نوع مقاله : مقاله پژوهشی
نویسندگان
دانشگاه علامه طباطبایی
چکیده
کلیدواژهها
موضوعات
عنوان مقاله [English]
نویسندگان [English]
Intelligent decision support systems play a crucial role in predicting failures, optimizing resource allocation, and minimizing equipment downtime in the oil and gas industry. However, traditional linear regression algorithms face significant challenges, including reduced accuracy and increased computational costs when handling large-scale datasets and complex operational conditions. In this study, an enhanced hybrid regression model is proposed that integrates linear regression, random forest, and artificial neural networks to improve prediction accuracy and mitigate production instability. The model is applied to a dataset containing 9,208 records of oil and gas equipment performance data. The results indicate that the proposed hybrid model improves prediction accuracy by 17% and reduces production instability by 15% compared to conventional methods. Furthermore, the model efficiently processes large-scale data, identifies critical operational patterns, and enhances the prediction of stable production trends. These findings suggest that the proposed model can serve as a powerful tool for industrial decision-making, predictive maintenance, and resource optimization in the oil and gas sector.
کلیدواژهها [English]
)