Method and System for Validating Energy Measurement in a High Pressure Gas Distribution Network

• US 20140351187A1
• Filed: 04/29/2011
• Published: 11/27/2014
• Est. Priority Date: 06/25/2010
• Status: Active Grant

• Current Assignee: Petroliam Nasional Barhad
• Original Assignee: Petroliam Nasional Barhad
• Inventors: Halim, M. Huzainy B., Ibrahim, Rosdiazli, Ismail, Idris, Ismail, Maryam Jamela
• Granted Patent: US 9,430,734 B2
• Time in Patent Office: Days
• US Class Current: 706/21
• CPC Class Codes: F17D 1/04 for distribution of gas
• CPC Class Codes: F17D 3/01 for controlling, signalling, or supervising the conveyance of a product
• CPC Class Codes: F17D 3/18 for measuring the quantity of conveyed product measuring volume or volume flow, in general G01F
• CPC Class Codes: F17D 5/005 of gas pipelines, e.g. alarm
• CPC Class Codes: G01K 17/00 Measuring quantity of heat measuring temperature by calorimetry G01K3/00 - G01K11/00; specially adapted for measuring thermal properties of materials, e.g. specific heat, heat of combustion G01N
• CPC Class Codes: G01N 33/225 Gaseous fuels, e.g. natural gas
• CPC Class Codes: G06N 3/02 Neural networks

Abstract

A method and system for validating energy measurement in a high pressure gas distribution network. The method comprises the steps of calculating a validation energy value using an artificial neural network (ANN) engine based on measured parameters associated with a gas flow in the gas distribution network; measuring an actual energy value of the gas flow; and comparing the validation energy value and the actual energy value, wherein the actual energy value is validated if the validation energy value and the actual energy value are substantially equal.

Claims

1. A method for validating energy measurement in a high pressure gas distribution network, the method comprising the steps of:

calculating a validation energy value using an artificial neural network (ANN) engine based on measured parameters associated with a gas flow in the gas distribution network;

measuring a field energy value of the gas flow; and

comparing the validation energy value and the measured energy value, wherein the measured energy value is validated if the validation energy value and the measured energy value are substantially equal.

2. The method as claimed in claim 1, wherein the ANN engine is programmed to represent an energy value prediction model based on the measured parameters.

3. The method as claimed in claim 1, wherein the measured parameters comprise a gross volume, a pressure, a temperature, a specific gravity, and a calorific value of the gas flow.

4. The method as claimed in claim 1, wherein the ANN engine comprises a multilayered perceptron network structure.

5. The method as claimed in claim 1, further comprising determining a percentage difference between the validation energy value and the measured energy value.

6. The method as claimed in claim 5, further comprising identifying an alarm event based on the percentage difference exceeding a threshold.

7. The method as claimed in claim 1, comprising providing the measured parameters as a block of data comprising respective sets of the measured parameters and respective measured energy values over a selected time period;

calculating respective validation energy values based on the respective sets of the measured parameters; and

plotting both the measured energy values and the calculated validation energy values.

8. The method as claimed in claim 1, further comprising learning the energy value prediction model.

9. The method as claimed in claim 8, wherein the learning comprises:

providing historical data for the measured parameters and the measured energy value; and

applying a learning algorithm to the ANN engine based on the historical data.

10. The method as claimed in claim 9, wherein providing the historical data comprises scaling the historical data for statistical standardization.

11. A system for validating energy measurement in a high pressure gas distribution network, comprising:

means for calculating a validation energy value using an artificial neural network (ANN) engine based on measured parameters associated with a gas flow in the gas distribution network;

means for measuring a field energy value of the gas flow; and

means for comparing the validation energy value and the measured energy value, wherein the measured energy value is validated if the validation energy value and the measured energy value are substantially equal.

12. The system as claimed in claim 11, wherein the ANN engine is programmed to represent an energy value prediction model based on the measured parameters.

13. The system as claimed in claim 11, wherein the measured parameters comprise a gross volume, a pressure, a temperature, a specific gravity, and a calorific value of the gas flow.

14. The system as claimed in claim 11, wherein the ANN engine comprises a multilayered perceptron network structure.

15. The system as claimed in claim 11, further comprising means for determining a percentage difference between validation energy value and the measured energy value.

16. The system as claimed in claim 15, further comprising means for identifying an alarm event based on the percentage difference exceeding a threshold.

17. The system as claimed in claim 11, comprising:

means for providing the measured parameters as a block of data comprising respective sets of the measured parameters and respective measured energy values over a selected time period;

means for calculating respective validation energy values based on the respective sets of the measured parameters; and

means for plotting both the measured energy values and the calculated validation energy values.

18. The system as claimed in claim 11, further comprising means for learning the energy value prediction model.

19. The system as claimed in claim 18, wherein the means for learning comprises:

means for providing historical data for the measured parameters and the measured energy value; and

means for applying a learning algorithm to the ANN engine based on the historical data.

20. The system as claimed in claim 19, wherein means for providing the historical data comprises means for scaling the historical data for statistical standardization.

21. A data storage medium comprising computer code for instructing a computing device to execute a method for validating energy measurement in a high pressure gas distribution network, the method comprising the steps of:

calculating a validation energy value using an artificial neural network (ANN) engine based on measured parameters associated with a gas flow in the gas distribution network;

measuring a field energy value of the gas flow; and

comparing the validation energy value and the measured energy value, wherein the measured energy value is validated if the validation energy value and the measured energy value are substantially equal.