Abhishek Raman

US Patent:

20200387119, Dec 10, 2020

Filed:

Mar 10, 2020

Appl. No.:

16/814388

Inventors:

- Valhalla NY, US
Younghun Kim - White Plains NY, US
Tarun Kumar - Mohegan Lake NY, US
Abhishek Raman - Santa Clara CA, US
Rui Zhang - Ossining NY, US

Assignee:

Utopus Insights, Inc. - Valhalla NY

International Classification:

G05B 13/02
G01F 22/02
H04L 12/26
H04L 29/08
G01M 3/28
G05D 7/06

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.

US Patent:

20170308834, Oct 26, 2017

Filed:

Apr 22, 2016

Appl. No.:

15/135726

Inventors:

- ARMONK NY, US
Abhishek Raman - Santa Clara CA, US
Chandramouli Visweswariah - Croton-on-Hudson NY, US

International Classification:

G06Q 10/06
G06F 17/30
G06F 17/30

Abstract:

A method for assessing an asset status is provided. The method may include identifying, by a processor, an asset within a plurality of tangible, deployed assets. The method may also include retrieving a plurality of images from at least one data repository, whereby the plurality of images are captured within a preconfigured distance of the identified asset. The method may further include determining a portion of the retrieved plurality of images depict the identified asset. The method may also include performing a plurality of image processing techniques on the determined portion. The method may further include creating an assessment of the asset status of the identified asset based on the performed plurality of image processing techniques, whereby the created assessment details whether the identified asset needs a repair or a replacement.

US Patent:

20170219454, Aug 3, 2017

Filed:

Jan 28, 2016

Appl. No.:

15/009340

Inventors:

- Armonk NY, US
Younghun Kim - White Plains NY, US
Tarun Kumar - Mohegan Lake NY, US
Abhishek Raman - Santa Clara CA, US
Rui Zhang - Ossining NY, US

International Classification:

G01M 3/28

Abstract:

A method and system method to detect a leak within a pipeline network include measuring pressure at each of a plurality of sensors distributed along the pipeline network as a time-varying pressure signal. Tuning a model is based on gas mass conservation law in the absence of the leak, the tuning including obtaining the time-varying pressure signal from each of the plurality of sensors, and monitoring the time-varying pressure signals is done to detect the leak based on the model.

US Patent:

20170176957, Jun 22, 2017

Filed:

Feb 17, 2017

Appl. No.:

15/436124

Inventors:

- Armonk NY, US
Younghun Kim - White Plains NY, US
Tarun Kumar - Mohegan Lake NY, US
Abhishek Raman - Santa Clara CA, US
Rui Zhang - Ossining NY, US

International Classification:

G05B 13/02
G05D 7/06

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.

US Patent:

20170177008, Jun 22, 2017

Filed:

Feb 9, 2017

Appl. No.:

15/428434

Inventors:

- ARMONK NY, US
Younghun Kim - White Plains NY, US
Tarun Kumar - Mohegan Lake NY, US
Abhishek Raman - Santa Clara CA, US
Rui Zhang - Ossining NY, US

International Classification:

G05D 7/06
G01F 1/00
G05B 15/02
G01M 3/02

Abstract:

Technical solutions are described for determining topological connectivity between stations of a fluid-delivery pipeline network. An example method includes receiving temporal sensor measurements of the fluid-delivery pipeline network, that include a series of sensor measurements from each respective station of the fluid-delivery pipeline network. The method also includes generating a causality graph of the fluid-delivery pipeline network based on the temporal sensor measurements, where the causality graph includes a set of nodes and a set of links, where 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. The method also includes determining a topological network of the stations based on the causality graph, where the topological network identifies one or more destination stations for a supply station in the fluid-delivery pipeline network.

US Patent:

20170178016, Jun 22, 2017

Filed:

Dec 22, 2016

Appl. No.:

15/387900

Inventors:

- ARMONK NY, US
Younghun Kim - White Plains NY, US
Tarun Kumar - Mohegan Lake NY, US
Abhishek Raman - Santa Clara CA, US
Rui Zhang - Ossining NY, US

International Classification:

G06N 7/00
G01M 3/28
G06F 17/18

Abstract:

Technical solutions are described for forecasting leaks in a pipeline network. An example method includes identifying a subsystem in the pipeline network that includes a first station. The method also includes accessing historical temporal sensor measurements of the stations. The method also includes generating a prediction model for the first station that predicts a pressure measurement at the first station based on the historical temporal sensor measurements at each station in the subsystem. The method also includes predicting a series of pressure measurements at the first station based on the historical temporal sensor measurements. The method also includes determining a series of deviations between the series of pressure measurements and historical pressure measurements of the first station and identifying a threshold value from the series of deviations, where a pressure measurement at the first station above or below the threshold value is indicative of a leak in the subsystem.