Drilling trouble prediction using stand-pipe-pressure real-time estimation
Raw, real-time drilling data is pulled from a centralized database for processing. The raw, real-time drilling data is re-formatted into a format required for processing by one or more predictive models. Real-time processing is performed with respect to one or more drilling parameters associated with the re-formatted data using the one or more predictive models to generate output data. The output data received from the one or more predictive models is re-formatted for storage in the centralized database. The reformatted output data is retrieved from the centralized database for analysis with respect to visualization, generating alerts, or generating recommendations.
1. A computer-implemented method, comprising:
pulling raw, real-time drilling data from a centralized database for processing;
re-formatting the raw, real-time drilling data according to a format required for processing by one or more predictive models;
performing real-time processing with respect to one or more drilling parameters associated with the re-formatted data using the one or more predictive models to generate output data, wherein the real-time processing comprises:
identifying a time interval during which mud flow-in values are within a fluctuation threshold, wherein the identified interval is divided into a first portion and a second portion;
determining an average value of a stand pipe pressure (SPP) parameter within the first portion of the identified time interval;
determining an extrapolated value of the SPP parameter based on the determined average value of the SPP parameter within the first portion of the identified time interval;
comparing the extrapolated value of the SPP parameter with actual values of the SPP parameter in the second portion of the identified time interval; and
determining an abnormal drilling event based on the comparing;
re-formatting the output data received from the one or more predictive models according to a format used for storage in the centralized database; and
retrieving the re-formatted output data from the centralized database for analysis with respect to visualization, generating alerts, or generating recommendations.
2. The computer-implemented method of claim 1 , further comprising integrating the centralized database with a real-time drilling operation data source.
3. The computer-implemented method of claim 1 , further comprising performing quality control (QC) and quality analysis (QA) on the raw, real-time drilling data.
4. The computer-implemented method of claim 3 , wherein the QC and QA is performed to remove noise from the raw, real-time drilling data.
5. The computer-implemented method of claim 1 , wherein the raw, real-time drilling data is stored in a Wellsite Information Transfer Standard Markup Language (WITSML) format and the format required for processing by one or more predictive models is a comma-separated value (CSV) format.
6. The computer-implemented method of claim 1 , further comprising:
analyzing and classifying the re-formatted data;
performing trend-based analysis on the re-formatted data;
obtaining calculated and predicted values for one or more data parameters; and
pushing the calculated and predicted values for the one or more data parameters to the centralized database.
7. The computer-implemented method of claim 1 , wherein the received output data is re-formatted from a comma-separated value (CSV) format into a Wellsite Information Transfer Standard Markup Language (WITSML) format.
8. A non-transitory, computer-readable medium storing one or more instructions executable by a computer system to perform operations comprising:
pulling raw, real-time drilling data from a centralized database for processing;
re-formatting the raw, real-time drilling data according to a format required for processing by one or more predictive models;
performing real-time processing with respect to one or more drilling parameters associated with the re-formatted data using the one or more predictive models to generate output data, wherein the real-time processing comprises:
identifying a time interval during which mud flow-in values are within a fluctuation threshold, wherein the identified interval is divided into a first portion and a second portion;
determining an average value of a stand pipe pressure (SPP) parameter within the first portion of the identified time interval;
determining an extrapolated value of the SPP parameter based on the determined average value of the SPP parameter within the first portion of the identified time interval;
comparing the extrapolated value of the SPP parameter with actual values of the SPP parameter in the second portion of the identified time interval; and
determining an abnormal drilling event based on the comparing;
re-formatting the output data received from the one or more predictive models according to a format used for storage in the centralized database; and
retrieving the re-formatted output data from the centralized database for analysis with respect to visualization, generating alerts, or generating recommendations.
9. The non-transitory, computer-readable medium of claim 8 , further comprising one or more instructions to integrate the centralized database with a real-time drilling operation data source.
10. The non-transitory, computer-readable medium of claim 8 , further comprising one or more instructions to perform quality control (QC) and quality analysis (QA) on the raw, real-time drilling data.
11. The non-transitory, computer-readable medium of claim 10 , wherein the QC and QA is performed to remove noise from the raw, real-time drilling data.
12. The non-transitory, computer-readable medium of claim 8 , wherein the raw, real-time drilling data is stored in a Wellsite Information Transfer Standard Markup Language (WITSML) format and the format required for processing by one or more predictive models is a comma-separated value (CSV) format.
13. The non-transitory, computer-readable medium of claim 8 , further comprising one or more instructions to:
analyze and classify the re-formatted data;
perform trend-based analysis on the re-formatted data;
obtain calculated and predicted values for one or more data parameters; and
push the calculated and predicted values for the one or more data parameters to the centralized database.
14. The non-transitory, computer-readable medium of claim 8 , wherein the received output data is re-formatted from a comma-separated value (CSV) format into a Wellsite Information Transfer Standard Markup Language (WITSML) format.
15. A computer-implemented system, comprising:
one or more computers; and
one or more computer memory devices interoperably coupled with the one or more computers and having tangible, non-transitory, machine-readable media storing one or more instructions that, when executed by the one or more computers, perform one or more operations comprising:
pulling raw, real-time drilling data from a centralized database for processing;
re-formatting the raw, real-time drilling data according to a format required for processing by one or more predictive models;
performing real-time processing with respect to one or more drilling parameters associated with the re-formatted data using the one or more predictive models to generate output data, wherein the real-time processing comprises:
identifying a time interval during which mud flow-in values are within a fluctuation threshold, wherein the identified interval is divided into a first portion and a second portion;
determining an average value of a stand pipe pressure (SPP) parameter within the first portion of the identified time interval;
determining an extrapolated value of the SPP parameter based on the determined average value of the SPP parameter within the first portion of the identified time interval;
comparing the extrapolated value of the SPP parameter with actual values of the SPP parameter in the second portion of the identified time interval; and
determining an abnormal drilling event based on the comparing;
re-formatting the output data received from the one or more predictive models according to a format used for storage in the centralized database; and
retrieving the re-formatted output data from the centralized database for analysis with respect to visualization, generating alerts, or generating recommendations.
16. The computer-implemented system of claim 15 , further comprising one or more operations to integrate the centralized database with a real-time drilling operation data source.
17. The computer-implemented system of claim 15 , further comprising one or more operations to perform quality control (QC) and quality analysis (QA) on the raw, real-time drilling data, and wherein the QC and QA is performed to remove noise from the raw, real-time drilling data.
18. The computer-implemented system of claim 15 , wherein the raw, real-time drilling data is stored in a Wellsite Information Transfer Standard Markup Language (WITSML) format and the format required for processing by one or more predictive models is a comma-separated value (CSV) format.
19. The computer-implemented system of claim 15 , further comprising one or more operations to:
analyze and classify the re-formatted data;
perform trend-based analysis on the re-formatted data;
obtain calculated and predicted values for one or more data parameters; and
push the calculated and predicted values for the one or more data parameters to the centralized database.
20. The computer-implemented system of claim 15 , wherein the received output data is re-formatted from a comma-separated value (CSV) format into a Wellsite Information Transfer Standard Markup Language (WITSML) format.