Drainage well overflow warning method, device, storage medium and electronic device

Abstract

The present invention discloses a method, device, storage medium, and electronic device for warning of drainage well overflow. The method comprises the following steps: obtaining historical data; selecting qualified data to be fitted from the historical data using a data self-checking method; fitting the data to be fitted to obtain a first mapping relationship between rainfall intensity and the maximum liquid level value of the drainage well; obtaining the maximum allowable liquid level value of the drainage well, and calculating a rainfall intensity threshold value based on the first mapping relationship and the maximum allowable liquid level value; obtaining rainfall intensity prediction data, and issuing an overflow warning message when the rainfall intensity prediction data exceeds the rainfall intensity threshold value. The method can provide an early warning of overflow events and dynamically modify the threshold value, thus breaking through the limitations of fixed threshold alarms and overcoming the influence of factors such as seasonal water consumption, rainfall frequency, and the degree of rainwater and sewage mixing. Furthermore, the method is calculated based on historical data from a statistical perspective and is not restricted by basic pipe network data.

Description

Technical Field

[0001] The present invention relates to the technical field of sewage pipe networks, and in particular to a method, device, storage medium and electronic equipment for warning of overflow of a drainage well. Background Art

[0002] As cities develop, the scale of my country's drainage networks continues to grow. At the same time, problems such as aging, poor design, improper operation, and structural and functional defects are becoming increasingly prominent, leading to insufficient drainage capacity. During severe weather such as heavy rain, drainage wells are at risk of overflowing, which can easily lead to waterlogging and even urban flooding. Sewage overflows can also cause environmental pollution, seriously impacting residents' lives and industrial production.

[0003] With the rapid development of information technology, a monitoring platform for urban sewage systems has been established based on the Internet of Things (IoT). Two main methods are employed: fixed threshold alarms and drainage model warnings. Fixed threshold alarms use overflow alarm values ​​set based on manhole cover lines, while drainage model warnings are calculated through numerical simulations of the drainage network. Fixed threshold alarms can only provide post-event warnings, not pre-event warnings. While drainage models can provide early warnings, their accuracy is limited by the incompleteness and accuracy of basic network data. Summary of the Invention

[0004] One purpose of the present invention is to propose a method, device, storage medium and electronic device for warning of drainage well overflow. The method for warning of drainage well overflow can not only provide advance warning of overflow events, but also dynamically correct the threshold value, break through the limitations of fixed threshold alarms, and overcome the influence of factors such as seasonal water consumption, rainfall frequency and the degree of mixing of rainwater and sewage. In addition, the method is calculated based on historical data from a statistical perspective and is not restricted by basic pipe network data.

[0005] To achieve the above-mentioned purpose, an embodiment of the first aspect of the present invention proposes a method for drainage well overflow warning, the method comprising: obtaining historical data, wherein the historical data includes rainfall intensity data and drainage well maximum liquid level value data in multiple historical rainfall events; using a data self-checking method to filter out data to be fitted from the historical data; fitting the data to be fitted to obtain a first mapping relationship between rainfall intensity and the drainage well maximum liquid level value; obtaining the maximum allowable liquid level value of the drainage well, and calculating a rainfall intensity threshold based on the first mapping relationship and the maximum allowable liquid level value; obtaining rainfall intensity prediction data, and issuing an overflow warning message when the rainfall intensity prediction data is greater than the rainfall intensity threshold.

[0006] In addition, the drainage well overflow warning method proposed in the above embodiment of the present invention may also have the following additional technical features:

[0007] According to one embodiment of the present invention, before the data to be fitted is filtered out from the historical data, the historical data is also deburred, including: calculating the first mean value and first standard deviation of the rainfall intensity in the historical data, and the second mean value and second standard deviation of the maximum liquid level value of the drainage well; deburring the rainfall intensity data according to a first preset accuracy, the first mean value and the first standard deviation, and deburring the maximum liquid level value data of the drainage well according to a second preset accuracy, the second mean value and the second standard deviation.

[0008] According to one embodiment of the present invention, the data self-checking method is used to filter out the data to be fitted from the historical data, including: selecting the most recent n groups of data from the historical data as test data, and recording the m groups of data adjacent to the test data as preset fitting data, wherein m and n are both positive integers, and m is greater than n; fitting the preset fitting data to obtain a second mapping relationship between rainfall intensity and the maximum liquid level value of the drainage well; predicting the maximum liquid level value of the drainage well according to the second mapping relationship and the rainfall intensity in the test data to obtain a maximum liquid level prediction value; calculating the difference between the maximum liquid level prediction value and the actual maximum liquid level value in the test data, and obtaining an average deviation value based on n differences; forwardly selecting m groups of data to superimpose on the preset fitting data, and going to the step of fitting to obtain the second mapping relationship until all the historical data are traversed; determining the preset fitting data and the test data corresponding to the minimum value in the average deviation value as the data to be fitted.

[0009] According to one embodiment of the present invention, fitting the data to be fitted to obtain a first mapping relationship between rainfall intensity and the maximum liquid level value of the drainage well includes: calculating the mean rainfall intensity of the data to be fitted and the mean maximum liquid level value of the drainage well; calculating a first fitting coefficient based on the mean rainfall intensity and the mean maximum liquid level value of the drainage well; calculating a second fitting coefficient based on the mean rainfall intensity, the mean maximum liquid level value of the drainage well and the first fitting coefficient; and constructing the first mapping relationship based on the first fitting coefficient and the second fitting coefficient.

[0010] According to one embodiment of the present invention, the first mapping relationship is calculated by the following formula:

[0011]

[0012] Wherein, Y is the rainfall intensity, W is the highest liquid level value of the drainage well, is the first fitting coefficient, is the second fitting coefficient.

[0013] According to one embodiment of the present invention, before fitting the data to be fitted to obtain a first mapping relationship between rainfall intensity and the maximum liquid level value of the drainage well, the method further includes: calculating the correlation coefficient between the rainfall intensity and the maximum liquid level value of the drainage well in the data to be fitted; judging whether the correlation coefficient meets a preset condition; if the correlation coefficient does not meet the preset condition, determining the outlier data in the data to be fitted, and eliminating the outlier data to update the data to be fitted, and going to the step of calculating the correlation coefficient until the correlation coefficient meets the preset condition.

[0014] According to one embodiment of the present invention, the rainfall intensity prediction data includes rainfall prediction data of a preset time in the future from a meteorological department.

[0015] The drainage well overflow warning method of an embodiment of the present invention first obtains historical data, then deburrs the rainfall intensity data and the drainage well maximum liquid level data in the historical data. Based on a fitting algorithm, the optimal predicted preset fitting data and test data are determined as the data to be fitted. When determining the relationship between rainfall intensity and the drainage well maximum liquid level, a correlation coefficient is calculated to determine whether the correlation coefficient meets a preset condition. If the correlation coefficient does not meet the preset condition, outlier data is removed until the correlation coefficient meets the preset condition. The relationship between rainfall intensity and the drainage well maximum liquid level is determined to be valid. The drainage well maximum allowable liquid level value is substituted into the relationship to obtain a rainfall intensity threshold, and rainfall intensity prediction data is obtained. When the rainfall intensity prediction data exceeds the rainfall intensity threshold, an overflow warning message is issued. This drainage well overflow warning method not only provides an advance warning of overflow events, but also dynamically adjusts the threshold, breaking through the limitations of fixed threshold alarms and overcoming the influence of factors such as seasonal water consumption, rainfall frequency, and the degree of rainwater and sewage mixing. Moreover, the method is calculated based on historical data from a statistical perspective and is not constrained by basic pipe network data.

[0016] To achieve the above-mentioned purpose, the second embodiment of the present invention proposes a drainage well overflow warning device, which includes: an acquisition module for acquiring historical data, wherein the historical data includes rainfall intensity data and drainage well maximum liquid level value data in multiple rainfall events; a screening module for using a data self-checking method to filter out the data to be fitted from the historical data; a fitting module for fitting the data to be fitted to obtain a first mapping relationship between rainfall intensity and the drainage well maximum liquid level value; a calculation module for obtaining the maximum allowable liquid level value of the drainage well, and calculating the rainfall intensity threshold value based on the first mapping relationship and the maximum allowable liquid level value; and an early warning module for obtaining rainfall intensity prediction data, and issuing an overflow warning message when the rainfall intensity prediction data is greater than the rainfall intensity threshold.

[0017] To achieve the above objectives, a third embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for warning of drainage well overflow as described above is implemented.

[0018] To achieve the above-mentioned purpose, the fourth embodiment of the present invention proposes an electronic device, including a memory and a processor, wherein a computer program is stored on the memory, and when the computer program is executed by the processor, the method for drainage well overflow warning as described above is implemented.

[0019] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is a flow chart of a drainage well overflow warning method according to an embodiment of the present invention;

[0021] Figure 2 This is a flow chart of deburring historical data according to an embodiment of the present invention;

[0022] Figure 3 This is a flowchart of screening data to be fitted according to an embodiment of the present invention;

[0023] Figure 4 This is a flow chart of obtaining a first mapping relationship between rainfall intensity and the maximum liquid level value of a drainage well by fitting according to an embodiment of the present invention;

[0024] Figure 5 is a flow chart for determining the correlation coefficient between rainfall intensity and the maximum liquid level value of a drainage well according to an embodiment of the present invention;

[0025] Figure 6 is a flow chart of a drainage well overflow warning method according to another embodiment of the present invention;

[0026] Figure 7 Schematic diagram of a drainage well overflow warning device according to an embodiment of the present invention;

[0027] Figure 8 FIG. 1 is a schematic diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The following describes embodiments of the present invention in detail, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and are not to be construed as limiting the present invention.

[0029] The following will describe in detail the drainage well overflow warning method, device, storage medium and electronic device according to the embodiment of the present invention in conjunction with the accompanying drawings and specific implementation methods.

[0030] Figure 1 The present invention is a flowchart of a drainage well overflow warning method according to an embodiment of the present invention.

[0031] In one embodiment of the present invention, Figure 1 As shown, the methods for warning of drainage well overflow include:

[0032] S1. Acquire historical data, wherein the historical data includes rainfall intensity data and maximum liquid level value data of drainage wells in multiple historical rainfall events.

[0033] Specifically, the drainage well overflow warning method of the present invention statistically determines the rainfall intensity threshold for the drainage well based on historical data. This method first acquires historical data from a sewage monitoring system. This historical data includes rainfall intensity data from multiple historical rainfall events and data on the highest liquid level values ​​in the drainage well. However, the amount of historical data is large. To improve prediction accuracy and efficiency, the present invention filters the historical data to identify data that can achieve the best prediction, specifically, to identify the data to be fitted. To further improve the accuracy of the selection of the data to be fitted, the historical data is deburred before the data to be fitted is selected.

[0034] In one embodiment of the present invention, Figure 2 As shown in FIG, before filtering out the data to be fitted from the historical data, the historical data is also deburred, including:

[0035] S101, calculating a first average value and a first standard deviation of rainfall intensity in historical data, and a second average value and a second standard deviation of the maximum liquid level value of the drainage well.

[0036] S102 , deburring the rainfall intensity data according to a first preset accuracy, a first average value, and a first standard deviation, and deburring the drainage well maximum liquid level value data according to a second preset accuracy, a second average value, and a second standard deviation.

[0037] Specifically, deburring historical data involves eliminating outliers and filtering them. This deburring can be performed on rainfall intensity data and drainage well maximum liquid level data using a method based on mean and standard deviation. For example, if the rainfall intensity data for a certain period of time in the historical data deviates significantly from the mean, this period of rainfall intensity data is considered outlier and is removed.

[0038] More specifically, the first average value μ1, the first standard deviation σ1 of the rainfall intensity in the historical data, and the second average value μ2, the second standard deviation σ2 of the maximum liquid level value of the drainage well are calculated respectively. The rainfall intensity data is deburred according to the first preset accuracy, the first average value μ1, and the first standard deviation σ1. For example, the first preset accuracy can be between μ1+3σ1 and μ1-3σ1. The probability of a value greater than μ1+3σ1 or less than μ1-3σ1 appearing in the rainfall intensity data is very small. Therefore, the rainfall intensity data greater than μ1+3σ1 or less than μ1-3σ1 is determined to be abnormal rainfall intensity data and is eliminated. Similarly, the drainage well maximum liquid level value data is deburred according to the second preset accuracy, the second average value μ2, and the second standard deviation σ2. The second preset accuracy can be the same as the first preset accuracy. The method for deburring the drainage well maximum liquid level value data is similar to the method for deburring the rainfall intensity data, and will not be repeated here.

[0039] After deburring the rainfall intensity data and the maximum liquid level value data of the drainage well in the historical data, the data to be fitted are screened out from the deburred data.

[0040] S2, uses the data self-checking method to filter out the data to be fitted from the historical data.

[0041] Specifically, the data to be fitted is screened out from the historical data by using the data self-checking method, that is, a section of test data is selected from the historical data, and the test data is predicted by grouping and superimposing other data in the historical data until the test data can be best predicted, and the group of data and the test data are determined to be the data to be fitted.

[0042] In one embodiment of the present invention, Figure 3 As shown in the figure, the data self-checking method is used to filter out the data to be fitted from the historical data, including:

[0043] S201, select the latest n groups of data from historical data as test data, and record the m groups of data adjacent to the test data as preset fitting data, where m and n are both positive integers, and m is greater than n.

[0044] S202: Fit the preset fitting data to obtain a second mapping relationship between rainfall intensity and the maximum liquid level value of the drainage well.

[0045] S203 , predicting the maximum liquid level value of the drainage well according to the second mapping relationship and the rainfall intensity in the test data to obtain a maximum liquid level prediction value.

[0046] S204: Calculate the difference between the predicted maximum liquid level value and the actual maximum liquid level value in the test data, and obtain an average deviation value based on the n differences.

[0047] S205 , forwardly selecting m groups of data and superimposing them onto the preset fitting data, and then going to the step of fitting to obtain a second mapping relationship until all historical data are traversed.

[0048] S206 , determining the preset fitting data and the test data corresponding to the minimum value in the average deviation value as the data to be fitted.

[0049] Specifically, the most recent n sets of data from all historical data are determined as test data, where n can be 3. The three most recent sets of data are determined as test data, and the m sets of data adjacent to the most recent n sets of test data are recorded as preset fitting data. The m sets of preset fitting data are also adjacent data, where m can be 10. For example, the 10 adjacent sets of preset fitting data are used to predict the three most recent sets of test data. The preset fitting data are fitted to obtain a second mapping relationship between rainfall intensity and the maximum liquid level value of the drainage well. The fitting algorithm can use the least squares method to obtain the second mapping relationship between rainfall intensity and the maximum liquid level value of the drainage well. The rainfall intensity in the test data is substituted into the second mapping relationship to obtain n maximum liquid level prediction values.

[0050] More specifically, the difference between the predicted maximum liquid level and the actual maximum liquid level in the test data is calculated to obtain n differences, and the n differences are averaged to obtain an average deviation value, which is used to determine the prediction accuracy of the m groups of preset fitting data. Then, m groups of data are selected and superimposed on the preset fitting data to obtain new preset fitting data with 2m groups of data. The new preset fitting data is refitted to obtain a second mapping relationship between rainfall intensity and the maximum liquid level value of the drainage well. The new second mapping relationship is then used to predict the test data to obtain the predicted maximum liquid level, and the average difference between the predicted maximum liquid level and the actual maximum liquid level is calculated. Similarly, 3m, 4m, and other groups of data are used as new preset fitting data, until all historical data are traversed to obtain multiple average deviation values. The preset fitting data corresponding to the minimum value among all average deviation values ​​is the data with the highest prediction accuracy, and it and the test data are selected as the data to be fitted.

[0051] S3, fitting the data to be fitted to obtain a first mapping relationship between rainfall intensity and the maximum liquid level value of the drainage well.

[0052] Specifically, the least squares method is used to fit the data to be fitted, and the first mapping relationship between the rainfall intensity and the maximum liquid level value of the drainage well is obtained by fitting. The algorithm for fitting the data to be fitted is the same as the algorithm for fitting the preset fitting data.

[0053] In one embodiment of the present invention, Figure 4 As shown, the first mapping relationship between rainfall intensity and the maximum liquid level value of the drainage well is obtained by fitting the data to be fitted, including:

[0054] S301, calculating the mean rainfall intensity and the mean maximum liquid level of the drainage well of the data to be fitted.

[0055] S302: Calculate a first fitting coefficient based on the average rainfall intensity and the average maximum liquid level value of the drainage well.

[0056] S303: Calculate a second fitting coefficient based on the average rainfall intensity, the average maximum liquid level value of the drainage well, and the first fitting coefficient.

[0057] S304: Construct a first mapping relationship according to the first fitting coefficient and the second fitting coefficient.

[0058] Specifically, the least squares method is used to fit the data to be fitted, and the linear regression equation between the rainfall intensity and the maximum liquid level value of the drainage well is obtained. First, the mean rainfall intensity of the data to be fitted and the mean maximum liquid level value of the drainage well are calculated, and the rainfall intensity data is denoted as Y. i , the average rainfall intensity The highest liquid level value of the drainage well is W i , average maximum liquid level value of drainage well The first fitting coefficient is calculated based on the mean rainfall intensity and the mean maximum liquid level of the drainage well. Then, the second fitting coefficient is calculated based on the first fitting coefficient, the average rainfall intensity, and the average maximum liquid level value of the drainage well. The second fitting coefficient A linear regression equation between rainfall intensity and the maximum liquid level value of the drainage well is constructed according to the first fitting coefficient and the second fitting coefficient, that is, a first mapping relationship.

[0059] In one embodiment of the present invention, the first mapping relationship is calculated by the following formula:

[0060]

[0061] Among them, Y is the rainfall intensity, W is the highest liquid level value of the drainage well, is the first fitting coefficient, is the second fitting coefficient.

[0062] Specifically, the above formula is the mapping relationship between the rainfall intensity and the maximum liquid level value of the drainage well obtained by fitting the data to be fitted. In the process of fitting the data to be fitted, in order to ensure the accuracy of the fitted linear regression equation, the correlation coefficient between the rainfall intensity and the maximum liquid level value of the drainage well is also calculated, and it is judged whether the correlation coefficient meets the preset conditions.

[0063] In one embodiment of the present invention, Figure 5 As shown, before fitting the data to be fitted to obtain a first mapping relationship between rainfall intensity and the maximum liquid level value of the drainage well, the method for warning of drainage well overflow further includes:

[0064] S401, calculating the correlation coefficient between the rainfall intensity and the maximum liquid level value of the drainage well in the data to be fitted.

[0065] S402: Determine whether the correlation coefficient meets a preset condition.

[0066] S403: If the correlation coefficient does not meet the preset condition, outlier data in the data to be fitted is determined, and the outlier data is removed to update the data to be fitted, and the process goes to the step of calculating the correlation coefficient until the correlation coefficient meets the preset condition.

[0067] Specifically, calculate the correlation coefficient R2 between rainfall intensity and the maximum liquid level value of the drainage well, and determine the correlation coefficient R 2 Whether the preset conditions are met, the preset conditions can be set according to the accuracy required by the experiment. 2 The preset conditions are not met, indicating that the correlation between the fitted rainfall intensity and the maximum liquid level value of the drainage well is low. The correlation can be improved by removing outlier data. The point of maximum value (Y i ,W i ) represents outlier data in the data to be fitted. The outlier data is removed and the correlation coefficient is recalculated until the correlation coefficient meets the preset conditions. A first mapping relationship between rainfall intensity and the maximum liquid level value of the drainage well is determined. The maximum allowable liquid level value of the drainage well is substituted into the first mapping relationship to obtain the rainfall intensity threshold value for the corresponding drainage well.

[0068] S4, obtaining the maximum allowable liquid level value of the drainage well, and calculating the rainfall intensity threshold value according to the first mapping relationship and the maximum allowable liquid level value.

[0069] Specifically, the depth data of the drainage well is obtained, and the maximum allowable liquid level value of the drainage well is obtained from the well depth data. The maximum allowable liquid level value is substituted into the first mapping relationship in the above formula to obtain the rainfall intensity threshold. This rainfall intensity threshold is used as the judgment basis to judge the rainfall intensity data.

[0070] S5, obtaining rainfall intensity prediction data, and issuing overflow warning information when the rainfall intensity prediction data is greater than a rainfall intensity threshold.

[0071] Specifically, rainfall intensity forecast data is obtained, and when the rainfall intensity forecast data is greater than the rainfall intensity threshold calculated by the above formula, an overflow warning message is issued.

[0072] In one embodiment of the present invention, the rainfall intensity prediction data includes rainfall prediction data of a preset time in the future from a meteorological department.

[0073] Specifically, the rainfall intensity forecast data may be the rainfall forecast data for a preset time in the future provided by the meteorological department, for example, the meteorological department's 3-hour rainfall forecast data. If the meteorological department's 3-hour rainfall forecast data exceeds the calculated rainfall intensity threshold, an overflow warning message is issued.

[0074] Figure 6 This is a method for drainage well overflow warning in an embodiment of the present invention. First, historical data is obtained, which includes rainfall intensity data and drainage well maximum liquid level value data in each rainfall event. The rainfall intensity data and drainage well maximum liquid level value data are deburred. In the rainfall intensity data and drainage well maximum liquid level value data after deburring, according to the fitting algorithm, the best predicted historical data is determined as the data to be fitted. When determining the relationship between rainfall intensity and drainage well maximum liquid level value, the correlation coefficient is also calculated to determine whether the correlation coefficient meets the preset conditions. When the correlation coefficient does not meet the preset conditions, the outlier data is removed until the correlation coefficient meets the preset conditions. It is determined that the relationship between rainfall intensity and drainage well maximum liquid level value is established. The drainage well maximum allowable liquid level value is substituted into the relationship to obtain the rainfall intensity threshold, and rainfall intensity prediction data is obtained. When the rainfall intensity prediction data is greater than the rainfall intensity threshold, an overflow warning message is issued.

[0075] The drainage well overflow warning method of an embodiment of the present invention first obtains historical data, then deburrs the rainfall intensity data and the drainage well maximum liquid level data in the historical data. Based on a fitting algorithm, the optimal predicted preset fitting data and test data are determined as the data to be fitted. When determining the relationship between rainfall intensity and the drainage well maximum liquid level, a correlation coefficient is calculated to determine whether the correlation coefficient meets a preset condition. If the correlation coefficient does not meet the preset condition, outlier data is removed until the correlation coefficient meets the preset condition. The relationship between rainfall intensity and the drainage well maximum liquid level is determined to be valid. The drainage well maximum allowable liquid level value is substituted into the relationship to obtain a rainfall intensity threshold, and rainfall intensity prediction data is obtained. When the rainfall intensity prediction data exceeds the rainfall intensity threshold, an overflow warning message is issued. This drainage well overflow warning method not only provides an advance warning of overflow events, but also dynamically adjusts the threshold, breaking through the limitations of fixed threshold alarms and overcoming the influence of factors such as seasonal water consumption, rainfall frequency, and the degree of rainwater and sewage mixing. Moreover, the method is calculated based on historical data from a statistical perspective and is not constrained by basic pipe network data.

[0076] The invention also provides a drainage well overflow warning device.

[0077] In this embodiment, if Figure 7As shown, the drainage well overflow warning device 100 includes: an acquisition module 10, used to obtain historical data, wherein the historical data includes rainfall intensity data and drainage well maximum liquid level value data in multiple rainfall events; a screening module 20, used to use a data self-checking method to filter out the data to be fitted from the historical data; a fitting module 30, used to fit the data to be fitted to obtain a first mapping relationship between the rainfall intensity and the drainage well maximum liquid level value; a calculation module 40, used to obtain the maximum allowable liquid level value of the drainage well, and calculate the rainfall intensity threshold value based on the first mapping relationship and the maximum allowable liquid level value; an early warning module 50, used to obtain rainfall intensity prediction data, and issue an overflow warning message when the rainfall intensity prediction data is greater than the rainfall intensity threshold.

[0078] It should be noted that, for other specific implementations of the drainage well overflow warning device according to the embodiment of the present invention, reference may be made to the specific implementation of the drainage well overflow warning method according to the above embodiment of the present invention.

[0079] The present invention also provides a computer-readable storage medium.

[0080] In this embodiment, a computer program is stored on a computer-readable storage medium. When the computer program is executed by a processor, the above-mentioned drainage well overflow warning method is implemented.

[0081] The present invention also provides an electronic device.

[0082] In this embodiment, if Figure 8 As shown, the electronic device 200 includes a memory 60 and a processor 70. The memory 60 stores a computer program. When the computer program is executed by the processor 70, the above-mentioned drainage well overflow warning method is implemented.

[0083] The drainage well overflow warning device, storage medium and electronic device of the embodiment of the present invention can not only provide advance warning of overflow events through the above-mentioned drainage well overflow warning method, but also dynamically correct the threshold value, breaking through the limitations of fixed threshold alarms, and overcoming the influence of factors such as seasonal water consumption, rainfall frequency and the degree of rainwater and sewage mixing. In addition, this method is calculated based on historical data from a statistical perspective and is not restricted by basic pipe network data.

[0084] It should be noted that the logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device), or in conjunction with such instruction execution system, apparatus, or device. For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by an instruction execution system, apparatus, or device, or in conjunction with such instruction execution system, apparatus, or device. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection portion having one or more wires (electronic device), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing it in another suitable manner if necessary, and then storing it in a computer memory.

[0085] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0086] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0087] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like to indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0088] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "plurality" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0089] In the present invention, unless otherwise specified or limited, the terms "installed," "connected," "connect," "fixed," etc. should be understood in a broad sense. For example, they can refer to fixed connection, detachable connection, or integration; mechanical connection, electrical connection; direct connection, or indirect connection through an intermediate medium; internal communication between two components, or interaction between two components, unless otherwise specified. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0090] In the present invention, unless otherwise expressly specified or limited, when a first feature is "above" or "below" a second feature, it may mean that the first and second features are in direct contact, or that the first and second features are in indirect contact through an intermediary. Furthermore, when a first feature is "above," "above," or "above" a second feature, it may mean that the first feature is directly above or diagonally above the second feature, or simply means that the first feature is at a higher level than the second feature. When a first feature is "below," "below," or "below" a second feature, it may mean that the first feature is directly below or diagonally below the second feature, or simply means that the first feature is at a lower level than the second feature.

[0091] Although the embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and are not to be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A drainage well overflow warning method, characterized in that: The method comprises: Acquiring historical data, wherein the historical data includes rainfall intensity data and maximum liquid level value data of drainage wells in multiple historical rainfall events; Using a data self-checking method to filter out data to be fitted from the historical data; Fitting the data to be fitted to obtain a first mapping relationship between rainfall intensity and the maximum liquid level value of the drainage well; Obtaining a maximum allowable liquid level value of the drainage well, and calculating a rainfall intensity threshold value based on the first mapping relationship and the maximum allowable liquid level value; Acquire rainfall intensity prediction data, and issue overflow warning information when the rainfall intensity prediction data is greater than the rainfall intensity threshold.

2. The drainage well overflow warning method according to claim 1, characterized in that: Before filtering out the data to be fitted from the historical data, the historical data is further subjected to burr removal processing, including: Calculating a first average value and a first standard deviation of rainfall intensity and a second average value and a second standard deviation of maximum liquid level values ​​of drainage wells in the historical data; The rainfall intensity data is deburred according to a first preset accuracy, the first average value and the first standard deviation, and the drainage well maximum liquid level value data is deburred according to a second preset accuracy, the second average value and the second standard deviation.

3. The drainage well overflow warning method according to claim 1, characterized in that: The method of using the data self-checking method to filter out the data to be fitted from the historical data includes: Select the latest n groups of data from the historical data as test data, and record the m groups of data adjacent to the test data as preset fitting data, where m and n are both positive integers, and m is greater than n; Fitting the preset fitting data to obtain a second mapping relationship between rainfall intensity and the maximum liquid level value of the drainage well; Predicting the maximum liquid level value of the drainage well according to the second mapping relationship and the rainfall intensity in the test data to obtain a maximum liquid level prediction value; Calculating the difference between the predicted maximum liquid level value and the actual maximum liquid level value in the test data, and obtaining an average deviation value based on n of the differences; Select m groups of data and superimpose them on the preset fitting data, and then proceed to the step of fitting to obtain the second mapping relationship until all the historical data are traversed; The preset fitting data corresponding to the minimum value of the average deviation value and the test data are determined as the data to be fitted.

4. The drainage well overflow warning method according to claim 1, characterized in that: The step of fitting the data to be fitted to obtain a first mapping relationship between rainfall intensity and the maximum liquid level value of the drainage well includes: Calculating the mean rainfall intensity and the mean maximum liquid level of the drainage well of the data to be fitted; A first fitting coefficient is calculated based on the average rainfall intensity and the average maximum liquid level value of the drainage well; A second fitting coefficient is calculated based on the rainfall intensity average, the drainage well maximum liquid level average, and the first fitting coefficient; The first mapping relationship is constructed according to the first fitting coefficient and the second fitting coefficient.

5. The drainage well overflow warning method according to claim 4, characterized in that: The first mapping relationship is calculated by the following formula: Wherein, Y is the rainfall intensity, W is the highest liquid level value of the drainage well, is the first fitting coefficient, is the second fitting coefficient.

6. The drainage well overflow warning method according to claim 4, characterized in that: Before fitting the data to be fitted to obtain a first mapping relationship between rainfall intensity and the maximum liquid level value of the drainage well, the method further includes: Calculating the correlation coefficient between the rainfall intensity and the maximum liquid level value of the drainage well in the data to be fitted; Determining whether the correlation coefficient meets a preset condition; If the correlation coefficient does not meet the preset condition, outlier data in the data to be fitted is determined, and the outlier data is removed to update the data to be fitted, and the step of calculating the correlation coefficient is performed until the correlation coefficient meets the preset condition.

7. The drainage well overflow warning method according to claim 1, characterized in that: The rainfall intensity prediction data includes rainfall prediction data of a preset time in the future by the meteorological department.

8. A drainage well overflow warning device, characterized in that: The device comprises: An acquisition module, configured to acquire historical data, wherein the historical data includes rainfall intensity data and maximum liquid level value data of drainage wells in multiple rainfall events; A screening module, configured to screen out data to be fitted from the historical data using a data self-checking method; A fitting module, configured to fit the data to be fitted to obtain a first mapping relationship between rainfall intensity and the maximum liquid level value of the drainage well; a calculation module, configured to obtain a maximum allowable liquid level value of the drainage well, and calculate a rainfall intensity threshold value based on the first mapping relationship and the maximum allowable liquid level value; The early warning module is used to obtain rainfall intensity prediction data and issue overflow warning information when the rainfall intensity prediction data is greater than the rainfall intensity threshold.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for early warning of drainage well overflow according to any one of claims 1 to 7 is implemented.

10. An electronic device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the computer program is executed by the processor, the method for early warning of drainage well overflow according to any one of claims 1 to 7 is implemented.

Images