Pipeline sensor integration for product mapping

Patent metadata

Field	Value
Publication number	US-11651278-B2
Application number	US-201916725414-A
Country	US
Kind code	B2
Filing date	Dec 23, 2019
Priority date	Dec 23, 2019
Publication date	May 16, 2023
Grant date	May 16, 2023

Abstract

An automated method of pipeline sensor integration for product mapping of a pipeline network is provided. The method includes acquiring, by a plurality of sensors of the pipeline network, first sensor responses of a pipeline in the pipeline network when a first hydrocarbon product is flowing through the pipeline. The method further includes using a prediction circuit to receive the acquired first sensor responses, integrate the received first sensor responses into one or more integrated first sensor responses in order to improve accuracy of the received first sensor responses, and identify the first hydrocarbon product in the pipeline based on the integrated first sensor responses. The prediction circuit is built from training data using a machine learning process. The training data includes first training sensor responses of the pipeline by the plurality of sensors acquired at a previous time when the first hydrocarbon product was flowing through the pipeline.

First claim

What is claimed is:

1. An automated method of pipeline sensor integration for liquid product mapping of a pipeline network, the method comprising:
acquiring, by a plurality of sensors of the pipeline network, first training sensor responses of a pipeline in the pipeline network when a first liquid hydrocarbon product is flowing through the pipeline;
building, by a machine learning circuit, a prediction circuit from the acquired first training sensor responses using a machine learning process;
acquiring, by the plurality of sensors, first sensor responses of the pipeline when the first liquid hydrocarbon product is again flowing through the pipeline;
receiving, by the built prediction circuit, the acquired first sensor responses;
integrating, by the prediction circuit, the received first sensor responses into one or more integrated first sensor responses in order to improve accuracy of the received first sensor responses; and
identifying, by the prediction circuit, the first liquid hydrocarbon product in the pipeline based on the integrated first sensor responses.

2. The method of claim 1 , further comprising:
detecting, by the prediction circuit, a leak in the pipeline based on the integrated first sensor responses; and
alerting, by the prediction circuit, an operator of the pipeline network about the detected leak.

3. The method of claim 1 , further comprising:
predicting, by the prediction circuit, a first arrival time of the first liquid hydrocarbon product at a group of one or more valves of the pipeline network based on the integrated first sensor responses, the valve group being for directing liquid hydrocarbon products in the pipeline network to their corresponding destinations; and
controlling, by the prediction circuit, the valve group to a first position at the predicted first arrival time based on the identified first liquid hydrocarbon product.

4. The method of claim 1 , further comprising:
predicting, by the prediction circuit, an arrival time of the first liquid hydrocarbon product at a location in the pipeline network based on the integrated first sensor responses; and
alerting, by the prediction circuit, an operator of the pipeline network about the predicted arrival time.

5. The method of claim 1 , further comprising:
acquiring, by the plurality of sensors, second training sensor responses of the pipeline when a second liquid hydrocarbon product different than the first liquid hydrocarbon product is flowing through the pipeline, wherein the machine learning circuit builds the prediction circuit from the acquired first and second training sensor responses;
acquiring, by the plurality of sensors, second sensor responses of the pipeline when the second liquid hydrocarbon product is again flowing through the pipeline, wherein the flowing of the second liquid hydrocarbon product through the pipeline and corresponding to the acquired second sensor responses follows the flowing of the first liquid hydrocarbon product through the pipeline and corresponding to the acquired first sensor responses;
receiving, by the prediction circuit, the acquired second sensor responses;
integrating, by the prediction circuit, the received second sensor responses into one or more integrated second sensor responses in order to improve accuracy of the received second sensor responses; and
identifying, by the prediction circuit, the second liquid hydrocarbon product in the pipeline based on the integrated second sensor responses.

6. The method of claim 5 , further comprising:
predicting, by the prediction circuit, a first arrival time of the first liquid hydrocarbon product at a group of one or more valves of the pipeline network based on the integrated first sensor responses, the valve group being for directing liquid hydrocarbon products in the pipeline network to their corresponding destinations;
controlling, by the prediction circuit, the valve group to a first position at the predicted first arrival time based on the identified first liquid hydrocarbon product;
predicting, by the prediction circuit, a second arrival time of the second liquid hydrocarbon product at the valve group based on the integrated second sensor responses; and
controlling, by the prediction circuit, the valve group to a second position at the predicted second arrival time based on the identified second liquid hydrocarbon product, the second position being different than the first position.

7. The method of claim 6 , wherein both receiving the acquired first sensor responses and receiving the acquired second sensor responses comprise using the Industrial Internet of Things (IIoT), and both controlling the valve group to the first position and controlling the valve group to the second position comprise using the IIoT.

8. The method of claim 5 , further comprising:
acquiring, by the plurality of sensors, third sensor responses of the pipeline when a mixture of the first and second liquid hydrocarbon products is flowing through the pipeline following the first liquid hydrocarbon product and preceding the second liquid hydrocarbon product;
receiving, by the prediction circuit, the acquired third sensor responses;
integrating, by the prediction circuit, the received third sensor responses into one or more integrated third sensor responses in order to improve accuracy of the received third sensor responses; and
identifying, by the prediction circuit, the mixture of the first and second liquid hydrocarbon products in the pipeline based on the integrated third sensor responses.

9. The method of claim 8 , further comprising:
detecting, by the prediction circuit, a liquid product change in the pipeline based on the identified first liquid hydrocarbon product, the identified second liquid hydrocarbon product, and the identified mixture of the first and second liquid hydrocarbon products; and
alerting, by the prediction circuit, an operator of the pipeline network about the detected liquid product change.

10. The method of claim 8 , further comprising:
predicting, by the prediction circuit, a first arrival time of the first liquid hydrocarbon product at a group of one or more valves of the pipeline network based on the integrated first sensor responses, the valve group being for directing liquid hydrocarbon products in the pipeline network to their corresponding destinations;
controlling, by the prediction circuit, the valve group to a first position at the predicted first arrival time based on the identified first liquid hydrocarbon product;
predicting, by the prediction circuit, a third arrival time of the mixture of the first and second liquid hydrocarbon products at the valve group based on the integrated third sensor responses;
controlling, by the prediction circuit, the valve group to a third position at the predicted third arrival time based on the identified mixture of the first and second liquid hydrocarbon products, the third position being different than the first position;
predicting, by the prediction circuit, a second arrival time of the second liquid hydrocarbon product at the valve group based on the integrated second sensor responses; and
controlling, by the prediction circuit, the valve group to a second position at the predicted second arrival time based on the identified second liquid hydrocarbon product, the second position being different than the first and third positions.

11. A system of automated pipeline sensor integration for liquid product mapping of a pipeline network, the system comprising:
a plurality of sensors configured to acquire first training sensor responses of a pipeline in the pipeline network when a first liquid hydrocarbon product is flowing through the pipeline

Assignees

• Saudi Arabian Oil Co

Inventors

• Cunningham Vincent
• Aldabbagh Ahmad
• Patel Sahejad
• Hussain Wesam

Classifications

• G06N3/09

  Supervised learning · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N20/10

  using kernel methods, e.g. support vector machines [SVM] · CPC title

• F17D3/00 Primary

  Arrangements for supervising or controlling working operations · CPC title

• F17D5/02

  Preventing, monitoring, or locating loss · CPC title