Method and system for unobstrusive automatic leak event detection in real-time conduit by template selection
One of the biggest challenges faced by oil and gas companies is to monitor such long pipelines for leak events and generate false leak event alarms during routine pipe maintenance. A data associated with a first sensing unit is processed to obtain an instant timing information (T 0 ) of a leak event in a conduit at a test environment. A data associated with a second sensing unit is processed to obtain a transient signal associated with the leak event at a specific band. An accelerometer data is filtered to obtain a band passed filtered accelerometer signal (Accel bpf ). The Accel bpf is truncated in a time domain from the T 0 to a duration T d of the leak event to obtain a temporal template signal (Accel template ). A leak event of a real-time conduit is dynamically detected at a physical environment based on Accel template when a cross-correlation value is greater than a threshold value (∝).
1 . A processor implemented method, comprising:
receiving, via one or more hardware processors, data associated with a first sensing unit and a second sensing unit, wherein the first sensing unit and the second sensing unit are placed in a proximity of a conduit at a test environment, wherein the first sensing unit corresponds to a pressure sensor placed inside the conduit at the test environment, for obtaining a pressure data (Pr), and wherein the second sensing unit corresponds to an accelerometer sensor placed on an outer surface of the conduit at the test environment, for obtaining an accelerometer data (Accel);
processing, via the one or more hardware processors, the data associated with the first sensing unit to obtain an instant timing information (T 0 ) of a leak event in the conduit at the test environment, wherein the instant timing information (T 0 ) is obtained by detecting a variation in a steady state of a pressure value of a fluid at the conduit at the test environment;
processing, via the one or more hardware processors, the data associated with the second sensing unit to obtain a transient signal associated with the leak event at a specific band by applying a continuous wavelet transformation (CWT);
filtering, by a bandpass filter, the accelerometer data (Accel) to obtain a band passed filtered accelerometer signal (Accel bpf ) with a low pass cut-off frequency and a high pass cut-off frequency by eliminating unnecessary computations;
processing, via the one or more hardware processors, the band passed filtered accelerometer signal (Accel bpf ) to obtain a duration (T d ) of the leak event;
truncating, via the one or more hardware processors, the band passed filtered accelerometer signal (Accel bpf ) in a time domain from the instant timing information (T 0 ) to the duration (Td) of the leak event to obtain a temporal template signal (Accel template );
receiving, via the one or more hardware processors, data associated with a sensing unit, wherein the sensing unit corresponds to an accelerometer sensor placed on an outer surface of a real-time conduit of a physical environment, for obtaining an accelerometer data and the data is recorded continuously;
filtering, by a bandpass filter, the accelerometer data to obtain a band passed filtered accelerometer signal (Accel bpf ) associated with the real-time conduit with a low pass cut-off frequency and a high pass cut-off frequency;
cross-correlating, via the one or more hardware processors, the band passed filtered accelerometer signal (Accel bpf ) associated with the real-time conduit at the physical environment and the temporal template signal (Accel template ) for every successive window of T 0 to T d length to obtain a cross correlation value; and
dynamically detecting, via the one or more hardware processors, a leak event of the real-time conduit at the physical environment when the cross-correlation value is greater than a threshold value (∝), and communicating an alarm notification thereby reducing a false alarm rate during routine pipe maintenance, wherein when leak occurs a low frequency negative pressure wave (NPW) is generated from a leak orifice and the NPW has low frequency components which travels long distance in both upstream and downstream directions;
isolating, via the one or more hardware processors, the NPW from other vibrational generating events on the real-time conduit based on the cross-correlation value and the threshold value (∝).
2 . The processor implemented method of claim 1 , wherein the conduit at the test environment is constructed based on (a) a pipe diameter, (b) a pipe thickness, (c) a material, (d) a flowing fluid, and (e) a pressure level at the real-time conduit.
3 . The processor implemented method of claim 1 , wherein the threshold value (∝) vary from one setup to another depending upon a pipe diameter and a pipe length.
4 . The processor implemented method of claim 1 , wherein the cross correlation value R 12 (τ) is a measurement of a similarity of two signals X 1 (t) and X 2 (t) and R 12 (τ) is given by:
R 12 (τ)=∫ −∞ ∞ X 1 ( t ) X 2 ( t −τ) dt
where X 1 (t) is the accelerometer data collected from the real-time conduit and X 2 (t) is the Accel template data generated from the conduit at the test environment.
5 . The processor implemented method of claim 1 , wherein the transient signal corresponds to a pressure wavefront travelling through a fluid inside the conduit at the test environment.
6 . A system, comprising:
a memory storing instructions;
one or more communication interfaces; and
one or more hardware processors coupled to the memory via the one or more communication interfaces, wherein the one or more hardware processors are configured by the instructions to:
receive, data associated with a first sensing unit and a second sensing unit, wherein the first sensing unit and the second sensing unit are placed in a proximity of a conduit at a test environment, wherein the first sensing unit corresponds to a pressure sensor placed inside the conduit at the test environment, for obtaining a pressure data (Pr), and wherein the second sensing unit corresponds to an accelerometer sensor placed on an outer surface of the conduit at the test environment, for obtaining an accelerometer data (Accel);
process, the data associated with the first sensing unit to obtain an instant timing information (T 0 ) of a leak event in the conduit at the test environment, wherein the instant timing information (T 0 ) is obtained by detecting a variation in a steady state of a pressure value of a fluid at the conduit at the test environment;
process, the data associated with the second sensing unit to obtain a transient signal associated with the leak event at a specific band by applying a continuous wavelet transformation (CWT);
filter, by a bandpass filter, the accelerometer data (Accel) to obtain a band passed filtered accelerometer signal (Accel bpf ) with a low pass cut-off frequency and a high pass cut-off frequency by eliminating unnecessary computations;
process, the band passed filtered accelerometer signal (Accel bpf ) to obtain a duration (Ta) of the leak event;
truncate, the band passed filtered accelerometer signal (Accel bpf ) in a time domain from the instant timing information (T 0 ) to the duration (Ta) of the leak event to obtain a temporal template signal (Accel template );
receive, data associated with a sensing unit, wherein the sensing unit corresponds to an accelerometer sensor placed on an outer surface of a real-time conduit of a physical environment, for obtaining an accelerometer data and the data is recorded continuously;
filter, by a bandpass filter, the accelerometer data to obtain a band passed filtered accelerometer signal (Accel bpf ) associated with the real-time conduit with a low pass cut-off frequency and a high pass cut-off frequency;
cross-correlate, the band passed filtered accelerometer signal (Accel bpf ) associated with the real-time conduit at the physical environment and the temporal template signal (Accel template ) for every successive window of T 0 to T d length to obtain a cross correlation value; and
dynamically detect, a leak event of the real-time conduit at the physical environment when the cross-correlation value is greater than a threshold value (∝), and communicate an alarm notification thereby reducing a false alarm rate during routine pipe maintenance, wherein when leak occurs a low frequency negative pressure wave (NPW) is generated from a leak orifice and the NPW has low frequency components which travels long distance in both upstream and downstream directions;
isolate, the NPW from other vibrational generating events on the real-time conduit based on the cross-correlation value and the threshold value (∝).
7 . The system of claim 6 , wherein the conduit at the test environment is constructed based on (a) a pipe diameter, (b) a pipe thickness, (c) a material, (d) a flowing fluid, and (e) a pressure level at the real-time conduit.
8 . The system of claim 6 , wherein the threshold value (∝) vary from one setup to another depending upon a pipe diameter and a pipe length.
9 . The system of claim 6 , wherein the cross correlation value R 12 (τ) is a measurement of a similarity of two signals X 1 (t) and X 2 (t) and R 12 (τ) is given by:
R 12 (τ)=∫ −∞ ∞ X 1 ( t ) X 2 ( t −τ) dt
where X 1 (t) is the accelerometer data collected from the real-time conduit and X 2 (t) is the Accel template data generated from the conduit at the test environment.
10 . The system of claim 6 , wherein the transient signal corresponds to a pressure wavefront travelling through a fluid inside the conduit at the test environment.
11 . One or more non-transitory machine-readable information storage mediums comprising one or more instructions which when executed by one or more hardware processors cause:
receiving, data associated with a first sensing unit and a second sensing unit, wherein the first sensing unit and the second sensing unit are placed in a proximity of a conduit at a test environment, wherein the first sensing unit corresponds to a pressure sensor placed inside the conduit at the test environment, for obtaining a pressure data (Pr), and wherein the second sensing unit corresponds to an accelerometer sensor placed on an outer surface of the conduit at the test environment, for obtaining an accelerometer data (Accel);
processing, the data associated with the first sensing unit to obtain an instant timing information (T 0 ) of a leak event in the conduit at the test environment, wherein the instant timing information (T 0 ) is obtained by detecting a variation in a steady state of a pressure value of a fluid at the conduit at the test environment;
processing, the data associated with the second sensing unit to obtain a transient signal associated with the leak event at a specific band by applying a continuous wavelet transformation (CWT);
filtering, by a bandpass filter, the accelerometer data (Accel) to obtain a band passed filtered accelerometer signal (Accel bpf ) with a low pass cut-off frequency and a high pass cut-off frequency by eliminating unnecessary computations;
processing, the band passed filtered accelerometer signal (Accel bpf ) to obtain a duration (T d ) of the leak event;
truncating, the band passed filtered accelerometer signal (Accel bpf ) in a time domain from the instant timing information (T 0 ) to the duration (Ta) of the leak event to obtain a temporal template signal (Accel template );
receiving, data associated with a sensing unit, wherein the sensing unit corresponds to an accelerometer sensor placed on an outer surface of a real-time conduit of a physical environment, for obtaining an accelerometer data and the data is recorded continuously;
filtering, by a bandpass filter, the accelerometer data to obtain a band passed filtered accelerometer signal (Accel bpf ) associated with the real-time conduit with a low pass cut-off frequency and a high pass cut-off frequency;
cross-correlating, the band passed filtered accelerometer signal (Accel bpf ) associated with the real-time conduit at the physical environment and the temporal template signal (Accel template ) for every successive window of T 0 to T d length to obtain a cross correlation value; and
dynamically detecting, a leak event of the real-time conduit at the physical environment when the cross-correlation value is greater than a threshold value (∝), and communicating an alarm notification thereby reducing a false alarm rate during routine pipe maintenance, wherein when leak occurs a low frequency negative pressure wave (NPW) is generated from a leak orifice and the NPW has low frequency components which travels long distance in both upstream and downstream directions;
isolating, the NPW from other vibrational generating events on the real-time conduit based on the cross-correlation value and the threshold value (∝).
12 . The one or more non-transitory machine-readable information storage mediums of claim 11 , wherein the conduit at the test environment is constructed based on (a) a pipe diameter, (b) a pipe thickness, (c) a material, (d) a flowing fluid, and (e) a pressure level at the real-time conduit.
13 . The one or more non-transitory machine-readable information storage mediums of claim 11 , wherein the threshold value (∝) vary from one setup to another depending upon a pipe diameter and a pipe length.
14 . The one or more non-transitory machine-readable information storage mediums of claim 11 , wherein the cross correlation value R 12 (τ) is a measurement of a similarity of two signals X 1 (t) and X 2 (t) and R 12 (τ) is given by:
R 12 (τ)=∫ −∞ ∞ X 1 ( t ) X 2 ( t −τ) dt
where X 1 (t) is the accelerometer data collected from the real-time conduit and X 2 (t) is the Accel template data generated from the conduit at the test environment.
15 . The one or more non-transitory machine-readable information storage mediums of claim 11 , wherein the transient signal corresponds to a pressure wavefront travelling through a fluid inside the conduit at the test environment.