Back to results
US 11,536,121 B1Granted
Systems and methods for analyzing resource production
AssigneeDataInfoCom USA, Inc.
InventorsAtanu Basu, Daniel Mohan, Chun Wang, Frederick Venter
Life of this patent
Estimating the term…
Abstract
A method for producing a well includes receiving production information associated with wells within a field; deriving a field specific model from the production information; receiving production information associated with the well; projecting production changes associated with installing artificial lift at the well at a projected date, the projecting using a production analysis engine applied to the field specific model, the projecting including determining a set of artificial lift parameters; and installing the artificial lift at the well in accordance with the artificial lift parameters.
Claims21
A method for producing a well within a field, the method comprising:
- receiving production information associated with one or more additional wells within the field, a first portion of the production information being received in a form of structured data, and a second portion of the production information being received in a form of unstructured data;
- transforming the unstructured data into transformed structured data;
- deriving one or more synthetic variables from the received production information in the form of the structured data and the transformed structured data, wherein the one or more synthetic variables comprise a proximity depletion synthetic variable derived from, at least, distances between and among adjacent wells, time differences between completion with respect to adjacent wells and associated depletion curves;
- based on the one or more synthetic variables and further based on the received production information in the form of the structured data and the transformed structured data, building a plurality of field-specific models, each of the plurality of field-specific models being specific to field characteristics of the field, each of the plurality of field-specific models including one or more machine learning models, each machine learning model comprising one or more of regression models, Markov chains, time series models, state space models, Bayesian models, neural networks, autoregressive integrated moving average (ARIMA) models, seasonal ARIMA (SARIMA) models, autoregressive conditional heteroskedasticity (ARCH) models, generalized autoregressive conditional heteroskedasticity (GARCH) models, and combinations thereof;
- receiving production information associated with the well within the field;
- selecting one of the plurality of field-specific models;
- based on the received production information associated with the well and the selected field-specific model, projecting, using a production analysis engine, production changes associated with installing an artificial lift at the well at a projected date, the production changes including a set of artificial lift parameters;
- and
- installing the artificial lift at the well in accordance with the artificial lift parameters.
6 more elements
A method for maintaining equipment associated with a well within a field, the method comprising:
- receiving production and maintenance information associated with one or more additional wells within the field, a first portion of the production and maintenance information being received in a form of structured data, and a second portion of the production and maintenance information being received in a form of unstructured data;
- transforming the unstructured data into transformed structured data;
- deriving one or more synthetic variables from the received production and maintenance information in the form of the structured data and the transformed structured data, wherein the one or more synthetic variables comprise a proximity depletion synthetic variable derived from, at least, distances between and among adjacent wells, time differences between completion with respect to adjacent wells, and associated depletion curves;
- based on the one or more synthetic variables and further based on the received production and maintenance information in the form of the structured data and the transformed structured data, building a plurality of field-specific models, each of the plurality of field-specific models being specific to field characteristics of the field, each of the plurality of field-specific models including one or more machine learning models, each machine learning model comprising one or more of regression models, Markov chains, time series models, state space models, Bayesian models, neural networks, autoregressive integrated moving average (ARIMA) models, seasonal ARIMA (SARIMA) models, autoregressive conditional heteroskedasticity (ARCH) models, generalized autoregressive conditional heteroskedasticity (GARCH) models, and combinations thereof;
- receiving production information and equipment information associated with the well within the field;
- selecting one of the plurality of field-specific models;
- based on the received production information and equipment information associated with the well and the selected field-specific model, projecting, using a production analysis engine, a maintenance event associated with the equipment associated with the well and an associated projected date;
- and
- performing preventative maintenance on the equipment associated with the well prior to the associated projected date.
6 more elements
Dependencies are inferred from the claim text.