АВТОМАТИЗАЦІЯ МОНІТОРИНГУ І ДІАГНОСТИКИ БУРОВОГО УСТАТКУВАННЯ З ВИКОРИСТАННЯМ ТЕХНОЛОГІЙ IOT

• Date: 2025
• Main Authors: Пащенко, O.A., Расцвєтаєв, В.О., Шумов, А.С., Дмитрук, O.O., Яворська, В.В.
• Format: Article
• Language: English
• Published: Институт сверхтвердых материалов им. В. Н. Бакуля Национальной академии наук Украины 2025
• Subjects: інтернет речей (IoT); бурове обладнання; прогнозне технічне обслуговування; виявлення несправностей; машинне навчання; моніторинг у реальному часі; операційна ефективність; аналітика даних; надійність мережі; промислова автоматизація
• Online Access: http://altis-ism.org.ua/index.php/ALTIS/article/view/457
• Journal Title: Tooling materials science

The rapid evolution of the oil and gas industry necessitates advanced solutions to enhance the reliability, efficiency, and safety of drilling operations. Traditional monitoring and diagnostics of drilling equipment, reliant on manual inspections and scheduled maintenance, suffer from inefficiencies, delayed fault detection, and high operational costs. This study explores the application of Internet of Things (IoT) technology to automate the monitoring and diagnostics of drilling equipment, addressing these challenges through real-time data acquisition and advanced analytics. The proposed IoT framework integrates sensors (e.g., vibration, temperature, pressure), lightweight communication protocols such as MQTT and CoAP, and cloud-based platforms like AWS IoT for data storage and processing. A case study was conducted on a simulated drilling rig, collecting 1.2 million data points over 30 days to evaluate system performance. Machine learning models, including Random Forest classifiers and LSTM networks, were employed for fault detection and predictive maintenance, achieving a precision of 0.92, recall of 0.89, and F1-score of 0.90 in identifying anomalies such as bearing wear and pump pressure issues. The IoT system reduced unplanned downtime by 18% and maintenance costs by 15% compared to traditional methods, with edge-based anomaly detection averaging 150 ms and cloud-based diagnostics at 1.2 seconds. Challenges include network reliability, with 5% packet loss in low-connectivity scenarios, data security requiring robust encryption, and integration with legacy systems necessitating custom middleware in 30% of cases. The system improved operational safety by early fault detection and reduced energy consumption by 12%, contributing to environmental sustainability. Comparative analysis with traditional methods underscores the IoT system’s superior accuracy and efficiency, driven by real-time data and predictive analytics. Future research should focus on integrating advanced AI, such as deep reinforcement learning, and edge computing to enhance system responsiveness and scalability to other industrial applications. Recommendations for industry adoption include using standardized protocols, investing in reliable networks, and training personnel for effective IoT implementation. This study demonstrates that IoT technology offers a transformative approach to drilling equipment management, with significant implications for operational efficiency, safety, and sustainability, provided challenges like network reliability and system integration are addressed.