IDIhor Dzerzhynskiy

Ihor Dzerzhynskiy

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Ihor Dzerzhynskiy has a total of 1 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    ОПТИМІЗАЦІЯ РОБОТИ БАШТОВОГО КРАНА ЗА ДОПОМОГОЮ АВТОМАТИЗОВАНИХ СИСТЕМ УПРАВЛІННЯ

    by Володимир Стефанов, Ігор Дзержинський

    У роботі розглядається процес оптимізації функціонування баштового крана через впровадження автоматизованих систем управління. Проаналізовано основні переваги автоматизації, серед яких підвищення ефективності роботи крана, зниження ризиків людських помилок та зменшення витрат на обслуговування. Особливу увагу приділено сучасним технологіям, що дозволяють здійснювати точне управління процесами підйому та переміщення вантажів, а також інтеграції систем моніторингу і діагностики стану обладнання. Впровадження таких систем дозволяє значно покращити продуктивність роботи, забезпечити безпеку та знизити вплив людського фактора на роботу баштового крана. У роботі розглянуто вплив людського фактора на працездатність баштових кранів та можливість його зменшення через впровадження систем машинного зору. Проаналізовано ризики, пов'язані з людськими помилками, та їхній вплив на безпеку й продуктивність робіт. Окреслено принципи роботи систем машинного зору, їхні технічні можливості та переваги в автоматизації керування краном, зокрема для моніторингу робочої зони, визначення траєкторій руху вантажів і мінімізації ризику зіткнень. Розглянуто методи реалізації цих систем за допомогою камер, сенсорів та алгоритмів глибокого навчання. Досліджено ефективність алгоритмів, таких як згорткові нейронні мережі (CNN), і технічні виклики, що виникають при інтеграції цих технологій. Результати показали, що системи машинного зору підвищують безпеку, знижують навантаження на оператора та покращують ефективність експлуатації кранів. Впровадження систем машинного зору є важливим кроком до покращення безпеки, підвищення ефективності та зниження навантаження на операторів при експлуатації баштових кранів. Крім того, такі системи можуть визначати безпечні траєкторії для переміщення вантажів, мінімізуючи можливість зіткнень або пошкоджень. Ключові слова: баштовий кран, аварії, людський фактор, моніторинг, машинне бачення, сонливість, штучний інтелект, система безпеки.

  • Open Access

    EXPLORING THE STABILITY OF TOWER CRANES AND METHODS FOR IMPROVING THEIR OPERATIONAL SAFETY

    by І. Dzerzhynskiy, V. Stefanov

    This article delves into the critical issue of stability in different types of tower cranes, specifically comparing those with rotating (slewing) towers and those with non-rotating (top-slewing) towers. It explores various methods to enhance the operational safety of these essential construction machines. Tower cranes, while indispensable in modern construction and heavy industries, are inherently susceptible to stability-related accidents due to their height, slenderness, and the dynamic nature of the loads they handle. This study comprehensively analyzes the influence of structural characteristics, operational loads, and a range of external forces on crane stability. The research explores factors such as wind loading, dynamic forces generated during operation (e.g., load swing, sudden stops), and even more extreme events like impact waves. The research methodology combines a thorough review of existing literature, standards, and regulations with advanced computational analysis and experimental validation. The literature review encompasses relevant standards, such as the EN 13001 series, Ukrainian national regulations, and research publications focusing on crane stability, dynamic load analysis, and safety improvement methods. This review identifies gaps in traditional calculation methods, particularly their limitations in accurately representing complex load combinations and the behavior of non-standard or modified crane configurations. To overcome these limitations, the study leverages 3D modeling and finite element analysis using industry-standard software. Detailed models of both rotating and non-rotating tower cranes are developed, allowing for a precise simulation of stress distributions, deformation patterns, and potential failure points under various loading scenarios. These models incorporate the specific geometric parameters, material properties, and connection details of the cranes. The finite element analysis approach allows for a significantly more accurate assessment of stress concentrations, particularly in critical areas such as the tower-to-base connection, compared to traditional methods of structural mechanics. The comparative analysis highlights key differences in the stability characteristics of the two crane types. The location of the center of gravity, the response to dynamic loads (especially during slewing operations), and the impact of wind forces are meticulously examined. The findings indicate that cranes with rotating towers exhibit a larger degree of load sway and potentially greater vulnerability to certain types of dynamic instability. To validate the theoretical and computational findings, experimental studies are conducted using a scaled-down (1:20) laboratory model of a KB-403 tower crane. A custom-designed computer program controls the model's movements, allowing for the precise simulation of various operational scenarios and the collection of empirical data on crane behavior. Based on the combined theoretical, computational, and experimental results, the research proposes a novel design concept: a tower crane with a load-compensating mechanism using a movable counterweight. The study outlines an algorithm for controlling the position of this counterweight, dynamically adjusting it based on real-time sensor data (load weight, jib extension, wind speed and direction, tower inclination, and stress levels in critical components). Furthermore, the article explores the potential integration of artificial intelligence and machine learning techniques to create an adaptive control system for enhanced stability. This system would utilize data from a network of sensors to predict and mitigate potential instability issues in real-time. The importance of ongoing data collection and continuous refinement of the artificial intelligence models is emphasized to ensure long-term reliability and effectiveness.

  • Open Access

    SYSTEM ANALYSIS OF TOWER CRANE ACCIDENTS AND INNOVATIVE METHODS OF THEIR PREVENTION

    by Volodymyr Stefanov, Ihor Dzerzhynskiy

    This article presents a comprehensive investigation into the causes of tower crane accidents, a critical concern considering their vital role in modern high-rise construction and the associated high risks. The analysis encompasses technical, organizational, and environmental factors that compromise crane stability. These include inherent design vulnerabilities (a high center of gravity coupled with a limited support base), dynamic external loads such as wind and seismic events, and the pervasive influence of human error across all stages of a crane's operational life.The study reveals that accidents involving tower crane overturning or structural collapse, often precipitated by hard-to-detect fatigue cracks, represent up to 40% of all lifting crane incidents. Such failures pose substantial threats not only to on-site personnel but also to adjacent structures and the general public. The growing density of urban construction, coupled with challenges like fluctuating operational conditions and inadequate operator training, amplifies these inherent risks. A global increase in tower crane utilization is unfortunately accompanied by a corresponding rise in accident frequency, highlighting deficiencies in current safety protocols, even on technologically advanced "smart" building sites.The research underscores the imperative for proactive, holistic risk management and enhanced safety systems. It places particular emphasis on harnessing cutting-edge technologies, most notably artificial intelligence and neural networks, to create automated monitoring and control mechanisms. These systems are designed to bolster crane stability under unpredictable and dynamic loading, and facilitate the early detection of structural weaknesses. The proposed approach uses sensors and machine learning algorithms for real-time data analysis and predictive control, representing a significant advancement over conventional, often reactive, safety methodologies. The findings offer practical benefits for minimizing construction accidents, improving the operational reliability of tower cranes in demanding environments, and promoting higher global standards of construction safety.

  • Open Access

    STABILITY MANAGEMENT OF A TOWER CRANE USING ARTIFICIAL INTELLIGENCE

    by Volodymyr Stefanov, Ihor Dzerzhynskiy

    Tower cranes remain an irreplaceable tool in the construction industry. The market for tower cranes is expected to grow to over $3 billion by 2025. Hundreds of thousands of tower cranes are in operation worldwide, with over 5,000 in Ukraine. Most of these cranes have reached the end of their service life. The limited size of construction sites forces the use of tower cranes with a small support base, which are prone to tipping over during assembly and operation. Accidents on tower cranes occur regularly, with an average of 2 per year in the United States. About half of all tower crane accidents are related to tipping over. The main causes of tower crane accidents are technical reasons (failure of technical devices and safety devices), organizational reasons (violation of technological and labor discipline), and external influences (wind load). This paper presents a system for ensuring the stability of a tower crane using artificial intelligence methods. The system includes sensors for collecting data on wind parameters and crane parameters, a controller with a neural network model for predicting wind parameters, and an algorithm for controlling crane mechanisms. The system is designed to ensure the stability of the crane in working condition. The results of the study showed that the proposed system can effectively ensure the stability of the tower crane in working condition. The system can predict dangerous wind gusts and take appropriate measures to prevent tipping over. The use of this system can significantly reduce the number of accidents on tower cranes.