmost importance in the industry, mainly in the sugar drying process of sugar mills for an updated version of the process. Sugar mills lack process control, leading to unexpected issues. Sugar mills with poor process control cause operational problems. This article presents significant innovation in the field of industrial process optimisation through the integration of digital twins with the k-ε standard model in computational fluid dynamics (CFD). The primary objective of this publication is to predict the ideal conditions of a centrifugal sugar dryer using CFD through the k-ε standard model to analyse the aerodynamic behaviour of the ambient air by applying heat through heat exchangers to obtain a suitable mass flow. The mathematical model was carried out under an energy balance to the thermodynamic system to study the behaviour through a simulation in MATLAB R2017 and an air-fluid simulation of drying with software CFD 2015. The results proved that the model of the thermal system and frontier conditions, when applying CFD, carried our simulation and remained stable. The ideal operating conditions of the centrifugal sugar dryer can be predicted effectively, with an energy saving of 4.25%.

Quality control in green coffee bean production is critical for food safety and economic sustainability. A persistent gap in existing automated inspection systems is their inability to capture both sides of each bean, which leads to systematic under-detection of surface defects. This work presents three contributions: (i) a novel mechatronic apparatus that mechanically guarantees dual-sided imaging of every bean, (ii) a public 12-class dataset of green coffee bean defects, and (iii) an embedded, real-time inspection pipeline validated on low-cost hardware. The apparatus sequentially presents each bean, from a standard 350 g sample, to two 16-megapixel cameras under controlled LED illumination. A dataset of 9600 images spanning 12 classes (11 defects and 1 normal) was generated from expert-classified samples and enriched through data augmentation. Four convolutional neural network (CNN) architectures, VGG-16, VGG-19, ResNet-50 and YOLOv8, were trained and benchmarked using precision, recall, F1-score and mean average precision. YOLOv8 achieved the best overall performance, with a precision of 97.4%, a recall of 99.6%, an F1-score of 0.930 and a mean average precision of 96.5%, outperforming VGG-16 (accuracy 86.07%), VGG-19 (accuracy 67.03%) and ResNet-50 (accuracy 87.76%). Dual-sided acquisition raised mean per-class detection accuracy from 0.727 to 0.908, a relative gain of 25.7% over an equivalent single-sided configuration. Deployed in real-time “track” mode on a Raspberry Pi 4, the system simultaneously classifies defects and counts beans by category, processing a 350 g sample in approximately 38 min. Combining mechanical innovation with lightweight deep learning enables practical, scalable, and cost-effective quality control for laboratories specialized in coffee analysis.