Overview

Real-time optimisation has been applied since the 1980s. Improvements are typically 2-10% although on occasion significantly higher improvements are achieved. Improvements are in areas such as increased production, lower energy use, higher yields, lower emissions. Legacy technologies have required some form of model to be developed of the facility to be optimised - either mechanistic models (based on the physics and chemistry of the process) or models based on regression or training using process data, often derived from plant tests to ensure sufficient information in the data. The need to develop and maintain a model of the facility being optimised requires specific expertise and incurs high costs. It has limited adoption of traditional technologies.

Recently ORTOmation has released a novel real-time optimiser based on self-learning technology. This has removed the need for a model. Consequently the need for expertise is reduced significantly and cost is much lower. Payback is significantly increased.

ORTOmation has implemented an initial industrial trial on an unconventional oil and gas production facility in the USA. ORTOmation and the operating company collaborated to implement a successful self-learning closed loop gas lift optimiser. The optimiser ran successfully, adjusting gas lift for several weeks and reduced gas lift usage by 44%, thereby reducing compressor OpEx costs by a similar amount.

This webinar provides an overview of the technology, early trials against digital twins and models and details of the gas lift optimisation project.

Speaker

Paul Oram, CEO, ORTOmation

By background, Paul is a process control and optimisation engineer. His PhD research focussed on adaptive closed loop control. 

Paul worked for a major oil and gas company for over 30 years in numerous locations, leaving in December 2020. He has extensive experience in designing, building and commissioning control and optimisation schemes across numerous petrochemical processes and oil and gas facilities around the world.

In his last role, as chief engineer for instrument, electrical and control, he became acutely aware that closed loop optimisation has the potential to deliver huge benefits across all processes but a new approach was needed to enable these to be captured at scale and pace. In short, the prize associated with real-time optimisation (RTO) was enormous but remained largely untapped.

In 2021, Paul set about tackling the difficulties which have, to date, impeded the widespread use RTO. This work has resulted in the novel ORTO algorithm which ORTOmation Ltd now markets.

Andrew Ogden-Swift, Consultant, ORTOmation Ltd

Andrew has over 40 years experience in justification, development, implementation and support of digital technologies in process manufacturing. He has held positions with Esso, KBC, ABB and Honeywell. He now works as a consultant for ORTOmation.

The material presented has not been peer-reviewed. Any opinions are the presenter’s own and do not necessarily represent those of IChemE or the Process Management and Control Special Interest Group. The information is given in good faith but without any liability on the part of IChemE.

Time

16:00–17:00 GMT.

Software

The presentation will be delivered via Microsoft Teams. We recommend downloading the app from the Microsoft website, rather than using the web portal.