Pipeline leakage detection method based on acceleration sensor

Abstract

This application discloses a pipeline leak detection method based on an acceleration sensor. The method comprises the following steps: acquiring a raw sampling signal via an acceleration sensor; sampling the raw sampling signal via a pipeline leak detection device; processing the raw sampling signal via a data processor within the pipeline leak detection device to obtain a preliminary analysis result; and determining whether a pipeline is leaking based on the preliminary analysis result obtained by the data processor within the pipeline leak detection device and a preset statistical model. The method utilizes an acceleration sensor to detect and locate leaks in a water supply network, thereby improving detection efficiency and reducing false alarm rates.

Description

Technical Field

[0001] The present application relates to the field of water supply network leakage detection, and specifically to a pipeline leakage detection method based on an acceleration sensor. Background Art

[0002] The gap between production and sales for water supply companies has long been a bottleneck restricting their development and a hotly debated issue within the industry. Leaks in water supply networks are a key factor contributing to this gap. Routine leak detection is crucial for reducing water waste and improving production and sales performance for water supply companies. Detecting leaks in water supply networks can identify leaks and enable timely remediation.

[0003] Traditional water supply network leak detection technologies often have high requirements for ambient sound. Specifically, for traditional water supply network leak detection technologies, sounds other than the sound of flowing water are considered noise, and when detecting water supply network leaks, the noise level must be kept as low as possible. Consequently, traditional water supply network leak detection technologies often require manual work in the dead of night using tools such as listening poles, resulting in low efficiency, high false alarm rates, and high risk. Summary of the Invention

[0004] An advantage of the present application is that it provides a pipeline leakage detection method based on an acceleration sensor, wherein the pipeline leakage detection method based on an acceleration sensor uses the acceleration sensor to detect and locate leakage points in the water supply network, which can improve detection efficiency and reduce false alarm rate.

[0005] One advantage of the present application is that it provides a pipeline leakage detection method based on an acceleration sensor, wherein the pipeline leakage detection method based on an acceleration sensor uses a data processor within the pipeline leakage detection device to convert and analyze the original sampling signals collected by the acceleration sensor. Compared with sending the original sampling signals collected by the acceleration sensor to a background server via the Internet of Things and converting and analyzing the collected original sampling signals by the background server, the present application uses the data processor within the pipeline leakage detection device to convert and analyze the original sampling signals collected by the acceleration sensor, which can simplify the signal processing process to a certain extent, improve algorithm efficiency, and reduce dependence on the network in the application scenario.

[0006] One advantage of the present application is that it provides a pipeline leakage detection method based on an acceleration sensor, wherein the pipeline leakage detection method based on an acceleration sensor uses a preset statistical model to obtain the level of pipeline leakage, and the preset statistical model can be optimized and adjusted based on empirical values, thereby improving recognition capabilities and reducing the probability of false alarms.

[0007] According to one aspect of the present application, a pipeline leakage detection method based on an acceleration sensor is provided, comprising the steps of: acquiring an original sampling signal using the acceleration sensor; sampling the original sampling signal using a pipeline leakage detection device; processing the original sampling signal using a data processor within the pipeline leakage detection device to obtain a preliminary analysis result; and determining whether a pipeline is leaking based on the preliminary analysis result obtained by the data processor within the pipeline leakage detection device and a preset statistical model.

[0008] In one embodiment of the acceleration sensor-based pipeline leakage detection method described in the present application, the original sampling signal is processed by a data processor in the pipeline leakage detection equipment to obtain a preliminary analysis result, including the steps of: converting the original sampling signal from the time domain to the frequency domain by the data processor in the pipeline leakage detection equipment to obtain a frequency domain sampling signal converted to the frequency domain; comparing the frequency domain sampling signal with a preset amplitude value to obtain a comparison result expression value, wherein the comparison result expression value is used to express the comparison result of the frequency domain sampling signal and the preset amplitude value.

[0009] In one embodiment of the pipeline leakage detection method based on an acceleration sensor described in the present application, the data processor in the pipeline leakage detection device converts the original sampling signal from the time domain to the frequency domain to obtain a frequency domain sampling signal converted to the frequency domain, including the steps of: segmenting the original sampling signal according to the time domain so that the original sampling signal is divided into at least two segmented time domain sampling signals, and the sampling time of each segmented time domain sampling signal is in a different time domain; and converting the at least two segmented time domain sampling signals from the time domain to the frequency domain to obtain at least two segmented frequency sampling signals; comparing the frequency domain sampling signals with a preset amplitude value to obtain a comparison result expression value, including the steps of: comparing the at least two segmented frequency domain sampling signals with the corresponding at least two preset amplitude values to obtain at least two preliminary comparison result values.

[0010] In one embodiment of the pipeline leakage detection method based on an acceleration sensor described in the present application, the preliminary comparison result value is the frequency of the frequency domain sampling signal in each segment of the segmented frequency domain sampling signal whose amplitude is greater than the preset amplitude value corresponding to it, and the number of frequency domain sampling signals of each frequency in each segment of the segmented frequency domain sampling signal whose amplitude is greater than the preset amplitude value corresponding to it; the comparison result expression value includes the frequency of the frequency domain sampling signal in each segment of the segmented frequency domain sampling signal whose amplitude is greater than the preset amplitude value corresponding to it, and the sum of the number of frequency domain sampling signals of the same frequency in each segment of the segmented frequency domain sampling signal whose amplitude is greater than the preset amplitude value corresponding to it.

[0011] In one embodiment of the acceleration sensor-based pipeline leakage detection method described in the present application, determining whether a pipeline is leaking based on the preliminary analysis results obtained by the data processor in the pipeline leakage detection equipment and a preset statistical model includes the steps of: comparing the preliminary analysis results obtained by the data processor in the pipeline leakage detection equipment with a preset statistical quantity corresponding to a preset statistical frequency of a preset statistical model to determine whether the pipeline is leaking; wherein, in response to the sum of the number of frequency domain sampling signals of the preset statistical frequency in the preliminary analysis results obtained by the data processor in the pipeline leakage detection equipment being greater than the preset statistical quantity corresponding to the preset statistical frequency in the preset statistical model, determining that the pipeline is leaking.

[0012] In one embodiment of the acceleration sensor-based pipeline leakage detection method described in the present application, during the process of performing domain conversion on the original sampled signal by a data processor in the pipeline leakage detection device, the data processor in the pipeline leakage detection device uses a discrete Fourier algorithm to perform domain conversion on the original sampled signal.

[0013] In one embodiment of the pipeline leakage detection method based on an acceleration sensor described in the present application, sampling the original sampling signal by a pipeline leakage detection device includes the steps of: receiving the original sampling signal from an adaptive gain signal conditioning circuit by a sampling unit within the pipeline leakage detection device.

[0014] In one embodiment of the acceleration sensor-based pipeline leakage detection method described in the present application, sampling the original sampling signal by the pipeline leakage detection equipment includes the steps of: acquiring the original sampling data collected by the acceleration sensor at a preset sampling frequency within a preset duration by a sampling unit within the pipeline leakage detection equipment.

[0015] In one embodiment of the acceleration sensor-based pipeline leakage detection method described in the present application, the raw sampling data collected by the acceleration sensor is obtained by a sampling unit in the pipeline leakage detection equipment at a preset sampling frequency within a preset duration, including the steps of: saving the raw sampling signal to a flash memory according to the preset sampling frequency by the sampling unit in the pipeline leakage detection equipment.

[0016] In one embodiment of the pipeline leakage detection method based on an acceleration sensor according to the present application, the data processor in the pipeline leakage detection device is a single-chip microcomputer.

[0017] Further objectives and advantages of the present application will be fully reflected through understanding of the following description and drawings.

[0018] These and other objects, features and advantages of the present application are fully reflected in the following detailed description, drawings and claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and other purposes, features and advantages of the present application will become more apparent by describing the embodiments of the present application in more detail in conjunction with the accompanying drawings. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the drawings, the same reference numerals generally represent the same components or parts.

[0020] Figure 1 The figure shows a flow chart of a pipeline leakage detection method based on an acceleration sensor according to an embodiment of the present application.

[0021] Figure 2 The figure shows a schematic diagram of an original sampling signal, wherein the original sampling signal is a time domain sampling signal.

[0022] Figure 3 The figure shows a schematic diagram of the comparison between the frequency of the first segmented frequency sampling signal and the first preset amplitude value.

[0023] Figure 4 The figure shows a schematic diagram of the comparison between the frequency of the second segmented frequency sampling signal and the second preset amplitude value.

[0024] Figure 5 The figure shows a schematic diagram of the comparison between the frequency of the S-th segment frequency sampling signal and the S-th preset amplitude value.

[0025] Figure 6 The figure shows the number of frequency sampling signals having frequencies greater than the corresponding preset amplitude values in each segmented frequency sampling signal. DETAILED DESCRIPTION

[0026] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described herein.

[0027] It is understood that the term "a" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element may be one, while in another embodiment, the number of the element may be multiple, and the term "a" should not be understood as limiting the number. "Multiple" means greater than or equal to two.

[0028] Although ordinal numbers such as "first," "second," and the like will be used to describe various components, these are not intended to limit those components. The terms are used solely to distinguish one component from another. For example, a first component could be referred to as a second component, and similarly, a second component could be referred to as a first component without departing from the teachings of the present disclosure. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0029] The terms used herein are for the purpose of describing various embodiments only and are not intended to be limiting. As used herein, the singular is intended to include the plural, unless the context clearly indicates otherwise. It will also be understood that the terms "including" and / or "having" when used in this specification specify the presence of a stated feature, number, operation, component, element, or combination thereof, and do not preclude the presence or addition of one or more other features, numbers, operations, components, elements, or combinations thereof.

[0030] Application Overview

[0031] As mentioned above, traditional water supply network leak detection technologies often have high requirements for ambient sound. Specifically, for traditional water supply network leak detection technologies, sounds other than the sound of flowing water are considered noise, and when detecting water supply network leaks, the noise level must be kept as low as possible. Consequently, traditional water supply network leak detection technologies often require manual work in the dead of night using tools such as listening poles, resulting in low efficiency, high false alarm rates, and high risk.

[0032] This application proposes the use of sound-insensitive devices to detect water supply network leaks, thereby preventing the influence of sounds other than the sound of flowing water on the detection results. Specifically, this application proposes the use of accelerometers to detect water supply network leaks. When a water supply pipeline leaks, the water impacts the pipe wall and surrounding soil, generating vibrations. The vibration signal propagates through the water supply pipeline. The vibration signal is sensed by an accelerometer within a pipeline leak detection device attached to the pipeline. This vibration signal can be analyzed to determine whether the water supply network is leaking.

[0033] Compared with manually listening to the sound of water flow to determine whether the water supply network is leaking, using acceleration sensors to detect water supply network leaks can not only improve efficiency but also reduce the false alarm rate.

[0034] It's worth noting that, in theory, the signals collected by the accelerometer can be sent to a backend server via the Internet of Things, which can then utilize the server's powerful computing power to calculate and analyze the signals. However, this approach suffers from an over-reliance on the communication network, making it impossible to detect network anomalies caused by complex field conditions.

[0035] Based on this, this application proposes moving the calculation and analysis steps forward, leveraging the pipeline leak detection device's own computing power to calculate and analyze the signals collected by the acceleration sensor. This can simplify the signal processing process to a certain extent, improve algorithm efficiency, and reduce reliance on the network in the application scenario. Furthermore, the recognition capabilities of the pipeline leak detection device can be continuously optimized and adjusted by adjusting the parameters of the preset statistical model.

[0036] Schematic diagram of pipeline leakage detection method based on acceleration sensor

[0037] like Figures 1 to 6 As shown, the accelerometer-based pipeline leak detection method according to the embodiment of the present application is illustrated. Compared to manually listening to the sound of water flow to determine whether a water supply network leaks, the accelerometer-based pipeline leak detection method described in the embodiment of the present application uses an accelerometer to detect water supply network leaks, which not only improves efficiency but also reduces the false alarm rate. Furthermore, the accelerometer-based pipeline leak detection method described in the embodiment of the present application utilizes the computing power of the pipeline leak detection equipment itself to calculate and analyze the signals collected by the accelerometer, which can simplify the signal processing process to a certain extent, improve algorithm efficiency, and reduce dependence on the network in the application scenario.

[0038] like Figure 1 As shown, the pipeline leakage detection method based on the acceleration sensor includes the following steps: S110, collecting original sampling signals through the acceleration sensor; S120, sampling the original sampling signals through the pipeline leakage detection equipment; S130, processing the original sampling signals through the data processor in the pipeline leakage detection equipment to obtain preliminary analysis results; and S140, obtaining the pipeline leakage level based on the preliminary analysis results obtained by the data processor in the pipeline leakage detection equipment and a preset statistical model.

[0039] In step S110, a raw sampling signal is collected using an acceleration sensor. Specifically, the pipeline leak detection device is installed in or near a pipeline. When water flows, the pipe wall and surrounding soil vibrate, causing the acceleration sensor within the pipeline leak detection device to detect the raw sampling signal. Accordingly, the raw sampling signal is generated by the vibration signal generated by the water flow. The raw sampling signal is a weak signal.

[0040] It is worth mentioning that in this application, the pipeline leakage detection equipment specifically refers to a pipeline leakage detection equipment installed on or near a pipeline, and is not a host computer used to control the pipeline leakage detection equipment, or does not include a host computer used to control the pipeline leakage detection equipment.

[0041] In step S120, the raw sampling signal is sampled by the pipeline leakage detection device. Specifically, after the raw sampling signal is collected by the acceleration sensor, the raw sampling signal is transmitted to a sampling unit in the pipeline leakage detection device through an adaptive gain signal conditioning circuit, so that the sampling unit of the pipeline leakage detection device can sample the raw sampling signal.

[0042] Correspondingly, sampling the original sampling signal by the pipeline leakage detection device includes the steps of: receiving the original sampling signal from the adaptive gain signal conditioning circuit by a sampling unit in the pipeline leakage detection device.

[0043] Specifically, in step S120, the sampling unit within the pipeline leakage detection device acquires the raw sampled data collected by the acceleration sensor at a preset sampling frequency within a preset duration. For example, if the preset duration is M seconds and the preset sampling frequency is N Hz / s, the total number of sampled data is L = M*N, where L represents the total number of sampled data; M represents the preset duration; and N represents the preset sampling frequency. If sampling is performed at a sampling frequency of N Hz / s within the sampling duration of M seconds, the total number of sampled data is M*N. M*N represents the product of M and N.

[0044] Optionally, the sampling unit in the pipeline leakage detection device saves the original sampling signal to a flash memory according to a preset sampling frequency, or the sampling unit in the pipeline leakage detection device saves the original sampling signal to other types of memory according to a preset sampling frequency.

[0045] The sampling unit in the pipeline leakage detection device may be an analog sampling unit.

[0046] In step S130, the raw sampled signal is processed by a data processor within the pipeline leak detection device to obtain a preliminary analysis result. It is worth noting that, in this application, the focus is on obtaining the preliminary analysis result through calculation by the data processor within the pipeline leak detection device, rather than obtaining the preliminary analysis result through calculation by a backend server communicatively connected to the pipeline leak detection device via the Internet of Things. Therefore, the specific implementation method of processing the raw sampled signal by the data processor within the pipeline leak detection device to obtain the preliminary analysis result is not limited.

[0047] The present application illustratively proposes an implementation method of processing the original sampling signal by a data processor in the pipeline leakage detection device to obtain a preliminary analysis result.

[0048] Specifically, in one embodiment of the present application, the original sampling signal is a time domain sampling signal. The original sampling signal is first domain-converted, and then the domain-converted sampling data is analyzed. Accordingly, step S130 includes the following steps: S131, converting the original sampling signal from the time domain to the frequency domain via the data processor within the pipeline leakage detection device to obtain a frequency domain sampling signal converted to the frequency domain; and S132, comparing the frequency domain sampling signal with a preset amplitude value to obtain a comparison result expression value, wherein the comparison result expression value is used to express the comparison result between the frequency domain sampling signal and the preset amplitude value.

[0049] In step S131 , the data processor in the pipeline leakage detection device may perform domain conversion on the original sampling signal using a discrete Fourier algorithm.

[0050] It is worth mentioning that when the time domain width of the original sampling signal is wide, the amount of data is large, the storage level is deep, and serial calculation cannot meet the efficiency requirements. This application proposes to segment the time domain sampling signal, then perform domain conversion on the segmented time domain sampling signal, and then analyze the converted sampling signal. Define the number of segmented sampling points P, the number of segments S=L / P, and the frequency resolution=N / P; P represents the number of sampling points of each segmented time domain sampling signal; S represents the number of segments of the segmented time domain sampling signal; L represents the total number of sampled data.

[0051] Accordingly, step S131 includes the steps of: S1311, segmenting the original sampled signal according to the time domain, so that the original sampled signal is divided into at least two segmented time domain sampled signals, wherein the sampling time of each segmented time domain sampled signal is in a different time domain; and S1312, converting the at least two segmented time domain sampled signals from the time domain to the frequency domain to obtain at least two segmented frequency sampled signals. Accordingly, the frequency domain sampled signals converted to the frequency domain include at least two segmented frequency domain sampled signals.

[0052] like Figure 2 As shown, in an example of the present application, in step S1311, the original sampling signal can be segmented according to the time domain, so that the original sampling signal is divided into S segments of segmented time domain sampling signals. The S segments of segmented time domain sampling signals are respectively the first segmented time domain sampling signal Q1, the second segmented time domain sampling signal Q2, the third segmented time domain sampling signal Q3, the fourth segmented time domain sampling signal Q4, ..., the S segmented time domain sampling signal Q S The first segmented time domain sampling signal Q1, the second segmented time domain sampling signal Q2, the third segmented time domain sampling signal Q3, the fourth segmented time domain sampling signal Q4, ..., the S segmented time domain sampling signal Q S Arranged in chronological order.

[0053] Step S132 includes the following steps: S1321 , comparing at least two segments of the segmented frequency domain sampling signals with corresponding at least two preset amplitude values to obtain at least two preliminary comparison result values.

[0054] The preliminary comparison result value is the frequency of the frequency domain sampling signals in each segmented frequency domain sampling signal whose amplitude is greater than the corresponding preset amplitude value, and the number of frequency domain sampling signals of each frequency in each segmented frequency domain sampling signal whose amplitude is greater than the corresponding preset amplitude value; the comparison result expression value includes the frequency of the frequency domain sampling signals in each segmented frequency domain sampling signal whose amplitude is greater than the corresponding preset amplitude value, and the sum of the number of frequency domain sampling signals of the same frequency in each segmented frequency domain sampling signal whose amplitude is greater than the corresponding preset amplitude value.

[0055] like Figure 3 As shown, there are three frequency sampling signals with amplitudes greater than the first preset amplitude value in the first segmented time domain sampling signal Q1. The frequencies of the three frequency sampling signals with amplitudes greater than the first preset amplitude value in the first segmented time domain sampling signal Q1 are 300, 400, and 800 respectively.

[0056] The number of frequency sampling signals with an amplitude greater than the first preset amplitude value and a frequency of 300 in the first segmented time domain sampling signal Q1 is 1, the number of frequency sampling signals with an amplitude greater than the first preset amplitude value and a frequency of 400 in the first segmented time domain sampling signal Q1 is 1, and the number of frequency sampling signals with an amplitude greater than the first preset amplitude value and a frequency of 800 in the first segmented time domain sampling signal Q1 is 1.

[0057] Correspondingly, Fx1(300)=1, Fx1(400)=1, Fx1(800)=1; Fx1(f) represents the number of frequency sampling signals with an amplitude greater than a first preset amplitude value and a frequency f in the first segmented time domain sampling signal Q1.

[0058] like Figure 4 As shown, there are five frequency sampling signals in the second segmented time domain sampling signal Q2 whose amplitudes are greater than the second preset amplitude value. The frequencies of the five frequency sampling signals in the second segmented time domain sampling signal Q2 whose amplitudes are greater than the second preset amplitude value are 200, 400, 500, 800, and 900, respectively.

[0059] The number of frequency sampling signals with an amplitude greater than the second preset amplitude value and a frequency of 200 in the second segmented time domain sampling signal Q2 is 1, the number of frequency sampling signals with an amplitude greater than the second preset amplitude value and a frequency of 400 in the second segmented time domain sampling signal Q2 is 1, the number of frequency sampling signals with an amplitude greater than the second preset amplitude value and a frequency of 500 in the second segmented time domain sampling signal Q2 is 1, the number of frequency sampling signals with an amplitude greater than the second preset amplitude value and a frequency of 800 in the second segmented time domain sampling signal Q2 is 1, and the number of frequency sampling signals with an amplitude greater than the second preset amplitude value and a frequency of 900 in the second segmented time domain sampling signal Q2 is 1.

[0060] Correspondingly, Fx2(200)=1, Fx2(400)=1, Fx2(500)=1, Fx2(800)=1, Fx2(900)=1; Fx2(f) represents the number of frequency sampling signals with an amplitude greater than the second preset amplitude value in the second segmented time domain sampling signal Q2.

[0061] like Figure 5 As shown, the S-th segment time domain sampling signal Q S There are 4 frequency sampling signals with amplitudes greater than the Sth preset amplitude value. The 4 Sth segmented time domain sampling signals Q S The frequencies of the frequency sampling signals with a medium amplitude greater than the Sth preset amplitude value are 300, 400, 500, and 700 respectively.

[0062] The S-th segmented time domain sampling signal Q S The number of frequency sampling signals with a frequency of 300 whose amplitude is greater than the Sth preset amplitude value is 1, and the Sth segmented time domain sampling signal Q S The number of frequency sampling signals with a frequency of 400 whose amplitude is greater than the Sth preset amplitude value is 1, and the Sth segmented time domain sampling signal Q S The number of frequency sampling signals with a frequency of 500 whose amplitude is greater than the Sth preset amplitude value is 1, and the Sth segmented time domain sampling signal Q S The number of frequency sampling signals with a frequency of 700 and an amplitude greater than the Sth preset amplitude value is 1.

[0063] Correspondingly, FxS(300)=1, FxS(400)=1, FxS(500)=1, FxS(700)=1; FxS(f) represents the S-th segmented time domain sampling signal Q S The number of frequency sampling signals with a frequency f whose amplitude is greater than the Sth preset amplitude value.

[0064] like Figure 6As shown, in an example of the present application, the sum of the number of frequency domain sampling signals with an amplitude greater than the corresponding preset amplitude value of 100 from the segmented frequency domain sampling signal of the first segment to the segmented frequency domain sampling signal of the S segment is 0; the sum of the number of frequency domain sampling signals with an amplitude greater than the corresponding preset amplitude value of 200 from the segmented frequency domain sampling signal of the first segment to the segmented frequency domain sampling signal of the S segment is 1; the sum of the number of frequency domain sampling signals with an amplitude greater than the corresponding preset amplitude value of 300 from the segmented frequency domain sampling signal of the first segment to the segmented frequency domain sampling signal of the S segment is 2; the sum of the number of frequency domain sampling signals with an amplitude greater than the corresponding preset amplitude value of 400 from the segmented frequency domain sampling signal of the first segment to the segmented frequency domain sampling signal of the S segment is 5; the sum of the number of frequency domain sampling signals with an amplitude greater than the corresponding preset amplitude value of 400 from the segmented frequency domain sampling signal of the first segment to the segmented frequency domain sampling signal of the S segment is 5; The sum of the number of frequency domain sampling signals with an amplitude of 500 and an amplitude greater than the corresponding preset amplitude value in the signal is 6; the sum of the number of frequency domain sampling signals with an amplitude of 600 and an amplitude greater than the corresponding preset amplitude value in the segmented frequency domain sampling signals from the first section to the segmented frequency domain sampling signals from the S section is 4; the sum of the number of frequency domain sampling signals with an amplitude of 700 and an amplitude greater than the corresponding preset amplitude value in the segmented frequency domain sampling signals from the first section to the segmented frequency domain sampling signals from the S section is 3; the sum of the number of frequency domain sampling signals with an amplitude of 800 and an amplitude greater than the corresponding preset amplitude value in the segmented frequency domain sampling signals from the first section to the segmented frequency domain sampling signals from the S section is 4; the sum of the number of frequency domain sampling signals with an amplitude of 1000 and an amplitude greater than the corresponding preset amplitude value in the segmented frequency domain sampling signals from the first section to the S section is 0.

[0065] Correspondingly, Fx(100)=0; Fx(200)=1; Fx(300)=2; Fx(400)=5; Fx(500)=6; Fx(600)=4; Fx(700)=3; Fx(800)=4; Fx(900)=1; Fx(1000)=0; Fx(f) represents the first segment of the segmented frequency domain sampling signal Q1 to the S segment of the segmented time domain sampling signal Q S The sum of the number of frequency sampling signals with a frequency f whose amplitude is greater than the preset amplitude value corresponding to the segmented frequency domain sampling signal of each segment.

[0066] The data processor in the pipeline leakage detection device may be a single chip microcomputer.

[0067] In step S140, a pipeline leakage level is determined based on the preliminary analysis results obtained by the data processor within the pipeline leakage detection device and a preset statistical model. Specifically, in step S140, the preliminary analysis results obtained by the data processor within the pipeline leakage detection device are compared with a preset statistical quantity corresponding to a preset statistical frequency of a preset statistical model to determine whether the pipeline is leaking. More specifically, a pipeline leak is determined in response to the sum of the number of frequency domain sampling signals at the preset statistical frequency in the preliminary analysis results obtained by the data processor within the pipeline leakage detection device being greater than the preset statistical quantity corresponding to the preset statistical frequency in the preset statistical model.

[0068] In an example of the present application, the preset statistical frequency is 500, and the preset statistical quantity corresponding to the frequency 500 of the preset statistical model is 5; in step S130, it is calculated that the sum of the number of frequency domain sampling signals with an amplitude greater than the corresponding preset amplitude value of 500 from the segmented frequency domain sampling signal of the first segment to the segmented frequency domain sampling signal of the S segment is 6, that is, Fx(500)=6, the sum of the number of frequency domain sampling signals with an amplitude greater than the corresponding preset amplitude value of 500 from the segmented frequency domain sampling signal of the first segment to the segmented frequency domain sampling signal of the S segment (that is, 6) is greater than the preset statistical quantity corresponding to the frequency 500 of the preset statistical model (that is, 5), and it is determined that the pipeline is leaking.

[0069] It is worth mentioning that the preset statistical model can be optimized and adjusted according to empirical values, thereby improving recognition capabilities and reducing the probability of false alarms.

[0070] In summary, the acceleration sensor-based pipeline leak detection method described in the embodiments of this application is explained. This acceleration sensor-based pipeline leak detection method uses acceleration sensors to detect water supply network leaks, not only improving efficiency but also reducing false alarm rates. Furthermore, compared to sending the raw sampling signals collected by the acceleration sensor to a backend server via the Internet of Things, which then converts and analyzes the collected raw sampling signals, the acceleration sensor-based pipeline leak detection method described in this application utilizes a data processor within the pipeline leak detection device to convert and analyze the raw sampling signals collected by the acceleration sensor. This can, to a certain extent, simplify the signal processing process, improve algorithm efficiency, and reduce reliance on the network in the application scenario.

[0071] The above description of the present application and its embodiments is non-limiting. The drawings show only one embodiment of the present application, and the actual structure is not limited thereto. In short, if a person skilled in the art is inspired by this and, without departing from the inventive purpose of this application, designs a structure and embodiment similar to this technical solution without creatively designing, they shall fall within the scope of protection of this application.

Claims

1. A pipeline leakage detection method based on an acceleration sensor, characterized in that: Including steps: Collecting original sampling signals through acceleration sensors; Sampling the original sampling signal by a pipeline leakage detection device; Processing the raw sampling signal by a data processor in the pipeline leakage detection device to obtain a preliminary analysis result; as well as Determining whether the pipeline is leaking based on the preliminary analysis results obtained by the data processor in the pipeline leakage detection device and a preset statistical model; The data processor in the pipeline leakage detection device processes the original sampling signal to obtain a preliminary analysis result, including the steps of: converting the original sampling signal from the time domain to the frequency domain by the data processor in the pipeline leakage detection device to obtain a frequency domain sampling signal converted to the frequency domain; comparing the frequency domain sampling signal with a preset amplitude value to obtain a comparison result expression value, wherein the comparison result expression value is used to express the comparison result of the frequency domain sampling signal and the preset amplitude value; The data processor in the pipeline leakage detection device converts the original sampling signal from the time domain to the frequency domain to obtain a frequency domain sampling signal converted to the frequency domain, including the steps of: segmenting the original sampling signal according to the time domain so that the original sampling signal is divided into at least two segmented time domain sampling signals, and the sampling time of each segmented time domain sampling signal is in a different time domain; converting the at least two segments of the segmented time domain sampling signals from the time domain to the frequency domain to obtain at least two segmented frequency domain sampling signals; comparing the frequency domain sampling signals with a preset amplitude value to obtain a comparison result expression value, including the steps of: comparing the at least two segments of the segmented frequency domain sampling signals with the corresponding at least two preset amplitude values to obtain at least two preliminary comparison result values; Wherein, the preliminary comparison result value is the frequency of the frequency domain sampling signal with an amplitude greater than the corresponding preset amplitude value in each segment of the segmented frequency domain sampling signal, and the number of frequency domain sampling signals of each frequency with an amplitude greater than the corresponding preset amplitude value in each segment of the segmented frequency domain sampling signal; the comparison result expression value includes the frequency of the frequency domain sampling signal with an amplitude greater than the corresponding preset amplitude value in each segment of the segmented frequency domain sampling signal, and the sum of the number of frequency domain sampling signals of the same frequency with an amplitude greater than the corresponding preset amplitude value in each segment of the segmented frequency domain sampling signal; Wherein, judging whether a pipeline is leaking based on the preliminary analysis results obtained by the data processor in the pipeline leakage detection device and a preset statistical model includes the following steps: comparing the preliminary analysis result obtained by the data processor in the pipeline leakage detection device with a preset statistical quantity corresponding to a preset statistical frequency of a preset statistical model to determine whether the pipeline is leaking; Wherein, in response to the fact that the sum of the number of frequency domain sampling signals of the preset statistical frequency in the preliminary analysis result obtained by the data processor in the pipeline leakage detection equipment is greater than the preset statistical quantity corresponding to the preset statistical frequency in the preset statistical model, pipeline leakage is determined.

2. The pipeline leakage detection method based on an acceleration sensor according to claim 1, wherein: In the process of performing domain conversion on the original sampled signal by the data processor in the pipeline leakage detection device, the data processor in the pipeline leakage detection device performs domain conversion on the original sampled signal by using a discrete Fourier algorithm.

3. The pipeline leakage detection method based on acceleration sensor according to claim 1, wherein: Sampling the original sampling signal by a pipeline leakage detection device includes the following steps: The original sampling signal from the adaptive gain signal conditioning circuit is received by a sampling unit in the pipeline leakage detection device.

4. The pipeline leakage detection method based on acceleration sensor according to claim 1, wherein: Sampling the original sampling signal by a pipeline leakage detection device includes the following steps: The raw sampling data collected by the acceleration sensor is acquired by a sampling unit in the pipeline leakage detection device at a preset sampling frequency within a preset duration.

5. The pipeline leakage detection method based on acceleration sensor according to claim 4, wherein: The raw sampling data collected by the acceleration sensor is acquired by a sampling unit in the pipeline leakage detection device at a preset sampling frequency within a preset duration, comprising the steps of: The original sampling signal is saved to a flash memory by the sampling unit in the pipeline leakage detection device according to a preset sampling frequency.

6. The pipeline leakage detection method based on acceleration sensor according to claim 1, wherein: The data processor in the pipeline leakage detection device is a single chip microcomputer.

Images