APPLICATION OF INTELLIGENT MEASUREMENT TECHNOLOGIES FOR THE ANALYSIS OF OPERATIONAL PARAMETERS OF ROAD CONSTRUCTION MACHINERY

The increasing mechanisation of the construction and road sectors necessitates improvements in the operational characteristics of road construction machinery, particularly in minimising noise pollution. Excessive noise generated by machinery such as motor graders affects operators' working conditions and the durability of machine components. This study focuses on applying intelligent measurement technologies to evaluate and optimise the acoustic characteristics of road construction machinery, emphasising noise prediction and reduction strategies. The research introduces a novel methodology for noise measurement using the DZ-99 motor grader, ensuring accurate data collection for assessing the machine’s operational parameters and environmental impact. Various factors influencing noise levels, such as engine speed, gear ratios, and measurement distances, were analysed through experimental studies. The results confirmed the presence of hazardous frequency ranges and enabled the calculation of measurement errors, which is crucial for optimising machine operating conditions. A neural network-based noise prediction model was developed with high accuracy (correlation >0.9), demonstrating its practical value in analysing working processes and mitigating noise pollution. Implementing artificial intelligence in machine monitoring systems allows for real-time noise analysis, improving road construction equipment's operational efficiency and safety. The study also highlights the potential of integrating machine learning techniques to enhance acoustic assessments' precision and develop proactive noise reduction measures. An intelligent noise monitoring system was proposed for real-time analysis, enhancing operators' conditions, ensuring regulatory compliance, and supporting sustainable construction. The study offers insights into optimizing operations and reducing noise exposure. The results of this study can be used to enhance existing evaluation methods for noise pollution, improve the reliability and safety of road construction equipment, and facilitate the development of intelligent systems for automated noise control. Future research should focus on refining noise prediction algorithms by incorporating additional factors such as terrain type, environmental conditions, and machine wear levels to enhance the accuracy and applicability of intelligent noise measurement technologies.