International Scientific Journals
of Scientific Technical Union of Mechanical Engineering "Industry 4.0"

This paper presents the development and experimental validation of a method for automatic identification of apple varieties based on the analysis of visual features extracted from digital images. The proposed approach uses classical computer vision techniques without applying neural networks or deep learning, which makes the system interpretable, lightweight, and reproducible for laboratory and industrial use.
The algorithm includes the stages of image acquisition, preprocessing, object segmentation, feature extraction, and classification using statistical models such as Support Vector Machines (SVM), k-Nearest Neighbors (k-NN), and logistic regression. The extracted features include geometric parameters (area, perimeter, circularity, eccentricity, axis ratio) and color characteristics (mean HSV values, red color percentage, hue distribution).
Experimental validation was performed on a dataset containing five apple varieties: Sinap Almaty, Fuji, Brebourne, Gold Delicious, and Hybrid. The system achieved an average classification accuracy of 90%, with the highest results for varieties with distinctive morphological or color characteristics. Comparative analysis with manual sorting demonstrated significant advantages in terms of processing speed, objectivity, and scalability.
The proposed method can be implemented on compact single-board computers, making it suitable for mobile quality control stations and automated sorting lines. Future work includes the integration of weight and texture parameters and the expansion of the variety database for broader applicability.

Mechanized carrot growing technologies involve the use of various operations, in particular, digging by pulling the root and removing it inside the combine, as well as by pre-cutting the green mass of the root and subsequent cleaning of the heads from the remains of the root before digging. Due to the fact that there are high requirements for cleaning carrot root heads from residues, the development of new, more improved cleaners is an important and urgent task. The solution to this problem was implemented by developing a new design of the purifier, which is able to perform the specified cleaning process with high quality. The cleaner consists of two shafts that cover each row of carrots on both sides and rotate in opposite directions. Cleaning shafts are located in a horizontal plane at an angle to each other. As cleaning elements, pairs of rubber blades are used, which are installed on hubs on each shaft, which are fixed on the shafts with the appropriate step. The rubber blades are mounted on hubs hinged and the ends of the blades of one shaft are located between the pairs of blades of the second shaft. By simultaneously hitting the heads of the carrot root crops with flexible blades from both sides, the process of cleaning them from residues is carried out. In order to study the process of cleaning carrot heads from the remains of ghee on the root, an experimental installation was made and a program of experimental studies of this technological process was developed.

This article examines the use of computer vision and deep learning to automatically determine key quality indicators of apples, enhancing product quality. It describes a digital method for measuring apple size, ripeness, and variety classification using an automated optoelectronic system, achieving an accuracy of at least 86%. Advantages, limitations, and potential productivity benefits for Kazakhstan’s apple production are discussed. An algorithm developed with OpenCV in Python analyzes apple images to determine diameter, height, surface area, red color proportion, and external defects. Tested on “Sinap Almaty” apples, the method measures linear dimensions, crosssectional area, and redness percentage.

In this paper is presented Synthesis of a for-bar linkage mechanism of the lift car extrusion. In this mechanism are introduced even higher kinematic pairs. The movement of the mechanism is repeated periodically and it is sufficient to do its kinematic study for an angle 75 [deg]. The description of the mechanism movement can be performed in the grafoanalytical or analytical path by centers of speed moments, which belong to a narrow link and a loop of the center mechanism, and the instant centers belonging to the two related movements. In the kinematic analysis of the forward mechanisms are used graphical methods. These are simple and universal, making it possible to determine the positions, velocity and acceleration of the links of any structure. With the application of contemporary calculating technology, the graphical methods in the analysis of mechanisms take the right place. The velocity of each link of the mechanism linkage that performs the movement of the plane can be shown as very geometric of the instant center speed and the speed of rotation around the center of the instantaneous. The analysis will be performed by Math Cad software, while kinetostatic analysis will be carried out using Contour Method, comparing results of two different software‘s Math CAD and Working Model. The simulation parameters will be computed for all points of the contours of mechanism. For the simulations results we have use MathCad and Working Model software’s.

This article shows the method and results of experimental RESEARCHES of machines for egg sorting into categories based on size and form using a vision system. The principal difference of the considered machine for automatic sorting of eggs into categories from existing sorting machines is the division of eggs into categories by size and the separation of substandard eggs in the flow. Experimental verification showed that the machine provides the division of eggs in size into four categories and the separation of eggs of irregular shapes and sizes in the flow. The accuracy of separation of eggs into categories depending on the performance. With a productivity of up to two eggs per second, the accuracy of egg separation averages 94.8%., With a productivity of three eggs per second was 87.4%.