Method and system to analyse pipeline condition

1. A method for analyzing a condition of a pipeline in real time, comprising:

generating a transient pressure wave in fluid carried along the pipeline;

detecting a transient pressure wave interaction signal responsive to the transient pressure wave, the transient pressure wave interaction signal having a time duration corresponding to a region of interest of the pipeline; and

processing the transient pressure wave interaction signal to analyze the region of interest of the pipeline, wherein processing the transient pressure wave interaction signal comprises:

downsampling in the time domain the transient pressure wave interaction signal to generate a downsampled time window of pressure information;

processing the downsampled time window of pressure information by an artificial neural network (ANN) trained to identify a hydraulic feature of a first type and determine associated hydraulic feature characteristics of the hydraulic feature of the first type; and

verifying whether the hydraulic feature of the first type occurs in the region of interest of the pipeline.

2. The method of claim 1 , wherein verifying whether the hydraulic feature of the first type occurs in the region of interest comprises determining whether one or more of the determined associated hydraulic feature characteristics of the hydraulic feature of the first type are within physical constraints of the pipeline.

3. The method of claim 1 , wherein verifying whether the hydraulic feature of the first type occurs in the region of interest, comprises:

numerically generating a transient pressure wave interaction signal based on the hydraulic feature of the first type and the associated determined hydraulic feature characteristics;

comparing the numerically generated transient pressure wave interaction signal with the detected transient pressure wave interaction signal to verify that the hydraulic feature of the first type occurs in the region of interest.

4. The method of claim 1 , further comprising:

processing the downsampled time window of pressure information by an artificial neural network (ANN) trained to determine a hydraulic feature of a second type and determine associated hydraulic feature characteristics of the hydraulic feature of the second type; and

verifying whether the hydraulic feature of the second type occurs in the region of interest of the pipeline.

5. The method of claim 4 , wherein verifying whether a hydraulic feature of the second type occurs in the region of interest comprises determining whether one or more associated determined hydraulic feature characteristics of the hydraulic feature of the second type are within physical constraints of the pipeline.

6. The method of claim 4 , wherein verifying whether a hydraulic feature of the second type occurs comprises:

numerically generating a transient pressure wave interaction signal based on the hydraulic feature of the second type and the associated determined hydraulic feature characteristics; and

comparing the numerically generated transient pressure wave interaction signal with the detected transient pressure wave interaction signal to verify that the hydraulic feature of the second type occurs in the region of interest.

7. The method of claim 1 , wherein verifying whether a hydraulic feature of a selected type occurs comprises:

numerically generating a transient pressure wave interaction signal based on the hydraulic feature of the selected type and the associated determined hydraulic feature characteristics of the hydraulic feature of the selected type;

downsampling in the time domain the numerically generated transient pressure wave interaction signal to determine a numerically generated downsampled time window of pressure information; and

comparing the numerically generated downsampled time window of pressure information with the generated downsampled time window of pressure information to verify that the hydraulic feature of the selected type occurs in the region of interest.

8. The method of claim 1 , wherein an associated hydraulic feature characteristic includes a location of the hydraulic feature.

9. The method of claim 1 , wherein an ANN trained to identify a hydraulic feature of a selected type and determine associated hydraulic feature characteristics of the hydraulic feature of the selected type is trained by:

selecting a range of values of the associated hydraulic feature characteristics of the hydraulic feature of the selected type;

numerically generating respective transient pressure wave interaction signals for the range of values of the hydraulic feature characteristics based on a hydrodynamic model of the pipeline;

downsampling in the time domain the respective transient pressure wave interaction signals to form respective downsampled time windows of pressure information each having a size or dimension corresponding to an input dimension of the ANN; and

training the ANN to identify the hydraulic feature of the selected type and determine the associated values of the hydraulic feature characteristics based on each of the downsampled time windows of pressure information and corresponding values of the hydraulic feature characteristics used to generate the downsampled time window of pressure information.

10. The method of claim 9 , wherein training the ANN to identify the hydraulic feature of the selected type and determine the associated values of the hydraulic feature characteristics comprises training the ANN using one or more empirically measured downsampled time windows of pressure information and corresponding values of the hydraulic feature characteristics originating from the hydraulic feature of the selected type.

11. A system for analyzing the condition of a pipeline, the system including:

a transient pressure wave generator for generating a transient pressure wave in fluid carried along the pipe;

a pressure detector for detecting a transient pressure wave interaction signal having a time duration corresponding to a region of interest of the pipeline; and

an analysis module comprising one or more data processors for processing in real-time the transient pressure wave interaction signal to analyze the region of interest of the pipeline, wherein processing the transient pressure wave interaction signal by the analysis module comprises:

downsampling in the time domain the transient pressure wave interaction signal to generate a downsampled time window of pressure information;

processing the downsampled time window of pressure information by an artificial neural network (ANN) trained to identify a hydraulic feature of a first type and determine associated hydraulic feature characteristics of the hydraulic feature of the first type; and

verifying whether the hydraulic feature of the first type occurs in the region of interest of the pipeline.

12. The system of claim 11 , wherein verifying by the analysis module whether the hydraulic feature of the first type occurs in the region of interest comprises determining whether one or more of the determined associated hydraulic feature characteristics of the hydraulic feature of the first type are within physical constraints of the pipeline.

13. The system of claim 11 , wherein verifying by the analysis module whether the hydraulic feature of the first type occurs in the region of interest comprises:

numerically generating a transient pressure wave interaction signal based on the hydraulic feature of the first type and the associated determined hydraulic feature characteristics;

comparing the numerically generated transient pressure wave interaction signal with the detected transient pressure wave interaction signal to verify that the hydraulic feature of the first type occurs in the region of interest.

14. The system of claim 11 , further comprising:

processing by the analysis module the downsampled time window of pressure information by an artificial neural network (ANN) trained to determine a hydraulic feature of a second type and determine associated hydraulic feature characteristics of the hydraulic feature of the second type; and

verifying by the analysis module whether the hydraulic feature of the second type occurs in the region of interest of the pipeline.

15. The system of claim 14 , wherein verifying by the analysis module whether a hydraulic feature of the second type occurs in the region of interest comprises determining whether one or more associated determined hydraulic feature characteristics of the hydraulic feature of the second type are within physical constraints of the pipeline.

16. The system of claim 14 , wherein verifying by the analysis module whether a hydraulic feature of the second type occurs comprises:

numerically generating a transient pressure wave interaction signal based on the hydraulic feature of the second type and the associated determined hydraulic feature characteristics; and

comparing the numerically generated transient pressure wave interaction signal with the detected transient pressure wave interaction signal to verify that the hydraulic feature of the second type occurs in the region of interest.

17. The system of claim 11 , wherein verifying by the analysis module whether a hydraulic feature of a selected type occurs comprises:

numerically generating a transient pressure wave interaction signal based on the hydraulic feature of the selected type and the associated determined hydraulic feature characteristics of the hydraulic feature of the selected type;

downsampling in the time domain the numerically generated transient pressure wave interaction signal to determine a numerically generated downsampled time window of pressure information; and

comparing the numerically generated downsampled time window of pressure information with the generated downsampled time window of pressure information to verify that the hydraulic feature of the selected type occurs in the region of interest.

18. The system of claim 11 , wherein an associated hydraulic feature characteristic includes a location of the hydraulic feature.

19. The system of claim 11 , wherein an ANN trained to identify a hydraulic feature of a selected type and determine associated hydraulic feature characteristics of the hydraulic feature of the selected type is trained by:

selecting a range of values of the associated hydraulic feature characteristics for the hydraulic feature of the selected type;

numerically generating respective transient pressure wave interaction signals for the range of values of the hydraulic feature characteristics based on a hydrodynamic model of the pipeline;

downsampling in the time domain the respective transient pressure wave interaction signals to form respective downsampled time windows of pressure information each having a size or dimension corresponding to an input dimension of the ANN; and

training the ANN to identify the hydraulic feature of the selected type and determine the associated values of the hydraulic feature characteristics based on each of the downsampled time windows of pressure information and the corresponding values of the hydraulic feature characteristics used to generate the downsampled time window of pressure information.

20. The system of claim 19 , wherein training the ANN to identify the hydraulic feature of the selected type and determine the associated values of the hydraulic feature characteristics comprises training the ANN using one or more empirically measured downsampled time windows of pressure information and corresponding values of the hydraulic feature characteristics originating from the hydraulic feature of the selected type.