Water supply network leakage monitoring and early warning method and system based on hydrodynamic noise, medium and equipment

Abstract

The invention relates to the field of leakage early warning of urban water supply pipe networks, and discloses a water supply pipe network leakage monitoring and early warning method, system, medium and equipment based on hydrodynamic noise, and the method comprises the steps: determining a monitoring site, analyzing a hydrodynamic noise source and a hydrodynamic noise generation site, and simulating the generation of the hydrodynamic noise; hydrodynamic noise data of the monitoring site are obtained, noise filtering processing is carried out on the hydrodynamic noise data, feature extraction is carried out, and extracted time-frequency domain features serve as characterization parameters of sound signals; and based on the extracted time-frequency domain features, adopting a random forest to construct a leakage identification early warning model, and judging whether fluid flow in the pipe is abnormal or not so as to carry out identification early warning on an abnormal state. According to the invention, acoustic vibration caused by leakage of the water supply network is deeply analyzed, leakage identification and early warning are carried out according to hydrodynamic noise characteristics, and effective monitoring of leakage events in a monitoring coverage range of the sensor is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of leakage early warning of urban water supply pipe networks, and in particular to a method, system, medium and equipment for monitoring and early warning of leakage of water supply pipe networks based on hydrodynamic noise. Background Art

[0002] Water supply network leakage identification and early warning technology is a vital part of the maintenance and management of modern urban infrastructure. With the continuous advancement of urbanization, the water supply network system has become increasingly large and complex, and the problem of pipeline leakage has become increasingly prominent. Pipeline leakage not only leads to the waste of precious water resources, but also may cause damage to underground infrastructure and environmental problems. Therefore, how to effectively identify leakage points in the water supply network has become an important part of the management and maintenance of urban water supply systems. The water supply network in modern cities has increased the difficulty of leak detection due to its large scale, complex structure, and diverse pipeline materials. Traditional manual inspection and pressure monitoring methods can no longer meet the needs of efficient and accurate detection. The frequent leakage of aging pipelines not only increases maintenance costs, but may also interfere with urban traffic and residents' lives, and even cause secondary disasters. Therefore, a variety of leak detection technologies are needed to deal with the problem of water supply network leakage monitoring in complex scenarios.

[0003] The leakage identification and early warning technology of the water supply network has been derived and iterated through continuous theoretical research and engineering practice. The existing water supply network leakage monitoring and early warning technologies include but are not limited to the following technical methods: pressure data monitoring, flow data monitoring, pipeline acoustic monitoring, pipeline endoscopy technology, etc. Monitoring and early warning of pipeline leakage incidents in engineering requires not only high-precision detection technology, but also the actual operating conditions of the water supply network. The pipeline outer wall detection method in the acoustic monitoring method is a non-destructive testing technology that does not affect the normal operation of the water supply network and the structure of the water supply pipeline system. Using high-precision vibration sensors to collect acoustic signals on the water supply pipeline, and analyzing relevant features to identify and warn of leaks is a key issue in the research field of acoustic monitoring of water supply network leaks.

[0004] Due to the complexity and diversity of the water supply pipeline system and the noise interference around the monitoring well, the acoustic monitoring technology of the pipeline outer wall faces the current problems of serious interference signals and unclear acoustic signal characteristics. Therefore, it is necessary to have a clear understanding of the acoustic vibration caused by pipeline leakage, and to achieve effective monitoring and early warning of water supply pipeline leakage by reasonably arranging sensor positions, analyzing acoustic signal characteristics in multiple ways, and using a combination of mechanism cognition and data-driven technology. Summary of the invention

[0005] In view of the above problems, the purpose of the present invention is to provide a water supply network leakage monitoring and early warning method, system, medium and equipment based on hydrodynamic noise. By deeply analyzing the acoustic vibration caused by the leakage of the water supply network, leakage identification and early warning are carried out according to the characteristics of hydrodynamic noise, so as to achieve effective monitoring of leakage events within the monitoring coverage of the sensor.

[0006] To achieve the above-mentioned purpose, in the first aspect, the technical solution adopted by the present invention is: a water supply network leakage monitoring and early warning method based on hydrodynamic noise, which includes: determining the monitoring site, analyzing the source and generation site of the hydrodynamic noise, so as to simulate the generation of hydrodynamic noise; obtaining the hydrodynamic noise data of the monitoring site, filtering the hydrodynamic noise data, and performing feature extraction, and using the extracted time-frequency domain features as the characterization parameters of the acoustic signal; constructing a leakage identification and early warning model based on the extracted time-frequency domain features using random forests to determine whether the fluid flow in the pipe is abnormal, so as to identify and warn of the abnormal state.

[0007] Furthermore, the monitoring sites are selected based on the upstream and downstream relationship of the water flow in the pipe network, and the hydrodynamic noise excitation points located upstream are selected, and the locations near the hydrodynamic noise source points of the elbows and / or tees are selected.

[0008] Furthermore, the hydrodynamic noise data of the monitoring site is obtained, and the hydrodynamic noise data is subjected to noise filtering, including:

[0009] The acoustic monitoring sensors are placed at monitoring sites near pipeline accessories to collect hydrodynamic noise data in different scenarios concentrated in the low frequency band;

[0010] The hydrodynamic noise data under different scenarios are filtered out to remove the pipeline interference noise that does not meet the characteristics of hydrodynamic noise and construct a hydrodynamic noise dataset.

[0011] Furthermore, wavelet transform is used to perform wavelet denoising on the collected hydrodynamic noise data.

[0012] Furthermore, the time-frequency domain features include: time-domain energy, time-domain average energy, time-domain maximum energy, time-domain kurtosis, time-domain skewness, frequency-domain shape factor, frequency-domain impulse factor, frequency-domain kurtosis factor and Mel-frequency cepstrum coefficient.

[0013] Furthermore, a leakage identification and early warning model is constructed using random forest based on the extracted time-frequency domain features, including:

[0014] Perform feature compression and information reconstruction on the extracted time-frequency domain features to obtain a feature information matrix;

[0015] The leakage identification and early warning model is constructed based on the feature information matrix, and multiple independent identification decision trees are established by adopting the mode of random data combination and random feature extraction;

[0016] The classification of data is comprehensively determined through the recognition results of multiple decision trees to determine whether a leakage event occurs at the monitoring location.

[0017] In the second aspect, the technical solution adopted by the present invention is: a water supply network leakage monitoring and early warning system based on hydrodynamic noise, which includes: a data analysis module, which determines the monitoring site, analyzes the source and generation site of the hydrodynamic noise, so as to simulate the generation of hydrodynamic noise; a feature extraction module, which obtains the hydrodynamic noise data of the monitoring site, performs noise filtering on the hydrodynamic noise data, and performs feature extraction, and uses the extracted time-frequency domain features as the characterization parameters of the acoustic signal; an early warning module, which uses random forests based on the extracted time-frequency domain features to construct a leakage identification and early warning model, determines whether the fluid flow in the pipe is abnormal, and identifies and warns of abnormal conditions.

[0018] Furthermore, the monitoring sites are selected based on the upstream and downstream relationship of the water flow in the pipe network, and the hydrodynamic noise excitation points located upstream are selected, and the locations near the hydrodynamic noise source points of the elbows and / or tees are selected.

[0019] In a third aspect, the technical solution adopted by the present invention is: a computer-readable storage medium storing one or more programs, wherein the one or more programs include instructions, and when the instructions are executed by a computing device, the computing device executes any one of the above methods.

[0020] In a fourth aspect, the technical solution adopted by the present invention is: a computing device, comprising: one or more processors, a memory and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for executing any of the above methods.

[0021] The present invention adopts the above technical solution, which has the following advantages:

[0022] 1. Since hydrodynamic noise is generated by inherent pipe accessories, its characteristic law is more recognizable than general non-stationary signals. When monitoring pipeline acoustic vibration, pipeline vibration caused by leakage is usually related to the characteristics of the leakage point, including but not limited to the shape of the leakage point, the location of the leakage point, the soil environment around the leakage point, etc. This causes the acoustic vibration caused by leakage to usually have problems such as instability, variable state, and irregular intensity.

[0023] 2. Leakage events will affect the state changes of the fluid in the pipe, so the change of hydrodynamic noise can be used as indirect observation data of leakage events. The essence of leakage events is the loss of fluid in the pipe, so the fluid loss in the downstream will be supplemented from the upstream, and the flow form of the fluid in the pipe will be different from the normal state. Its monitoring distance is longer than that of general acoustic monitoring and the coverage is larger.

[0024] 3. The frequency band of the hydrodynamic noise distribution of the present invention is more concentrated than that of general noise, which is suitable for feature extraction and characterization in interference environments. Due to the complex environment around the pipeline well, the diverse interference noise, and the characteristics of randomness and non-steady state, removing noise interference is an important content in acoustic monitoring. Compared with general non-stationary signals, the regularity of the vibration mode of the sound source of hydrodynamic noise has advantages in separating data. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a flow chart of a water supply network leakage monitoring and early warning method based on hydrodynamic noise in an embodiment of the present invention;

[0026] Figure 2 is a diagram of fluid flow rate and pressure distribution in the elbow structure in an embodiment of the present invention;

[0027] Figure 3 is a power spectrum of the hydrodynamic noise of the elbow in the embodiment of the present invention;

[0028] Figure 4 This is a layout diagram of the elbow-tee hydrodynamic noise monitoring in an embodiment of the present invention;

[0029] Figure 5 is a wavelet denoising result analysis diagram in an embodiment of the present invention;

[0030] Figure 6 1 is a structural diagram of a random forest model in an embodiment of the present invention. DETAILED DESCRIPTION

[0031] In order to solve the current problems faced by the existing pipeline outer wall acoustic monitoring technology, such as serious interference signals and unclear acoustic signal characteristic information, the present invention provides a water supply network leakage monitoring and early warning method, system, medium and equipment based on hydrodynamic noise. First, the source and generation site of the hydrodynamic noise are analyzed to explain that the intensity characteristics of the hydrodynamic noise are correlated with the flow state of the fluid in the pipeline. Pipeline leakage will cause the fluid in the pipe to present a flow pattern inconsistent with the normal state, which in turn affects the correlation change of the hydrodynamic noise. With the help of the hydrodynamic noise data of the elbow, tee and other positions collected by the vibration sensor, the abnormal flow of the fluid in the pipe is determined. For the hydrodynamic noise in normal and abnormal states, data processing and feature extraction are performed, and a hydrodynamic noise abnormality early warning method is established through a model recognition method. The hydrodynamic noise monitored by the present invention is a relatively stable sound data, which has a large difference from other pipeline interference noises, which is conducive to data noise reduction processing and feature extraction. At the same time, the monitoring range covers the downstream area of ​​the monitoring point, with a wide monitoring coverage area.

[0032] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the described embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the present invention.

[0033] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0034] In one embodiment of the present invention, a water supply network leakage monitoring and early warning method based on hydrodynamic noise is provided, which uses a highly sensitive vibration sensor to monitor hydrodynamic noise, analyzes the characteristics of the collected data, and is used to warn of water supply network leakage events. In this embodiment, Figure 1 As shown, the method comprises the following steps:

[0035] 1) Determine the monitoring sites, analyze the sources and generation sites of hydrodynamic noise, and simulate the generation of hydrodynamic noise;

[0036] 2) Obtaining the hydrodynamic noise data of the monitoring site, filtering the hydrodynamic noise data, and performing feature extraction, and using the extracted time-frequency domain features as the characterization parameters of the acoustic signal;

[0037] 3) Based on the extracted time-frequency domain features, a random forest is used to construct a leakage identification and warning model to determine whether the fluid flow in the pipe is abnormal, so as to identify and warn of abnormal conditions.

[0038] In the above step 1), the monitoring site is selected based on the upstream and downstream relationship of the water flow in the pipe network, and the hydrodynamic noise excitation point located upstream is selected, and the location near the hydrodynamic noise source point of the elbow and / or tee is selected.

[0039] In this embodiment, the source of the acoustic vibration signal collected on the pipe is analyzed by simulating the flow state of the fluid in the water supply network. There are various acoustic signals that can be collected on the water supply pipe, among which the noise generated by the friction between the turbulent fluid and the pipe wall is defined as hydrodynamic noise. Hydrodynamic noise is usually generated at the pipe accessories in the water supply network, such as elbows, tees, and valves that are not fully opened. The fluid in the pipe is in a flowing state. During the flow process, the fluid is blocked at the pipe accessories, thereby generating turbulence. The interaction between turbulence and the pipe wall generates hydrodynamic noise. By simulating the fluid state at the pipe accessories, the fluid pressure and flow velocity at different positions at the pipe accessories are displayed, reflecting hydrodynamic noise of different intensities.

[0040] The generation of hydrodynamic noise is simulated and its theoretical characteristics are analyzed, taking the hydrodynamic noise at the elbow as an example. CFD (computational fluid dynamics) is used for simulation. After the steps of geometry construction, mesh division, calculation and solution, and post-processing, the simulation of the research object is completed. Figure 2 As shown in the figure, the simulation results show the fluid velocity and pressure distribution at the elbow. It can be analyzed that the hydrodynamic noise at the elbow is related to the flow velocity, and the hydrodynamic noise it excites comes from the mutual friction between the fluid particles and the pipe wall. Since the turbulence is relatively weak, the vibration sound wave generated is a signal with weak intensity and low frequency. The experimental test results also show the same result. Compared with the vibration sound wave at the leakage point, the hydrodynamic noise has a lower intensity and a lower frequency distribution at the sound source, such as Figure 3 The hydrodynamic noise spectrum at the elbow shown.

[0041] In the above step 2), the hydrodynamic noise data of the monitoring site is obtained, and the hydrodynamic noise data is subjected to noise filtering, including the following steps:

[0042] 2.1) The acoustic monitoring sensors are placed at monitoring sites near pipeline accessories to collect hydrodynamic noise data in different scenarios concentrated in the low frequency band; the low frequency band is below 500 Hz.

[0043] 2.2) The hydrodynamic noise data under different scenarios are filtered to remove the pipeline interference noise that does not meet the characteristics of hydrodynamic noise and construct a hydrodynamic noise dataset.

[0044] In this embodiment, hydrodynamic noise is generated at the pipe attachment, propagates along the pipe, and has the maximum vibration intensity at the pipe attachment. Therefore, the location of the point for collecting hydrodynamic noise is located near the pipe attachment. At the same time, since the generation of hydrodynamic noise is related to the flow state of the pipeline fluid, the monitoring point located at the upstream position is more likely to cover the downstream water flow state changes, and the vibration sensor is arranged upstream of the pipe.

[0045] Specifically, a hydrodynamic noise data set is collected. Hydrodynamic noise is closely related to the turbulent state in the pipe and the type of pipe accessories. The data set here is to enrich the understanding of hydrodynamic noise. The data set includes hydrodynamic noise under different conditions, such as pressure, flow rate, and accessory type. Since hydrodynamic noise is a relatively weak energy signal, its collection point needs to be arranged at a specific pipe accessory location. When a leak occurs downstream, the change in flow state can be transmitted to the upstream position, and the corresponding hydrodynamic noise can be collected. Figure 4 As shown, it illustrates that when a leak occurs in the tee-elbow structure, the leakage state at the downstream position is transmitted to the tee-elbow structure through the fluid flow, and the flow state excites hydrodynamic noise different from the normal state.

[0046] In this embodiment, the construction of the hydrodynamic noise data set is as follows: Common pipe accessories in the water supply network include elbows, tees, valves, etc. The hydrodynamic noise corresponding to each pipe accessory has different characteristics. Collect hydrodynamic noise data in different situations, analyze the characteristics of noise data, and establish a hydrodynamic noise database to provide data support for leak identification and early warning.

[0047] In this embodiment, wavelet transform is used to perform wavelet denoising on the collected hydrodynamic noise data. The principle of wavelet denoising is not described here in detail. The original signal is processed and transformed using db2 wavelet to perform feature extraction. Figure 5 As shown in the figure, the coefficients of each signal component generated during the wavelet denoising process are shown. A 5-layer wavelet denoising decomposition is used, and the residual term represents the remaining amount after decomposition. After the signal is processed by denoising, some interference noise and signal fluctuations are removed.

[0048] Specifically, the acoustic data collected on the water supply network includes multiple components, such as hydrodynamic noise, leakage noise, interference noise transmitted to the pipeline, etc. The acoustic data monitored by the sensor is decoupled, the characteristic components of the hydrodynamic noise are extracted and characterized, and the hydrodynamic noise components are analyzed. In this embodiment, wavelet transform is used to analyze the collected leakage signal, separate different signal components, and analyze the main components of the hydrodynamic noise.

[0049] In the above step 2), the time-frequency domain features include: time domain energy, time domain average energy, time domain maximum energy, time domain kurtosis, time domain skewness, frequency domain shape factor, frequency domain impulse factor, frequency domain kurtosis factor and Mel-frequency cepstral coefficients and other parameters.

[0050] In this embodiment, the calculation formulas of various parameters are as follows:

[0051] Time domain feature calculation, the signal is a time series X = [x1 x2 x3 ... x i ... x N ]; where x Nrepresents the Nth sequence segment of signal X. Each sequence segment is an equally spaced sampling of signal X, from x1 to x N Constitute the entire timing signal X.

[0052] The time domain energy E calculation formula is:

[0053]

[0054] Time domain average energy E mean Calculation formula:

[0055]

[0056] Maximum energy in time domain E max Calculation formula:

[0057] E max =max[x i ]

[0058] The calculation formula of time domain kurtosis Kurt(x) is:

[0059] Kurt(x)=E[(x-μ) 4 ] / (E[(x-μ) 2 ]) 2

[0060] Among them, x represents the time domain value of the signal, and μ represents the time domain mean value of the signal.

[0061] The calculation formula of time domain skew (x) is:

[0062] Skew(x)=E[(x-μ) 3 ] / (E[(x-μ) 2 ]) 2

[0063] Frequency domain feature calculation, the signal is first converted from time domain to frequency domain: F = [f1 f2 f3 ... f i ... f M ]; This expression is the calculated value of the frequency F in different frequency bands when the signal X is converted to the frequency domain space, f M is the Mth value in the frequency domain.

[0064] Frequency domain shape factor FD_shape calculation formula:

[0065]

[0066] Where M represents the number of frequency domain values, f i Represents the i-th frequency domain value.

[0067] Frequency domain pulse factor FD_pulse calculation formula:

[0068]

[0069] Frequency domain kurt factor FD_kurt calculation formula:

[0070]

[0071] in, represents the frequency domain mean.

[0072] The calculation method of Mel cepstral coefficient is to transform the signal to the Mel frequency scale and then perform discrete cosine transform to obtain the Mel cepstral coefficient. The relationship between Mel frequency and normal frequency is:

[0073]

[0074] Among them, f mel represents the Mel frequency and f represents the normal frequency.

[0075] The time-frequency domain features are extracted as the characterization parameters of the signal, and the collected acoustic signal is compressed for data features.

[0076] In the above step 3), the classification and recognition process uses the random forest model, the basic principle of which is to linearly combine multiple decision trees to form an integrated model. In the random forest, each decision tree is independent of each other, and the final result is generated by the weighted votes of each tree. Different decision trees are generated by randomly extracting samples and features, and each decision tree is given independent judgment ability, which enhances the robustness and accuracy of the entire model. Figure 6 As shown in the figure, the established random forest model determines whether a leakage event occurs at the monitoring location.

[0077] In this embodiment, a leakage identification and early warning model is constructed using random forest based on the extracted time-frequency domain features, including the following steps:

[0078] 3.1) Perform feature compression and information reconstruction on the extracted time-frequency domain features to obtain a feature information matrix;

[0079] 3.2) Construct a leakage identification and early warning model based on the feature information matrix, adopt a mode of random data combination and random feature extraction, and establish multiple independent identification decision trees;

[0080] 3.3) The classification of data is comprehensively determined through the recognition results of multiple decision trees to determine whether a leakage event occurs at the monitoring location.

[0081] During the classification process, the characteristic representations corresponding to different types of pipe accessories are considered, mainly elbows, tees, and valve structures.

[0082] In one embodiment of the present invention, a water supply network leakage monitoring and early warning system based on hydrodynamic noise is provided, which comprises:

[0083] The data analysis module determines the monitoring sites, analyzes the sources and generation sites of hydrodynamic noise, and simulates the generation of hydrodynamic noise;

[0084] The feature extraction module obtains the hydrodynamic noise data of the monitoring site, performs noise filtering on the hydrodynamic noise data, and performs feature extraction, and uses the extracted time-frequency domain features as the characterization parameters of the acoustic signal;

[0085] The early warning module uses random forest to build a leakage identification and early warning model based on the extracted time-frequency domain features to determine whether the fluid flow in the pipe is abnormal, so as to identify and warn of abnormal conditions.

[0086] In the above embodiment, the monitoring site is selected based on the upstream and downstream relationship of the water flow in the pipe network, and the hydrodynamic noise excitation point located upstream is selected, and the location near the hydrodynamic noise source point of the elbow and / or tee is selected.

[0087] In the above embodiment, the hydrodynamic noise data of the monitoring site is obtained, and the hydrodynamic noise data is subjected to noise filtering, including:

[0088] The acoustic monitoring sensors are placed at monitoring sites near pipeline accessories to collect hydrodynamic noise data in different scenarios concentrated in the low frequency band;

[0089] The hydrodynamic noise data under different scenarios are filtered out to remove the pipeline interference noise that does not meet the characteristics of hydrodynamic noise and construct a hydrodynamic noise dataset.

[0090] In this embodiment, wavelet transform is used to perform wavelet denoising on the collected hydrodynamic noise data.

[0091] In the above embodiment, the time-frequency domain features include: time-domain energy, time-domain average energy, time-domain maximum energy, time-domain kurtosis, time-domain skewness, frequency-domain shape factor, frequency-domain impulse factor, frequency-domain kurtosis factor and Mel-frequency cepstrum coefficient.

[0092] In the above embodiment, a leakage identification and warning model is constructed using random forest based on the extracted time-frequency domain features, including:

[0093] Perform feature compression and information reconstruction on the extracted time-frequency domain features to obtain a feature information matrix;

[0094] The leakage identification and early warning model is constructed based on the feature information matrix, and multiple independent identification decision trees are established by adopting the mode of random data combination and random feature extraction;

[0095] The classification of data is comprehensively determined through the recognition results of multiple decision trees to determine whether a leakage event occurs at the monitoring location.

[0096] The system provided in this embodiment is used to execute the above-mentioned method embodiments. Please refer to the above-mentioned embodiments for specific processes and detailed contents, which will not be repeated here.

[0097] A computing device provided in one embodiment of the present invention may be a terminal, which may include: a processor, a communications interface, a memory, a display screen, and an input device. The processor, the communications interface, and the memory communicate with each other through a communication bus. The processor is used to provide computing and control capabilities. The memory includes a non-volatile storage medium and an internal memory, wherein the non-volatile storage medium stores an operating system and a computer program, and the computer program is executed by the processor to implement the methods in the above embodiments; the internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be implemented through WIFI, a management network, NFC (near field communication) or other technologies. The display screen may be a liquid crystal display screen or an electronic ink display screen, and the input device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computing device, or an external keyboard, touchpad or mouse, etc. The processor may call the logic instructions in the memory.

[0098] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0099] In one embodiment of the present invention, a computer program product is provided, wherein the computer program product includes a computer program stored on a non-transitory computer-readable storage medium, wherein the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the methods provided by the above-mentioned method embodiments.

[0100] In one embodiment of the present invention, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium stores server instructions, and the computer instructions enable a computer to execute the methods provided in the above embodiments.

[0101] The above embodiment provides a computer-readable storage medium, whose implementation principle and technical effect are similar to those of the above method embodiment, and will not be repeated here.

[0102] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0103] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0104] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0105] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A water supply network leakage monitoring and early warning method based on hydrodynamic noise, characterized in that: include: Determine monitoring sites, analyze the sources and generation sites of hydrodynamic noise, and simulate the generation of hydrodynamic noise; Obtain the hydrodynamic noise data of the monitoring site, filter the hydrodynamic noise data, perform feature extraction, and use the extracted time-frequency domain features as the characterization parameters of the acoustic signal; Based on the extracted time-frequency domain features, a random forest is used to construct a leakage identification and warning model to determine whether the fluid flow in the pipe is abnormal, so as to identify and warn of the abnormal state.

2. The water supply network leakage monitoring and early warning method based on hydrodynamic noise as claimed in claim 1, characterized in that: The monitoring sites are selected based on the upstream and downstream relationship of the water flow in the pipe network. The upstream hydrodynamic noise excitation points are selected, and the locations near the hydrodynamic noise sources of the elbows and / or tees are selected.

3. The water supply network leakage monitoring and early warning method based on hydrodynamic noise as claimed in claim 1, characterized in that: Obtain the hydrodynamic noise data of the monitoring site and perform noise filtering on the hydrodynamic noise data, including: The acoustic monitoring sensors are placed at monitoring sites near pipeline accessories to collect hydrodynamic noise data in different scenarios concentrated in the low frequency band; The hydrodynamic noise data under different scenarios are filtered out to remove the pipeline interference noise that does not meet the characteristics of hydrodynamic noise and construct a hydrodynamic noise dataset.

4. The water supply network leakage monitoring and early warning method based on hydrodynamic noise as claimed in claim 3 is characterized in that: Wavelet transform is used to filter the collected hydrodynamic noise data.

5. The water supply network leakage monitoring and early warning method based on hydrodynamic noise as claimed in claim 1, characterized in that: The time-frequency domain features include: time-domain energy, time-domain average energy, time-domain maximum energy, time-domain kurtosis, time-domain skewness, frequency-domain shape factor, frequency-domain impulse factor, frequency-domain kurtosis factor and Mel-cepstral coefficient.

6. The water supply network leakage monitoring and early warning method based on hydrodynamic noise as claimed in claim 1, characterized in that: Based on the extracted time-frequency domain features, a random forest is used to build a leakage identification and warning model, including: Perform feature compression and information reconstruction on the extracted time-frequency domain features to obtain a feature information matrix; The leakage identification and early warning model is constructed based on the feature information matrix, and multiple independent identification decision trees are established by adopting the mode of random data combination and random feature extraction; The classification of data is comprehensively determined through the recognition results of multiple decision trees to determine whether a leakage event occurs at the monitoring location.

7. A water supply network leakage monitoring and early warning system based on hydrodynamic noise, characterized in that: include: The data analysis module determines the monitoring sites, analyzes the sources and generation sites of hydrodynamic noise, and simulates the generation of hydrodynamic noise; The feature extraction module obtains the hydrodynamic noise data of the monitoring site, performs noise filtering on the hydrodynamic noise data, and performs feature extraction, and uses the extracted time-frequency domain features as the characterization parameters of the acoustic signal; The early warning module uses random forest to build a leakage identification and early warning model based on the extracted time-frequency domain features to determine whether the fluid flow in the pipe is abnormal, so as to identify and warn of abnormal conditions.

8. The water supply network leakage monitoring and early warning system based on hydrodynamic noise as claimed in claim 7, characterized in that: The monitoring sites are selected based on the upstream and downstream relationship of the water flow in the pipe network. The upstream hydrodynamic noise excitation points are selected, and the locations near the hydrodynamic noise sources of the elbows and / or tees are selected.

9. A computer-readable storage medium storing one or more programs, characterized in that: The one or more programs include instructions, which, when executed by a computing device, cause the computing device to perform any one of the methods of claims 1 to 6.

10. A computing device, characterized in that include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for executing any one of the methods described in claims 1 to 6.

Images