A method and system for early warning of low water inlet pressure in municipal pipe network

Abstract

The present invention relates to the field of pressure monitoring, and in particular to a method and system for early warning of low water inlet pressure in a municipal pipe network, the method comprising: obtaining pressure data of multiple data points at the same time in the municipal pipe network, calculating the initial decision function value of the pressure data using the SVM algorithm, correcting the initial decision function value to obtain the optimal decision function value, and sending an early warning signal in response to the optimal decision function value being less than a preset early warning threshold. The present invention improves the accuracy of the monitoring result by correcting the initial decision function value to obtain the optimal decision function value.

Description

Technical Field

[0001] The present invention relates to the field of pressure monitoring, and in particular to a method and system for early warning of low-pressure inlet water pressure in a municipal pipe network. Background Art

[0002] In the municipal water supply system, it is very important to monitor the water inlet pressure to ensure the normal operation of the water pipes. If the water inlet pressure is too low, the water flow will not be smooth and the water cannot be smoothly transported to the corresponding location, which will affect the water quality and quality of life of the residents. In serious cases, it may cause the water supply to be interrupted and affect the daily operation of the city. Therefore, it is of great significance to monitor the water inlet pressure to avoid the water inlet pressure being too low.

[0003] A Chinese patent with announcement number CN113189450B discloses a line icing monitoring system based on micrometeorological monitoring and SVM algorithm, including: a Raman sensing module, a Brillouin sensing module, a comprehensive Rayleigh scattering module, a time division multiplexing module, an icing area monitoring module, an icing thickness monitoring module, a wind speed monitoring module and an icing alarm module based on SVM. The icing area of ​​the overhead transmission line is monitored based on the temperature value of each point on the OPGW; the equivalent icing thickness of the overhead transmission line is monitored based on the strain value of each point on the OPGW; the wind speed of the overhead transmission line is monitored according to the vibration frequency of the OPGW; and an icing warning is issued according to the temperature value, strain value and wind speed of each point on the OPGW.

[0004] The SVM (Support Vector Machine) algorithm, as an algorithm with strong classification and regression capabilities, can be used to monitor the water pressure of municipal pipe networks. By learning from historical data, it can discover the potential patterns of pressure changes, identify normal and abnormal pressure patterns, issue early warnings in a timely manner, and reduce the occurrence of low pressure situations.

[0005] In the process of monitoring the water pipe pressure, the SVM algorithm will calculate the decision function value, which reflects whether the pressure data of the monitored water pipe is abnormal data. However, in the process of monitoring the water pipe pressure of the municipal water supply system, as the water pipe is used for a longer time, the inner wall of the water pipe will have certain corrosion, scaling, blockage and other problems, which will affect the distribution of water flow and pressure in the water pipe, and thus lead to low accuracy of the water pipe pressure monitoring results. Summary of the invention

[0006] In order to solve the problem of low accuracy of monitoring results of the SVM algorithm in the process of monitoring water pipe pressure, the present invention provides a method and system for early warning of low water inlet pressure in a municipal pipe network.

[0007] In a first aspect, the present invention provides a method for early warning of low water inlet pressure in a municipal pipe network, which adopts the following technical solution:

[0008] Obtain pressure data of multiple data points at the same time in the municipal pipe network, calculate the initial decision function value of the pressure data using the SVM algorithm, correct the initial decision function value to obtain the optimal decision function value, and issue a warning signal in response to the optimal decision function value being less than a preset warning threshold;

[0009] Among them, the calculation method of the optimal decision function value is:

[0010] Calculate the distribution characteristics of multiple pressure data, the distribution characteristics represent the stability of the multiple pressure data, calculate the difference level of any pressure data, the difference level represents the difference between any pressure data and other pressure data;

[0011] Calculate the local difference degree of any pressure data, which is positively correlated with the difference level; calculate the optimal decision function value of any pressure data, the expression is: ; In the formula, is the optimal decision function value of the pressure data at the jth data point at the tth moment, is the initial decision function value of the pressure data at the jth data point at the tth moment, is the overall distribution characteristic of the pressure data of all data points, is the local difference degree of pressure data at the jth data point at the tth moment, and exp is an exponential function with e as the base.

[0012] By correcting the initial decision function value to obtain the optimal decision function value, it is possible to more accurately identify abnormal pressure data caused by corrosion, scaling, blockage and leakage of the inner wall of the water pipe, facilitate the maintenance of the municipal pipeline network, and ensure the stable operation of the municipal pipeline network, thereby avoiding potential risks caused by false alarms or omissions.

[0013] Preferably, the calculation method of the distribution characteristics of pressure data is:

[0014] Calculate the change rate of each pressure data, and use the least square method to fit all the obtained change rates to obtain the fitting plane; calculate the mean distance from the change rate of all pressure data to the fitting plane and the flatness of the fitting plane, and the flatness is positively correlated with the mean distance;

[0015] Calculate the distribution characteristics of pressure data, the expression is:

[0016]

[0017] In the formula, For the Fitting plane of the changing rate of pressure data at each moment The normal vector of Fitting plane The coefficient of determination, Fitting plane Flatness.

[0018] By calculating the distribution characteristics, we can understand the overall stability of the system and the uniformity of pressure distribution, which is convenient for evaluating the overall performance of the system and discovering abnormal data.

[0019] Preferably, the expression for the flatness of the fitting plane is:

[0020]

[0021] In the formula, Fitting plane The flatness, is the rate of change of the pressure data at the jth data point at the tth moment to the fitting plane The vertical distance is the number of data points, and exp is the exponential function with e as the base.

[0022] Preferably, the expression for the flatness of the fitting plane is:

[0023]

[0024] In the formula, Fitting plane The flatness, is the rate of change of the pressure data at the jth data point at the tth moment to the fitting plane The vertical distance is the number of data points, is the logarithmic function with base e.

[0025] By calculating the flatness of the fitting plane, we can understand the distribution and fluctuation of data points, making it easier to find abnormal data.

[0026] Preferably, the expression of the local difference degree is:

[0027]

[0028] In the formula, For the The local difference degree of pressure data of data point at time t, is the difference level of the pressure data at the jth data point at the tth moment, For the The difference level of pressure data of data points at time t, is the number of data points, is the maximum value of the difference level of the pressure data of all data points at the tth moment, It is the minimum value of the difference level of pressure data of all data points at the tth moment.

[0029] Preferably, the expression of the local difference degree is:

[0030]

[0031] In the formula, is the local difference degree of pressure data at the jth data point at the tth moment, is the difference level of the pressure data at the jth data point at the tth moment, For the The difference level of pressure data of data points at time t, is the number of data points.

[0032] Preferably, the expression of the local difference degree is:

[0033]

[0034] In the formula, is the local difference degree of pressure data at the jth data point at the tth moment, is the difference level of the pressure data at the jth data point at the tth moment, For the The difference level of pressure data of data points at time t, is the maximum value of the difference level of the pressure data of all data points at the tth moment, It is the minimum value of the difference level of pressure data of all data points at the tth moment.

[0035] By calculating the degree of local abnormality, it is easy to discover abnormal data and find abnormal pressure points in the pipeline network.

[0036] Preferably, the expression of the difference level is:

[0037]

[0038] In the formula, is the difference level of the pressure data at the jth data point at the tth moment, is the pressure data of the jth data point at the tth moment, is the pressure data of the rth data point at the tth moment, is the rate of change of pressure data at the jth data point at the tth moment, is the rate of change of the pressure data of the rth sensor at the tth moment, is the number of data points.

[0039] By calculating the difference level of the data points, it is possible to understand the degree of difference between the pressure of the corresponding data point and the pressure of the remaining data points, so as to further understand the possibility that the pressure data is in an abnormal state.

[0040] Preferably, the expression of the difference level is:

[0041]

[0042] In the formula, is the difference level of the pressure data at the jth data point at the tth moment, is the rate of change of pressure data at the jth data point at the tth moment, is the rate of change of the pressure data of the rth sensor at the tth moment, is the number of data points.

[0043] In a second aspect, the present invention provides a low pressure warning system for water inlet pressure in a municipal pipe network, which adopts the following technical solution:

[0044] A municipal pipe network water inlet low pressure early warning system comprises: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a municipal pipe network water inlet low pressure early warning method is implemented.

[0045] The present invention has the following technical effects:

[0046] 1. By correcting the initial decision function value to obtain the optimal decision function value, the accuracy of the monitoring results is improved. It can more accurately identify abnormal pressure data caused by corrosion, scaling, blockage and leakage of the inner wall of the water pipe, facilitate the maintenance of the municipal pipeline network, and ensure the stable operation of the municipal pipeline network, thereby avoiding potential risks caused by false alarms.

[0047] 2. By correcting the initial decision function value to obtain the optimal decision function value, the problematic water pipe area can be located more accurately, so as to carry out targeted repairs and replacements and reduce unnecessary waste of resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0049] Figure 1 The present invention is a method flow chart of a method for early warning of low water inlet pressure in a municipal pipe network.

[0050] Figure 2 It is a structural block diagram of a low-pressure early warning system for water inlet pressure of a municipal pipe network according to the present invention. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0052] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0053] The embodiment of the present invention discloses a method for early warning of low water inlet pressure in a municipal pipe network, referring to Figure 1 , including the following steps, as follows:

[0054] S1: Obtain pressure data of multiple data points in the municipal pipe network at the same time.

[0055] In the water pipes of the municipal pipe network system, pressure sensors are installed in multiple different locations. For example, pressure sensors are installed at the bends of the water pipes and at the connections between the water pipes and the water supply equipment to collect pressure data in the water pipes at the same time. The collection frequency is 10 Hz. It should be noted that one pressure sensor is one data point.

[0056] S2: Calculate distribution characteristics of the multiple pressure data, where the distribution characteristics represent the stability of the multiple pressure data.

[0057] S21: Calculate the change rate of each pressure data, and use the least square method to fit all the obtained change rates to obtain a fitting plane.

[0058] The expression for the rate of change of pressure data is:

[0059]

[0060] In the formula, is the rate of change of pressure data at the jth data point at the tth moment, is the pressure data of the jth data point at the tth moment, is the pressure data at time t one day before the jth data point. is the difference between the pressure data at the jth data point at the tth moment and the pressure data at the same moment of the previous day, It indicates the degree of change of the pressure data of the jth data point at the tth time, that is, the rate of change of the pressure data of the data point at the tth time. The rate of change of the water pipe pressure data can reflect the changing trend of the water pipe pressure data over time, and then reflect the state of the pressure change in the pipeline. For example, when the rate of change of the pressure data is large, it means that the pressure in the pipe network is more likely to be abnormal.

[0061] Since multiple pressure sensors are installed in the municipal pipe network system, the pressure data of multiple data points at the same time corresponds to each pressure data corresponding to a change rate, and a plane fitting is performed on multiple change rates at the same time, specifically, the plane fitting is performed on the three dimensions of the change rate using the least squares method, where the three dimensions are the collected pressure data, the collection time, and the water temperature in the pipe. Using the least squares method for plane fitting is an existing technology, and the specific principle is not repeated here.

[0062] S22: Calculate the mean distance from the change rate of all pressure data to the fitting plane and the flatness of the fitting plane. The flatness is positively correlated with the mean distance.

[0063] In one embodiment, the expression for the flatness of the fitting plane is:

[0064]

[0065] In the formula, Fitting plane The flatness, is the rate of change of the pressure data at the jth data point at the tth moment to the fitting plane The vertical distance is the number of data points, and exp is an exponential function with e as the base. The smaller the mean of the distance from the rate of change of the pressure data to the fitting plane, the greater the flatness of the fitting plane, indicating that the flatness of the fitting plane is higher.

[0066] In other embodiments, the expression for the flatness of the fitting plane is:

[0067]

[0068] In the formula, Fitting plane The flatness, is the rate of change of the pressure data at the jth data point at the tth moment to the fitting plane The vertical distance is the number of data points, is the logarithmic function with base e.

[0069] S23: Calculate the distribution characteristics of the pressure data.

[0070] The distribution characteristic expression of pressure data is:

[0071]

[0072] In the formula, is the distribution characteristic of pressure data, is the fitting plane of the pressure data change rate at the tth moment The normal vector of Fitting plane The decision coefficient of Fitting plane The flatness, is the modulus of the vector. The calculation of the normal vector and decision coefficient of the fitting plane is a prior art, and the specific process will not be repeated here. The higher the flatness of the fitting plane and the smaller the difference between the decision coefficient and 1, the stronger the fitting plane's ability to explain the pressure data and the more obvious the distribution characteristics of the pressure data. The distribution characteristics of the water pipe pressure data can be used to understand the overall stability of the system and the uniformity of the pressure distribution. Specifically, the larger the distribution characteristics, the better the uniformity of the pressure distribution in the pipe network and the more stable the pressure.

[0073] S3: Calculate the local difference degree of pressure data, which is positively correlated with the difference level.

[0074] S31: Calculate the difference level of the pressure data.

[0075] In one embodiment, the expression for the difference level is:

[0076]

[0077] In the formula, is the difference level of the pressure data at the jth data point at the tth moment, is the pressure data of the jth data point at the tth moment, is the pressure data of the rth data point at the tth moment, is the rate of change of pressure data at the jth data point at the tth moment, is the rate of change of the pressure data of the rth sensor at the tth moment, is the number of data points; among them, the greater the difference between the pressure data of the j-th data point at the t-th moment and the pressure data of the remaining data points at the t-th moment and the greater the difference in the rate of change, the higher the difference level of the pressure data of the j-th data point at the t-th moment, and the greater the possibility that the pressure data is in an abnormal state.

[0078] In another embodiment, the expression for the difference level is:

[0079]

[0080] In the formula, is the difference level of the pressure data at the jth data point at the tth moment, is the rate of change of pressure data at the jth data point at the tth moment, is the rate of change of the pressure data of the rth sensor at the tth moment, is the number of data points.

[0081] S32: Calculate the local difference degree of any pressure data, where the local difference degree is positively correlated with the difference level.

[0082] In one embodiment, the expression of the local difference degree is:

[0083]

[0084] In the formula, is the local difference degree of pressure data at the jth data point at the tth moment, is the difference level of the pressure data at the jth data point at the tth moment, is the difference level of the pressure data at the rth data point at the tth moment, is the number of data points, is the maximum value of the difference level of the pressure data of all data points at the tth moment, It is the minimum value of the difference level of pressure data of all data points at the tth moment.

[0085] in, is the cumulative sum of the pressure data difference levels of all data points, It represents the range of the pressure data difference level of all data points at the tth moment. The smaller the range, the more reliable the local difference of the pressure data of the jth data point at the tth moment. If the pressure data of a data point has a large local difference, it means that the water pipe pressure data of the data point has a more obvious anomaly, and its decision function value needs to be reduced to ensure that the model outputs a true abnormal monitoring result of the value.

[0086] In another embodiment, the expression of the local difference degree is:

[0087]

[0088] In the formula, is the local difference degree of pressure data at the jth data point at the tth moment, is the difference level of the pressure data at the jth data point at the tth moment, is the difference level of the pressure data at the rth data point at the tth moment, and m is the number of data points.

[0089] In yet another embodiment, the expression of the local difference degree is:

[0090]

[0091] In the formula, is the local difference degree of pressure data at the jth data point at the tth moment, is the jth data point The difference level of pressure data at each moment, is the difference level of the pressure data at the rth data point at the tth moment, is the maximum value of the difference level of the pressure data of all data points at the tth moment, It is the minimum value of the difference level of pressure data of all data points at the tth moment.

[0092] S4: Calculate the initial decision function value of the pressure data using the SVM algorithm, modify the initial decision function value to obtain the optimal decision function value, and issue a warning signal in response to the optimal decision function value being less than a preset warning threshold.

[0093] The optimal decision function value expression is:

[0094]

[0095] In the formula, is the optimal decision function value of the pressure data at the jth data point at the tth moment, is the initial decision function value of the pressure data of the jth data point at the tth moment, F is the overall distribution characteristics of the pressure data of all data points, is the jth data point The degree of local difference in pressure data at each moment, is an exponential function with base e. is the degree of correction of the pressure data of the jth data point at the tth moment. The greater the local difference of the pressure data of the data point, the greater the possibility that the pressure data of the data point is in an abnormal state, and the smaller the optimal decision function value finally obtained. When the optimal decision function value is less than the preset warning threshold, it indicates that the pressure of the data point here is small and in an abnormal state, and a warning signal is issued to prompt the operating personnel to inspect and maintain the pipeline network in time to ensure that the pipeline network can operate normally and stably.

[0096] Combination Figure 2 As shown, an embodiment of the present invention also discloses a municipal pipe network water inlet pressure low pressure warning system, including a processor and a memory, the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a municipal pipe network water inlet pressure low pressure warning method according to the present invention is implemented.

[0097] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0098] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high bandwidth memory HBM (High Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module or both. Any such computer storage medium may be part of a device or accessible or connectable to a device.

[0099] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0100] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for early warning of low water inlet pressure in a municipal pipe network, characterized in that: Includes steps: Obtain pressure data of multiple data points at the same time in the municipal pipe network, calculate the initial decision function value of the pressure data using the SVM algorithm, correct the initial decision function value to obtain the optimal decision function value, and issue a warning signal in response to the optimal decision function value being less than a preset warning threshold; Among them, the calculation method of the optimal decision function value is: The method for calculating the distribution characteristics of multiple pressure data is as follows: calculating the change rate of each pressure data, fitting all the obtained change rates using the least squares method to obtain a fitting plane; calculating the mean distance from the change rate of all pressure data to the fitting plane and the flatness of the fitting plane, where the flatness is positively correlated with the mean distance; Calculate the distribution characteristics of pressure data, the expression is: In the formula, is the fitting plane of the pressure data change rate at the tth moment The normal vector of Fitting plane The coefficient of determination, Fitting plane The flatness of the distribution characteristics indicates the stability of multiple pressure data, and the difference level of any pressure data is calculated. The difference level indicates the difference between any pressure data and other pressure data; The expression for calculating the degree of local difference of any pressure data is: In the formula, is the local difference degree of pressure data at the jth data point at the tth moment, is the difference level of the pressure data at the jth data point at the tth moment, is the difference level of the pressure data at the rth data point at the tth moment, is the number of data points, and the local difference degree is positively correlated with the difference level; the optimal decision function value for any pressure data is calculated, and the expression is: ; In the formula, is the optimal decision function value of the pressure data at the jth data point at the tth moment, is the initial decision function value of the pressure data at the jth data point at the tth moment, is the overall distribution characteristic of the pressure data of all data points, is the local difference degree of pressure data at the jth data point at the tth moment, and exp is an exponential function with e as the base.

2. A method for early warning of low water inlet pressure in a municipal pipe network according to claim 1, characterized in that: The expression for the flatness of the fitting plane is: In the formula, Fitting plane The flatness, is the rate of change of the pressure data at the jth data point at the tth moment to the fitting plane The vertical distance is the number of data points, and exp is the exponential function with e as the base.

3. A method for early warning of low water inlet pressure in a municipal pipe network according to claim 1, characterized in that: The expression for the flatness of the fitting plane is: In the formula, Fitting plane The flatness, is the rate of change of the pressure data at the jth data point at the tth moment to the fitting plane The vertical distance is the number of data points, is the logarithmic function with base e.

4. A method for early warning of low water inlet pressure in a municipal pipe network according to claim 1, characterized in that: The expression of local difference degree is: In the formula, is the local difference degree of pressure data at the jth data point at the tth moment, is the difference level of the pressure data at the jth data point at the tth moment, is the difference level of the pressure data at the rth data point at the tth moment, is the number of data points, is the maximum value of the difference level of the pressure data of all data points at the tth moment, It is the minimum value of the difference level of pressure data of all data points at the tth moment.

5. A method for early warning of low water inlet pressure in a municipal pipe network according to claim 1, characterized in that: The expression of local difference degree is: In the formula, is the local difference degree of pressure data at the jth data point at the tth moment, is the difference level of the pressure data at the jth data point at the tth moment, For all data points The maximum value of the difference level of the pressure data at the moment, It is the minimum value of the difference level of pressure data of all data points at the tth moment.

6. A method for early warning of low water inlet pressure in a municipal pipe network according to claim 1, characterized in that: The expression for the difference level is: In the formula, is the difference level of the pressure data at the jth data point at the tth moment, is the pressure data of the jth data point at the tth moment, is the pressure data of the rth data point at the tth moment, is the rate of change of pressure data at the jth data point at the tth moment, is the rate of change of the pressure data of the rth sensor at the tth moment, is the number of data points.

7. A method for early warning of low water inlet pressure in a municipal pipe network according to claim 1, characterized in that: The expression for the difference level is: In the formula, is the difference level of the pressure data at the jth data point at the tth moment, is the rate of change of pressure data at the jth data point at the tth moment, is the rate of change of the pressure data of the rth sensor at the tth moment, is the number of data points.

8. A low pressure warning system for water inlet pressure in a municipal pipe network, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a municipal pipe network water inlet low pressure early warning method according to any one of claims 1-7 is implemented.

Images