Session: 04-01-02 Leak Detection

Paper Number: 134184

134184 - Advancing Leak Detection in Natural Gas Pipelines: A Novel Approach Using Real-Time Transient Modeling for Methane Emissions Mitigation 

Abstract: 

Currently, methane emissions account for approximately 25% of human-induced global warming, with the oil and gas sector ranking among the leading contributors. Early detection of methane leaks in pipelines significantly reduces the greenhouse gases emissions, aiding in the mitigation of adverse economic and environmental consequences associated with climate change. Computational Pipeline Monitoring (CPM) systems, tailored for leak detection, provide continuous pipeline monitoring and offer early identification of leaks while minimizing false alarms. This study harnesses advancements in data-driven methodologies and integrates them with physics-based models to address the intricacies of modeling gas pipelines and introduces a real-time transient model (RTTM) used for leak detection of natural gas pipelines.

The presented model solves the partial differential equations of mass, momentum, and energy conservation. An overall heat transfer coefficient is considered to account for composite lateral layers of a typical pipeline, addressing heat gain or dissipation to the surroundings. Successful detection of leaks in pipelines with compressible flow necessitates the real-time calculation of density. To achieve this, an auxiliary equation of state is integrated into the model to determine density as a function of pressure and temperature. To account for uncertainties in system parameters, data collection, and model calculations, machine-learning-based estimators are designed. They are trained on historical data and patterns, allowing the model to adapt and make more accurate predictions or estimations in real-time scenarios. The discrepancies observed in the measured and calculated values will be flagged as a possible leak event when it exceeds a certain threshold. The final decision to alarm is made using a multi-layered classification framework.

Initial validation of the model is performed using existing experimental data from the literature, followed by an assessment of its performance using data from an industrial pipeline. The results demonstrate the model's efficacy in enhancing the accuracy and sensitivity of leak detection, showcasing its potential for practical implementation in reducing methane emissions and promoting sustainable pipeline management.

Presenting Author: Hamed Ghasvari Jahromi Vanmok Leak Detection Technologies

Presenting Author Biography: Hamed Ghasvari Jahromi is Chief Scientific Officer at Vanmok Leak Detection Technologies, bringing over 18 years of expertise in computational fluid dynamics to the forefront. He holds a patent for prediction of pipeline column separations and published impactful research papers.
He has extensive experience in applying mathematical modeling and fluid dynamics to address industrial challenges and is a leading expert in developing leak detection technologies using RTTM, and pattern recognition approaches.

Authors:

Hamed Ghasvari Jahromi Vanmok Leak Detection Technologies
Fatemeh Ekram Vanmok Leak Detection Technologies
Satya Mokamati Vanmok Leak Detection Technologies