Well site machine learning based analytics

Patent metadata

Field	Value
Publication number	US-12398718-B2
Application number	US-202017018730-A
Country	US
Kind code	B2
Filing date	Sep 11, 2020
Priority date	Sep 12, 2019
Publication date	Aug 26, 2025
Grant date	Aug 26, 2025

Abstract

Systems and methods for real-time monitoring and control of well operations at a well site use machine learning (ML) based analytics at the well site. The systems and methods perform ML-based analytics on data from the well site via an edge device directly at the well site to detect operations that fall outside expected norms and automatically respond to such abnormal operations. The edge device can issue alerts regarding the abnormal operations and take predefined steps to reduce potential damage resulting from such abnormal operations. The edge device can also anticipate failures and a time to failure by performing ML-based analytics on operations data from the well site using normal operations data. This can help decrease downtime and minimize lost productivity and cost as well as reduce health and safety risks for field personnel.

First claim

We claim:

1. A method of monitoring well site operations, comprising:
receiving well site data from a remote terminal unit (RTU) at the well site, the well site data being received from the RTU in the form of dynagraphs;
generating images for the dynagraphs, each image composed of pixels;
performing machine learning (ML) based analytics on an edge device at the well site using the images, the edge device operable to provide access or entry to a network for the well site, the network including a local area network (LAN), a wide area network (WAN), or a metropolitan area network (MAN);
identifying dynagraph classifications for the images of the dynagraphs on the edge device for the well site operations from the ML-based analytics; and
initiating a responsive action on the edge device based on the one or more dynagraph classifications, the responsive action including at least one of logging a date and time, sending an alert message to a control system, adjusting a motor speed of a rod pump, or shutting off power to the rod pump, depending on a severity of the one or more dynagraph classifications;
wherein the edge device is one of a gateway, a router, a routing switch, or an integrated access device (IAD).

2. The method of claim 1 , wherein the well site operations include artificial lift operations performed by a rod pump assembly at the well site, and the dynagraph classifications include one or more of: “fluid pound,” “gas interference,” “gas lock,” “normal,” “plunger stuck,” “solids grinding,” “solids in pump,” and “worn pump”.

3. The method of claim 2 , wherein the ML-based analytics is performed using ML models, the ML models being deployed on the edge device in a standalone container.

4. The method of claim 3 , wherein performing ML-based analytics includes inputting the well site data into one or more ML models.

5. The method of claim 4 , wherein performing ML-based analytics further includes inputting an output from each of the one or more ML models into at least one Ensemble model.

6. The method of claim 5 , wherein the one or more ML models and the Ensemble model are trained using historical data, further comprising generating augmented training data using the historical data.

7. The method of claim 6 , wherein identifying one or more dynagraph classifications includes providing a probability for each of the one or more dynagraph classifications.

8. The method of claim 1 , further comprising allowing an operator to accept or reject each of the one or more dynagraph classifications.

9. The method of claim 8 , further comprising allowing the operator to provide an alternative dynagraph classification for each of the one or more dynagraph classifications that is rejected.

10. The method of claim 9 , further comprising performing Transfer Learning using the alternative dynagraph classification provided by the operator.

11. An edge device installed at a well site and operable to monitor well site operations, comprising:
a processor; and
a storage device coupled to the processor and storing computer-readable instructions for a well site monitoring and control application thereon;
wherein the edge device is operable to provide access or entry to a network for the well site, the network including a local area network (LAN), a wide area network (WAN), or a metropolitan area network (MAN); and
wherein the well site monitoring and control application, when executed by the processor, causes the edge device to:
receive well site data from a remote terminal unit (RTU) at the well site, the well site data being received from the RTU in the form of dynagraphs;
generate images for the dynagraphs, each image composed of pixels;
perform machine learning (ML) based analytics on an edge device at the well site using the images;
identify one or more dynagraph classifications for the images of the dynagraphs on the edge device for the well site operations from the ML-based analytics; and
initiate a responsive action on the edge device based on the one or more dynagraph classifications, the responsive action including at least one of logging a date and time, sending an alert message to a control system, adjusting a motor speed of a rod pump, or shutting off power to the rod pump, depending on a severity of the one or more dynagraph classifications;
wherein the edge device is one of a gateway, a router, a routing switch, or an integrated access device (IAD).

12. The edge device of claim 11 , wherein the well site operations include artificial lift operations performed by a rod pump assembly at the well site, and the dynagraph classifications include one or more of: “fluid pound,” “gas interference,” “gas lock,” “normal,” “plunger stuck,” “solids grinding,” “solids in pump,” and “worn pump”.

13. The edge device of claim 12 , wherein the ML-based analytics is performed using ML models, the ML models being deployed on the edge device in a standalone container.

14. The edge device of claim 13 , wherein the well site monitoring and control application causes the edge device to perform ML-based analytics by inputting the well site data into one or more ML models.

15. The edge device of claim 14 , wherein the well site monitoring and control application causes the edge device to further perform ML-based analytics by inputting an output from each of the one or more ML models into at least one Ensemble model.

16. The edge device of claim 15 , wherein the one or more ML models and the Ensemble model are trained using historical data, further comprising generating augmented training data using the historical data.

17. The edge device of claim 16 , wherein the well site monitoring and control application causes the edge device to identify one or more dynagraph classifications by providing a probability for each of the one or more dynagraph classifications.

18. The edge device of claim 11 , wherein the well site monitoring and control application causes the edge device to allow an operator to accept or reject each of the one or more dynagraph classifications.

19. The edge device of claim 18 , wherein the well site monitoring and control application causes the edge device to further allow the operator to provide an alternative dynagraph classification for each of the one or more dynagraph classifications that is rejected.

20. The edge device of claim 19 , wherein the well site monitoring and control application causes the edge device to perform Transfer Learning using the alternative dynagraph classification provided by the operator.

Assignees

• Schneider Electric Systems Usa Inc

Inventors

• Boguslawski Bartosz
• Boujonnier Matthieu
• Beauvais Loryne Bissuel
• Saghir Fahd
• Gilabert Helenio

Classifications

• G06F18/2415

  based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate · CPC title

• G05B2219/24065

  Real time diagnostics · CPC title

• G05B23/0243 Primary

  model based detection method, e.g. first-principles knowledge model · CPC title

• F04B49/065

  and making use of computers · CPC title

• F04B47/02

  the driving mechanisms being situated at ground level (F04B47/12 takes precedence) · CPC title