Authors: Sagdiyev T.A.,Maturazov I.S.,Isakov N.A.

Abstract. The article investigates the causes, consequences, and prevention strategies related to aircraft engine failures. It provides a comprehensive classification of common engine malfunctions, examining mechanical wear, thermal stress, and operational factors that contribute to failures. A detailed analysis of statistical data on engine failure rates highlights critical trends and risk factors affecting engine performance and reliability. Furthermore, the study explores various diagnostic techniques designed to detect potential failures at early stages, reducing the likelihood of unexpected breakdowns. Modern aviation heavily relies on advanced maintenance strategies and cutting-edge technological solutions to enhance engine durability and efficiency. The article discusses preventive maintenance approaches, including predictive analytics, condition-based monitoring, and real-time diagnostics, which play a crucial role in minimizing failures. Additionally, the role of artificial intelligence and machine learning in fault detection and predictive maintenance is examined as a promising direction for improving aircraft engine reliability. The findings indicate that most engine malfunctions stem from mechanical degradation, excessive thermal loads, and human errors in operation and maintenance. Implementing regular inspections, utilizing advanced diagnostic tools, and integrating modern engineering solutions can significantly improve engine safety and longevity. The study underscores the necessity of continuous monitoring, timely preventive actions, and the adoption of innovative maintenance practices to enhance aviation safety and operational efficiency.

Keywords: aviation engines, fault analysis, aircraft maintenance, turbine inspection, non-destructive testing, thermal stress, mechanical wear, predictive maintenance, engine diagnostics.

Authors: Nagimov A.,Beketova G.

Abstract. In modern applications, Unmanned Aerial Vehicles (UAVs) are widely used in various industries such as logistics, agriculture, environmental monitoring, and emergency services. However, their operation is highly dependent on weather conditions, including wind speed, temperature, precipitation, and atmospheric pressure. The unpredictability of meteorological factors poses significant risks to the safety and efficiency of UAV flights.
This study proposes an intelligent weather prediction system for UAV flight planning, based on big data and machine learning technologies. The research examines modern methods of meteorological data processing, incorporating satellite imagery, IoT sensors, and historical records. To predict key weather parameters, advanced deep learning algorithms such as Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNN) are utilized. The developed system achieves a forecast accuracy of up to 92%, reducing flight planning time by 30% and enhancing overall operational safety. The integration of machine learning into UAV weather prediction systems ensures adaptability and enables rapid responses to changing climatic conditions. The obtained results highlight the significance of artificial intelligence and big data analytics in aviation. Additionally, this work suggests future research directions, including the consideration of additional environmental factors such as air quality and solar radiation, as well as the potential integration with autonomous flight management systems.

Keywords: big data, machine learning, weather forecasting, UAVs, flight planning, flight safety, predictive modeling.

Authors: Akhmet A.,Gusmanov A.,Akramkhanov A.,Akimbay Sh.

Abstract. Unmanned Aerial Vehicles (UAVs) have emerged as pivotal tools for addressing region-specific challenges in Kazakhstan, a nation characterized by vast geographic diversity, extreme climatic conditions, and infrastructural demands in remote areas. However, deploying UAVs in Kazakhstan’s unique operational environments—marked by temperature extremes (-40°C to +45°C), unpredictable wind gusts (15–20 m/s in the Almaty and Kostanay regions), and frequent GPS signal degradation in mountainous terrain—poses significant technical and logistical challenges. Physical testing of UAV control algorithms under these conditions is not only prohibitively expensive but also constrained by safety regulations, environmental unpredictability, and the sheer scale of operational zones. To address these barriers, this article proposes the development of a Kazakhstan-centric UAV simulation platform, designed to emulate the country’s environmental and operational realities with high fidelity.
Built on the Robot Operating System (ROS Noetic) and Gazebo 11, the platform integrates three novel components: (1) physics-based UAV dynamics calibrated using field data from Kazakh agricultural and disaster-response UAV deployments, including mass (1.5 kg), inertia tensor, and rotor thrust profiles; (2) synthetic sensor models (LiDAR, IMU, RGB cameras) with noise profiles tailored to regional conditions, such as dust-induced LiDAR range errors (±0.15 m) and temperature-dependent IMU drift (0.2°/hour at +40°C); and (3) environmental disturbance models derived from meteorological datasets provided by Kazhydromet, Kazakhstan’s national weather agency, including steppe wind dynamics (gusts up to 18 m/s) and probabilistic GPS signal loss (25–35% dropout rates in the Tian Shan mountains).
The platform’s modular architecture supports testing of adaptive control algorithms, including Model Predictive Control (MPC) for wind disturbance rejection, swarm coordination strategies for search-and-rescue missions, and reinforcement learning (RL)-based fault tolerance systems, under scenarios mirroring real-world Kazakh challenges. Case studies demonstrate its efficacy: in simulated high-wind scenarios (18 m/s gusts), a decentralized swarm coordination algorithm achieved 88% mission success in maintaining formation over the Tian Shan mountains, while an adaptive PID controller reduced trajectory tracking errors by 35% under +40°C sensor drift conditions. Cross-validation with field data from a DJI Matrice 300 UAV deployed in the Turkestan region confirmed a 94% correlation between simulated and real-world trajectory RMSE (0.12 m vs. 0.15 m), with energy consumption predictions deviating by less than 3% from observed values.

Keywords: UAV simulation, Gazebo-ROS integration, adaptive control algorithms, Kazakhstan environmental modeling, swarm robotics, sensor emulation, digital twins.

Authors: Abdulayev Kh.I., Allakhverdiyeva S.

Abstract. This article examines the application of non-destructive testing (NDT) methods for assessing the structural integrity of aircraft components made from polymer-based composite materials. Composite materials are widely used in aviation due to their high strength-to-weight ratio, corrosion resistance, and durability. However, these materials are subject to various defects caused by manufacturing processes, operational loads, and environmental factors such as temperature and humidity fluctuations. Traditional NDT methods, including ultrasonic, radiographic, optical-visual, capillary, and thermal testing, each have specific advantages and limitations. Ultrasonic testing, for example, does not provide comprehensive volumetric analysis, while radiographic methods require complex safety measures. Optical-visual techniques fail to detect internal defects, and capillary methods suffer from low productivity. To address these challenges, the study proposes improvements to existing diagnostic techniques, the development of new automated models, and the optimization of parametric indicators. The research also explores an integrated “human-machine-environment” system to enhance the reliability of defect detection and assessment. Advancements in NDT technologies will not only increase the accuracy and efficiency of aircraft inspections but also improve safety, extend service life, and reduce maintenance costs. The findings of this study contribute to the development of modern diagnostic complexes that ensure higher operational reliability of aircraft structures.

Key words: composite materials, defect, non-destructive testing method, loaded parts, diagnostic models, dynamic correlation.

Authors: Abzhapbarova A.Zh.,Garmash O.V.

Abstract. The problem of flight delays is one of the key issues in the field of air transportation in Kazakhstan, having a significant impact on passenger service, airline operations and airport economics. Given the growth of passenger traffic and the active development of the aviation market, identifying and eliminating the causes of delays is becoming an important task to increase the competitiveness of the industry. The subject of the study is the causes of flight delays and their impact on the efficiency of airlines and airports in Kazakhstan. The study solved such tasks as analyzing the current state of flight punctuality in Kazakhstan, identifying the main factors influencing delays, assessing the economic and social consequences of flight schedule violations, and developing recommendations to reduce delays and improve punctuality. The purpose of the study was to study the causes of flight delays in the Kazakhstan air transportation market and to develop effective measures to minimize them.
The paper uses methods of statistical analysis, expert surveys, analysis of regulatory documents, as well as a comparative analysis of punctuality indicators of leading air carriers. The main results of the study were the identification of key causes of flight delays, including weather conditions, technical malfunctions, airport congestion and organizational factors, the analysis of flight delay statistics of the largest airlines in Kazakhstan, the development of proposals to optimize the processes of planning and management of air transportation.
As a result of the study, measures have been proposed to reduce flight delays, including improving the operational planning system, introducing digital technologies to predict delays, modernizing airport infrastructure, and improving the regulatory framework. The implementation of these recommendations will improve the punctuality of air transportation and improve the quality of passenger service in Kazakhstan.

Keywords: flight delays, air transport market, flight regularity, airports, airlines, quality of service, flight safety.

Authors: Makogonova V.O., Assilbekova I.Zh

Abstract. In modern conditions, despite the development of technology, companies continue to face problems of optimizing cargo transportation. One solution is to implement automated logistics management systems, but this process involves a number of challenges, including cyber threats, market risks, and the need for significant financial investments. Air cargo transportation remains one of the most demanded transportation methods, providing fast and efficient delivery at the international level. Kazakhstan, having a strategically advantageous geographical location, has a high transit potential. One of the promising areas is the development of Almaty Airport as an international cargo hub, which will increase cargo flow and strengthen the country’s position in global trade. However, the high cost of airport services can become a deterrent, which requires a revision of the tariff policy and an increase in revenue due to non-aviation activities. The modernization of the airport’s infrastructure, the introduction of innovative technologies and digital solutions such as SAP Transportation Management will improve the accuracy and efficiency of logistics processes. This will not only improve the level of service, but also strengthen Kazakhstan’s competitive position in the field of air cargo transportation, contributing to sustainable economic development and integration into the global transport system.

Keywords: cargo transportation, aviation company, efficiency improvement, SAP Transportation Management, airport, marketing.

Authors: Alimbekova N., Hari Mohan Rai, Turymbetov T., Zhumadillayeva A.

Abstract. This study investigates the use of a hybrid neural network architecture that combines convolutional neural networks (CNN) and long short-term memory (LSTM) for efficient sorting of plastic containers. The study focuses on classifying plastic waste based on chemical composition and contamination level, obtained with a near-infrared (NIR) spectroscopy device. Experimental results show that the CNN+LSTM hybrid model achieves relatively high accuracy in recognizing different types and colors of plastics, including the detection of contaminants in containers. A comparative evaluation of the model’s performance was conducted with traditional classification methods such as logistic regression, partial least squares (PLS), and linear discriminant analysis (LDA). The results show that the CNN+LSTM model performs better than traditional approaches, especially in scenarios with small spectral differences between classes. This study demonstrates the potential of machine learning to improve the efficiency of plastic waste sorting and recycling processes, thereby contributing to improved environmental sustainability.

Keywords. Plastic waste, NIRS (Near-infrared spectroscopy), Neural network, Hybrid model, CNN, LSTM.

Authors: Kumarkanova A.,Khasеnova Z.,Weiss Yu.

Abstract. Forecasting drug demand plays a key role in ensuring sustainable supply, effective inventory management, and timely patient access to life-saving medicines. This article presents a study of ARIMA time series and exponential smoothing methods for predicting demand for an antihypertensive blood pressure drug. The research is aimed at developing and identifying a model that ensures high accuracy and efficiency of forecasting based on selected data sets. The analysis includes the study of forecasting methods, data collection and processing, determining the optimal parameters for each method, developing a hybrid model, evaluating accuracy based on specified metrics, and analyzing the results. In the course of the conducted research, it was found that the most effective forecasting methods are time series-based approaches, including ARIMA models and exponential smoothing methods. And the developed hybrid model demonstrates high forecast accuracy by combining the advantages of the two approaches. The results show that the hybrid model is superior to ARIMA and exponential smoothing in all key metrics. Based on the findings, the introduction of hybrid models is proposed to improve the accuracy of forecasting demand in the pharmaceutical industry.

Keywords: forecasting, forecasting methods, exponential smoothing, ARIMA, time series, drug, hybrid model.

Authors: Койшиева Д.Е., Сыдыбаева М.А., Бельгинова С.А., Жаксыбаев А.М., Ерсаинова Ж.Е.

Abstract. Segmentation of medical images is one of the key tasks of biomedical informatics, especially in the context of cancer diagnosis. The task of precise segmentation of cell nuclei is particularly relevant and necessary to identify morphological changes in tissues. However, the main challenges and problems in this area remain the variability of image quality, limited amounts of available data, and the need to ensure the high accuracy and stability of deep learning models. This study analysed the impact of ten data augmentation techniques, including the addition of random noise of varying intensity, on the cell nucleus segmentation model’s performance. The experiment also specialises in techniques using artificial noise addition, simulating real-world conditions such as lighting variations, artefacts, and defects during sample preparation. Two types of noise were used to add: additive Gaussian noise and uniform random noise with an intensity from minus 0.05 to 0.05, which demonstrated a significant effect on the generalizing ability of the model, improving its resistance to heterogeneous data. The architecture used was based on a modified UNet model with the introduction of the CBAM module, which focuses the model’s attention on significant areas of the image. The module has been added to the decoding part of the model architecture. For the experiments, two reference datasets CryoNuSeg and MoNuSeg were combined with preprocessing, including patching and image format conversion. Applied augmentation techniques included horizontal and vertical reflection, random rotation, contrast change, elastic deformation, and noise addition. In addition, augmentation combinations were investigated during the experiments. The study results showed that the techniques of horizontal and vertical reflection augmentation and random rotation achieved minimal losses, while the accuracy of the models exceeded ninety per cent. The contrast change technique demonstrated the most balanced performance, providing an average intersection ratio over the union of 0.928 and an accuracy of 92.2 per cent. The data from the study results emphasize the importance of using artificial noise addition to increase the model’s resistance to artefacts and data variability, as well as the use of combined augmentation techniques. In the future, combined augmentation techniques may become the basis for the development of adaptive algorithms capable of effectively working with heterogeneous biomedical images
Keywords. Histological images, cancer, nuclei segmentation, convolutional neural networks, attention module, augmentation.

Authors: Mekhdiev T.,Shaikhanova A.K., Bekeshova G.B.,Iklasova K.E.,Bakenova K.S.

Abstract. The article discusses methods of intelligent text processing (Text Mining), which allow to transform poorly structured text data into structured and easily analysed information. With the growth of data volumes in the digital age, Text Mining is becoming an indispensable tool for analysing texts in various fields. These technologies find wide application in information security where text analysis helps to identify threats and anomalies, in healthcare to process medical records and extract diagnostic information, in marketing to analyse consumer preferences, and in legal practice where automation of document analysis improves accuracy and reduces time costs. The paper details both traditional statistical methods such as TF-IDF, Word2Vec, Latent Dirichlet Allocation (LDA) and state-of-the-art approaches including deep learning models based on transformer architecture such as BERT, GPT and their derivatives. The state-of-the-art methods show significant advances in context-awareness, semantics analysis, and extraction of hidden meanings from texts, which makes them indispensable for solving complex problems. Particular attention is paid to comparing the effectiveness of different methods and their applicability in automation tasks. The possibilities of Text Mining integration for analysing large amounts of data, identifying patterns and automating knowledge extraction processes are described. The presented research results emphasise the relevance of using these technologies to improve the efficiency of specialists’ work, accelerate the processes of information analysis and problem solving in key industries, which opens new perspectives for the implementation of intelligent data processing systems.

Keywords: Text Mining, intelligent text processing, machine learning, natural language processing, TF-IDF, Word2Vec, BERT, GPT, text analysis automation.

Authors: Nurgaliyeva S.A., Naiman N.B., Adikanova S.S.

Abstract. Plant disease detection is crucial to modern-day agriculture because timely diagnosis can reduce the loss of crops to an appreciable level and improve productivity. This review presents advanced disease detection systems based on machine learning techniques and multimodal data analysis. A comprehensive comparison of different machine learning algorithms, including convolutional neural networks (CNNs), transfer learning models, and object detection methods like YOLO, has been done. This study demonstrates that combining visual data with the analysis of volatile organic compounds (VOC) enhances the accuracy and reliability of the diagnosis. This provides opportunities for the actual development of satellite and cheap systems for monitoring operable in the field. Theoretically, this work contributes to developing strategies for integrating heterogeneous data and optimizing deep neural network models to make them lightweight and effective. The review emphasizes developing scalable and adaptive technologies for plant disease detection within precision agriculture.

Keywords: plant disease detection, machine learning, convolutional neural networks, MobileNet, multimodal data, real-time detection, agricultural technology, VOC sensors.

Authors: Tursunov T.S., Kaibassova D.

Abstract. Recommender systems play a crucial role in personalized content delivery by leveraging user preferences and content attributes. This study evaluates three advanced recommendation models: Neural Collaborative Filtering (NCF), Graph Neural Network-based Content Model (GNN-based Content Model), and Hybrid Neural Network (HNN). Each model integrates deep learning techniques to enhance prediction accuracy and user experience. The NCF model employs a dual-branch structure consisting of Generalized Matrix Factorization (GMF) and a Multi-Layer Perceptron (MLP) to model non-linear user-item interactions. The GNN-based Content Model represents users and items as nodes in a bipartite graph, utilizing Graph Convolutional Networks (GCN) to propagate relational and content-based information across connections. Lastly, the Hybrid Neural Network combines collaborative filtering embeddings with content-based features, aligning content representation within the learned latent space. Our evaluation, based on the MovieLens dataset, demonstrates that the Hybrid Neural Network achieves the highest accuracy (85%), outperforming NCF (80%) and the GNN-based Content Model (77.5%). The hybrid approach benefits from both collaborative and content-driven features, leading to improved user-item match quality. The GNN-based Content Model, despite leveraging structured relationships, struggles with cold-start users due to reliance on content information.
These findings suggest that hybrid approaches are more effective in capturing diverse recommendation signals. Future work may focus on integrating transformer-based architectures and reinforcement learning to further enhance recommendation relevance and adaptability.

Keywords: Recommender systems, Deep learning, Collaborative filtering, Graph neural networks, Hybrid models, Personalization