A monitoring device based on data aggregation in intelligent water affairs

Abstract

The application provides a kind of monitoring device based on data aggregation in intelligent water affairs, belongs to intelligent water affairs technical field, specifically includes: pressure monitoring module, power supply module, flow measurement module, leakage signal monitoring module;Pressure monitoring module is responsible for monitoring the water flow pressure in pipeline, when there is an anomaly, generate pressure anomaly signal, and transmit pressure anomaly signal to flow measurement module;Power supply module is responsible for providing electric energy;Flow measurement module is responsible for monitoring the water flow in pipeline, and when receiving pressure anomaly signal, when there is an anomaly, output flow anomaly signal, and transmit flow anomaly signal to leakage signal monitoring module;Leakage signal monitoring module receives the flow anomaly signal and opens, and monitors the water flow leakage signal in the pipeline, determines whether the pipeline exists leakage using the classification model based on GWO-DenseNet algorithm, so as to gather a variety of information together, improve the prediction accuracy.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of intelligent water affairs, and particularly relates to a monitoring device based on data aggregation in intelligent water affairs. BACKGROUND

[0002] With the continuous acceleration of urbanization, the tension of water resources is deteriorating, and how to effectively deal with the water crisis has become a major issue that a country must face in economic development. According to statistics, by 2015, the total length of the water supply pipe network in China reached 710,000 kilometers, accounting for the first place in municipal pipe networks, and grew at a construction speed of more than 30,000 kilometers per year. However, since a considerable number of pipe networks in China have been in service for more than 30 years, and some pipe sections have even been in service for 50 years, the corrosion problem of pipe networks in China is serious, and the running, leaking, dripping and leaking phenomena are very serious. Pipe network leakage will cause the water pressure of the pipe network to drop, and in order to maintain normal water supply, the water supply pressure needs to be increased, which not only increases energy consumption, but also makes the leakage more serious, forming a vicious cycle and causing greater resource waste.

[0003] In the paper "Research on Water Supply Pipe Network Leakage Monitoring System", the author Shi Shangshang obtained the frequency domain characteristics of the background noise signal and the leakage signal of the water supply pipeline by time domain analysis, frequency domain analysis and time-frequency joint analysis of the leakage signal. In order to realize the extraction of the leakage signal characteristics, a wavelet denoising time delay estimation method for locating the leakage point of the water supply pipe network is proposed, the threshold value is obtained by using the threshold function in the MATLAB toolbox, the signal is decomposed by wavelet, and then a band-pass filter is used to filter the denoised signal. The position of the leakage point is determined by time delay estimation of the processed signal, but in the field of water supply, the monitoring device is distributed on the water supply pipeline, and the pressure, temperature, PH value, residual chlorine, turbidity and other parameters of the water supply are collected, there is no convenient power supply measure, generally using storage batteries and other ways to supply power, and the water supply pipeline is generally in normal state. If real-time frequency spectrum analysis is performed, it will cause great waste of electric energy, which is not conducive to the stable operation of the overall device, and the accuracy of the analysis of the pipeline leakage by relying only on frequency spectrum analysis is not high.

[0004] In view of the above technical problems, the application provides a monitoring device based on data aggregation in intelligent water affairs. SUMMARY

[0005] In order to achieve the purpose of the application, the application adopts the following technical solutions:

[0006] According to one aspect of the application, a monitoring device based on data aggregation in intelligent water affairs is provided.

[0007] A monitoring device based on data aggregation in intelligent water affairs, characterized in that it specifically comprises:

[0008] a pressure monitoring module, a power supply module, a flow measurement module, a leakage signal monitoring module;

[0009] The pressure monitoring module is responsible for monitoring the water flow pressure in the pipeline, and generating a pressure anomaly signal when the water flow pressure changes by more than a first pressure threshold within a first time threshold, and transmitting the pressure anomaly signal to the flow measurement module.

[0010] The power supply module is responsible for providing power to the pressure monitoring module, the flow measurement module, and the leakage signal monitoring module.

[0011] The flow measurement module is responsible for monitoring the water flow in the pipeline, and when it receives the pressure anomaly signal, it determines whether the water flow changes by more than a first flow threshold within a second time threshold, and outputs a flow anomaly signal and transmits the flow anomaly signal to the leakage signal monitoring module.

[0012] The leakage signal monitoring module is turned on when it receives the flow anomaly signal, and monitors the water flow leakage signal in the pipeline, and uses a classification model based on the GWO-DenseNet algorithm to determine whether there is a leak.

[0013] By using the pressure monitoring module, when the pressure changes abnormally within the first time threshold, a pressure anomaly signal is sent, and when the flow measurement device receives the pressure anomaly signal, it analyzes whether the flow changes abnormally within the second time threshold, and when there is an abnormality, it outputs a flow anomaly signal and transmits it to the leakage signal monitoring module. After receiving the flow anomaly signal, the leakage signal monitoring module starts monitoring the leakage signal, and determines whether there is a leak through a classification model based on the GWO-DenseNet algorithm, thereby solving the problem of excessive power waste caused by real-time spectral analysis, which is not conducive to the stable operation of the overall device. By combining the pressure and flow measurement results, the leakage signal monitoring module is turned on in a timely manner, further saving power and promoting the stable operation of the monitoring device. It also solves the problem of low accuracy of relying on spectral analysis to analyze pipeline leaks. Through the comprehensive consideration of pressure, flow, and spectral leakage signals, the accuracy of the judgment is further improved.

[0014] The pressure abnormal signal is generated when the pressure variation of the water flow pressure within the first time threshold is greater than the first pressure threshold, thereby avoiding the problem of false generation of the pressure abnormal signal caused by sudden abnormal signal, further improving the reliability and stability of the output signal of the pressure monitoring module, and when the flow measurement module receives the pressure abnormal signal, the flow abnormal signal is output when the water flow variation within the second time threshold is greater than the first flow threshold, thereby avoiding the problem of false generation of the pressure abnormal signal caused by sudden abnormal signal, further improving the reliability and stability of the output signal of the pressure monitoring module, and further saving the power of the flow measurement module, promoting the stability of the device, and by using the leakage signal monitoring module, the water flow leakage signal in the pipeline is monitored, and by using the step-by-step method, the leakage signal monitoring module is opened when the conditions are met, thereby further reducing the power consumption of the device, further improving the stability of the overall device, and combining the pressure, flow, and leakage signal together to evaluate the pipeline leakage, thereby further improving the accuracy of the final judgment.

[0015] The further technical solution is that it further includes a second pressure threshold, when the pressure variation of the water flow pressure within the first time threshold is greater than the second threshold, and the duration of the pressure is greater than the third time threshold, at this time, the pressure abnormal signal is generated, and the pressure abnormal signal is transmitted to the leakage signal monitoring module, so that the leakage signal monitoring module is opened, and whether the pipeline has leakage is judged.

[0016] By setting the second pressure threshold, the problem of waste of water supply caused by too long judgment steps due to excessive leakage is avoided, the pipeline leakage can be found within the first time, the judgment sensitivity is further improved on the basis of ensuring stable and reliable judgment results, and by using the pressure variation within the first time threshold being greater than the second threshold, and the duration of the pressure greater than the second threshold being greater than the third time threshold, only when the variation maintains for a certain time, it is determined that there is a problem, and the stability and reliability of the overall judgment accuracy are ensured.

[0017] The further technical solution is that it further includes a third pressure threshold, when the pressure variation of the water flow pressure within the fourth time threshold is greater than the third pressure threshold, it is determined that the pressure monitoring module has an abnormality, and the pressure abnormal signal or the pressure abnormal signal is not generated.

[0018] By setting the third pressure threshold, when the pressure variation within the fourth time threshold is greater than the third pressure threshold, it is determined that the pressure monitoring module at this time is abnormal, thereby preventing the signal false alarm problem caused by the pressure monitoring module in the presence of abnormal cases, further improving the overall reliability.

[0019] Further, the first pressure threshold is less than the second pressure threshold, and the second pressure threshold is less than the third pressure threshold, and the first pressure threshold, the second pressure threshold, and the third pressure threshold are determined according to the pipe radius and the pipe position of water supply.

[0020] By determining the pressure threshold according to the pipe radius and the pipe position of water supply, the pressure threshold is adjusted according to the pipe condition, so that the overall threshold setting can be combined with the specific actual situation, further improving the scientificity of threshold setting.

[0021] Further, the fourth time threshold is less than the first time threshold, and the first time threshold is less than the third time threshold, and the first time threshold, the third time threshold, and the fourth time threshold are determined according to the pipe radius and the pipe position of water supply.

[0022] By determining the time threshold according to the pipe radius and the pipe position of water supply, the time threshold is adjusted according to the pipe condition, so that the overall threshold setting can be combined with the specific actual situation, further improving the scientificity of threshold setting.

[0023] Further, the fifth time threshold is also included, and when the flow variation within the fifth time threshold is greater than the second flow threshold, it is determined that the flow measurement module at this time is abnormal, and the flow abnormal signal is no longer sent.

[0024] By setting the second flow threshold, when the flow variation within the fifth time threshold is greater than the second flow threshold, it is determined that the flow measurement module at this time is abnormal, thereby preventing the signal false alarm problem caused by the flow measurement module in the presence of abnormal cases, further improving the overall reliability.

[0025] Further, the fifth time threshold is less than the second time threshold, and the first flow threshold is less than the second flow threshold, and the second time threshold, the fifth time threshold, the first flow threshold, and the second flow threshold are determined according to the pipe radius and the pipe position of water supply.

[0026] By determining the flow threshold and the time threshold according to the pipe radius and the pipe position of water supply, the flow threshold and the time threshold are adjusted according to the pipe condition, so that the overall threshold setting can be combined with the specific actual situation, further improving the scientificity of threshold setting.

[0027] Further, the leakage signal monitoring module performs spectrum analysis on the leakage signal to obtain a spectrum graph of the leakage signal, and sends the spectrum graph to the GWO-DenseNet algorithm-based classification model to determine whether there is leakage.

[0028] The GWO-DenseNet algorithm-based classification model is used to classify and determine the leakage signal. Compared with the classification model using the CNN algorithm, the dense connection in the DenseNet can also alleviate the problem of gradient disappearance, can strengthen feature propagation and feature reuse, reduce the number of parameters, require less memory and computing resources, and achieve better performance.

[0029] Further, the GWO-DenseNet algorithm is used to optimize the weights and the number of hidden layers of the DenseNet algorithm by using the GWO algorithm.

[0030] By optimizing the weights and the number of hidden layers of the DenseNet algorithm by using the GWO algorithm, the overall classification efficiency and the overall prediction efficiency are further improved.

[0031] Further, the classification result is divided into three types: normal, slight leakage, and serious leakage.

[0032] By dividing the leakage result into three categories, it is ensured that maintenance is not performed due to leakage, and corresponding measures are taken according to the specific situation of the leakage. When there is slight leakage, the sensitivity of the judgment can be improved by reducing the pressure threshold of the pressure monitoring module and / or reducing the flow threshold of the flow measurement module. When there is serious leakage, immediate repair is required, thereby further improving the scientific nature of the classification and further reducing the occurrence of water stop problems caused by faults. BRIEF DESCRIPTION OF DRAWINGS

[0033] The above and other features and advantages of the present application will become more apparent by describing in detail example embodiments thereof with reference to the attached drawings.

[0034] Figure 1 is a configuration diagram of an intelligent water affairs monitoring device based on data aggregation according to embodiment 1.

[0035] Figure 2 is a flow chart of leakage judgment according to embodiment 1. DETAILED DESCRIPTION

[0036] Example implementations will now be described more fully with reference to the accompanying drawings. Example implementations can be implemented in any

[0037] The words "comprise", "comprising", "include", "including", and "has" or "having", when used herein, are used in their open-ended, conventional sense, that is, they are used to indicate open-ended including but not limited to.

[0038] With the accelerating urbanization process, the tension of water resources is deteriorating, and how to effectively deal with the water crisis has become a major issue that a country must face in economic development. According to statistics, by 2015, the total length of the water supply pipe network in China reached 710,000 kilometers, accounting for the first place in municipal pipe network, and grew at a construction speed of more than 30,000 kilometers per year. However, because a considerable number of pipe networks in China have been in service for more than 30 years, and some pipe sections have even been in service for 50 years, the corrosion problem of pipe network in China is prominent, and the running, leaking, dripping and leaking phenomenon is very serious. Pipe network leakage will cause the water pressure of the pipe network to drop, and in order to normal water supply, the water supply pressure needs to be increased, which not only increases the energy consumption, but also makes the leakage more serious, forming a vicious cycle and causing greater resource waste.

[0039] In the paper "Research on Water Supply Pipe Network Leakage Monitoring System", the author Shi Shangshang obtained the frequency domain characteristics of the background noise signal and the leakage signal of the water supply pipeline by time domain analysis, frequency domain analysis and time-frequency joint analysis of the leakage signal. In order to realize the extraction of the leakage signal characteristics, a wavelet denoising time delay estimation water supply pipe network leakage point positioning method is proposed, the threshold value is obtained by using the threshold function in the MATLAB toolbox, the signal is decomposed by wavelet, and then the band-pass filter is used to filter the denoised signal. The processed signal is subjected to time delay estimation to determine the leakage point position, but in the field of water supply, the monitoring device is distributed on the water supply pipeline, and the pressure, temperature, PH value, residual chlorine, turbidity and other parameters of the water supply are collected. There is no convenient power supply measure, and generally a storage battery and other ways are used for power supply. Moreover, the water supply pipeline is generally in normal state, and if real-time frequency spectrum analysis is performed, it will cause great waste of electric energy, which is not conducive to the stable operation of the overall device, and the accuracy of the analysis of the pipeline leakage by relying on frequency spectrum analysis is not high.

[0040] Example 1

[0041] To solve the above problems, according to one aspect of the present application, as Figure 1As shown, a data aggregation-based monitoring device in intelligent water affairs is provided.

[0042] A data aggregation-based monitoring device in intelligent water affairs, characterized in that it specifically comprises:

[0043] A pressure monitoring module, a power supply module, a flow measurement module, and a leakage signal monitoring module.

[0044] The pressure monitoring module is responsible for monitoring the water flow pressure in the pipeline and generating a pressure anomaly signal when the pressure variation within a first time threshold is greater than a first pressure threshold, and transmitting the pressure anomaly signal to the flow measurement module.

[0045] The power supply module is responsible for providing power to the pressure monitoring module, flow measurement module, and leakage signal monitoring module.

[0046] The flow measurement module is responsible for monitoring the water flow in the pipeline and outputting a flow anomaly signal when the water flow variation within a second time threshold is greater than a first flow threshold after receiving the pressure anomaly signal, and transmitting the flow anomaly signal to the leakage signal monitoring module.

[0047] The leakage signal monitoring module is turned on when it receives the flow anomaly signal and monitors the water flow leakage signal in the pipeline, and uses a classification model based on the GWO-DenseNet algorithm to determine whether there is a leak.

[0048] For example, when the pressure variation within 1 minute is 50MPa, the first pressure threshold is 40MPa, and the pressure monitoring module outputs a pressure anomaly signal, when the flow measurement module receives the pressure anomaly signal, the measured water flow variation within 1 minute is 6t, and the first flow threshold is 5t, the flow measurement module outputs a flow anomaly signal, when the leakage signal monitoring module receives the flow anomaly signal, it starts to monitor the water flow anomaly signal, and based on the monitoring result, it determines whether there is a leak through the classification model, if the prediction result is a leak, the prediction result is output to the monitoring personnel.

[0049] By adopting the pressure monitoring module, when the pressure variation within the first time threshold is abnormal, a pressure abnormal signal is sent out. When the flow measurement device receives the pressure abnormal signal, it analyzes whether the flow variation within the second time threshold is abnormal. When there is an abnormality, a flow abnormal signal is output, and the flow abnormal signal is transmitted to the leakage signal monitoring module. After the flow abnormal signal is obtained, the leakage signal monitoring module starts monitoring the leakage signal and determines whether there is a leakage through the classification model based on the GWO-DenseNet algorithm. Thus, the problem of great waste of electric energy caused by real-time spectrum analysis is solved, which is not conducive to the stable operation of the overall device. By combining the pressure and flow measurement results, the leakage signal monitoring module is started in time, which further saves electric energy and promotes the stable operation of the monitoring device. The problem of low accuracy of analyzing pipeline leakage by relying on spectrum analysis is solved. Through comprehensive consideration of pressure, flow, and spectrum leakage signals, the accuracy of judgment is further improved.

[0050] By generating a pressure abnormal signal when the pressure variation of the water flow within the first time threshold is greater than the first pressure threshold, the problem of false generation of the pressure abnormal signal caused by sudden abnormal signals is avoided. The reliability and stability of the output signal of the pressure monitoring module are further improved. When the flow measurement module receives the pressure abnormal signal, it judges that the water flow variation within the second time threshold is greater than the first flow threshold, and outputs a flow abnormal signal. Thus, the problem of false generation of the pressure abnormal signal caused by sudden abnormal signals is avoided. The reliability and stability of the output signal of the pressure monitoring module are further improved. At the same time, when the pressure abnormal signal is received, further judgment is performed, thereby further saving the electric energy of the flow measurement module and promoting the stability of the device. By adopting the leakage signal monitoring module, when the flow abnormal signal is received, the leakage signal monitoring module is started and monitors the water flow leakage signal in the pipeline. Through the step-by-step process, when the conditions are met, the leakage signal monitoring module is started, thereby further reducing the power consumption of the device, further improving the stability of the overall device, and combining pressure, flow, and leakage signals to evaluate the pipeline leakage, thereby further improving the accuracy of the final judgment.

[0051] In another possible embodiment, a second pressure threshold is also included. When the pressure variation of the water flow within the first time threshold is greater than the second threshold, and the duration of the pressure is greater than the third time threshold, a pressure abnormal signal is generated, and the pressure abnormal signal is transmitted to the leakage signal monitoring module to start the leakage signal monitoring module to determine whether there is a leakage in the pipeline.

[0052] For example, when the pressure 1 minute ago is 100 MPa, the pressure at this moment is 190 MPa, the pressure change in 1 minute is 90 MPa, the second pressure threshold is 60 MPa, at this moment, the pressure greater than the second pressure threshold is 190 MPa, and the duration of the pressure change of 90 MPa is greater than 2 minutes, at this moment, the pressure change signal needs to be output to the leakage signal monitoring module, so that it is immediately opened for monitoring.

[0053] By setting the second pressure threshold, the waste of a large amount of water caused by a long judgment step due to a large leakage is avoided, the pipeline leakage is found at the first time, the judgment sensitivity is further improved on the basis of ensuring a stable and reliable judgment result, and by adopting the pressure change in the first time threshold being greater than the second threshold, and the duration of the pressure greater than the second threshold being greater than the third time threshold, the problem is determined to exist only when the maintenance time of the change is greater than a certain time, and the stability and reliability of the overall judgment accuracy are ensured.

[0054] In another possible embodiment, a third pressure threshold is further included, when the pressure change in the fourth time threshold is greater than the third pressure threshold, at this moment, it is determined that the pressure monitoring module has an abnormality, and the pressure change signal or the pressure abnormal signal is no longer output.

[0055] For example, when the pressure change in 20s is greater than 200 MPa, the third pressure threshold is 100 MPa, at this moment, it is determined that the pressure monitoring module has an abnormality.

[0056] By setting the third pressure threshold, when the pressure change in the fourth time threshold is greater than the third pressure threshold, it is determined that the pressure monitoring module has an abnormality at this moment, thereby preventing the signal false alarm problem caused by the pressure monitoring module in the abnormal condition, and further improving the overall reliability.

[0057] In another possible embodiment, the first pressure threshold is less than the second pressure threshold, the second pressure threshold is less than the third pressure threshold, and the first pressure threshold, the second pressure threshold, and the third pressure threshold are determined according to the pipe radius and the pipe position of water supply.

[0058] By determining the pressure threshold according to the pipe radius and the pipe position of water supply, the pressure threshold is adjusted according to the condition of the pipe, so that the overall threshold setting can be combined with the specific actual situation, and the scientificity of the threshold setting is further improved.

[0059] In a possible additional embodiment, the fourth time threshold is less than the first time threshold, and the first time threshold is less than the third time threshold, and the first time threshold, the third time threshold, and the fourth time threshold are determined according to a pipe radius and a pipe location of the water supply.

[0060] By determining the time threshold according to the pipe radius and the pipe location of the water supply, the adjustment of the time threshold is performed according to the situation of the pipe, so that the overall threshold setting can be combined with the specific actual situation, and the scientificity of the threshold setting is further improved.

[0061] In a possible additional embodiment, a fifth time threshold is further included, and when a flow fluctuation amount of the flow within the fifth time threshold is greater than a second flow threshold, it is determined that the flow measurement module is abnormal, and the flow abnormality signal is no longer sent.

[0062] For example, when the flow fluctuation amount is 30 t within 10 s, and the second flow threshold is 25 t, it is determined that the flow measurement module is abnormal, and the flow abnormality signal is no longer sent.

[0063] By setting the second flow threshold, when the flow fluctuation amount within the fifth time threshold is greater than the second flow threshold, it is determined that the flow measurement module is abnormal at this time, so that the signal false alarm problem caused by the abnormality of the flow measurement module is prevented, and the overall reliability is further improved.

[0064] In a possible additional embodiment, the fifth time threshold is less than the second time threshold, and the first flow threshold is less than the second flow threshold, and the second time threshold, the fifth time threshold, the first flow threshold, and the second flow threshold are determined according to the pipe radius and the pipe location of the water supply.

[0065] By determining the flow threshold and the time threshold according to the pipe radius and the pipe location of the water supply, the adjustment of the flow threshold and the time threshold is performed according to the situation of the pipe, so that the overall threshold setting can be combined with the specific actual situation, and the scientificity of the threshold setting is further improved.

[0066] In a possible additional embodiment, the leakage signal monitoring module performs spectrum analysis on the leakage signal, obtains a spectrum graph of the leakage signal, and sends the spectrum graph to the GWO-DenseNet algorithm-based classification model to determine whether there is leakage.

[0067] By adopting the classification model based on the GWO-DenseNet algorithm, the leakage signal is classified and judged, compared with the classification model adopting the CNN algorithm, the dense connection in the DenseNet can also relieve the problem of gradient disappearance, can strengthen the feature propagation and feature reuse, and reduce the number of parameters, the required memory and computing resources are less, and better performance is achieved.

[0068] In a possible additional embodiment, the GWO-DenseNet algorithm is to optimize the weight and number of hidden layers of the DenseNet algorithm by adopting the GWO algorithm.

[0069] By optimizing the weight and number of hidden layers of the DenseNet algorithm by adopting the GWO algorithm, the overall classification efficiency is further improved, and the overall prediction efficiency is improved.

[0070] In a possible additional embodiment, the classification result is divided into three types: normal, slight leakage and serious leakage.

[0071] By dividing the leakage result into three categories, maintenance will not be performed due to leakage, and corresponding measures are adopted according to the specific situation of leakage, when there is slight leakage, the sensitivity of judgment can be improved by reducing the pressure threshold of the pressure monitoring module and / or reducing the flow threshold of the flow measurement module, when there is serious leakage, immediate repair is required, thereby further improving the scientificity of classification and further reducing the occurrence of water stop problems caused by faults.

[0072] In the embodiments of the present application, the term "a plurality of" refers to two or more, unless otherwise explicitly limited. The terms "mounting", "connecting", "fixing" and the like should be understood in a broad sense, for example, "connecting" can be fixed connection, can also be detachable connection, or integral connection. For those skilled in the art, the specific meaning of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0073] In the description of the embodiments of the present application, it should be understood that the positions or position relationships indicated by the terms "upper", "lower" and the like are based on the positions or position relationships shown in the drawings, and are only for the convenience of describing the embodiments of the present application and simplifying the description, and do not indicate or imply that the devices or units referred to must have a particular direction, be constructed and operated in a particular direction, therefore, it cannot be understood as a limitation on the embodiments of the present application.

[0074] In the description of the specification, the description of the terms "one embodiment", "one preferred embodiment", and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are contained in at least one embodiment or example of the embodiments of the present application. In the specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0075] The above only is the preferred embodiment of the embodiments of the present application, and is not used to limit the embodiments of the present application. For those skilled in the art, the embodiments of the present application can have various changes and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present application shall be included in the protection scope of the embodiments of the present application.

Claims

1. A monitoring device based on data aggregation in smart water, characterized by, Specifically comprising: a pressure monitoring module, a power supply module, a flow measurement module, a leakage signal monitoring module; The pressure monitoring module is responsible for monitoring the water flow pressure in the pipeline, and when the water flow pressure changes by more than a first pressure threshold within a first time threshold, a pressure anomaly signal is generated and transmitted to the flow measurement module. The power supply module is responsible for providing power to the pressure monitoring module, flow measurement module, and leakage signal monitoring module. The flow measurement module is responsible for monitoring the water flow in the pipeline, and when it receives the pressure anomaly signal, it determines whether the water flow changes by more than a first flow threshold within a second time threshold, and outputs a flow anomaly signal and transmits it to the leakage signal monitoring module. The leakage signal monitoring module receives the flow anomaly signal and turns on, and monitors the water flow leakage signal in the pipeline. A classification model based on the GWO-DenseNet algorithm is used to determine whether there is a leak. It also includes a second pressure threshold. When the water flow pressure changes by more than the second threshold within the first time threshold, and the duration of the pressure is greater than a third time threshold, a pressure anomaly signal is generated and transmitted to the leakage signal monitoring module, causing the leakage signal monitoring module to turn on and determine whether there is a leak in the pipeline. It also includes a third pressure threshold. When the water flow pressure changes by more than the third pressure threshold within a fourth time threshold, it is determined that the pressure monitoring module is abnormal, and the pressure anomaly signal or pressure anomaly signal is no longer sent. The GWO-DenseNet algorithm uses the GWO algorithm to optimize the weights and number of hidden layers of the DenseNet algorithm.

2. The monitoring device based on data aggregation in smart water affairs as claimed in claim 1 is characterized by, The first pressure threshold is less than the second pressure threshold, and the second pressure threshold is less than the third pressure threshold. The first pressure threshold, second pressure threshold, and third pressure threshold are determined based on the radius and location of the water supply pipeline.

3. The monitoring device based on data aggregation in smart water affairs as claimed in claim 1 is characterized in that, The fourth time threshold is less than the first time threshold, and the first time threshold is less than the third time threshold. The first time threshold, third time threshold, and fourth time threshold are determined based on the radius and location of the water supply pipeline.

4. The monitoring device based on data aggregation in smart water affairs as claimed in claim 1 is characterized by, It also includes a fifth time threshold. When the water flow changes by more than a second flow threshold within a fifth time threshold, it is determined that the flow measurement module is abnormal, and the flow anomaly signal is no longer sent.

5. A monitoring device based on data aggregation in smart water affairs as claimed in claim 4, characterized by, The fifth time threshold is less than the second time threshold, and the first flow threshold is less than the second flow threshold. The second time threshold, fifth time threshold, first flow threshold, and second flow threshold are determined based on the radius and location of the water supply pipeline.

6. The monitoring device based on data aggregation in smart water affairs as claimed in claim 1 is characterized by, The leakage signal monitoring module performs frequency spectrum analysis on the leakage signal to obtain a frequency spectrum graph of the leakage signal, and inputs the frequency spectrum graph into the classification model based on the GWO-DenseNet algorithm to determine whether there is a leak.

Images