Linepack delay measurement in fluid delivery pipeline

Patent metadata

Field	Value
Publication number	US-9599499-B1
Application number	US-201514976870-A
Country	US
Kind code	B1
Filing date	Dec 21, 2015
Priority date	Dec 21, 2015
Publication date	Mar 21, 2017
Grant date	Mar 21, 2017

Abstract

Technical solutions are described for predicting linepack delays. An example method includes receiving temporal sensor measurements of a first fluid-delivery pipeline network and generating a causality graph of the first fluid-delivery pipeline network. The method also includes determining a topological network of the stations based on the causality graph, where the topological network identifies a temporal delay between a pair of stations. The method also includes generating a temporal delay prediction model based on the topological network and predicting the linepack delays of a second fluid-delivery pipeline network based on the temporal delay prediction model, where a compressor station of the second fluid-delivery pipeline network compresses fluid based on the predicted linepack delays to maintain a predetermined pressure.

First claim

What is claimed is:

1. A computer implemented method for controlling flow of fluid by predicting linepack delays, the method comprising:
receiving, by a processing unit of a supervisory control and data acquisition system, temporal sensor measurements of a first fluid-delivery pipeline network, wherein the temporal sensor measurements comprises a series of sensor measurements from each respective station from the stations of the fluid-delivery pipeline network;
generating, by the processing unit, a causality graph of the first fluid-delivery pipeline network based on the temporal sensor measurements, wherein the causality graph comprises a set of nodes and a set of links, wherein the nodes are representative of the stations, and a pair of nodes is connected by a link in response to the pair of stations being temporally dependent;
determining, by the processing unit, a topological network of the stations based on the causality graph, wherein the topological network identifies a temporal delay between a pair of stations in the first fluid-delivery pipeline network, wherein determining the topological network comprises:
selecting a node of the causality graph, wherein the selected node corresponds to a supply station of the first fluid-delivery pipeline network;
determining a set of nodes linked to the selected node in the causality graph;
identifying, from the set of nodes, a first node that has the least temporal lag among the set of nodes; and
removing, from the set of nodes, a second node that is linked to the first node;

generating, by the processing unit, a temporal delay prediction model based on the topological network associated with the first fluid-delivery pipeline network;
predicting, by the processing unit, the linepack delays of a second fluid-delivery pipeline network based on the temporal delay prediction model generated using the first fluid-delivery pipeline network, wherein the second fluid-delivery pipeline network is a non-monitored pipeline network; and

compressing, by a compressor station of the second fluid-delivery pipeline network, fluid being transported by the second fluid-delivery pipeline network based on the predicted linepack delays to maintain at least a predetermined pressure in the second fluid-delivery pipeline network.

2. The computer implemented method of claim 1 , wherein generating the temporal delay prediction model comprises:
identifying values of predetermined attributes of the pair of stations in the first fluid-delivery pipeline network; and
mapping the temporal delay and the values of predetermined attributes associated with the pair of stations in the first fluid-delivery pipeline network.

3. The computer implemented method of claim 2 , wherein the predetermined attributes comprise at least one of a length of a pipeline between the pair of stations, a diameter of the pipeline, an elevation difference of the pipeline between the pair of stations.

4. The computer implemented method of claim 1 , wherein generating the temporal delay prediction model comprises:
computing values of predetermined measurements of the pair of stations in the first fluid-delivery pipeline network; and
mapping the temporal delay and the values of predetermined measurements associated with the pair of stations in the first fluid-delivery pipeline network.

5. The computer implemented method of claim 4 , wherein the predetermined measurements comprise an average operating pressure and an average operating flow rate.

6. The computer implemented method of claim 1 , wherein the first fluid-delivery pipeline network is a first portion of a pipeline network, and the second fluid-delivery pipeline network is a second portion of said pipeline network, wherein the first portion is monitored by a supervisory control and data acquisition system.

7. A supervisory control and data acquisition (SCADA) system for controlling flow of fluid by predicting linepack delays, the SCADA system comprising:
a memory; and
a processor configured to:
receive temporal sensor measurements of a first fluid-delivery pipeline network, wherein the temporal sensor measurements comprises a series of sensor measurements from each respective station from the stations of the fluid-delivery pipeline network;
generate a causality graph of the first fluid-delivery pipeline network based on the temporal sensor measurements, wherein the causality graph comprises a set of nodes and a set of links, wherein the nodes are representative of the stations, and a pair of nodes is connected by a link in response to the pair of stations being temporally dependent;
determine a topological network of the stations based on the causality graph, wherein the topological network identifies a temporal delay between a pair of stations in the first fluid-delivery pipeline network, wherein determining the topological network comprises:
selecting a node of the causality graph, wherein the selected node corresponds to a supply station of the first fluid-delivery pipeline network;
determining a set of nodes linked to the selected node in the causality graph;
identifying, from the set of nodes, a first node that has the least temporal lag among the set of nodes; and
removing, from the set of nodes, a second node that is linked to the first node;

generate a temporal delay prediction model based on the topological network associated with the first fluid-delivery pipeline network;
predict the linepack delays of a second fluid-delivery pipeline network based on the temporal delay prediction model generated using the first fluid-delivery pipeline network, wherein the second fluid-delivery pipeline network is a non-monitored pipeline network; and

compress, by a compressor station of the second fluid-delivery pipeline network, fluid being transported by the second fluid-delivery pipeline network based on the predicted linepack delays to maintain at least a predetermined pressure in the second fluid-delivery pipeline network.

8. The system of claim 7 , wherein generation of the temporal delay prediction model comprises:
identification of values of predetermined attributes of the pair of stations in the first fluid-delivery pipeline network; and
determination of a mapping of the temporal delay and the values of predetermined attributes associated with the pair of stations in the first fluid-delivery pipeline network.

9. The system of claim 8 , wherein the predetermined attributes comprise at least one of a length of a pipeline between the pair of stations, a diameter of the pipeline, an elevation difference of the pipeline between the pair of stations.

10. The system of claim 7 , wherein generation of the temporal delay prediction model comprises:
computation of values of predetermined measurements of the pair of stations in the first fluid-delivery pipeline network; and
determination of a mapping of the temporal delay and the values of predetermined measurements associated with the pair of stations in the first fluid-delivery pipeline network.

11. The system of claim 10 , wherein the predetermined measurements comprise an average operating pressure and an average operating flow rate.

12. The system of claim 7 , wherein the second fluid-delivery pipeline network has physical dimensions identical to the first fluid-delivery pipeline network, and the second fluid-delivery pipeline network transfers a different amount of fluid than the first fluid-delivery pipeline network.

13. A computer program product for facilitating a supervisory control and data acquisition (SCADA) system to control flow of fluid by predicting linepack delays, the computer program product comprising a

Assignees

• IBM

Inventors

• Chaudhary Harsh
• Kim Younghun
• Kumar Tarun
• Raman Abhishek
• Zhang Rui

Classifications

• G01M3/2815

  using pressure measurements · CPC title

• G01M3/2807

  for pipes (G01M3/2892, G01M3/30 take precedence) · CPC title

• G05D7/0682

  using a plurality of flow sources · CPC title

• G05B13/026 Primary

  using a predictor · CPC title

• G05B13/0255

  the criterion being a time-optimal performance criterion · CPC title