US US20180240021A1

A concise summary of U.S. Patent Application Publication No. US20180240021A1, which has been granted as U.S. Patent No. 11,087,221 B2, is provided below.

Title: Well performance classification using artificial intelligence and pattern recognition

Assignee: Saudi Arabian Oil Company

Inventors: Badr M. Al-Harbi, Amell Ali Al-Ghamdi, Ali A. Al-Turki

Filing Date: February 20, 2017

Issue Date: August 10, 2021

Abstract:
A heterogeneous classifier based on actual reservoir and well data is developed to qualitatively classify oil well producer performance, and based on the classification drill a new well into a producing reservoir or adjust fluid flows in an existing well. The data includes perforation interval(s), completion type, and how far or close the perforated zones are located relative to the free water level or gas cap. The data also include geological data, such as major geological bodies like regional faults and fractures. The features may be prioritized before classification. The classifier utilizes four different techniques to apply pattern recognition on reservoir simulation vector data to classify the wells. Three of the classification techniques are supervised learning methods: Bayesian classification, dynamic time warping and Neural Network. The fourth classification is an unsupervised method, clustering, to automate well grouping into similar categories.

Overview of Independent Claims:

This patent has three independent claims, each directed to a different aspect of the invention: a method, a data processing system, and a data storage device.

Independent Claim 1 (Method): This claim outlines a method for deciding whether to drill a new well in a hydrocarbon reservoir. The process begins by feeding proposed well parameters, such as production rates and its physical configuration and location, into a data processing system. The system then creates a "classification model" that predicts fluid production, flow, and pressure. Using this model, a probabilistic estimate of the target well's production rates is generated. If this estimate is deemed acceptable, the well is then physically drilled in the reservoir.

Independent Claim 8 (Data Processing System): This claim describes a data processing system designed to carry out the method of the first claim. It specifies a system with a processor that receives the proposed well parameters. The processor is configured to build the classification model and then calculate the probabilistic estimate of the well's production rates. The system also includes an output display that indicates whether the estimated production rates are acceptable for proceeding with the drilling of the well.

Independent Claim 15 (Data Storage Device): This claim covers a non-transitory computer-readable storage medium (such as a hard drive or flash memory) that contains instructions for a data processing system. When these instructions are executed, they cause the system to perform the same essential steps as the method claim: receiving well parameters, creating a classification model, generating a probabilistic production estimate, and displaying whether the result is acceptable for drilling a new well.

A search of the U.S. Court of Appeals for the Federal Circuit (CAFC) dockets for 2026 did not reveal any cases associated with US20180240021A1 or its granted counterpart, US11087221B2.