Michael Smith is a chartered Chemical Engineer and Data Scientist with a Master’s degree in Chemical Engineering from the University of Cambridge. Within ROSEN he leads the development of new asset integrity technologies, with a specific focus on 'Integrity Analytics' – the use of data analytics to support integrity management decisions.
Virtual Pipeline Summit 9 Dec
Virtual In-Line Inspection – Condition assessment for the most challenging pipelines
There is an ever increasing need to operate aging pipelines safely and efficiently. Pipelines that are challenging to inspect are a particular problem. The costs of precautionary replacement at the end of the design life, preclude this approach, leaks are not acceptable, and the modifications or special tools needed for the most challenging cases can also be very hard to justify. Machine learning methods trained on large data-sets and honed for specific systems offer a new way to predict condition with a ‘Virtual ILI’ that is not restrained by flow rate, tight bends, valves, tees, or any of the other features that traditionally create obstacles for ILI.
The results of a ‘Virtual ILI’ create clear justification for planning optimized actual inspections of challenging pipelines.