Regional intelligent drainage system

Abstract

The invention discloses a regional intelligent drainage system, and belongs to the technical field of water supply and drainage. The system comprises a data acquisition module, a data segmentation processing module, a statistical analysis module, a weight distribution module, a trend feature extraction module, a data cleaning module, a prediction module and an adaptive control module. Water flow data of a target area can be acquired in real time, and stage features of water yield fluctuation are identified through data segmentation processing and statistical analysis; and a scientific basis is provided for dynamic adjustment of the drainage system.

Description

Technical Field

[0001] The present invention relates to the technical field of water supply and drainage, and more particularly to a regional intelligent drainage system. Background Art

[0002] With the acceleration of urbanization, urban drainage systems are facing a series of challenges such as water flow fluctuations, insufficient drainage capacity, and environmental pollution. Traditional drainage systems often rely on fixed design standards and empirical rules, which are difficult to adapt to the ever-changing climate conditions and urban development needs. Therefore, an intelligent, regional, and dynamically responsive drainage management system is urgently needed to improve the efficiency and reliability of urban drainage.

[0003] Most existing drainage systems are passive responses and lack real-time monitoring and analysis of water flow data, which results in the inability to adjust the drainage system in time when extreme weather or emergencies occur, causing problems such as waterlogging and waterlogging. In addition, traditional data processing methods often cannot effectively identify trend features in water flow data, resulting in inaccurate predictions of future water flow changes, thus affecting the scientific nature of drainage decisions.

[0004] In order to solve the above problems, it is particularly important to develop an intelligent drainage system based on data acquisition, analysis and adaptive control.

[0005] Therefore, how to provide a regional intelligent drainage system that can solve the above problems is an issue that technical personnel in this field urgently need to solve. Summary of the invention

[0006] In view of this, the present invention provides a regional intelligent drainage system, which can collect water flow data in the target area in real time, identify the stage characteristics of water volume fluctuations through data segmentation processing and statistical analysis, and thus provide a scientific basis for the dynamic adjustment of the drainage system.

[0007] In order to achieve the above object, the present invention provides the following technical solutions:

[0008] A regional intelligent drainage system, including:

[0009] Data acquisition module, collecting water flow data in the target area;

[0010] The data segmentation processing module segments the collected water flow data, identifies the water flow data corresponding to the stage causing the water volume fluctuation, and obtains multiple segmented data sets;

[0011] The statistical analysis module selects any segmented data set as the target segment, sorts the data points in the target segment, and calculates the deviation value;

[0012] The weight assignment module assigns weights to each data point in the target segment according to the deviation value and calculates the weighted mean;

[0013] A trend feature extraction module calculates the cumulative average of the deviations between each data point in the target segment and the weighted mean as the trend feature of the target segment;

[0014] The data cleaning module fits each segmented data set, calculates the residual value of the data points before and after fitting, removes invalid trend features based on the residual value, and retains valid trend features;

[0015] The prediction module builds and trains a prediction model based on effective trend characteristics, and predicts the changes in drainage volume in the target area over a period of time in the future based on the prediction model;

[0016] The adaptive control module automatically adjusts the drainage status of the drainage system according to the above prediction results.

[0017] Furthermore, the data segmentation processing module includes:

[0018] Scale adjustment unit: adjust the collected water flow data to the same scale;

[0019] Time Series Analysis Unit: Extract mean flow, peak flow, and standard deviation from scale-adjusted streamflow data;

[0020] Segment processing unit: set a threshold to distinguish different states; when the flow exceeds the set threshold, it is marked as the beginning of a new segment; when the flow falls below the threshold, the segment ends;

[0021] Segment storage unit: number or mark each segment, and record the start time, end time, maximum value, and minimum value of each segment to obtain multiple segment data sets.

[0022] Furthermore, the statistical analysis module includes:

[0023] Target selection unit: select any segmented data set as the target segment;

[0024] Target calculation unit: calculates the upper and lower quartiles of the target segmented data;

[0025] The deviation degree value determining unit evaluates the deviation between each data point and the quartile values ​​based on the upper and lower quartiles as the deviation degree value.

[0026] Furthermore, the weight distribution module includes:

[0027] Weight assignment unit: assigns weights to each data point in the target segment according to the deviation value;

[0028] Weighted mean calculation unit: calculates the weighted mean based on the result of the assigned weights.

[0029] Furthermore, the calculation formula of the weight allocation unit is:

[0030]

[0031] In the formula, IQR i is the interquartile range, which indicates the degree of dispersion of the data; x ij Represents the value of the jth data point in the i-th segment data, M i represents the middle value, w ij Indicates the weight of the jth data point in the i-th segment data participating in the mean calculation.

[0032] Furthermore, the calculation formula of the weighted mean calculation unit is:

[0033]

[0034] In the formula, represents the weighted mean of the i-th segment data, ni Indicates the number of data in the i-th segment data, x ij represents the value of the jth data point in the i-th segment data, w ij Indicates the weight of the jth data point in the i-th segment data participating in the mean calculation.

[0035] Furthermore, the trend feature extraction module includes:

[0036] The first calculation unit: calculate the deviation between each data point and the weighted mean, and find the cumulative average of the deviation as the trend feature. The deviation is calculated as:

[0037]

[0038] Where, d ij Indicates the deviation value, x ij Represents the value of the jth data point in the i-th segment data, Represents the weighted mean of the i-th segment data;

[0039] Second calculation unit: Calculate the cumulative average of the deviation:

[0040]

[0041] Where D i Represents the cumulative average, which is the trend characteristic of the target segment.

[0042] Furthermore, the data cleaning module includes:

[0043] Fitting unit: Fit each segmented data set;

[0044] Residual calculation unit: calculate the residual of each data point;

[0045] Cleaning unit: Set the threshold θ, if the residual of a data point | r ij ∣>θ, then this data point is considered to be an outlier or noise, and this data point is removed from the valid trend features, retaining the valid trend features.

[0046] Furthermore, the prediction model is any one of a linear regression model, a polynomial regression model, a support vector machine (SVM) model, and a long short-term memory network (LSTM).

[0047] Furthermore, the adaptive control module automatically adjusts the drainage state of the drainage system according to the above prediction results, including:

[0048] Determine the maximum drainage capacity of the target area and the drainage requirements of each drainage point in the target area;

[0049] Set a basic discharge volume for each discharge point;

[0050] When the upper limit of the maximum drainage capacity is less than the sum of the basic drainage of all drainage points, the following steps are taken to distribute drainage:

[0051] S100: Ensure that each drainage point can at least get the basic drainage volume;

[0052] S200: Calculate the allocable drainage capacity, calculate the upper limit of the current drainable capacity minus the baseline drainage volume allocated to at least one drainage point, and use the remaining maximum drainage capacity to supplement the drainage points with additional drainage needs.

[0053] It can be seen from the above technical solutions that, compared with the prior art, the present invention discloses a regional intelligent drainage system, which can collect water flow data in the target area in real time, identify the phased characteristics of water volume fluctuations through data segmentation processing and statistical analysis, and thus provide a scientific basis for the dynamic adjustment of the drainage system. The specific beneficial effects are as follows:

[0054] (1) Through the data acquisition module, the system can obtain water flow data in the target area in real time, ensuring the timeliness and accuracy of the data and providing a reliable basis for subsequent analysis.

[0055] (2) By using segmented processing and statistical analysis modules, the system can effectively identify the fluctuation stages in water flow data, calculate the deviation value and assign weights, thereby extracting effective trend features. This intelligent analysis method can better adapt to complex water flow changes and improve the accuracy of data processing.

[0056] (3) By calculating the weighted mean of data points and analyzing the cumulative average of deviations, the system can effectively extract the trend characteristics of the target segment, thereby providing a scientific basis for drainage decisions.

[0057] (4) The data cleaning module can automatically remove invalid trend features and retain valid data through fitting analysis and residual calculation to ensure the accuracy of the prediction model.

[0058] (5) The prediction model constructed based on effective trend characteristics can accurately predict the changes in drainage volume in the future, provide a scientific basis for drainage management, and reduce the risk of urban flooding.

[0059] (6) The system’s adaptive control module can automatically adjust the drainage status according to the prediction results, realize dynamic management, and improve the responsiveness and flexibility of the drainage system.

[0060] In summary, the regional intelligent drainage system provided by the present invention not only improves the intelligence level of drainage management, but also effectively improves the efficiency and safety of urban drainage, providing strong support for the sustainable development of cities. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0062] Figure 1 It is a schematic diagram of the system structure of the present invention. DETAILED DESCRIPTION

[0063] 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 only 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0064] See also Figure 1 The embodiment of the present invention discloses a regional intelligent drainage system, including:

[0065] Data acquisition module, collecting water flow data in the target area;

[0066] The data segmentation processing module segments the collected water flow data, identifies the water flow data corresponding to the stage causing the water volume fluctuation, and obtains multiple segmented data sets;

[0067] The statistical analysis module selects any segmented data set as the target segment, sorts the data points in the target segment, and calculates the deviation value;

[0068] The weight assignment module assigns weights to each data point in the target segment according to the deviation value and calculates the weighted mean;

[0069] A trend feature extraction module calculates the cumulative average of the deviations between each data point in the target segment and the weighted mean as the trend feature of the target segment;

[0070] The data cleaning module fits each segmented data set, calculates the residual value of the data points before and after fitting, removes invalid trend features based on the residual value, and retains valid trend features;

[0071] The prediction module builds and trains a prediction model based on effective trend characteristics, and predicts the changes in drainage volume in the target area over a period of time in the future based on the prediction model;

[0072] The adaptive control module automatically adjusts the drainage status of the drainage system according to the above prediction results.

[0073] In a specific embodiment, the data segment processing module includes:

[0074] Scale adjustment unit: adjust the collected water flow data to the same scale;

[0075] Time Series Analysis Unit: Extract mean flow, peak flow, and standard deviation from scale-adjusted streamflow data;

[0076] Segment processing unit: set a threshold to distinguish different states; when the flow exceeds the set threshold, it is marked as the beginning of a new segment; when the flow falls below the threshold, the segment ends;

[0077] Segment storage unit: number or mark each segment, and record the start time, end time, maximum value, and minimum value of each segment to obtain multiple segment data sets.

[0078] In a specific embodiment, the statistical analysis module includes:

[0079] Target selection unit: select any segmented data set as the target segment;

[0080] Target calculation unit: calculates the upper and lower quartiles of the target segmented data;

[0081] Deviation degree value determination unit: Based on the upper and lower quartiles (i.e., the 25th percentile and the 75th percentile), the deviation between each data point and these quartile values ​​is evaluated as the deviation degree value.

[0082] In a specific embodiment, the weight allocation module includes:

[0083] Weight assignment unit: assigns weights to each data point in the target segment according to the deviation value;

[0084] Weighted mean calculation unit: calculates the weighted mean based on the result of the assigned weights.

[0085] In a specific embodiment, the calculation formula of the weight allocation unit is:

[0086]

[0087] In the formula, IQR i is the interquartile range, which indicates the degree of dispersion of the data; x ij Represents the value of the jth data point in the i-th segment data, M i represents the middle value, w ij Indicates the weight of the jth data point in the i-th segment data participating in the mean calculation.

[0088] Specifically, this weight distribution method ensures that data points near the quartiles have higher weights, while data points far from the quartiles are given lower weights. This can reduce the impact of outliers on the mean and make the weighted mean more reflective of the main trend of the data.

[0089] In a specific embodiment, the calculation formula of the weighted mean calculation unit is:

[0090]

[0091] In the formula, represents the weighted mean of the i-th segment data, n i Indicates the number of data in the i-th segment data, x ij represents the value of the jth data point in the i-th segment data, w ij Indicates the weight of the jth data point in the i-th segment data participating in the mean calculation.

[0092] Specifically, the weighted mean is calculated by multiplying each data point by its corresponding weight, then summing the sum and dividing it by the sum of all weights. This ensures that those data points with higher weights have a greater impact on the final result.

[0093] In a specific embodiment, the trend feature extraction module includes:

[0094] The first calculation unit: calculate the deviation between each data point and the weighted mean, and find the cumulative average of the deviation as the trend feature. The deviation is calculated as:

[0095]

[0096] Where, d ij Indicates the deviation value, x ij Represents the value of the jth data point in the i-th segment data, Represents the weighted mean of the i-th segment data;

[0097] Second calculation unit: Calculate the cumulative average of the deviation:

[0098]

[0099] Where D i Represents the cumulative average, which is the trend characteristic of the target segment.

[0100] In a specific embodiment, the data cleaning module includes:

[0101] Fitting unit: Fit each segmented data set; you can use a simple linear regression model or other more complex models (such as polynomial regression, spline regression, etc.). Suppose we use a linear regression model, which is in the form of:

[0102] y = a + bx;

[0103] In the formula, y is the dependent variable, such as flow, x is the independent variable, such as time, and a and b are model parameters.

[0104] Residual calculation unit: calculate the residual of each data point;

[0105] The specific calculation is:

[0106] r ij =y ij -(a+bx ij );

[0107] In the formula, (x ij ,y ij ) is the data point, r ij is the calculated residual of the data point.

[0108] Cleaning unit: Set the threshold θ, if the residual of a data point | r ij If |>θ, the data point is considered to be an outlier or noise, and the data point is removed from the effective trend features, and the effective trend features are retained. Finally, the data points with smaller residuals are retained as effective trend features.

[0109] In a specific embodiment, the prediction model is any one of a linear regression model, a polynomial regression model, a support vector machine (SVM) model, and a long short-term memory network (LSTM).

[0110] Specifically, historical data is used to train the prediction model. This embodiment selects the LSTM model, and its structure is as follows:

[0111] Input layer: receives time series data.

[0112] LSTM layer: handles temporal dependencies.

[0113] Fully connected layer: outputs the predicted value for a period of time in the future.

[0114] Specifically, based on the trained model, the current effective trend characteristics are input to predict the changes in discharge volume in the future.

[0115] In a specific embodiment, the adaptive control module automatically adjusts the drainage state of the drainage system according to the above prediction results, including:

[0116] Determine the maximum drainage capacity of the target area and the drainage requirements of each drainage point in the target area;

[0117] Set a basic discharge volume for each discharge point;

[0118] When the upper limit of the maximum drainage capacity is less than the sum of the basic drainage of all drainage points, the following steps are taken to distribute drainage:

[0119] S100: Ensure that each drainage point can at least get the basic drainage volume;

[0120] S200: Calculate the allocable drainage capacity, calculate the upper limit of the current drainable capacity minus the baseline drainage volume allocated to at least one drainage point, and use the remaining maximum drainage capacity to supplement the drainage points with additional drainage needs.

[0121] Specifically, first, the adaptive control module evaluates the maximum drainage capacity of the entire drainage system and the actual drainage demand of each drainage point / area. Then a basic drainage volume is defined for each drainage point / area, which is the minimum drainage standard that should be guaranteed under any circumstances. When it is found that the total drainage demand exceeds the maximum drainage capacity of the system, at least one drainage point / area is selected as a priority. The selection basis may include but is not limited to the importance of the site, the current water level, historical flood risks, etc. Ensure that all drainage points / areas can obtain their basic drainage volume. For those drainage points / areas selected as priority, after their basic drainage volume is met, the remaining maximum drainage capacity is used to increase their drainage volume as much as possible until the maximum drainage capacity of the system is reached. For drainage points / areas that are not selected as priority, only their basic drainage volume is maintained unchanged. Such a strategy aims to ensure that limited drainage capacity can be reasonably arranged even when resources are tight.

[0122] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0123] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A regional intelligent drainage system, characterized in that: include: Data acquisition module, collecting water flow data in the target area; The data segmentation processing module segments the collected water flow data, identifies the water flow data corresponding to the stage causing the water volume fluctuation, and obtains multiple segmented data sets; The statistical analysis module selects any segmented data set as the target segment, sorts the data points in the target segment, and calculates the deviation value; The weight assignment module assigns weights to each data point in the target segment according to the deviation value and calculates the weighted mean; A trend feature extraction module calculates the cumulative average of the deviations between each data point in the target segment and the weighted mean as the trend feature of the target segment; The data cleaning module fits each segmented data set, calculates the residual value of the data points before and after fitting, removes invalid trend features based on the residual value, and retains valid trend features; The prediction module builds and trains a prediction model based on effective trend characteristics, and predicts the changes in drainage volume in the target area over a period of time in the future based on the prediction model; The adaptive control module automatically adjusts the drainage status of the drainage system according to the above prediction results.

2. According to claim 1, a regional intelligent drainage system is characterized in that: The data segmentation processing module comprises: Scale adjustment unit: adjust the collected water flow data to the same scale; Time Series Analysis Unit: Extract mean flow, peak flow, and standard deviation from scale-adjusted streamflow data; Segment processing unit: set a threshold to distinguish different states; when the flow exceeds the set threshold, it is marked as the beginning of a new segment; when the flow falls below the threshold, the segment ends; Segment storage unit: number or mark each segment, and record the start time, end time, maximum value, and minimum value of each segment to obtain multiple segment data sets.

3. The regional intelligent drainage system according to claim 1, characterized in that: The statistical analysis module comprises: Target selection unit: select any segmented data set as the target segment; Target calculation unit: calculates the upper and lower quartiles of the target segmented data; The deviation degree value determining unit evaluates the deviation between each data point and the quartile values ​​based on the upper and lower quartiles as the deviation degree value.

4. The regional intelligent drainage system according to claim 1, characterized in that: The weight distribution module comprises: Weight assignment unit: assigns weights to each data point in the target segment according to the deviation value; Weighted mean calculation unit: calculates the weighted mean based on the result of the assigned weights.

5. A regional intelligent drainage system according to claim 4, characterized in that: The calculation formula of the weight distribution unit is: In the formula, IQR i is the interquartile range, indicating the degree of dispersion of the data; x ij Represents the value of the jth data point in the i-th segment data, M i represents the middle value, w ij Indicates the weight of the jth data point in the i-th segment data participating in the mean calculation.

6. The regional intelligent drainage system according to claim 4, characterized in that: The calculation formula of the weighted mean calculation unit is: In the formula, represents the weighted mean of the i-th segment data, ni Indicates the number of data in the i-th segment data, x ij represents the value of the jth data point in the i-th segment data, w ij Indicates the weight of the jth data point in the i-th segment data participating in the mean calculation.

7. The regional intelligent drainage system according to claim 1, characterized in that: The trend feature extraction module comprises: The first calculation unit: calculate the deviation between each data point and the weighted mean, and find the cumulative average of the deviation as the trend feature. The deviation is calculated as: Where, d ij Indicates the deviation value, x ij Represents the value of the jth data point in the i-th segment data, Represents the weighted mean of the i-th segment data; Second calculation unit: Calculate the cumulative average of the deviation: Where D i Represents the cumulative average, which is the trend characteristic of the target segment.

8. The regional intelligent drainage system according to claim 1, characterized in that: The data cleaning module comprises: Fitting unit: Fit each segmented data set; Residual calculation unit: calculate the residual of each data point; Cleaning unit: Set the threshold θ, if the residual of a data point | r ij ∣>θ, then this data point is considered to be an outlier or noise, and this data point is removed from the valid trend features, retaining the valid trend features.

9. The regional intelligent drainage system according to claim 1, characterized in that: The prediction model is any one of a linear regression model, a polynomial regression model, a support vector machine (SVM) model, and a long short-term memory network (LSTM).

10. The regional intelligent drainage system according to claim 1, characterized in that: The adaptive control module automatically adjusts the drainage state of the drainage system according to the above prediction results, including: Determine the maximum drainage capacity of the target area and the drainage requirements of each drainage point in the target area; Set a basic discharge volume for each discharge point; When the upper limit of the maximum drainage capacity is less than the sum of the basic drainage of all drainage points, the following steps are taken to distribute drainage: S100: Ensure that each drainage point can at least get the basic drainage volume; S200: Calculate the allocable drainage capacity, calculate the upper limit of the current drainable capacity minus the baseline drainage volume allocated to at least one drainage point, and use the remaining maximum drainage capacity to supplement the drainage points with additional drainage needs.

Images