Method and portable device for detecting leaks in a pipeline

A portable device with real-time signal processing and AI enhances leak detection in pipes by analyzing acoustic signatures, providing rapid and accurate leak identification.

FR3135325B1Active Publication Date: 2024-11-08ALCOM TECH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
FR2022004199
Authority / Receiving Office
FR · FR
Patent Type
Patents
Current Assignee / Owner
Filing Date
2022-05-03
Publication Date
2024-11-08
Estimated Expiration
2042-05-03

AI Technical Summary

Technical Problem

Existing leak detection methods for pipes, especially those under pressure, are tedious, imprecise, expensive, or complex, and lack a portable, easy-to-use solution for rapid and precise detection.

Method used

A portable device using a microphone and real-time signal processing with frequency analysis, entropy calculation, Kalman filter, and principal component analysis, combined with artificial intelligence, to detect leaks in pipes by analyzing acoustic signatures.

Benefits of technology

Enables rapid, precise, and automated leak detection in under a minute with up to 100% accuracy, using a smartphone or laptop, optimizing detection with genetic algorithm-optimized coefficients.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 00000011_0000
    Figure 00000011_0000
  • Figure 00000012_0000
    Figure 00000012_0000
  • Figure 00000013_0000
    Figure 00000013_0000
Patent Text Reader

Abstract

METHOD AND PORTABLE DEVICE FOR DETECTING LEAKS IN A PIPELINE Method (500) for electro-acoustic detection of a leak in a pipeline carrying a fluid, implemented by a portable device (100) and comprising: a step (510) of acquiring a sound signal (S) emitted by the pipeline by means of a microphone (10); a step (520) of real-time processing of the signal (S) with frequency analysis (521) of the signal (S) by means of a periodogram and extraction (522) of characteristics of the signal (S), including entropy, a fault-sensitive characteristic called DSF and a centered frequency corresponding to the centroid of the periodogram; a step (530) of applying a Kalman filter to estimate residuals; a principal component analysis step (540) allowing to model a normal signal of the pipeline and to detect a possible leak by comparing the signal (S) observed to the normal signal;and an alert and / or notification step (560) in case of leak detection. Figure for the abbreviation: figure 2;
Need to check novelty before this filing date? Find Prior Art

Description

Title of the invention: Method and portable device for detecting leaks in a pipeline Technical field

[0001] The present invention belongs to the field of signal processing devices, in particular the acoustic signal emitted during a fluid-structure interaction, and relates more particularly to a method for detecting a leak in a pipe carrying any fluid and a portable device for implementing such a method.

[0002] The present invention finds a direct, but not exclusive, application in the detection of leaks in a drinking water network. State of the art

[0003] Pipelines, especially pressurized supply lines such as water pipes in a drinking water network or industrial fluid pipes in factories, are susceptible to various failures which can cause leaks to appear.

[0004] These leaks compromise the normal functioning of the pipes and can have serious consequences both technically and economically and environmentally.

[0005] Detecting these leaks often turns out to be a difficult task, particularly because of the difficulty of accessing the sometimes buried pipes and their size.

[0006] Some "homemade" solutions rely on human analysis of the sound emitted by a pipe and recorded with a microphone or probed with a stethoscope.

[0007] These solutions are tedious, imprecise and require the intervention of technicians with great expertise.

[0008] Document US4309576 describes a listening device for locating water leaks, comprising a manually operated rod having a handle at one end for manual positioning of the listening device. An acoustic pickup apparatus is mounted at the other end of the rod, and it comprises a ceramic audio tone transducer which is operatively connected to an amplifier-receiver which has a level indicator on which visual leak signals can be seen. The acoustic pickup apparatus is also connected to headphones to enable hearing of leaks. The transducer comprises a brass diaphragm directly attached to a threaded stud for mounting in the rod.

[0009] There are so-called invasive solutions because they require the introduction of an object into the pipe to carry out leak detection.

[0010] For example, methods are known using photonic detection technology which transforms a fiber optic cable running along a network of water pipes into thousands of vibration sensors, capable of detecting a disturbance along the entire length of the pipe.

[0011] Document FR2935800 describes a method for detecting leaks in an underground liquid pipe, in particular a water pipe, according to which: a gas is injected into the liquid of the pipe by a diffuser, the content of which in the atmosphere is low, and the path of the pipe is traveled on the surface with a detection system to measure at successive points the content of injected gas in the air, an abnormally high content constituting an indication of a leak.

[0012] This solution is obviously extremely expensive and very impractical.

[0013] Document EP2710291 describes a system for identifying leaks in pipe construction for liquids, consisting of at least one detection unit positioned in proximity to at least one outlet point of said pipe construction and comprising an acoustic sensor and a wireless communication unit, an electronically controlled closing unit installed on an inlet point of the pipe construction, the unit comprising a valve, an acoustic sensor and a wireless communication unit arranged to transmit water flow rate data and receive control signals, and a controller network device for receiving measurement data from all sensors. The controller is programmed to detect leaks when it identifies differences between the liquid flow rate measured at the inlet point and the flow rate measured at the outlet points.

[0014] Document WO2004 / 063623 describes a method and a device for detecting possible leaks in a pipeline. The pipeline is continuously monitored by acoustic monitoring means, and acoustic events indicating a possible leak are recorded. The pipeline is also equipped with means for continuous temperature monitoring, periodically or on demand. According to this solution, a leak is estimated to be probable when an acoustic event indicates a possible leak at a location and if, at approximately the same time, a temperature difference greater than a predetermined value is detected between this location and adjacent locations. In this solution, the temperature can be monitored by a satellite, an aircraft or a drone.

[0015] Document EP2028471 discloses a leak detector for accurate and stable detection of the presence and position of a leak in an underground water pipeline. The leak detector comprises a vibration detector having a sensor incorporating a piezoelectric element, a main body of the detector incorporating voltage amplifiers for amplifying the voltage of an output signal and several types of noise elimination units for eliminating noise from the signal of output and an earphone. The main body of the detector has a display unit to display detected sound data on a predefined screen.

[0016] These prior art solutions are complex to implement and do not allow leaks to be detected in a short time with great precision. In addition, none of these solutions is presented as a portable device that is easy to use and very compact to facilitate the intervention of leak detection technicians. Presentation of the invention

[0017] The present invention aims to overcome the drawbacks of the prior art set out above and proposes a simple-to-use solution allowing automatic detection of leaks in a pipeline in a very short time (less than one minute).

[0018] A main objective of the invention is to propose a portable device making it possible to instantly discriminate the existence or absence of a leak in a pipe with very high acuity, which can reach 100% in most cases.

[0019] Another objective of the invention is to use a set of artificial intelligences to optimize leak detection and make it discreet and fast, and therefore implementable in a laptop or in a mobile phone of the smartphone type.

[0020] To this end, the present invention relates to a method for electroacoustic detection of a leak in a pipe carrying a fluid, comprising:

[0021] • a step of acquiring a sound signal emitted by the pipeline by means of a microphone; and • a real-time signal processing step.

[0022] This method is remarkable in that the signal processing step comprises:

[0023] • a step of frequency analysis of the signal by means of a periodogram; and • a step of extracting characteristics of the signal, including entropy, a characteristic sensitive to defects called DSF (Damage-Sensitive Fealure) and a centered frequency corresponding to the weighted barycenter of the periodogram.

[0024] It should be noted that the weights and coefficients used in the previous calculations are optimized by a genetic algorithm for each application after a learning period.

[0025] This method is further remarkable in that it comprises, after the above steps:

[0026] • a step of applying a Kalman filter to estimate residues corresponding to signals revealing leakage; • a principal component analysis (PCA) step to model a normal signal from the pipeline and detect a possible leak by comparing the observed signal to the normal signal; and • a stage for presenting the results and alerting and / or notifying in the event of leak detection.

[0027] This method is finally remarkable in that it is entirely implemented by a portable device comprising the microphone.

[0028] For a better result, the signal entropy is calculated with an approximate entropy model ApEn (Approximate Entropy).

[0029] Advantageously, the DSF characteristic is calculated from an AR (autoregressive) model of the signal.

[0030] More particularly, the AR model of the signal is an ARIMA (Auto-Regressive Integrated Moving Average) adjusted integrated model having ARIMA coefficients, and the DSF characteristic is equal to the ratio between the first ARIMA coefficient and the square root of the sum of the squares of the first three ARIMA coefficients.

[0031] According to an advantageous embodiment, the ACP signal analysis step implements artificial intelligence algorithms, of the neural network type, to improve leak detection by giving a weight to each characteristic calculated in the characteristic extraction step. It should be noted that the weights and coefficients used in the previous calculations are optimized by a genetic algorithm for each application after a learning period.

[0032] The present invention also relates to a portable device comprising a microphone and calculation means in the form of a microprocessor, for implementing a method for detecting a leak in a pipeline as presented.

[0033] Advantageously, the portable device comprises a mobile terminal of the smartphone type connected to the microphone, the method then being executed in a dedicated mobile application.

[0034] The fundamental concepts of the invention having just been set out above in their most elementary form, other details and characteristics will emerge more clearly on reading the description which follows and with reference to the appended drawings, giving by way of non-limiting example an embodiment of a method and a device for detecting leaks in a pipeline, in accordance with the principles of the invention. Presentation of the drawings

[0035] The figures are given purely for illustrative purposes for the understanding of the invention and do not limit the scope thereof. The various elements are represented schematically and are not necessarily on the same scale. Throughout the figures, identical or equivalent elements bear the same numerical reference.

[0036] It is thus illustrated in:

[0037] [Fig.l]: a portable leak detection device placed near a pipeline, according to a first embodiment of the invention;

[0038] [Fig.2]: a flowchart of the main steps of a leak detection process in a pipeline according to the invention;

[0039] [Fig.3]: a portable leak detection device, according to a second mode of rea lization of the invention. Detailed description of embodiments

[0040] In the embodiment described below, reference is made to a portable device for detecting leaks in a pipeline, intended mainly for searching for leaks in water pipes. This non-limiting example is given for a better understanding of the invention and does not exclude the use of the device for searching for leaks in other pipelines such as pipelines, gas pipelines, oil pipelines and more generally all circulation of industrial fluids in factories or power stations.

[0041] In the present description, the term "portable device" designates a small-sized device that a user can carry with his hands for use, such as a mobile phone.

[0042] [Fig.l] represents a portable leak detection device 100 placed near a pipe 200 in which a fluid F flows in a normal flow direction (in thick arrows).

[0043] The pipe 200 is subject to a leak L (in thin arrow) caused in particular by damage such as a crack 210.

[0044] Naturally, the leak L induces a particular acoustic signature in the sound signal S produced by the fluid flowing in the pipe 200.

[0045] The portable device 100 thus makes it possible to probe the sound signal S emitted by the pipe 200 and to detect the presence of the leak L by recognizing the acoustic signature of the latter.

[0046] Prior to this recognition, a microphone integrated or connected to the portable device 100 allows acquisition of the sound signal S when it is placed near the pipe 200.

[0047] Of course, the recognition of the acoustic signature is the result of specific signal processing carried out by calculation means of the portable device 100.

[0048] Thus, the portable device 100, thanks to its microphone and its on-board calculation means, implements a leak detection method according to the present invention.

[0049] [Fig.2] represents the main steps of a method 500 for detecting a leak in a pipeline, said method comprising:

[0050] • a step 510 of acquiring the sound signal emitted by the pipeline; • a step 520 of processing this signal following a sequence of well-defined operations; • a step 530 of applying a Kalman filter; • a step 540 of principal component analysis; • a step 550 of checking for the presence of a leak; and • a conditional step 560 of alert and / or notification in the event of leak detection.

[0051] Step 510 of acquiring the sound signal consists of recording this signal by the microphone of the portable device 100, at different accessible points of the pipeline.

[0052] The signal is then analyzed in a processing and calculation unit of the portable device 100.

[0053] The signal processing step 520 is carried out using a frequency approach on the continuous signal that is the sound signal from the pipeline. This involves digital signal processing carried out in real time in an on-board microprocessor, preferably specialized in digital signal processing.

[0054] The signal processing performed during step 520 comprises:

[0055] • a step 521 of frequency analysis of the signal; and • a step 522 of extracting characteristics from the signal;

[0056] Frequency analysis step 521 consists of obtaining a frequency representation of the recorded signal using a periodogram in order to estimate its power spectral density (PSD).

[0057] DSP makes it possible, within the framework of harmonic analysis, to characterize the random and stationary signal that is the sound signal from the pipeline.

[0058] This makes it possible to identify the harmonics (or fundamental frequencies) of the sound signal, which therefore correspond to normal operation of the pipeline, and to remove external sounds from the environment which are parasitic sounds to the leak being sought.

[0059] Step 522 of extracting characteristics from the signal consists of calculating characteristics from a previously established AR (autoregressive) model of the signal.

[0060] This extraction of characteristics includes in particular a calculation 5221 of the entropy, a calculation 5222 of a characteristic sensitive to defects called DSF (Damage-Sensitive Féal tire) and a calculation 5223 of the centered frequency which is the barycenter of the periodogram.

[0061] Indeed, as soon as there is an anomaly in the operation of the pipeline and this anomaly modifies the resulting sound signal, there is necessarily more complexity in said signal and therefore more entropy. Thus, the entropy of the sound signal from a pipeline with a leak is necessarily greater than that of the signal from the same pipeline without a leak.

[0062] Preferably, the entropy of the recorded signal is calculated with the statistical model of approximate entropy ApEn (Approximate Entropy). The ApEn model has achieved better results compared to other models for calculating entropy such as sample entropy SampEn (Sample Entropy), which is a model derived from ApEn, or Kolmogorov-Sinai entropy.

[0063] In addition, the ApEn model has many advantages, including low computational consumption, operation for small data samples, real-time operation, and limited effect of noise on measurements.

[0064] The AR model of the signal is preferably an ARIMA (Auto-Regressive Integrated Moving Average) integrated autoregressive model whose ARIMA coefficients make it possible to calculate the DSF which is equal to the ratio of the first coefficient and the square root of the sum of the squares of the first three coefficients.

[0065] Thus, normal signals have frequencies concentrated in the same region, while abnormal signals (with leakage) do not have such a concentration of frequencies.

[0066] Then, from all these characteristics, a principal component analysis ACP and a Kalman filter are applied, to detect and locate a possible leak in the pipeline.

[0067] Step 530 of applying a Kalman filter makes it possible to estimate the state of the system representing the flow in the pipeline, in order to generate the residues of the system, from a model of proper operation of the system (without leakage) and the available measurements, these residues being the acoustic signatures revealing the presence of a leak in the pipeline.

[0068] The ACP analysis step 540 makes it possible to generate an ACP model in which all the correlations between the different characteristics are taken into account.

[0069] Thus, the ACP analysis makes it possible to model the behavior of the pipeline (system) in normal operation, and the leaks (faults) are then detected by comparing the behavior observed in the recorded sound signal and that given by the ACP model.

[0070] The combination of the results of the characteristics extracted in step 520 and the PCA analysis makes it possible to obtain a segmentation of a two-dimensional space into which the vectors of a higher-dimensional space (5 for example) having as a base the extracted characteristics are projected. This segmentation separates the signals without leakage from the signals with leakage and therefore makes it possible to detect leaks.

[0071] Preferably, the method 500 implements artificial intelligence algorithms of the neural network type to improve the PCA analysis by giving a weight to each of the characteristics calculated in step 520. It should be noted that the weights and coefficients used in the preceding calculations are optimized by an algorithm genetics for each application after a learning period.

[0072] [Fig. 3] represents a portable device 100', according to another embodiment, for implementing the leak detection method, said device comprising a detached microphone 10 and a mobile terminal such as a smartphone 20.

[0073] The microphone 10 and the smartphone 20 can be connected with a cable 30 or by a wireless connection.

[0074] Thus, the portable leak detection device can simply be transported and used by a technician wishing to check the condition of a pipeline.

[0075] It is clear from the present description that certain steps of the method may be modified, replaced or deleted and that certain adjustments may be made to the implementation of this method according to the objectives sought, without departing from the scope of the invention.

Claims

Claims

1. Method (500) for electroacoustic detection of a leak in a pipe carrying a fluid, comprising: a step (510) of acquiring a sound signal (S) emitted by the pipe by means of a microphone (10); and a step (520) of processing the signal (S) in real time; characterized in that the step (520) of processing the signal comprises: a step (521) of frequency analysis of the signal (S) by means of a periodogram; and a step (522) of extracting characteristics of the signal (S), including the entropy, a characteristic sensitive to defects called DSF and a centered frequency corresponding to the barycenter of the periodogram; in that it comprises, after the above steps: a step (530) of applying a Kalman filter to estimate residues corresponding to leak-revealing signals;a step (540) of principal component analysis making it possible to model a normal signal from the pipeline and to detect a possible leak by comparing the observed signal (S) with the normal signal; and a step (560) of presenting the results and of alerting and / or notifying in the event of detection of a leak; and in that it is entirely implemented by a portable device (100, 100') comprising the microphone (10).;

2. The method of claim 1, wherein the entropy of the signal (S) is calculated with an approximate entropy model.

3. A method according to claim 1 or 2, wherein the DSF characteristic is calculated from an autoregressive model of the signal (S).

4. Method according to claim 3, in which the autoregressive model of the signal (S) is an integrated model with adjusted mean having so-called ARIMA coefficients, and the DSF characteristic is equal to the ratio between the first ARIMA coefficient and the square root of the sum of the squares of the first three ARIMA coefficients.

5. Method according to any one of the preceding claims, in which the step (540) of principal component analysis of the signal (S) implements artificial intelligence algorithms to improve leak detection by giving a weight to each characteristic calculated in the step (522) of extracting the characteristics.

6. A method according to claims 4 and 5, wherein the weights and coefficients used in the calculations are optimized by a genetic algorithm for each implementation after a learning period.

7. Portable device (100, 100') comprising a microphone (10) and computing means in the form of a microprocessor, for implementing a method (500) for detecting a leak in a pipeline according to one of claims 1 to 5.

8. Portable device (100') according to claim 7, comprising a mobile terminal of the smartphone type (20) connected to the microphone (10), the method (500) being executed in a dedicated mobile application.