5th Computational Methods and Ocean Technology (COTech 2026)

Session

Smart Operations and Maintenanc

CT05

Not scheduled

KE E-102 (University of Stavanger, Norway)

36. A Machine Learning–Enabled Digital Twin Framework for Risk-Prioritized Autonomous Underwater Vehicle Inspection of Subsea Oil and Gas Pipeline Networks

Dr Harish Kumar Devarakonda (Associate Professor)

Paper Contribution

Inspecting subsea oil and gas pipelines is expensive. Autonomous Underwater Vehicles have limited mission time, yet most operators still follow fixed inspection schedules that treat every pipeline section the same regardless of age, water depth, or operating history. Low-risk sections get checked anyway. High-risk sections wait their turn. This paper builds a digital twin framework that uses...

71. Anomaly Detection in Oil Well Production Time-Series Data

Ms Iqra Ishtiaq (University of Stavanger)

Paper Contribution

Anomaly detection in industrial time-series data is challenged by the scarcity of labeled fault data, limiting the applicability of supervised machine learning methods. This study investigates two complementary approaches for anomaly detection in the Petrobras 3W oil production dataset. A semi-supervised Temporal Convolutional Network (TCN) autoencoder was trained exclusively on normal...

58. Applying Agentic AI for Predictive Maintenance Decision Support in Offshore Wind Turbines

Arvind Keprate (Oslo Metropolitan University)

Paper Contribution

Operation and maintenance costs account for 25–35% of the total lifetime cost of an offshore wind farm. This study addresses that gap by developing and testing a prototype agentic AI framework for offshore wind turbine maintenance decision support.
The proposed framework uses four specialized agents in sequence, with each agent producing a validated output for the next stage. The framework...

98. Computational Assessment of Municipal Infrastructure Asset Performance for Smart Operations And Maintenance

Prof. Abimbola Windapo (University of Cape Town)

Paper Contribution

Smart Operations and Maintenance (O&M) requires infrastructure owners to move from reactive maintenance toward data-driven, risk-informed and financially sustainable asset management. This study examines whether current and planned asset investments are adequate to maintain service delivery, productive capacity, and long-term financial sustainability in Municipality X, and to develop asset...

52. Fault Diagnostics for Hydrogen-Fuelled Micro Gas Turbines Using Physics-Based Modeling and Random Forest Classification

Mustafa Mahmoud Fatalla (Mechanical Engineering, Arab academy for science & Maritime, Alexandria, Egypt), Ali Karimi (Department of Energy and Petroleum Engineering, University of Stavanger, Stavanger, Norway)

Paper Contribution

The shift toward cleaner energy systems has placed hydrogen at the forefront of fuel research, particularly for distributed power generation where Micro Gas Turbines (MGTs) offer a practical and flexible solution. Unlike conventional fuels, hydrogen produces no CO₂ at the point of combustion, and even a 75% hydrogen blend can cut emissions by up to 50% compared to natural gas. A major...

96. Fault Injection Methodology for Generating Labelled Fault Data and Improving Intelligent Fault Diagnosis

IDRISS ELTHALJI (Associate Professor), Mr Makafui Botsoe

Paper Contribution

The development of data-driven fault-diagnosis systems is often constrained by the limited availability of representative faulty data. Industrial faults may occur rarely, require long observation periods to capture, or be unsafe and costly to reproduce under actual operating conditions. Consequently, operational datasets frequently contain abundant normal or healthy data but insufficient...

27. Improving Production Environment Through Lean Manufac￾turing in the Manufacturing Of Plastic Panels: The Case Of HK Business Group

Bikila Worku (Wallaga University)

Paper Contribution

Abstract
This study investigates the implementation and impact of the 5S methodology on operational efficiency in the plastic panel production line of HK Business Group, located in Addis Ababa, Ethiopia. The research was motivated by challenges such as poor workplace organization, high defect rates, excessive waste, long lead times, and workplace safety concerns. A mixed-methods approach...

25. Operator-enabled context-sensitive decision process for high-risk offshore drilling Operations: Enhancing contextual knowledge, advanced situation awareness, and operational resilience

Prof. Jayantha Prasanna Liyanage, Mr Mohammad Bakhshandeh (University of Stavanger)

Paper Contribution

The rapid evolution of automation along with other technologies has improved operational efficiency in modern industrial assets and systems, such as oil and gas drilling platforms. On the other hand, modern developments in offshore industry have also introduced solutions that are increasingly opaque and cognitively demanding for human operators. For instance, in the context of increasing...

95. Prescriptive Design of Metro Operations for Major Events: A Simulation-Based Decision-Support System for Managing Passenger Surges

Mr ABDULLAH ALNASSER, Mr Abdullah AlFheed, Mr MESHAL ALJUBAIR, Mr SULAIMAN ALSUGAIR, Mr SULTAN ALKHIDHR

Paper Contribution

Major events in Riyadh can generate sudden passenger surges that lead to severe platform crowding, long waiting times, and slow crowd dispersal at key interchange stations such as the King Abdullah Financial District (KAFD) Metro Station. Existing metro systems support passenger monitoring and demand forecasting; however, operators have limited ability to evaluate alternative interventions...

89. Smart Manufacturing Supply Chain through Artificial Intelligence Technologies: - An Empirical Study in the Ethiopian Context

Edossa Dugassa Eticha (Ambo University)

Paper Contribution

Abstract
The advent of AI has transformed various industries, with significant implications for manufacturing supply chain performance (SCP). This study aims to investigate the effects of AI-enabled factors on manufacturing SCP. Based on an extensive review of the literature, a conceptual framework integrating key AI-enabled factors and SCP was developed. Data were collected from 412...

93. Spatially resolved limits of data-driven forecasting for online impedance-based condition monitoring of submarine power cables

Prof. Arvind Keprate (Oslomet University)

Paper Contribution

Cable failure is among the costliest failure modes in offshore wind, and online condition monitoring avoids the production loss of offline testing. Frequency Domain Reflectometry (FDR) produces a spatial impedance profile that can be acquired while the cable remains energized, making it a natural candidate input for data-driven prognostics. Whether such measurements support reliable temporal...

11. The Relationship between Trim and Fuel Consumption for a Vessel

Ove Tobias Gudmestad (University of Stavanger, Norway)

Paper Contribution

Abstract. The objective of this study is to find the influence of the trim of a ship on the hydrodynamic resistance and the associated fuel consumption of a container ship. The KRISO Container Ship (KCS) design is used in this study as the reference vessel. It is a container ship that has been used in many research studies and towing tank experiments. The main dimensions of the ship are 232.5...

85. The Trust Paradox in Renewable Technology Adoption: Balancing Acceptance and Risk Perception in Offshore Oil and Gas

Ms Anne Marit Gårseth (Department of Mechanical and Industrial Engineering, Norwegian University of Science and Technology)

Paper Contribution

Renewable and low-emission technologies are increasingly used in green transition. However, the introduction of new technologies also creates uncertainties and risks, particularly in the safety-critical industries such as offshore oil and gas production. While trust has been shown to promote acceptance of technology, it can also reduce risk perception by lowering perceptions of the likelihood...

97. Toward Agentic Maintenance Management System: A Case Study of UiS Technical Laboratories

Makafui Botsoe, Prof. Idriss El-Thalji

Paper Contribution

Conventional computerized maintenance management systems (CMMSs) support the documentation and administration of maintenance activities, but they largely depend on users to interpret information, initiate workflows, coordinate resources, and make decisions. This paper proposes an agentic maintenance management system that extends traditional CMMS capabilities through autonomous and...