Water Flooding Performance Prediction in Layered Heavy Oil Reservoir

Abstract

Abstract Prediction of oilfield development data is one of the important technical indicators for oilfields to achieve maximum economic benefits. Numerical simulation method is the most commonly used method. However it has been widely used with a long run time and too much information to solve this problem. With the continuous development of big data technology and artificial intelligence technology, there is an urgent need to form a development index prediction method based on such technologies. This paper proposed a new method to predict water flooding performance in layered reservoir. The method regards layered reservoir as a vertical superposition of a series of single layer reservoirs. An injection-production analysis model is established in each single layer reservoir respectively, which considers invasion of natural water and the start-up pressure gradient of heavy oil reservoir. And then a composite model is established only by production data. Finally, the least square principle and artificial intelligence algorithm are used to optimize the model. Then the Gentil's correlation method is used to predict production performance. As development progresses, the production data became more and more abundant, and they replaced the model and re-optimized it. Oilfield applications showed that this technique has capability to predict oil performance in layered reservoir.