Oil Development Engineering Company, Tehran, Iran

  • سال انتشار: 1403
  • محل انتشار: مجله علوم و فن آوری نفت، دوره: 14، شماره: 2
  • کد COI اختصاصی: JR_JPSTR-14-2_006
  • زبان مقاله: انگلیسی
  • تعداد مشاهده: 65
دانلود فایل این مقاله

نویسندگان

Seyed Ali Mohammad Tajalli

Department of Electrical Engineering, Marvdasht Branch, Islamic Azad University, Marvdasht, Iran

Mazda Moattari

Department of Electrical Engineering, Marvdasht Branch, Islamic Azad University, Marvdasht, Iran\Mechateronic & Artificial Intelligence Research Center, Marvdasht Branch, Islamic Azad University, Marvdasht, Iran

Vahid Naghavi

Engineering Devision, Reseach Institute of Petroleum Industry, Tehran, Iran

Mohammad Reza Salehizadeh

Department of Electrical Engineering, Marvdasht Branch, Islamic Azad University, Marvdasht, Iran

چکیده

This paper delves into the transformative implications of Digital Twin (DT) technology on pipeline management within Industry ۴.۰, emphasizing its pivotal role in ensuring integrity, efficiency, and leak detection for oil, gas, and water transportation. The proposed pipeline management platform adopts a conceptual DT architecture, integrating key components such as the Asset Administration Shell (AAS), Admin-Shell-IO, Node-RED, Apache StreamPipes, SimCenter, MATLAB, and Ignition software.The platform focuses on automation, operational optimization, safety, and regulatory compliance through this integration. To achieve these goals, the paper introduces the Modified Real-Time Transient Modeling (MRTTM) framework, which aims to swiftly and accurately detect and locate leaks. Furthermore, the operational procedure of this framework involves three key stages. In the “Data Collection” phase, sensor data are monitored by observing nodes. In the subsequent “Detection” stage, leaks are identified, and in the concluding “Decision-making” module, the exact magnitude and location of the leakage are determined using MRTTM. Leveraging a hybrid approach that combines the Extended Kalman Filter (EKF), Real-Time Transient Modeling (RTTM), and machine learning algorithms, the framework offers accurate insights into the pipeline’s operational status. Moreover, machine learning models, including K-nearest neighbors (KNN) and support vector machines (SVM), enhance anomaly detection precision, allowing for early identification and localization of potential leaks.Ultimately, the proposed framework brings several key benefits to pipeline management, including early anomaly detection, real-time data integration, predictive maintenance, and regulatory compliance. By identifying potential leaks and anomalies early on, operators can take measures to prevent failures, respond quickly to disruptions, and comply with environmental and safety regulations.

کلیدواژه ها

Pipeline Management, Theft/Leak detection, Industry ۴.۰, Digital twin, Asset Administration Shell, Modified Real-Time Transient Modelin

اطلاعات بیشتر در مورد COI

COI مخفف عبارت CIVILICA Object Identifier به معنی شناسه سیویلیکا برای اسناد است. COI کدی است که مطابق محل انتشار، به مقالات کنفرانسها و ژورنالهای داخل کشور به هنگام نمایه سازی بر روی پایگاه استنادی سیویلیکا اختصاص می یابد.

کد COI به مفهوم کد ملی اسناد نمایه شده در سیویلیکا است و کدی یکتا و ثابت است و به همین دلیل همواره قابلیت استناد و پیگیری دارد.