IP Library Granted Patent US 9,599,499
Granted Patent B1
US 9,599,499 · App. 14/976,870 · Granted Mar 21, 2017

Linepack delay measurement in fluid delivery pipeline

Inventors: Harsh Chaudhary (Briarcliff Manor, NY); Younghun Kim (White Plains, NY); Tarun Kumar (Mohegan Lake, NY); Abhishek Raman (Santa Clara, CA); Rui Zhang (Ossining, NY)
Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
G01F22/02G01M3/2807H04L43/045H04L67/12
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 9,599,499
App. No.
14/976,870
Granted
Mar 21, 2017
Kind
B1
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.

Claims (62)

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 non-transitory computer readable storage medium, the computer readable storage medium comprising computer executable instructions, wherein the computer readable storage medium comprises instructions 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.

14. The computer program product of claim 13 , 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.

15. The computer program product of claim 14 , 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.

16. The computer program product of claim 13 , 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,

wherein the predetermined measurements comprise an average operating pressure and an average operating flow rate.

17. The computer program product of claim 13 , wherein the second fluid-delivery pipeline network transfers a fluid that is compressed at a compression ratio different than a fluid in the first fluid-delivery pipeline network.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 6, 2017
From: INTERNATIONAL BUSINESS MACHINES CORPORATION
To: UTOPUS INSIGHTS, INC.
Reel/Frame 042700/0530 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 21, 2015
From: CHAUDHARY, HARSH; KIM, YOUNGHUN; KUMAR, TARUN; RAMAN, ABHISHEK; ZHANG, RUI
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 037343/0699 →