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

The article presents a comprehensive scientific and engineering development — an automated installation and an algorithmic platform for assessing the quality characteristics of varietal seed potato tubers. The development is aimed at solving key agroengineering problems related to increasing the accuracy, standardization and productivity of tuber analysis processes in seed production.
The methodological basis of the study is a combination of tensometric measurement of tuber mass with computer vision algorithms based on the OpenCV library in the Python programming environment. The algorithm allows for automatic and highly accurate determination of mass, linear dimensions (length, width, height), area and perimeter of the tuber, as well as calculation of derived indicators such as shape index and shape coefficient, which are important for sorting and determining varietal affiliation.
To verify the developed system, experimental studies were conducted on an automated setup using control measurements performed by traditional methods (calipers, electronic scales). The study included both mini-tubers and standard seed tubers of the Alliance potato variety. Statistical analysis of the data showed a high degree of consistency between digital and manual measurements, and also revealed a significant advantage of the automated method in terms of productivity: the analysis time for one tuber was reduced by an average of seven times.
Particular attention is paid to the compliance of the proposed method with national and international standards, in particular, the requirements of GOST 33996–2016, which guarantees the possibility of its practical application in real production conditions. The authors substantiate that the introduction of digital technologies in the process of sorting seed potatoes allows minimizing subjective errors, reducing labor costs, increasing the speed of data processing and standardizing the quality assessment process.
The scientific novelty of the work lies in the integration of algorithmic data processing with physical measurements on one platform, which allows for the implementation of a comprehensive agro-engineering system for solving problems of selection, seed production and automated sorting. The developed installation can be adapted and scaled for use with other fruit and vegetable crops, which opens up opportunities for further research and expansion of the range of applications.
The results of the study are relevant for agro-industrial enterprises, research institutes, seed farms and agricultural machinery manufacturers. The proposed system can be integrated into existing sorting and processing lines, ensuring the transition to precision agriculture and industry 4.0 technologies in the agricultural sector..

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.

In order to address multiple UN Sustainable Development Goals, we aim to revolutionize iceberg lettuce harvesting with intelligent robots. Our team, comprised of agricultural producers and engineers, has utilized TRIZ methodology, brainstorming, and other techniques to develop an agricultural technology solution: an Integrated Complex that automates harvesting and loading of produce onto transportation vehicles. Our design leverages state-of-the-art deep computer vision – a form of AI that analyzes camera images – to precisely locate mature lettuce heads. The robot identifies optimal grasping points for harvesting and carefully places the heads in a designated transport area. With deep learning at its core, our robots will optimize yield, reduce waste and costs, ushering in a new era of intelligent agriculture.

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.

Nowadays, many structures should be inspected, analyzed, and repaired. This is a complex and expensive process that also includes predictive analytics to prevent possible construction failures.
One of the most used predictive analytics applications involves extracting necessary metadata from images and videos to evaluate the condition of real-world systems and recommend measures to sustain these systems. Image analysis is not a new concept – many solutions have been used for several decades.
The current paper mainly focuses on OpenAI-based capabilities to implement Image Analysis and Cognitive Digital Twins and proposes faster, cheaper implementation and more adaptive approaches to offering predictive analysis for constructions.
ChatGPT (Chat Generative Pre-Trained Transformer) is one of the trending technologies in modern Artificial Intelligence (AI), and experts in this area expect to have a very high impact on the industry shortly.
One of the latest versions – GPT-4 Turbo with Vision, developed by OpenAI, is a significant multimodal model (LMM) capable of interpreting images and providing text-based answers to queries regarding those images. It combines capabilities in natural language processing and visual comprehension.
The proposed approach considers using OpenAI LLM and Digital Twins for three different aspects of predictive analysis for Construction: image analysis, case decomposition, and creation of self-adaptive models to find possible trends to compromise structures and offer preventive actions. This research compares traditional methods for inspection and repair of Construction, including the time required for predictive analysis, the correctness of the proposed actions, and the cost of the methodology.

This article describes the actual trends and applications in industry where artificial intelligence models are deployed. This paper provides a more detailed description of the principles and methods of deploying models in the field of quality evaluation in industry and also in the areas of predictive maintenance and data analytics in the manufacturing process. Computer vision is increasingly coming to the fore due to its wide range of applications – object detection, categorisation of objects, reading QR codes and others. The area of predictive maintenance is important in terms of reducing downtime and saving costs for machine components. Models designed for data analytics, in turn, help to optimize the parameters of the production process so that the desired parameter is maximized or its optimal value is achieved.