A water supply management system based on hydraulic simulation data analysis

Abstract

This invention relates to the field of water supply management technology, specifically to a water supply management system based on hydraulic simulation data analysis, comprising: a water flow detection module for real-time acquisition of three indicator data from various monitoring points in the water supply network via sensors, including water flow data, water pressure data, and water quality parameter data; and a data preprocessing module for removing puncture data and pre-statistically collected fault status data from the indicator data using a puncture detection algorithm. This application enables real-time analysis and monitoring of network operation data, quickly identifying patterns and characteristics among various data points, meeting the needs of real-time processing and rapid analysis, enabling faster judgment of abnormal data, and timely formulation of management strategies to improve the scientific nature and accuracy of decision-making.

Description

Technical Field

[0001] This invention relates to the field of water supply management technology, and more specifically to a water supply management system based on hydraulic simulation data analysis. Background Technology

[0002] In traditional pipeline network management, production departments can only focus on the pressure, flow, and water quality of specific pipeline monitoring points within the water supply area. This lacks a holistic perspective, making it impossible to fully understand the operational status and anomalies of the pipeline system. Equipment malfunctions also affect the production department's analysis of the pipeline network. This situation limits the effectiveness of pipeline network monitoring, troubleshooting, and preventative measures, and also impacts the accuracy of subsequent analysis. Traditional management systems are inefficient at processing massive amounts of data and struggle to quickly identify data patterns and characteristics, failing to meet the demands of real-time processing and rapid analysis. They also cannot predict trends in indicator data based on anomalies in the data. Summary of the Invention

[0003] In view of the above problems, the present invention proposes a water supply management system based on hydraulic simulation data analysis, including: a water flow detection module: used to collect three index data of each monitoring point in the water supply network in real time through sensors, including water flow data, water pressure data and water quality parameter data;

[0004] Data preprocessing module; used to remove punctured data from various indicator data and remove pre-statistical fault status data through puncture detection algorithm;

[0005] The data analysis module is used to analyze the preprocessed indicator data using the 3σ principle, identify abnormal indicator data, and calculate the correlation between other indicator data related to abnormal indicator data based on simulated data. Based on the correlation between abnormal indicator data and other indicator data related to abnormal indicator data, management strategies are formulated.

[0006] Preferably, removing punctured data from various indicator data using a puncture detection algorithm includes: extracting n single indicator data points within a certain time period at the monitoring point, with the data point values ​​sequentially as follows: Calculate the average fluctuation (avg) over the time period:

[0007]

[0008] The criteria for detecting spikes are set, including setting three average fluctuation values ​​arg1, arg2, and arg3 based on empirical analysis, and satisfying the following condition:

[0009]

[0010]

[0011] And simultaneously satisfy one of the following two sub-conditions:

[0012]

[0013]

[0014] Data from identified burrs will be removed.

[0015] Preferably, the analysis of the preprocessed index data using the 3σ principle includes: calculating the mean μ, standard deviation σ, and outliers for each index; wherein the calculation of the mean μ includes:

[0016]

[0017] in, This represents the value of a single data point, and n represents the sample size within a specified time period.

[0018] Calculate the standard deviation σ, which reflects the dispersion of the indicator data:

[0019]

[0020] The identification of outliers includes: if <μ−3σ or >μ+3σ, then This is an outlier.

[0021] Preferably, the correlation between the various indicator data includes: the linear correlation r between water flow rate and water pressure at a single data point and the linear correlation R between water flow rate and water quality parameters at a single data point; and the methods for calculating each correlation are as follows:

[0022] a. Calculate the linear correlation r between water flow rate and water pressure for a single data point based on the Pearson correlation coefficient:

[0023]

[0024] Where r>0 indicates a positive correlation, r<0 indicates a negative correlation, |r|≥0.7 indicates a strong correlation, 0.3≤|r|<0.7 indicates a moderate correlation, and |r|<0.3 indicates a weak correlation; This represents the water flow data measured at a single data point. This represents the water flow pressure data at a single measured data point. This is expressed as the standard deviation of water flow rate within a predetermined time period. Expressed as the standard deviation of water flow pressure within a predetermined time period, This represents the average water flow rate over a predetermined period of time. This represents the average water flow pressure over a predetermined time period; m represents the sample size over the predetermined time period.

[0025] b. Calculate the linear correlation R between water flow and water quality parameters for a single data point based on the Pearson correlation coefficient:

[0026]

[0027] Where r>0 indicates a positive correlation, r<0 indicates a negative correlation, |r|≥0.7 indicates a strong correlation, 0.3≤|r|<0.7 indicates a moderate correlation, and |r|<0.3 indicates a weak correlation. Represented as water flow pressure data at a single measured data point. This indicates the standard deviation of water flow pressure within a predetermined time period. This represents the average water pressure over a predetermined period of time.

[0028] Preferably, the management strategy based on the correlation between abnormal indicator data and other indicator data related to the abnormal indicator data includes: if the analyzed water flow rate data is abnormal, then calculate the linear correlation r between water flow rate and water pressure at a single data point or the linear correlation R between water flow rate and water quality parameters at a single data point, and formulate a management strategy based on the two obtained correlation values; if the analyzed water pressure data is abnormal, calculate the linear correlation r between water flow rate and water pressure at a single data point, and formulate a management strategy based on the obtained correlation value; if the water quality parameter data is abnormal, calculate the linear correlation R between water flow rate and water quality parameters at a single data point, and formulate a management strategy based on the obtained correlation value.

[0029] The beneficial effects of this application are as follows: This application performs real-time analysis and monitoring of pipeline operation data, quickly discovers the patterns and characteristics between various data, meets the needs of real-time processing and rapid analysis, can more quickly judge abnormal data, and formulate management strategies in a timely manner, thereby improving the scientific nature and accuracy of decision-making. Attached Figure Description

[0030] Figure 1 The diagram shown is a schematic of the management system of this application. Detailed Implementation

[0031] To enable those skilled in the art to better understand the technical solution of this application, the following description is provided in conjunction with the appendix.

[0032] The invention will be further described in detail with reference to the figures and preferred embodiments.

[0033] Water flow detection module: used to collect three indicators of data from each monitoring point in the water supply network in real time through sensors, including water flow data, water pressure data and water quality parameter data;

[0034] Data preprocessing module; used to remove punctured data from various indicator data and remove pre-statistical fault status data through puncture detection algorithm;

[0035] The data analysis module is used to analyze the preprocessed indicator data using the 3σ principle, identify abnormal indicator data, and calculate the correlation between other indicator data related to abnormal indicator data based on simulated data. Based on the correlation between abnormal indicator data and other indicator data related to abnormal indicator data, management strategies are formulated.

[0036] Using a glitch detection algorithm, glitch data is removed from various indicator data. This includes extracting n single indicator data points within a certain time period from the monitoring points, with the data point values ​​as follows: Calculate the average fluctuation (avg) over the time period:

[0037]

[0038] The criteria for detecting spikes are set, including setting three average fluctuation values ​​arg1, arg2, and arg3 based on empirical analysis, and satisfying the following condition:

[0039]

[0040]

[0041] And simultaneously satisfy one of the following two sub-conditions:

[0042]

[0043]

[0044] The glitch removal method in this application is specifically applied as follows: The average fluctuation over the past day is set as avg, there are n time points for data collection over the past day, and three average fluctuation values ​​arg1, arg2, and arg3 are set for each indicator data:

[0045] dataType: traffic arg1=7.5, arg2=2.5, arg3=7.5;

[0046] dataType: pressure arg1=4.0, arg2=2.0, arg3=7.5;

[0047] dataType: Turbidity (water quality) arg1=5.0, arg2=2.0, arg3=7.5;

[0048] The data of each indicator from three consecutive collection points are sequentially fed into the glitch judgment condition. If the glitch judgment condition is met, the data of the intermediate collection point is removed. During the round-robin process, the removed point is replaced by the median value between the previous and next points.

[0049] The analysis of the preprocessed index data using the 3σ principle includes: calculating the mean μ, standard deviation σ, and outliers for each index; the calculation of the mean μ includes:

[0050]

[0051] in, This represents the value of a single data point, and n represents the sample size within a specified time period.

[0052] Calculate the standard deviation σ, which reflects the dispersion of the indicator data:

[0053]

[0054] The identification of outliers includes: if <μ−3σ or >μ+3σ, then This is an outlier.

[0055] Preferably, the correlation between the various indicator data includes: the linear correlation r between water flow rate and water pressure at a single data point and the linear correlation R between water flow rate and water quality parameters at a single data point; and the methods for calculating each correlation are as follows:

[0056] a. Calculate the linear correlation r between water flow rate and water pressure for a single data point based on the Pearson correlation coefficient:

[0057]

[0058] Where r>0 indicates a positive correlation, r<0 indicates a negative correlation, |r|≥0.7 indicates a strong correlation, 0.3≤|r|<0.7 indicates a moderate correlation, and |r|<0.3 indicates a weak correlation; This represents the water flow data measured at a single data point. This represents the water flow pressure data at a single measured data point. This is expressed as the standard deviation of water flow rate within a predetermined time period. Expressed as the standard deviation of water flow pressure within a predetermined time period, This represents the average water flow rate over a predetermined period of time. This represents the average water flow pressure over a predetermined time period; m represents the sample size over the predetermined time period.

[0059] b. Calculate the linear correlation R between water flow and water quality parameters for a single data point based on the Pearson correlation coefficient:

[0060]

[0061] Where r>0 indicates a positive correlation, r<0 indicates a negative correlation, |r|≥0.7 indicates a strong correlation, 0.3≤|r|<0.7 indicates a moderate correlation, and |r|<0.3 indicates a weak correlation. Represented as water flow pressure data at a single measured data point. This indicates the standard deviation of water flow pressure within a predetermined time period. This represents the average water pressure over a predetermined period of time.

[0062] The water quality parameters included residual chlorine and turbidity. The correlation between water flow pressure and water quality parameters was not significant and was weak. Therefore, the correlation between water flow pressure and water quality parameters was not analyzed further.

[0063] Developing management strategies based on the correlation between abnormal indicator data and other related indicator data includes: if the analysis shows abnormal water flow data, calculating the linear correlation r between water flow and water pressure at a single data point, or the linear correlation R between water flow and water quality parameters at a single data point, and developing management strategies based on the two obtained correlation values. For example, if water flow data suddenly increases abnormally, and the linear correlation r between water flow and water pressure at a single data point strengthens, the abnormality may be caused by pipeline damage or leakage, or abnormal operation of upstream and downstream gates. At the same time, if the linear correlation R between water flow and water quality parameters at a single data point strengthens, it is judged that there may be backflow or excessive flow velocity causing impurities in the pipeline to be flushed down from the pipe wall, increasing turbidity and affecting water quality.

[0064] When the flow rate and turbidity are stable, a slight increase or decrease in flow rate will not affect the turbidity. However, a surge or decrease in flow rate will cause a surge in turbidity, forming a positive or negative correlation and strengthening the correlation. Therefore, changes in flow rate will cause an increase in turbidity.

[0065] If abnormal water flow pressure data is detected, calculate the linear correlation r between water flow rate and water flow pressure for a single data point, and formulate management strategies based on the calculated correlation value. If abnormal water quality parameter data is detected, calculate the linear correlation R between water flow rate and water quality parameter for a single data point, and formulate management strategies based on the calculated correlation value. For example, when turbidity increases, if the linear correlation R between water flow rate and water quality parameter for a single data point strengthens, it is determined that the increase in turbidity may be caused by water flow fluctuations due to water plant regulation, pump station regulation, abnormal gate operation, or pipeline damage and leakage.

[0066] Developing management strategies based on the correlation between abnormal data and other related indicators can help accurately identify the type of anomaly and formulate targeted strategies in a timely manner.

[0067] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A water supply management system based on hydraulic simulation data analysis, characterized in that, include: Water flow detection module: used to collect three indicators of data from each monitoring point in the water supply network in real time through sensors, including water flow data, water pressure data and water quality parameter data; Data preprocessing module; Used to remove punctured data from various indicator data and remove pre-statistical fault status data through punctured data identification algorithms; The data analysis module is used to analyze the preprocessed indicator data using the 3σ principle, identify abnormal indicator data, and calculate the correlation between other indicator data related to the abnormal indicator data based on simulated data. Management strategies are then formulated based on the correlation between the abnormal indicator data and other related indicator data. This includes calculating the linear correlation r between water flow rate and water pressure for a single data point, or the linear correlation R between water flow rate and water quality parameters for a single data point, if the analyzed water flow rate data is abnormal, and formulating management strategies based on the two obtained correlation values. If anomalies are found in the water flow pressure data, calculate the linear correlation r between water flow rate and water flow pressure for a single data point, and formulate management strategies based on the calculated correlation value. If the water quality parameter data is abnormal, calculate the linear correlation R between the water flow rate and the water quality parameter for a single data point, and formulate management strategies based on the calculated correlation value. Using a glitch detection algorithm, glitch data is removed from various indicator data. This includes extracting n single indicator data points within a certain time period from the monitoring points, with the data point values ​​as follows: Calculate the average fluctuation (avg) over the time period: ； The criteria for detecting spikes are set, including setting three average fluctuation values ​​arg1, arg2, and arg3 based on empirical analysis, and satisfying the following condition: ； ； And simultaneously satisfy one of the following two sub-conditions: ； ； Data from identified burrs will be removed.

2. The water supply management system based on hydraulic simulation data analysis according to claim 1, characterized in that, The analysis of the preprocessed index data using the 3σ principle includes: calculating the mean μ, standard deviation σ, and outliers of each index data.

3. The water supply management system based on hydraulic simulation data analysis according to claim 1, characterized in that, The correlations between various indicator data include: the linear correlation r between water flow rate and water pressure at a single data point, and the linear correlation R between water flow rate and water quality parameters at a single data point; and the methods for calculating each correlation are as follows: a. Calculate the linear correlation r between water flow rate and water pressure for a single data point based on the Pearson correlation coefficient: ； Where r>0 indicates a positive correlation, r<0 indicates a negative correlation, |r|≥0.7 indicates a strong correlation, 0.3≤|r|<0.7 indicates a moderate correlation, and |r|<0.3 indicates a weak correlation; This represents the water flow data measured at a single data point. This represents the water flow pressure data at a single measured data point. This is expressed as the standard deviation of water flow rate within a predetermined time period. Expressed as the standard deviation of water flow pressure within a predetermined time period, This represents the average water flow rate over a predetermined period of time. This represents the average water flow pressure over a predetermined time period; m represents the sample size over the predetermined time period. b. Calculate the linear correlation R between water flow and water quality parameters for a single data point based on the Pearson correlation coefficient: ； Where R>0 indicates a positive correlation, R<0 indicates a negative correlation, |R|≥0.7 indicates a strong correlation, 0.3≤|R|<0.7 indicates a moderate correlation, and |R|<0.3 indicates a weak correlation. This represents water quality parameter data for a single measured data point. This indicates the standard deviation of water quality parameters within a predetermined time period. This represents the average water quality parameters over a predetermined period.

Images