Water affair platform intelligent supervision system and method based on digitized information

Abstract

The application discloses a water affair platform intelligent supervision system and method based on digital information, relates to the technical field of data supervision, and comprises the following steps: periodically collecting water quality data of each monitoring area to obtain monitoring records of each monitoring area; performing multidimensional evaluation on water quality data presented by any monitoring record to obtain a water quality evaluation value; performing difference comparison of water quality data on different monitoring records of any monitoring area to extract a plurality of characteristic events and analyze to obtain a correlation value of any characteristic event; identifying pollution sources of pollution based on pollution conditions of each monitoring area; analyzing pollution conditions of each monitoring area by the pollution sources, predicting water quality conditions of any monitoring area; obtaining a prediction evaluation value of each monitoring area in real time; and collecting water quality data of each monitoring area in real time and identifying abnormalities of each monitoring area.

Description

Technical Field

[0001] This invention relates to the field of data supervision technology, specifically to an intelligent supervision system and method for water affairs platforms based on digital information. Background Technology

[0002] A water management platform typically refers to a comprehensive system for managing and monitoring water resources, involving multiple aspects such as water supply, distribution, monitoring, and management. Through the monitoring system, the efficiency and transparency of water management can be improved by using digital means.

[0003] Traditional water quality monitoring systems rely heavily on manual inspections and offline laboratory testing, which suffer from problems such as delayed data collection and low monitoring frequency. For example, most systems cannot achieve real-time monitoring covering the entire pipe network, leading to delays in the detection of abnormal water quality events and an increased risk of pollution spread. Although some smart water management platforms have introduced big data analytics, most systems are still stuck in the stage of static threshold alarms, lacking dynamic risk assessment capabilities and unable to dynamically adjust early warning strategies by combining historical data with real-time environmental parameters, resulting in false alarms or missed alarms. Summary of the Invention

[0004] The purpose of this invention is to provide an intelligent monitoring system and method for water management platforms based on digital information, so as to solve the problems raised in the prior art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: an intelligent monitoring method for a water affairs platform based on digital information, the monitoring method comprising the following steps:

[0006] Step S100: Divide the target area into monitoring zones according to the pre-installed monitoring equipment, collect water quality data of each monitoring zone periodically to obtain several monitoring records for each monitoring zone; conduct multi-dimensional evaluation of the water quality data presented in any monitoring record to obtain the water quality evaluation value of any monitoring zone;

[0007] Step S200: Compare the differences in water quality data from different monitoring records in any monitoring area and extract several feature events; based on the differences in water quality assessment between different monitoring records, obtain the correlation value of any feature event;

[0008] Step S300: Identify pollution in each monitoring area within any unit period; identify pollution sources based on the pollution status of each monitoring area; analyze the pollution status of pollution sources in each monitoring area; and predict the water quality of any monitoring area.

[0009] Step S400: Analyze the pollution situation in each monitoring area in real time to obtain the predicted assessment value of each monitoring area; collect water quality data in real time for each monitoring area to obtain the real-time water quality assessment value of each monitoring area; and identify anomalies in each monitoring area.

[0010] Furthermore, step S100 includes the following steps:

[0011] Step S101: Several sets of monitoring equipment are installed in the target area according to a preset distribution plan. Each set of monitoring equipment contains several different monitoring devices, and the monitoring range of each set of monitoring equipment is the same. The monitoring range of each set of monitoring equipment in the target area is obtained, and the area corresponding to each monitoring range is set as a monitoring area in the target area. The monitoring equipment set includes various monitoring devices such as pH sensor, turbidity sensor, and dissolved oxygen sensor.

[0012] Step S102: The water quality data of the monitoring area is continuously collected by the monitoring equipment group. The water quality data collected by any monitoring equipment group is summarized every unit cycle to obtain the water quality data set of each monitoring area in the unit cycle, and the corresponding monitoring record is generated.

[0013] Step S103: Randomly select monitoring records for a monitoring area, and divide the water quality data set of the selected monitoring records into several dimensions of water quality datasets according to the type of monitoring equipment. One monitoring equipment corresponds to one dimension of water quality dataset. Preset corresponding evaluation rules for each dimension of water quality dataset to obtain the evaluation value of each dimension. Calculate the average value of all dimensions of evaluation values ​​to obtain the water quality evaluation value of the monitoring area in the selected monitoring records. Set evaluation rules for each monitoring equipment. For example, the deviation of the pH value detected by the pH sensor from the normal range reflects the water quality. The turbidity evaluation of water quality can also reflect the water quality.

[0014] Furthermore, step S200 includes the following steps:

[0015] Step S201: Arbitrarily select a monitoring area, and arbitrarily extract two monitoring records from the selected monitoring area to obtain the water quality datasets of the two monitoring records in any dimension; let D1 be the water quality dataset of the two monitoring records in the a-th dimension. a and D2 a Obtain water quality dataset D1 respectively a Water quality data d1 at time point t a (t) and water quality dataset D2 a Water quality data at time point t, d2 a (t), to obtain the data difference Δd of the a-th dimension at time point t.a (t)=d1 a (t)-d2 a (t);

[0016] Step S202: Preset a data difference threshold Δt th If Δd a (t)>Δt th Then, time point t is set as an abnormal time point; the number of abnormal time points contained in the a-th dimension within a unit period is counted as N. t Let N be the number of time points in a unit period, and then obtain the anomaly frequency f of the a-th dimension. a =N t / N; Preset an abnormal frequency threshold f th If f a >f th Then the a-th dimension is set as a differential feature;

[0017] Step S203: A feature event database is pre-established, containing several feature events and corresponding feature sets. Each feature time corresponds to a feature set, and each feature in the feature set has a set of numerical values. The difference features between two monitoring records are obtained. A feature set is arbitrarily selected. If each feature in the feature set has a corresponding difference feature, the numerical range of any feature in the feature set is compared with the water quality data range of the difference feature. If the water quality data range falls within the numerical range of the feature, the feature event corresponding to the feature set is set as a feature event between the two monitoring records. Feature events include rainfall introducing other substances, drought causing water level drops and concentrating pollutants, and changes in water flow velocity causing changes in sediments.

[0018] Step S204: Randomly select a feature event between two monitoring records, randomly extract a difference feature from the selected feature event, take the average value of the data difference at any time point under the corresponding dimension of the difference feature to obtain the average difference value, and sum the average differences under all dimensions to obtain the average difference value of the difference feature.

[0019] Step S205: Obtain the average difference of each differential feature in the feature event, and sum them to obtain the average difference of the feature events; set the average difference of the b-th feature event as (Δd ave ) b According to the formula:

[0020] ;

[0021] Where b is a positive integer and b∈(1,e), and e is the total number of differential features included; the correlation coefficient γ of the b-th feature event is calculated.b ;

[0022] Step S206: Obtain the water quality assessment values ​​P1 and P2 from the two monitoring records respectively, and obtain the water quality assessment difference ΔP = P1 - P2 between the two monitoring records. Calculate the correlation value G for the b-th feature event. b =ΔP×γ b The average value PG of the b-th characteristic event is obtained by averaging the correlation values ​​between any two monitoring records. b .

[0023] Furthermore, step S300 includes the following steps:

[0024] Step S301: Obtain the record generation time of each monitoring record; arbitrarily select a record generation time to obtain the time difference between each monitoring record; extract the target monitoring record with the smallest time difference from each monitoring area; preset a pollution assessment value P. th Let P be the water quality assessment value presented by the target monitoring record for the i-th monitoring area. i If P i <P th If so, then the i-th monitoring area will be set as the polluted area;

[0025] Step S302: Obtain target monitoring records for each polluted area to obtain a target monitoring record set. Assume that the i-th and j-th monitoring areas are both polluted areas and adjacent to each other. Obtain the feature events contained in the two polluted areas and compare them to obtain the difference feature events between the two polluted areas. Set the average evaluation value of the k-th difference feature event in the i-th monitoring area to PG. (i,k) According to the formula: Where m is the number of differential characteristic events in the i-th monitoring area; the expected evaluation value P of the i-th monitoring area is calculated. ’ i The expected assessment value of a monitoring area is determined based on the difference in characteristic events between it and its neighboring areas. Since the same characteristic events will not affect each other, the expected assessment value can be effectively obtained through the correlation value of the difference in characteristic events, which is beneficial for subsequent prediction and anomaly identification.

[0026] Step S303: Obtain the expected evaluation value P for the j-th monitoring area. ’ j If P ’ i >P ’ jIf the target pollution source is set as the i-th monitoring area, the expected assessment value of the target pollution source is compared with that of other adjacent pollution areas until the target pollution source is compared with all adjacent pollution areas. Then the pollution area where the target pollution source is located is set as a pollution source of the target area. The pollution source is the first pollution area to be polluted, and the pollution spreads from high concentration to low concentration. Therefore, it is only necessary to compare the water quality assessment values ​​between different areas. At the same time, different areas will not have only one source. Therefore, the comparison of water quality differences can only be carried out by comparing adjacent areas, rather than comparing any two areas.

[0027] Step S304: Set the pollution source in the target area as the i-th monitoring area. Randomly select a monitoring area adjacent to the i-th monitoring area from the remaining monitoring areas. Acquire the difference characteristic events of the selected monitoring area compared with the i-th monitoring area, extract the average evaluation value of any difference characteristic event, and obtain the expected evaluation value P of the selected monitoring area. ’ The water quality assessment value of the selected monitoring area was obtained as P. ac The actual assessment difference ΔP of the selected monitoring area is obtained. ac =P ac -P ’ ;

[0028] Step S305: After calculating the expected evaluation value for any monitoring area and its adjacent monitoring areas, the actual evaluation difference for any monitoring area is obtained. The average of the actual evaluation differences is then taken to obtain an average difference (ΔP). ac ) ave ; Select any monitoring area from the remaining monitoring areas and set it as the test area. Count the minimum number of connected areas between the i-th monitoring area and the test area as Z. The minimum number of connected areas is the number of areas that are connected to each other by different adjacent monitoring areas. For example, A is adjacent to B, and B is adjacent to C, so the connected areas are ABC.

[0029] Step S306: Obtain the monitoring regions involved in the minimum number of connected regions Z. Starting from the i-th monitoring region, calculate the expected evaluation value of the adjacent monitoring regions, and continue to calculate the expected evaluation value of the monitoring regions adjacent to the adjacent monitoring regions until the expected evaluation value P of the test region is obtained. ’ test Finally, the predicted evaluation value of the test area is (P). ex ) test =P ’ test +Z×(ΔP ac ) ave +U, where U is a constant coefficient; obtain the water quality assessment value of the test area as P. testThe constant coefficients U=P are obtained. test -(P ex ) test ;

[0030] Step S307: Obtain the expected evaluation value of any other monitoring area relative to the i-th monitoring area, and obtain the expected evaluation value of the other arbitrary monitoring area; extract the water quality evaluation value of the other arbitrary monitoring area. If the difference between the obtained expected evaluation value and the water quality evaluation value exceeds the preset evaluation difference threshold, the constant coefficient U is continuously corrected until the difference between the expected evaluation value and the water quality evaluation value in any monitoring area is less than or equal to the preset evaluation difference threshold.

[0031] Furthermore, step S400 includes the following steps:

[0032] Step S401: Obtain the real-time monitoring records generated in each monitoring area to obtain the real-time water quality assessment value P for each monitoring area. now The pollution assessment value is set at P. th When there are several monitoring areas that meet P now >P th Then, the pollution sources in the target area are identified, and anomaly alerts are sent to the monitoring areas where the pollution sources are located;

[0033] Step S402: When only one monitoring area satisfies P now >P th When this happens, the predicted evaluation value (P) for any of the remaining monitoring areas is obtained. ex ) now ; Set the evaluation difference threshold as σ, if |(P ex ) now -P now If |≥σ, then an anomaly alert will be sent to the remaining monitoring areas.

[0034] The intelligent monitoring system for water affairs platforms includes a regional water quality analysis module, a characteristic event correlation module, a pollution diffusion prediction module, and a real-time pollution identification module.

[0035] The regional water quality analysis module is used to divide the target area into monitoring zones based on pre-installed monitoring equipment, periodically collect water quality data for each monitoring zone, and obtain several monitoring records for each monitoring zone; it also performs multi-dimensional evaluation on the water quality data presented in any monitoring record to obtain the water quality assessment value for any monitoring zone.

[0036] The feature event association module is used to compare the differences in water quality data of different monitoring records in any monitoring area and extract several feature events; based on the differences in water quality assessment between different monitoring records, the association value of any feature event is obtained;

[0037] The pollution diffusion prediction module is used to identify pollution in each monitoring area within any unit period, identify pollution sources based on the pollution status of each monitoring area, analyze the pollution status of pollution sources in each monitoring area, and predict the water quality status of any monitoring area.

[0038] The real-time pollution identification module is used to analyze the pollution status of each monitoring area in real time and obtain the predicted assessment value of each monitoring area; to collect water quality data in real time for each monitoring area and obtain the real-time water quality assessment value of each monitoring area; and to identify anomalies in each monitoring area.

[0039] Furthermore, the regional water quality analysis module includes a water quality data acquisition unit and a regional water quality assessment unit;

[0040] The water quality data acquisition unit is used to divide the target area into monitoring areas based on the pre-installed monitoring equipment, and to collect water quality data of each monitoring area on a regular basis, thereby obtaining several monitoring records for each monitoring area; the regional water quality assessment unit is used to conduct multi-dimensional assessments of the water quality data presented in any monitoring record, thereby obtaining the water quality assessment value of any monitoring area.

[0041] Furthermore, the feature event association module includes a feature event extraction unit and an association analysis unit;

[0042] The feature event extraction unit is used to compare the differences in water quality data of different monitoring records in any monitoring area and extract several feature events; the correlation analysis unit is used to obtain the correlation value of any feature event based on the differences in water quality assessment between different monitoring records.

[0043] Furthermore, the pollution diffusion prediction module includes a pollution source identification unit and a regional diffusion prediction unit;

[0044] The pollution source identification unit is used to identify pollution in each monitoring area within any unit period and to identify the pollution sources that cause pollution based on the pollution status of each monitoring area. The regional diffusion prediction unit is used to analyze the pollution status of pollution sources in each monitoring area and to predict the water quality status of any monitoring area.

[0045] Furthermore, the real-time pollution identification module includes a pollution area identification unit and an abnormal area alert unit;

[0046] The pollution area identification unit is used to analyze the pollution status of each monitoring area in real time and obtain the predicted assessment value of each monitoring area; the abnormal area alert unit is used to collect water quality data in real time for each monitoring area, obtain the real-time water quality assessment value of each monitoring area, and identify abnormalities in each monitoring area.

[0047] Compared with the prior art, the beneficial effects of the present invention are:

[0048] 1. This invention implements comprehensive monitoring of the target and automatically monitors the water quality in each monitoring area; by analyzing the differences in water quality between different areas, it identifies various characteristic events that affect water quality anomalies, and can automatically identify characteristic events through the monitored water quality data, thereby making timely judgments on pollution and improving the efficiency of water pollution treatment.

[0049] 2. This invention can promptly capture the source of pollution when multiple monitoring areas are simultaneously polluted, helping staff to solve pollution problems at their source, improving processing efficiency, and enabling them to make the most correct decisions in the first instance, thus saving resources to the greatest extent.

[0050] 3. This invention analyzes the pollution diffusion from the pollution source to other areas and predicts the pollution situation in other areas. By comparing deviations through real-time monitoring data, it can identify abnormal pollution and determine whether the pollution in each area is caused by equipment malfunction or prediction error, thereby taking the correct strategy to solve the problem and effectively improving processing efficiency. Attached Figure Description

[0051] Figure 1 This is a schematic diagram illustrating the steps of an intelligent monitoring method for water management platforms based on digital information.

[0052] Figure 2 This is a schematic diagram of the structure of an intelligent monitoring system for water affairs platforms based on digital information. Detailed Implementation

[0053] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0054] Example: Figures 1 to 2 As shown, this invention provides an intelligent monitoring method for water management platforms based on digital information. The monitoring method includes the following steps:

[0055] Step S100: Divide the target area into monitoring zones according to the pre-installed monitoring equipment, collect water quality data of each monitoring zone periodically to obtain several monitoring records for each monitoring zone; conduct multi-dimensional evaluation of the water quality data presented in any monitoring record to obtain the water quality evaluation value of any monitoring zone;

[0056] Step S100 includes the following steps:

[0057] Step S101: Several sets of monitoring equipment are installed in the target area according to a preset distribution plan. Each set of monitoring equipment contains several different types of monitoring equipment, and the monitoring range of each set of monitoring equipment is the same. The monitoring range of each set of monitoring equipment in the target area is obtained, and the area corresponding to each monitoring range is set as a monitoring area in the target area.

[0058] Step S102: The water quality data of the monitoring area is continuously collected by the monitoring equipment group. The water quality data collected by any monitoring equipment group is summarized every unit cycle to obtain the water quality data set of each monitoring area in the unit cycle, and the corresponding monitoring record is generated.

[0059] Step S103: Randomly select monitoring records of a monitoring area, divide the water quality data set of the selected monitoring records into several dimensions of water quality datasets according to the type of monitoring equipment, with one monitoring equipment corresponding to one dimension of water quality dataset; preset corresponding evaluation rules for each dimension of water quality dataset to obtain the evaluation value of each dimension; calculate the average value of all dimension evaluation values ​​to obtain the water quality evaluation value of the monitoring area in the selected monitoring records.

[0060] Step S200: Compare the differences in water quality data from different monitoring records in any monitoring area and extract several feature events; based on the differences in water quality assessment between different monitoring records, obtain the correlation value of any feature event;

[0061] Step S200 includes the following steps:

[0062] Step S201: Arbitrarily select a monitoring area, and arbitrarily extract two monitoring records from the selected monitoring area to obtain the water quality datasets of the two monitoring records in any dimension; let D1 be the water quality dataset of the two monitoring records in the a-th dimension. a and D2 a Obtain water quality dataset D1 respectively a Water quality data d1 at time point t a (t) and water quality dataset D2 a Water quality data at time point t, d2 a(t), to obtain the data difference Δd of the a-th dimension at time point t. a (t)=d1 a (t)-d2 a (t);

[0063] Step S202: Preset a data difference threshold Δt th If Δd a (t)>Δt th Then, time point t is set as an abnormal time point; the number of abnormal time points contained in the a-th dimension within a unit period is counted as N. t Let N be the number of time points in a unit period, and then obtain the anomaly frequency f of the a-th dimension. a =N t / N; Preset an abnormal frequency threshold f th If f a >f th Then the a-th dimension is set as a differential feature;

[0064] Step S203: First, establish a feature event database. The feature event database contains several feature events and corresponding feature sets. Each feature time corresponds to a feature set, and each feature in the feature set is assigned a numerical range. Second, obtain the difference features between two monitoring records. Third, arbitrarily select a feature set. If each feature in the feature set has a difference feature that is the same as it, then compare the numerical range of any feature in the feature set with the water quality data range of the difference feature. If the water quality data range is within the numerical range of the feature, then set the feature event corresponding to the feature set as a feature event between the two monitoring records.

[0065] Step S204: Randomly select a feature event between two monitoring records, randomly extract a difference feature from the selected feature event, take the average value of the data difference at any time point under the corresponding dimension of the difference feature to obtain the average difference value, and sum the average differences under all dimensions to obtain the average difference value of the difference feature.

[0066] Step S205: Obtain the average difference of each differential feature in the feature event, and sum them to obtain the average difference of the feature events; set the average difference of the b-th feature event as (Δd ave ) b According to the formula:

[0067] ;

[0068] Where b is a positive integer and b∈(1,e), and e is the total number of differential features included; the correlation coefficient γ of the b-th feature event is calculated. b ;

[0069] Step S206: Obtain the water quality assessment values ​​P1 and P2 from the two monitoring records respectively, and obtain the water quality assessment difference ΔP = P1 - P2 between the two monitoring records. Calculate the correlation value G for the b-th feature event. b =ΔP×γ b The average value PG of the b-th characteristic event is obtained by averaging the correlation values ​​between any two monitoring records. b ;

[0070] Example 1: Set up two characteristic events between two monitoring records, with average differences of 0.4 and 0.6 respectively. Therefore, the correlation coefficients of the two characteristic events are 0.4 and 0.6 respectively. The water quality assessment difference between the two monitoring records is 10, and the correlation values ​​of the two characteristic events are 10×0.4=4 and 10×0.6=6 respectively.

[0071] Step S300: Identify pollution in each monitoring area within any unit period; identify pollution sources based on the pollution status of each monitoring area; analyze the pollution status of pollution sources in each monitoring area; and predict the water quality of any monitoring area.

[0072] Step S300 includes the following steps:

[0073] Step S301: Obtain the record generation time of each monitoring record; arbitrarily select a record generation time to obtain the time difference between each monitoring record; extract the target monitoring record with the smallest time difference from each monitoring area; preset a pollution assessment value P. th Let P be the water quality assessment value presented by the target monitoring record for the i-th monitoring area. i If P i <P th If so, then the i-th monitoring area will be set as the polluted area;

[0074] Step S302: Obtain target monitoring records for each polluted area to obtain a target monitoring record set. Assume that the i-th and j-th monitoring areas are both polluted areas and adjacent to each other. Obtain the feature events contained in the two polluted areas and compare them to obtain the difference feature events between the two polluted areas. Set the average evaluation value of the k-th difference feature event in the i-th monitoring area to PG. (i,k) According to the formula: Where m is the number of differential characteristic events in the i-th monitoring area; the expected evaluation value P of the i-th monitoring area is calculated. ’ i ;

[0075] Example 2: Assume that there are two differential characteristic events in the i-th monitoring area with average evaluation values ​​of 4 and 6 respectively. Set the water quality evaluation value of the i-th monitoring area to 50. The expected evaluation value is 50 + 4 + 6 = 50, which is the water quality evaluation value of the i-th monitoring area after excluding the differential characteristic events. Similarly, the expected evaluation value of the j-th monitoring area after excluding the differential characteristic events is 55. When both monitoring areas are under the influence of the same event, 50 < 55. Therefore, the pollution severity of the j-th monitoring area is higher than that of the i-th monitoring area, so the i-th monitoring area cannot be the source of pollution.

[0076] Step S303: Obtain the expected evaluation value P for the j-th monitoring area. ’ j If P ’ i >P ’ j If the target pollution source is set as the i-th monitoring area, the target pollution source will continue to be compared with the expected evaluation value of other adjacent pollution areas until the target pollution source and the adjacent pollution areas are all compared. Then the pollution area where the target pollution source is located will be set as a pollution source of the target area.

[0077] Step S304: Set the pollution source in the target area as the i-th monitoring area. Randomly select a monitoring area adjacent to the i-th monitoring area from the remaining monitoring areas. Acquire the difference characteristic events of the selected monitoring area compared with the i-th monitoring area, extract the average evaluation value of any difference characteristic event, and obtain the expected evaluation value P of the selected monitoring area. ’ The water quality assessment value of the selected monitoring area was obtained as P. ac The actual assessment difference ΔP of the selected monitoring area is obtained. ac =P ac -P ’ ;

[0078] Step S305: After calculating the expected evaluation value for any monitoring area and its adjacent monitoring areas, the actual evaluation difference for any monitoring area is obtained. The average of the actual evaluation differences is then taken to obtain an average difference (ΔP). ac ) ave ; Select any monitoring area from the remaining monitoring areas and set it as the test area, and count the minimum number of connected regions between the i-th monitoring area and the test area as Z;

[0079] Step S306: Obtain the monitoring regions involved in the minimum number of connected regions Z. Starting from the i-th monitoring region, calculate the expected evaluation value of the adjacent monitoring regions, and continue to calculate the expected evaluation value of the monitoring regions adjacent to the adjacent monitoring regions until the expected evaluation value P of the test region is obtained.’ test Finally, the predicted evaluation value of the test area is (P). ex ) test =P ’ test +Z×(ΔP ac ) ave +U, where U is a constant coefficient; obtain the water quality assessment value of the test area as P. test The constant coefficients U=P are obtained. test -(P ex ) test ;

[0080] Step S307: Obtain the expected evaluation value of any other monitoring area relative to the i-th monitoring area, and obtain the expected evaluation value of the other arbitrary monitoring area; extract the water quality evaluation value of the other arbitrary monitoring area. If the difference between the obtained expected evaluation value and the water quality evaluation value exceeds the preset evaluation difference threshold, the constant coefficient U is continuously corrected until the difference between the expected evaluation value and the water quality evaluation value in any monitoring area is less than or equal to the preset evaluation difference threshold.

[0081] Step S400: Analyze the pollution situation of each monitoring area in real time to obtain the predicted assessment value of each monitoring area; collect water quality data in real time for each monitoring area to obtain the real-time water quality assessment value of each monitoring area; and identify anomalies in each monitoring area.

[0082] Step S400 includes the following steps:

[0083] Step S401: Obtain the real-time monitoring records generated in each monitoring area to obtain the real-time water quality assessment value P for each monitoring area. now The pollution assessment value is set at P. th When there are several monitoring areas that meet P now >P th Then, the pollution sources in the target area are identified, and anomaly alerts are sent to the monitoring areas where the pollution sources are located;

[0084] Step S402: When only one monitoring area satisfies P now >P th When this happens, the predicted evaluation value (P) for any of the remaining monitoring areas is obtained. ex ) now ; Set the evaluation difference threshold as σ, if |(P ex ) now -P now If |≥σ, then an anomaly alert will be sent to the remaining monitoring areas.

[0085] The intelligent monitoring system for water affairs platforms includes a regional water quality analysis module, a characteristic event correlation module, a pollution diffusion prediction module, and a real-time pollution identification module.

[0086] The regional water quality analysis module is used to divide the target area into monitoring zones based on pre-installed monitoring equipment, periodically collect water quality data for each monitoring zone, and obtain several monitoring records for each monitoring zone; it also performs multi-dimensional evaluation on the water quality data presented in any monitoring record to obtain the water quality assessment value for any monitoring zone.

[0087] The feature event association module is used to compare the differences in water quality data of different monitoring records in any monitoring area and extract several feature events; based on the differences in water quality assessment between different monitoring records, the association value of any feature event is obtained;

[0088] The pollution diffusion prediction module is used to identify pollution in each monitoring area within any unit period, identify pollution sources based on the pollution status of each monitoring area, analyze the pollution status of pollution sources in each monitoring area, and predict the water quality status of any monitoring area.

[0089] The real-time pollution identification module is used to analyze the pollution status of each monitoring area in real time and obtain the predicted assessment value of each monitoring area; to collect water quality data in real time for each monitoring area and obtain the real-time water quality assessment value of each monitoring area; and to identify anomalies in each monitoring area.

[0090] The regional water quality analysis module includes a water quality data acquisition unit and a regional water quality assessment unit.

[0091] The water quality data acquisition unit is used to divide the target area into monitoring areas based on the pre-installed monitoring equipment, and to collect water quality data of each monitoring area on a regular basis, thereby obtaining several monitoring records for each monitoring area; the regional water quality assessment unit is used to conduct multi-dimensional assessments of the water quality data presented in any monitoring record, thereby obtaining the water quality assessment value of any monitoring area.

[0092] The feature event association module includes a feature event extraction unit and an association analysis unit.

[0093] The feature event extraction unit is used to compare the differences in water quality data of different monitoring records in any monitoring area and extract several feature events; the correlation analysis unit is used to obtain the correlation value of any feature event based on the differences in water quality assessment between different monitoring records.

[0094] The pollution diffusion prediction module includes a pollution source identification unit and a regional diffusion prediction unit.

[0095] The pollution source identification unit is used to identify pollution in each monitoring area within any unit period and to identify the pollution sources that cause pollution based on the pollution status of each monitoring area. The regional diffusion prediction unit is used to analyze the pollution status of pollution sources in each monitoring area and to predict the water quality status of any monitoring area.

[0096] The real-time pollution identification module includes a pollution area identification unit and an abnormal area alert unit.

[0097] The pollution area identification unit is used to analyze the pollution status of each monitoring area in real time and obtain the predicted assessment value of each monitoring area; the abnormal area alert unit is used to collect water quality data in real time for each monitoring area, obtain the real-time water quality assessment value of each monitoring area, and identify abnormalities in each monitoring area.

[0098] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A method for intelligent supervision of water management platforms based on digital information, characterized in that: The regulatory approach includes the following steps: Step S100: Divide the target area into monitoring zones according to the pre-installed monitoring equipment, collect water quality data of each monitoring zone periodically to obtain several monitoring records for each monitoring zone; conduct multi-dimensional evaluation of the water quality data presented in any monitoring record to obtain the water quality evaluation value of any monitoring zone; Step S200: Compare the differences in water quality data from different monitoring records in any monitoring area and extract several feature events; based on the differences in water quality assessment between different monitoring records, obtain the correlation value of any feature event; Step S200 includes the following steps: Step S201: Arbitrarily select a monitoring area, and arbitrarily extract two monitoring records from the selected monitoring area to obtain the water quality datasets of the two monitoring records in any dimension; let D1 be the water quality dataset of the two monitoring records in the a-th dimension. a and D2 a Obtain water quality dataset D1 respectively a Water quality data d1 at time point t a (t) and water quality dataset D2 a Water quality data at time point t, d2 a (t), to obtain the data difference Δd of the a-th dimension at time point t. a (t)=d1 a (t)-d2 a (t); Step S202: Preset a data difference threshold Δt th If Δd a (t)>Δt th Then, time point t is set as an abnormal time point; the number of abnormal time points contained in the a-th dimension within a unit period is counted as N. t Let N be the number of time points in a unit period, and then obtain the anomaly frequency f of the a-th dimension. a =N t / N; Preset an abnormal frequency threshold f th If f a >f th Then the a-th dimension is set as a differential feature; Step S203: First, establish a feature event database. The feature event database contains several feature events and corresponding feature sets. Each feature time corresponds to a feature set, and each feature in the feature set is assigned a numerical range. Second, obtain the difference features between two monitoring records. Third, arbitrarily select a feature set. If each feature in the feature set has a difference feature that is the same as it, then compare the numerical range of any feature in the feature set with the water quality data range of the difference feature. If the water quality data range is within the numerical range of the feature, then set the feature event corresponding to the feature set as a feature event between the two monitoring records. Step S204: Randomly select a feature event between two monitoring records, randomly extract a difference feature from the selected feature event, take the average value of the data difference at any time point under the corresponding dimension of the difference feature to obtain the average difference value, and sum the average differences under all dimensions to obtain the average difference value of the difference feature. Step S205: Obtain the average difference of each differential feature in the feature event, and sum them to obtain the average difference of the feature events; set the average difference of the b-th feature event as (Δd ave ) b According to the formula: ； Where b is a positive integer and b∈(1,e), and e is the total number of differential features included; the correlation coefficient γ of the b-th feature event is calculated. b ; Step S206: Obtain the water quality assessment values ​​P1 and P2 from the two monitoring records respectively, and obtain the water quality assessment difference ΔP = P1 - P2 between the two monitoring records. Calculate the correlation value G for the b-th feature event. b =ΔP×γ b The average value PG of the b-th characteristic event is obtained by averaging the correlation values ​​between any two monitoring records. b ; Step S300: Identify pollution in each monitoring area within any unit period; identify pollution sources based on the pollution status of each monitoring area; analyze the pollution status of pollution sources in each monitoring area; and predict the water quality of any monitoring area. Step S400: Analyze the pollution situation in each monitoring area in real time to obtain the predicted assessment value of each monitoring area; collect water quality data in real time for each monitoring area to obtain the real-time water quality assessment value of each monitoring area; and identify anomalies in each monitoring area.

2. The intelligent monitoring method for water affairs platforms based on digital information according to claim 1, characterized in that: Step S100 includes the following steps: Step S101: Several sets of monitoring equipment are installed in the target area according to a preset distribution plan. Each set of monitoring equipment contains several different types of monitoring equipment, and the monitoring range of each set of monitoring equipment is the same. The monitoring range of each set of monitoring equipment in the target area is obtained, and the area corresponding to each monitoring range is set as a monitoring area in the target area. Step S102: The water quality data of the monitoring area is continuously collected by the monitoring equipment group. The water quality data collected by any monitoring equipment group is summarized every unit cycle to obtain the water quality data set of each monitoring area in the unit cycle, and the corresponding monitoring record is generated. Step S103: Randomly select monitoring records of a monitoring area, divide the water quality data set of the selected monitoring records into several dimensions of water quality datasets according to the type of monitoring equipment, with one monitoring equipment corresponding to one dimension of water quality dataset; preset corresponding evaluation rules for each dimension of water quality dataset to obtain the evaluation value of each dimension; calculate the average value of all dimension evaluation values ​​to obtain the water quality evaluation value of the monitoring area in the selected monitoring records.

3. The intelligent monitoring method for water affairs platforms based on digital information according to claim 1, characterized in that: Step S300 includes the following steps: Step S301: Obtain the record generation time of each monitoring record; arbitrarily select a record generation time to obtain the time difference between each monitoring record; extract the target monitoring record with the smallest time difference from each monitoring area; preset a pollution assessment value P. th Let P be the water quality assessment value presented by the target monitoring record for the i-th monitoring area. i If P i <P th If , then the i-th monitoring area is set as the polluted area; Step S302: Obtain target monitoring records for each polluted area to obtain a target monitoring record set. Assume that the i-th and j-th monitoring areas are both polluted areas and adjacent to each other. Obtain the feature events contained in the two polluted areas and compare them to obtain the difference feature events between the two polluted areas. Set the average evaluation value of the k-th difference feature event in the i-th monitoring area to PG. (i,k) According to the formula: Where m is the number of differential characteristic events in the i-th monitoring area; the expected evaluation value P of the i-th monitoring area is calculated. ’ i ; Step S303: Obtain the expected evaluation value P for the j-th monitoring area. ’ j If P ’ i >P ’ j If the target pollution source is set as the i-th monitoring area, the target pollution source will continue to be compared with the expected evaluation value of other adjacent pollution areas until the target pollution source and the adjacent pollution areas are all compared. Then the pollution area where the target pollution source is located will be set as a pollution source of the target area. Step S304: Set the pollution source in the target area as the i-th monitoring area. Randomly select a monitoring area adjacent to the i-th monitoring area from the remaining monitoring areas. Acquire the difference characteristic events of the selected monitoring area compared with the i-th monitoring area, extract the average evaluation value of any difference characteristic event, and obtain the expected evaluation value P of the selected monitoring area. ’ The water quality assessment value of the selected monitoring area was obtained as P. ac The actual assessment difference ΔP of the selected monitoring area is obtained. ac =P ac -P ’ ; Step S305: After calculating the expected evaluation value for any monitoring area and its adjacent monitoring areas, the actual evaluation difference for any monitoring area is obtained. The average of the actual evaluation differences is then taken to obtain an average difference (ΔP). ac ) ave ; Select any monitoring area from the remaining monitoring areas and set it as the test area, and count the minimum number of connected regions between the i-th monitoring area and the test area as Z; Step S306: Obtain the monitoring regions involved in the minimum number of connected regions Z. Starting from the i-th monitoring region, calculate the expected evaluation value of the adjacent monitoring regions, and continue to calculate the expected evaluation value of the monitoring regions adjacent to the adjacent monitoring regions until the expected evaluation value P of the test region is obtained. ’ test Finally, the predicted evaluation value of the test area is (P). ex ) test =P ’ test +Z×(ΔP ac ) ave +U, where U is a constant coefficient; obtain the water quality assessment value of the test area as P. test The constant coefficients U=P are obtained. test -(P ex ) test ; Step S307: Obtain the expected evaluation value of any other monitoring area relative to the i-th monitoring area, and obtain the expected evaluation value of the other arbitrary monitoring area; extract the water quality evaluation value of the other arbitrary monitoring area. If the difference between the obtained expected evaluation value and the water quality evaluation value exceeds the preset evaluation difference threshold, the constant coefficient U is continuously corrected until the difference between the expected evaluation value and the water quality evaluation value in any monitoring area is less than or equal to the preset evaluation difference threshold.

4. The intelligent monitoring method for water affairs platforms based on digital information according to claim 3, characterized in that: Step S400 includes the following steps: Step S401: Obtain the real-time monitoring records generated in each monitoring area to obtain the real-time water quality assessment value P for each monitoring area. now The pollution assessment value is set at P. th When there are several monitoring areas that meet P now >P th Then, the pollution sources in the target area are identified, and anomaly alerts are sent to the monitoring areas where the pollution sources are located; Step S402: When only one monitoring area satisfies P now >P th When this happens, the predicted evaluation value (P) for any of the remaining monitoring areas is obtained. ex ) now ; Set the evaluation difference threshold as σ, if |(P ex ) now -P now If |≥σ, then an anomaly alert will be sent to the remaining monitoring areas.

5. A water affairs platform intelligent monitoring system, used to execute the water affairs platform intelligent monitoring method based on digital information as described in any one of claims 1-4, characterized in that: The monitoring system includes a regional water quality analysis module, a characteristic event correlation module, a pollution diffusion prediction module, and a real-time pollution identification module; The regional water quality analysis module is used to divide the target area into monitoring areas according to the pre-installed monitoring equipment, collect water quality data of each monitoring area periodically, and obtain several monitoring records for each monitoring area; and to perform multi-dimensional evaluation on the water quality data presented in any monitoring record to obtain the water quality evaluation value of any monitoring area. The feature event association module is used to compare the differences in water quality data of different monitoring records in any monitoring area and extract several feature events; based on the differences in water quality assessment between different monitoring records, the association value of any feature event is obtained. The pollution diffusion prediction module is used to identify pollution in each monitoring area within any unit period, identify pollution sources based on the pollution status of each monitoring area, analyze the pollution status of pollution sources in each monitoring area, and predict the water quality status of any monitoring area. The real-time pollution identification module is used to analyze the pollution situation of each monitoring area in real time, obtain the predicted assessment value of each monitoring area, collect water quality data in real time for each monitoring area, obtain the real-time water quality assessment value of each monitoring area, and identify anomalies in each monitoring area.

6. The intelligent monitoring system for water affairs platforms according to claim 5, characterized in that: The regional water quality analysis module includes a water quality data acquisition unit and a regional water quality assessment unit. The water quality data acquisition unit is used to divide the target area into monitoring areas according to the pre-installed monitoring equipment, and to collect water quality data of each monitoring area periodically to obtain several monitoring records for each monitoring area; the regional water quality assessment unit is used to conduct multi-dimensional assessment of the water quality data presented by any monitoring record to obtain the water quality assessment value of any monitoring area.

7. The intelligent monitoring system for water affairs platforms according to claim 5, characterized in that: The feature event association module includes a feature event extraction unit and an association analysis unit; The feature event extraction unit is used to compare the differences in water quality data of different monitoring records in any monitoring area and extract several feature events. The correlation analysis unit is used to obtain the correlation value of any feature event based on the differences in water quality assessment between different monitoring records.

8. The intelligent monitoring system for water affairs platforms according to claim 5, characterized in that: The pollution diffusion prediction module includes a pollution source identification unit and a regional diffusion prediction unit. The pollution source identification unit is used to identify pollution in each monitoring area within any unit period, and to identify the pollution source that causes pollution based on the pollution status of each monitoring area; the regional diffusion prediction unit is used to analyze the pollution status of the pollution source in each monitoring area and to predict the water quality status of any monitoring area.

9. The intelligent monitoring system for water affairs platforms according to claim 5, characterized in that: The real-time pollution identification module includes a pollution area identification unit and an abnormal area alert unit; The pollution area identification unit is used to analyze the pollution status of each monitoring area in real time and obtain the predicted assessment value of each monitoring area; the abnormal area alert unit is used to collect water quality data in real time for each monitoring area, obtain the real-time water quality assessment value of each monitoring area, and identify abnormalities in each monitoring area.

Images