By International Petroleum Technology Conference (IPTC) Monday, 25 March 0900-1600 hours Instructors: Olivier Dubrule and Lukas Mosser, Imperial College London Deep Learning (DL) is already bringing game-changing applications to the petroleum industry, and this is certainly the beginning of an enduring trend. Many petroleum engineers and geoscientists are interested to know more about DL but are not sure where to start. This one-day course aims to provide this introduction. The first half of the course presents the formalism of Logistic Regression, Neural Networks and Convolutional Neural Networks and some of their applications. Much of the standard terminology used in DL applications is also presented. In the afternoon, the online environment associated with DL is discussed, from Python libraries to software repositories, including useful websites and big datasets. The last part of the course is spent discussing the most promising subsurface applications of DL.
Rana, Rohit (Independent Geomechanics and Pore Pressure Consultant) | Hansen, Kirk S. (Shell India Markets Private Limited) | Kandpal, Jyoti (Shell India Markets Private Limited) | Kumar, Rajan (Shell India Markets Private Limited) | Schutjens, Peter (Shell India Markets Private Limited) | Muro, Leytzher (Shell India Markets Private Limited) | Rees, Daniel (Brunei Shell Petroleum Co Sdn Bhd) | Latief, Agus I. (Brunei Shell Petroleum Co Sdn Bhd)
Knowledge of the in-situ stress state and how it varies with reservoir depletion is important for the design and execution of in-fill drilling. This paper highlights the key geomechanical aspects and their usage in planning of wells through severely depleted (up to 25 MPa) and overpressured zones within a very short depth interval (few 10s of m), in an onshore gas field in Brunei. With focus shifting from oil to deep-gas development, drilling complications include risks of wellbore instability, excessive mud loss and internal blowouts, as well as differential sticking in the depleted reservoirs. Moreover, fracturing of the depleted sands while drilling infill wells carries the risk of jeopardizing production at nearby producing wells because of locally altered flow paths. The risks were evaluated by application of empirical and analytical geomechanical models of stress changes with depletion, and by elasto-plastic finite element models of borehole instability (collapse) due to shear failure.
Our results show that for an average depletion rate of 1 MPa/year, the drilling window (difference between maximum allowable mud weight controlled by fracture pressure and minimum mud weight controlled by formation pore pressure or borehole collapse pressure, whichever is greater) is likely to remain open for the coming 12 years. Minifrac or extended leak-off tests at different stages of field development should be taken to monitor stress changes within the reservoirs and provide updates for calibration of the geomechanical model.
Next to showing the geomechanical model results and their application to drilling, we demonstrate the refinement of pore pressure/fracture pressure predictions (i.e. narrowing down the uncertainty in the drilling window) for mature fields where producing "from the bottom up" has not been feasible. We also indicate how risks associated with drilling through depleted/undepleted reservoir sequences in a single hole section can be managed to as low as reasonably practicable with the help of geomechanical input. These results "open the door" for accessing deeper potential pay zones by drilling through severely depleted formations.
State of the art technology has been incorporated into the Seria North Flank waterflood development. Both producer and water injector wells are completed with interval control valves, distributed temperature sensing (DTS) and downhole gauges. DTS has been commercially available for more than a decade, however only recently it has been employed in the oil industry. Interpretation of the data has been difficult and therefore its value questioned.
This paper presents an original technique of monitoring wax build up through the use of the DTS data. PVT analysis from the appraisal well showed significant wax content in some of the reservoirs to be produced. The critical wax deposition temperature is higher than the surface temperature and therefore wax is expected to be deposited inside the tubing. The DTS provided temperature trends that showed temperature decline in a section of the tubing string; caused by the additional layer of wax between the crude oil and the gas filled annulus. The paraffin layer has its own heat transfer coefficient therefore thickness can be estimated from temperature data for unchanged flow rate and fluid composition.
Using the temperature trends, the Well and Reservoir Management (WRM) team was able to determine the exact depths where the wax accumulated. This information avoided slick line interventions to determine hold-up depths and also allowed the required volume of solvents to be calculated, prior to for coiled tubing clean out. The Coiled Tubing activity enabled production to be maintained before the wax build-up could significantly impact the well flowrate. This technique has been extended to other wells and is now part of the standard WRM monitoring parameters for this field.
The winner was announced at the International Petroleum Technology Conference in Kuala Lumpur in February. The project was a major advance in the production of Brazil’s abundant heavy-oil reserves and became the world’s first full-field development based on subsea oil and gas separation and subsea pumping. The Parque das Conchas fields are located 120 km off the coast of Brazil, where ultradeep water and a constant swell make for difficult operating conditions. A series of technology firsts unlocked major new resources beneath water nearly 2 km deep. Huge technical challenges had to be overcome to bring the fields to production.
Shell’s Parque das Conchas project, an ultradeepwater heavy-oil development in the northern Campos basin offshore Brazil, has won the IPTC Excellence in Project Integration Award. The award recognizes a project team that has made significant and unique achievements in managing and directing an integrated oil or gas project from discovery to delivery. The winner was announced at the International Petroleum Technology Conference in Kuala Lumpur in February. The project was a major advance in the production of Brazil’s abundant heavy-oil reserves and became the world’s first full-field development based on subsea oil and gas separation and subsea pumping. The Parque das Conchas fields are located 120 km off the coast of Brazil, where ultradeep water and a constant swell make for difficult operating conditions.
Brunei Shell Petroleum (BSP) first started completing Smart Wells in 1999, trialing standalone technologies such as permanent downhole gauges and inflow control valves in individual wells. Once these were seen as successful, the technology was used extensively on a single platform. This was later extended to application in a whole field, taking advantage of refinements such as variable downhole control valves and multiphase flow metering.
Learning from the successes of other oil producing fields such as Champion West and Bugan, Seria North Flank was planned and designed as a fully Smart field. Seria North Flank would be the first field to fully integrate Smart technology with Smart field processes, improving the efficiency of Well and Reservoir Management activities and accelerating reservoir understanding in order to reduce uncertainties for future development. This resulted in the development of over 120 million barrels of oil, with improved Unit Technical Costs compared to an offshore development.
Building Smart capabilities
Brunei Shell Petroleum (BSP) initially trialed the individual elements of Smart technology in standalone wells from 1999. Downhole gauges and fibre optics (for Distributed Temperature Sensing, or DTS) were run on different wells, mainly to trial the technology and study reservoir inflow profiles. Several key findings from these wells formed the basis for the requirements of surface operated inflow control valves (ICV). The main one of these was that contribution from long horizontals tended to be negligible from the toe of the well (furthest from the stinger section).
The Champion West field was selected to further develop Smart technology. In order to manage and develop appropriate solutions for the network infrastructure, a dedicated IT team was created to support to real time data management. A small team within the operations discipline was also formed to help manage the interfaces with the existing offshore network infrastructure.
Initial completion designs incorporated one ICV above a ball valve and a dual gauge for multizone wells. At this stage, only monitoring was applied remotely with the downhole and surface gauge data transmitted to the main production facility and control requiring human intervention at the platform location. These wells showed the time benefits of have surface operated capabilities to monitor well pressures and change zones. In 2002, Shell started to develop the Smart Fields program, defining the technology and processes required in order to operate a Smart Field.
In 2003, the surface control was further developed so that remote operations from one of the Champion West jackets was possible from the main production platform and then from the Head Office. These successes led to the development of the Champion West Drilling Platform in 2005, a fully Smart, not normally manned platform. This platform incorporated almost all aspects of Smart technology that were available commercially at the time, with almost all aspects of the wells operated and monitored remotely. Surface flow control valves and sequencing valves to control surface rates and select wells for testing, a multiphase flow meter to accurately test wells, and the full suite of downhole tools that included inflow control valves to control flow, permanent downhole gauges for pressure data and fibre-optics to acquire distributed temperature surveys. Each well had up to five individual zones to maximize hydrocarbon recovery and value.