A collection of experimental data from a multiphase plant simulating oil and gas transport

This paper details the data gathered from an experimental plant designed to simulate an oil and gas transportation system. The plant was configured to replicate various working conditions, including both normal and anomalous operational states. Different scenarios were created to reflect realistic conditions encountered in oil and gas transportation, such as steady-state operations, typical operational fluctuations, and a range of anomalies like leakages, obstructions, and working parameter modifications. The data provide a comprehensive view of the plant behaviour under these diverse conditions. This information can be instrumental for applications in machine learning, where it can aid in the development of predictive maintenance algorithms and anomaly detection models. In the realm of control theory, the data can support the design and validation of advanced control strategies to ensure efficient and safe operations. Additionally, the data enhance process comprehension, offering insights into the mechanisms governing oil and gas transportation systems. This dataset can be helpful for the analysis of the dynamic responses of an oil and gas transportation system under various operational scenarios. The structured data can be used to model and simulate system behaviour, providing a foundation for improving process resilience, efficiency and reliability. The information captured in this dataset can be useful for improving theoretical and practical understanding in the fields of machine learning, control theory, and process engineering.