Mange bransjer, for eksempel olje og gass, CO2 -lagring, geotermisk eller energilagring, bruker brønner, ikke bare for injeksjon og produksjon, men også for overvåking for å sikre kvaliteten og sikkerheten i prosessene som foregår i reservoarene i undergrunnen.
Mulighetene for å hente ut data fra brønnene, slik som strømmingsrater, trykk, temperatur etc., er blitt kraftig forbedret de seneste årene. Signalene kan nå måles med høy presisjon og lagres i nærmest ubegrensede mengder. Det som ikke har utviklet seg tilsvarende er mulighetene til å effektivt analysere og tolke disse dataene slik at informasjonen som ligger der blir synlig og kan utnyttes til overvåkning og styre brønnene på den mest hensiktsmessige måten.
Fram til nå har slike analyser hovedsakelig blitt gjort manuelt, noe som er både tid og arbeidskrevende, og gjerne medfører at viktig informasjon blir oversett, eller kommer for sent. Dette prosjektet tar sikte på å utvikle metoder, modeller og algoritmer for å effektivt håndtere disse store datamengdene, fjerne støy, og gjenkjenne mønstre som kan inneholde nyttig informasjon. Potensielt nyttige data blir ført videre til avanserte tolknings-systemer som kan trekke ut slik informasjon ved å kombinere tradisjonelle analysemetoder (analytiske og numeriske modeller) med mer data-baserte tilnærminger som maskin-læring og stor-data analyser.
Målet er en automatisert prosess der datastrømmen behandles kontinuerlig. På denne måten kan unormal oppførsel, for eksempel lekkasjer, oppdages tidlig, og viktig informasjon om brønn- og reservoarforhold kan raskt nå beslutningstakere.
Utfallet av dette prosjektet har stor betydning, ikke bare for kostnadene med og resultatene av den aktuelle undergrunns-aktiviteten, men også for miljø og klima gjennom mindre forurensing, bedre energiutnyttelse og lavere utslipp av klimagasser.
The project outcomes include:
• New methodology and tools for knowledge extraction from available well data (pressure and rate) via advanced interpretation combining model- and data-driven approaches.
• New tools for increasing the knowledge via active well surveys and automated solutions to optimize well control for improved well performance and safe operations.
• Testing of the tools and solutions in the mature (O&G) industry with transferring to the emerging industries such as geothermal and CCS.
The project focused on injection operations as the main application area, while addressing production wells may be a natural extension and the scope for a follow-up project. The main impact of the project outcomes consists in automating interpretation of the well monitoring datasets acquired in the industry using the new methodology and tools described above. Further integration of the tools within the industry workflows will provide a breakthrough in monitoring and optimizing well performance via reduced human intervention, ability to address large well monitoring datasets in a reasonable time-frame to take timely and well-informed decisions. In addition, analysis of big historical datasets using the tools will provide valuable information for reservoir management and can help to improve prediction capabilities of reservoir simulations. The project has also confirmed the feasibility of automated well control, a new page in the reservoir engineering book, where the progress in real-time well surveillance led to an ability to monitor and optimize wells on-the-fly. The methodology and tools developed should facilitate significant improvement of injection operations in the O&G industry as the main application area as well as the emerging industries such as geothermal and CCS.
Potential impact of the outcomes combines:
• Improved efficiency and economics of O&G, geothermal and CCS operations via reduced well surveillance and intervention costs and prevention of performance issues.
• Reduction of energy used by turbines for compression and pumps and reduction of CO2 emissions via optimizing water injection and re-circulation in O&G.
• Decreasing environmental footprint of well operations in all the industries above via reservoir containment control and optimized injection.
Well surveillance and control remain key issues for industries like oil and gas (O&G), geothermal, geological carbon storage (CCS) and compressed air energy storage (CAES). Significant progress with real-time well measurements and automated data gathering has recently been achieved, while interpretation and well control optimization remain labour and time-consuming work mainly done manually.
The project aims at development and testing of a new methodology and tool (prototype software) for automated injection well monitoring and control based on real-time pressure, temperature and rate data. The basis is time-lapse Pressure Transient Analysis (PTA) providing capabilities to monitor well performance and interference, containment of injected fluids and safety of abandoned wells. Modern gauges provide high frequency and resolution data, however some challenges are unresolved. The project will focus on these challenges including recognition of well and reservoir response from noisy / biased data, interpretation of low-amplitude changes and combination with other transients like temperature. A separate issue is real-time data interpretation needed to optimize well control.
Advanced interpretation and automation will be achieved via combining model- (time-lapse PTA) and data- (big data analytics / machine learning) driven approaches. Real field data will guide the project tasks and priorities and serve as a testing and application environment for the research and development. Automated well monitoring and warning system will be integrated with injection well control. The control includes rate changes designed to send signals with real-time interpretation of the response (on-the-fly well testing) to optimize well performance and inter-well communication and prevent injection safety issues.
The automated solution developed in the project will reduce costs, improve efficiency and minimize environmental footprint in O&G and facilitate CCS, CAES and geothermal industries.
