Park, SimonHugo, RonaldCristello, Josmar Baruffaldi2023-10-172023-10-172023-10-13Cristello, J. B. (2023). Safe transportation of blended hydrogen through pipeline (Master's thesis, University of Calgary, Calgary, Canada). Retrieved from https://prism.ucalgary.ca.https://hdl.handle.net/1880/11739410.11575/PRISM/42237Pipelines are a crucial part of Canada's infrastructure, providing a cost-effective and safe way to transport oil and gas. As the world moves towards a potential hydrogen economy, pipelines will also play a significant role in transporting hydrogen. Rather than building new pipelines, which can be costly in terms of materials, permits, excavation, and labor, this study explores the viability of using existing pipelines for transporting blended hydrogen with natural gas. This is done through two primary aspects, the feasibility of transporting blended hydrogen with existing pipelines and developing a leak detection system for this blended gas. The feasibility of blended hydrogen transportation is assessed through a steady-state gas hydraulic model, analyzing key operational metrics such as pressure, flow rate, and energy delivery. A virtual pipeline serves as a case study to evaluate the impact of transitioning from pure natural gas to blended hydrogen. It also delves into the trade-offs involved in selecting an optimal blend ratio. Given the scarcity of leak data for hydrogen-natural gas pipelines, the study introduces a Real-Time Transient Model (RTTM). The model simulates the behaviour of mixed gas through a combination of Equations of State and thermodynamic databases and is built upon the continuity and momentum equations. This model simulates the leak dynamics of blended hydrogen gases, filling a critical data gap. Moreover, a leak detection system (LDS) is developed using a fusion of Convolutional Neural Networks (CNN) and Explainable artificial intelligence (AI) through Adaptive Neuro-Fuzzy Inference Systems (ANFIS). This innovative LDS framework overcomes the “black box” issue common in AI-driven systems, enabling reliable detection and localization of leaks. The fusion of Explainable Machine Learning models and traditional AI techniques holds promising implications for blended hydrogen pipelines and other fluid transportation systems. This study contributes to the ongoing efforts to enhance the safety and efficiency of hydrogen transportation, thereby mitigating economic and environmental impacts and addressing public concerns.enUniversity of Calgary graduate students retain copyright ownership and moral rights for their thesis. You may use this material in any way that is permitted by the Copyright Act or through licensing that has been assigned to the document. For uses that are not allowable under copyright legislation or licensing, you are required to seek permission.Blended Hydrogen TransportationLeak Detection SystemReal-Time Transient Model (RTTM)Artificial Intelligence (AI)Explainable Artificial Intelligence (XAI)Hydrogen EconomyMachine LearningEngineering--MechanicalArtificial IntelligenceApplied Mechanicsmaster thesis