Water pollution composite treatment method and system based on real-time monitoring of water quality pollution

Abstract

The present application belongs to the technical field of water pollution composite treatment, and discloses a water pollution composite treatment method and system based on real-time monitoring of water quality pollution; the system comprises a pollution responsibility tracing and identifying module, a multi-scenario risk early warning simulation module, an intelligent comprehensive treatment strategy generating module, an instruction processing and output module and a treatment effect evaluation and optimization module, obtains a pollution source analysis report, performs risk prediction based on a water quality space-time matrix, performs simulation prediction based on future meteorological data obtained by a sensor network, obtains an active early warning report, processes the active early warning report, obtains a comprehensive treatment strategy report, processes the comprehensive treatment strategy report, obtains a device control instruction set, and outputs the device control instruction set to generate a treatment optimization report; in general, the present application has the remarkable advantages of high reliability of treatment decision basis data, good active effect of pollution early warning and large synergistic effect of treatment means.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of water pollution composite treatment, more specifically, the present application relates to a water pollution composite treatment method and system based on real-time monitoring of water pollution. BACKGROUND

[0002] The water pollution composite treatment system refers to a comprehensive system integrating physical, chemical, biological and other treatment technologies, relying on real-time monitoring data to collaboratively treat water environmental problems. The core concept is to break the limitations of single technology and achieve more efficient and complete water quality purification and ecological restoration through multi-faceted collaboration.

[0003] However, the traditional water pollution composite treatment system has the following shortcomings in use. First, although the traditional system can collect a large amount of real-time monitoring data, these monitoring data are often scattered and isolated, making it difficult for workers to intuitively obtain the migration and diffusion path of pollutants and the transformation rule based on these monitoring data, and even more difficult to predict future water quality changes, resulting in the need for artificial experience for treatment decisions, and the lack of stability and reliability of treatment decisions. Second, the warning mechanism of the traditional system mostly adopts a single threshold exceeding judgment method, and when the alarm is triggered, pollution has often been formed, resulting in long-term passive conditions for treatment measures. At the same time, due to the lack of precise tracing ability, the system also has difficulty in determining the pollution source in complex water environments, resulting in inefficiency of treatment measures. Third, the treatment units of the traditional system are mostly independent and manually controlled, lacking a holistic collaborative control strategy, which makes it difficult for workers to quickly develop optimal treatment measures. In addition, after the implementation of the treatment measures, the system cannot judge the effectiveness of the treatment measures and whether adjustment is needed, resulting in low stability of treatment effect. Overall, how to effectively solve the problems of poor reliability of treatment decision basis, passive pollution warning ability and low collaborative effect of treatment means in the traditional system has become a problem that the current water pollution composite treatment system needs to face and solve.

[0004] In view of this, the present application proposes a water pollution composite treatment method and system based on real-time monitoring of water pollution to solve the above problems. SUMMARY

[0005] In order to overcome the above-mentioned defects of the prior art, in order to achieve the above-mentioned purpose, the present application provides the following technical scheme, comprising:

[0006] A multi-source data fusion processing module is used to collect raw data in real time based on a sensor network and to preprocess the raw data to obtain a raw processed data set;

[0007] Further, the step of collecting raw data in real time based on the sensor network and preprocessing includes:

[0008] S1.1: Based on the preset collection time window, raw data set is obtained by collecting raw data in real time according to the sensor network, the sensor network includes water quality sensors, hydrological sensors, weather release platforms and pollution source sensors, and the raw data includes:

[0009] sensor ID, three-dimensional coordinates of collection site, collection timestamp and measurement value collected by the water quality sensor;

[0010] hydrological station ID, collection timestamp, flow rate data, flow data and water level data collected by the hydrological sensor;

[0011] weather area ID, collection timestamp, weather forecast period, rainfall, wind speed and wind direction collected by the weather release platform;

[0012] pollution outlet ID, collection timestamp, three-dimensional coordinates of collection site, pollution type and allowable discharge collected by the pollution source sensor;

[0013] S1.2: The validity check processing is performed on the raw data set to obtain the raw check data set, and the validity check refers to eliminating data items exceeding the physical range;

[0014] S1.3: Based on the unified system clock and the fixed time length, all data items in the raw check data set are aligned in the same time period to obtain the raw alignment data set, and when there is no data item at the time point in the same time period, the linear interpolation method is used to fill in;

[0015] S1.4: Based on the database, the monitoring section and the pollution source association rule table are retrieved, and the data items in the raw alignment data set are fused to obtain the raw processing data set;

[0016] S1.5: The raw processing data set is output to the water quality digital twin prediction module;

[0017] The water quality digital twin prediction module is used for updating the water body simulation model based on the raw processing data set, and predicting water pollution based on the updated water body simulation model to obtain a water quality space-time matrix.

[0018] Further, the step of updating the water body simulation model based on the raw processing data set and predicting water pollution based on the updated water body simulation model includes:

[0019] S2.1: based on the database, call the preset water body simulation model, input the original processed data set into the water body simulation model, and adjust all state variables of the water body simulation model by using the data assimilation algorithm to obtain an updated water body simulation model;

[0020] S2.2: taking the current state of the updated water body simulation model as the initial condition, and predicting the future time period according to the control equation to obtain a water quality space-time matrix, and the specific expression of the control equation is: ;

[0021] Wherein, is the concentration of a certain pollutant in the water body, is a time point, is the velocity vector field of the water flow, is the gradient operator, is the diffusion coefficient of the pollutant, is the external source and sink term, is the chemical reaction term;

[0022] S2.3: output the water quality space-time matrix to the pollution responsibility tracing identification module and the multi-scenario risk early warning simulation module;

[0023] The pollution responsibility tracing identification module is used for triggering an abnormal event based on the original processed data set, and performing reverse tracing based on the water quality space-time matrix and the water body simulation model to obtain a pollution source analysis report;

[0024] Further, the step of triggering an abnormal event based on the original processed data set and performing reverse tracing based on the water quality space-time matrix and the water body simulation model comprises:

[0025] S3.1: real-time monitoring is performed on all data items in the original processed data set, and when at least one data item exceeds a corresponding preset threshold, an abnormal data report is generated, and step S3.2 is entered;

[0026] S3.2: calling the updated water body simulation model in step S2.1, taking the abnormal data item in the abnormal data report as the end condition, and performing reverse tracing along the time stamp in the updated water body simulation model to obtain a pollution source analysis report;

[0027] The pollution source analysis report includes a description of the abnormal data item, the most likely pollution source ID and the responsibility probability;

[0028] S3.3: outputting the pollution source analysis report to a staff receiving end;

[0029] The multi-scenario risk early warning simulation module is used for risk prediction based on the water quality space-time matrix, and simulation prediction based on future meteorological data obtained by the sensor network to obtain a proactive warning report;

[0030] Further, the step of risk prediction based on the water quality spatiotemporal matrix and simulation prediction based on future meteorological data obtained by the sensor network comprises:

[0031] S4.1: risk prediction based on the water quality spatiotemporal matrix based on a preset reading time, obtaining a risk prediction report, the risk prediction comprising traversing all spatiotemporal units in the water quality spatiotemporal matrix and comparing the predicted pollutant concentration with the corresponding early warning threshold;

[0032] The risk prediction report comprises a prediction occurrence timestamp, a three-dimensional coordinate of the collection site, a predicted pollutant concentration, and a risk level;

[0033] S4.2: obtaining future meteorological type data based on a meteorological publishing platform in the sensor network, obtaining a future meteorological data set;

[0034] Based on the updated water body simulation model, a multi-target simulation scenario is created, and the multi-target simulation scenario is run based on the updated water body simulation model, obtaining a simulated water quality spatiotemporal matrix set;

[0035] S4.3: generating an active early warning report based on the risk prediction report and the simulated water quality spatiotemporal matrix set;

[0036] The active early warning report comprises an early warning ID, an early warning level, an impact range area, a risk data value, a risk start time, a risk peak time, a risk end time, and a recommended use strategy ID;

[0037] S4.4: outputting the active early warning report to the comprehensive management strategy intelligent generation module;

[0038] The comprehensive management strategy intelligent generation module is used for processing based on the active early warning report, obtaining a comprehensive management strategy report;

[0039] Further, the step of processing based on the active early warning report comprises:

[0040] S5.1: based on the database, calling a management strategy rule library and searching based on the active early warning report, obtaining a standard management template;

[0041] S5.2: adjusting the standard management template based on the detailed parameters in the active early warning report, obtaining a comprehensive management strategy report, the detailed parameters comprising a risk start time, a risk peak time, and a risk end time;

[0042] S5.3: outputting the comprehensive management strategy report to the instruction processing output module;

[0043] The instruction processing output module is used for processing the comprehensive management strategy report, obtaining a device control instruction set, and outputting;

[0044] Further, the step of processing the comprehensive management strategy report to obtain a device control instruction set and outputting the device control instruction set comprises:

[0045] S6.1: decompose the strategy based on the comprehensive management strategy report, and convert the decomposed strategy into execution instructions to obtain a strategy execution instruction set;

[0046] S6.2: perform execution sequence dependency checking on all execution instructions in the strategy execution instruction set, and when there is at least one execution sequence dependency between the execution instructions, perform execution sequence adjustment on the execution instructions in the strategy execution instruction set to obtain a device control instruction set;

[0047] S6.3: output the device notification instruction set to the corresponding intelligent controller;

[0048] The management effect evaluation optimization module is used to comprehensively evaluate the water quality after management, and generate a management optimization report according to the evaluation result;

[0049] Further, the step of comprehensively evaluating the water quality after management and generating a management optimization report according to the evaluation result comprises:

[0050] S7.1: continuously obtain the original processing data set in step S1.4 to obtain a real-time original data set, associate the execution-end comprehensive management strategy report with the real-time original data set according to the early warning ID, and enter step S7.2;

[0051] S7.2: based on the water quality improvement evaluation window, calculate the pollutant removal rate and the improvement rate respectively to obtain removal evaluation values and improvement evaluation values, and the specific formula group for calculation is: ;

[0052] respectively obtain removal evaluation values and improvement evaluation values , wherein, is the average concentration of the target pollutant in the target area before execution of the device control instruction set, is the average concentration of the target pollutant in the target area after execution of the device control instruction set, is the management duration;

[0053] S7.3: compare the removal evaluation values and the improvement evaluation values with the expected target respectively to generate a management optimization report;

[0054] The management optimization report includes the strategy execution situation and the recommended parameter adjustment;

[0055] S7.4: output the management optimization report to the comprehensive management strategy intelligent generation module for updating the management strategy rule library;

[0056] Further, S1: based on the sensor network, real-time acquisition of raw data is carried out, and preprocessing is carried out to obtain an original processing data set;

[0057] S2: based on the original processing data set, a water body simulation model is updated, and water quality pollution prediction is carried out based on the updated water body simulation model to obtain a water quality space-time matrix;

[0058] S3: based on the original processing data set, an abnormal event trigger is carried out, and reverse tracing is carried out according to the water quality space-time matrix and the water body simulation model to obtain a pollution source analysis report;

[0059] S4: based on the water quality space-time matrix, risk prediction is carried out, and simulation prediction is carried out according to future meteorological data obtained by the sensor network to obtain an active early warning report;

[0060] S5: based on the active early warning report, processing is carried out to obtain a comprehensive management strategy report;

[0061] S6: the comprehensive management strategy report is processed to obtain a device control instruction set, and output is carried out;

[0062] S7: the water quality after management is comprehensively evaluated, and a management optimization report is generated according to the evaluation result.

[0063] The water pollution composite management method and system based on real-time monitoring of water quality pollution have the following technical effects and advantages:

[0064] The application obtains an original processing data set by collecting original data in real time based on a sensor network and preprocessing, updates a water body simulation model based on the original processing data set, and obtains a water quality space-time matrix based on the water quality pollution prediction of the updated water body simulation model, triggers an abnormal event based on the original processing data set, and obtains a pollution source analysis report based on the water quality space-time matrix and the water body simulation model, performs risk prediction based on the water quality space-time matrix, and obtains an active early warning report based on simulation prediction of future meteorological data obtained by the sensor network, processes the active early warning report to obtain a comprehensive management strategy report, processes the comprehensive management strategy report to obtain a device control instruction set, and outputs, comprehensively evaluates the water quality after management, and generates a management optimization report according to the evaluation result, so that the system can provide a direct, real-time and reliable "virtual regional entity" through the collaborative work of the multi-source data fusion processing module and the water quality digital twin prediction module, thereby effectively solving the pain points of the traditional system that need to rely on artificial experience for management decision-making, providing solid and reliable data support for management decision-making, in addition, through the establishment of the pollution responsibility traceability identification module and the multi-scenario risk early warning simulation module, the system can provide workers with important data such as the specific location, intensity and duration of pollution before pollution occurs, and convert the passive management of the traditional system into active intervention, thereby maximizing the management response capability, finally, through the collaborative work of the comprehensive management strategy intelligent generation module, the instruction processing output module and the management effect evaluation optimization module, an automatic closed loop from prediction to plan to execution to evaluation to optimization is constructed for the system, thereby realizing the efficiency maximization and the whole life cycle operation cost optimization of pollution management, and overall, the application has the significant advantages of high data reliability degree for management decision-making, good active effect of pollution early warning and large synergistic effect of management means. BRIEF DESCRIPTION OF DRAWINGS

[0065] Figure 1 It is a schematic diagram of the water pollution composite management system based on real-time monitoring of water pollution of the application.

[0066] Figure 2 It is a schematic diagram of the water pollution composite management method based on real-time monitoring of water pollution of the application. DETAILED DESCRIPTION

[0067] The technical solutions in the embodiments of the application will be described clearly and completely below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, not all. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of the application.

[0068] The terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting thereof. As used in the description of the application and the appended claims, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0069] The word "if" can be interpreted to mean "upon" or "when" or "in response to the determination" or "in response to the occurrence" of, depending on the context. Similarly, the phrase "if it is determined" or "if [a stated condition or event] is detected" can be interpreted to mean "upon determining" or "in response to determining" or "upon detecting [the stated condition or event]" or "in response to detecting [the stated condition or event]", depending on the context.

[0070] In addition, the sequence of steps in the following method embodiments is only an example, not a strict limitation.

[0071] In fact, the server equipment deployed by the water pollution composite treatment system based on real-time monitoring of water quality pollution can be composed of one or more devices. The water pollution composite treatment system based on real-time monitoring of water quality pollution can be implemented as a business instance, a virtual machine, or a hardware device. For example, the water pollution composite treatment system based on real-time monitoring of water quality pollution can be implemented as a business instance deployed on one or more devices in a cloud node. In short, the water pollution composite treatment system based on real-time monitoring of water quality pollution can be understood as a software deployed on a cloud node to provide the water pollution composite treatment system based on real-time monitoring of water quality pollution for each user end. Alternatively, the water pollution composite treatment system based on real-time monitoring of water quality pollution can also be implemented as a virtual machine deployed on one or more devices in a cloud node. The virtual machine has application software installed for managing each user end. Alternatively, the water pollution composite treatment system based on real-time monitoring of water quality pollution can also be implemented as a server composed of a plurality of same or different types of hardware devices, and one or more hardware devices are provided to provide the water pollution composite treatment system based on real-time monitoring of water quality pollution for each user end.

[0072] In terms of implementation, the water pollution composite treatment system based on real-time monitoring of water quality pollution and the user end adapt to each other. That is, the water pollution composite treatment system based on real-time monitoring of water quality pollution is an application installed on a cloud service platform, and the user end is a client that establishes a communication connection with the application; or the water pollution composite treatment system based on real-time monitoring of water quality pollution is implemented as a website, and the user end is implemented as a webpage; or the water pollution composite treatment system based on real-time monitoring of water quality pollution is implemented as a cloud service platform, and the user end is implemented as an applet in an instant messaging application.

[0073] AsFigure 1 Fig. 1 shows a system architecture diagram of a water pollution composite treatment system based on real-time water pollution monitoring according to an embodiment of the present application.

[0074] The water pollution composite treatment system based on real-time water pollution monitoring according to the present application can be set in a cloud server, and in terms of implementation, can be used as one or more service devices, or can be installed as an application on a cloud (such as a server or server cluster of a mobile service operator), or can be developed as a website. According to the functions implemented, the water pollution composite treatment system based on real-time water pollution monitoring can include a multi-source data fusion processing module, a water quality digital twin prediction module, a pollution responsibility traceability identification module, a multi-scenario risk early warning simulation module, an integrated treatment strategy intelligent generation module, an instruction processing output module, and a treatment effect evaluation optimization module. The modules according to the present application can also be referred to as units, which refer to a series of computer program segments that can be executed by an electronic device processor and can complete a fixed function, and are stored in the memory of the electronic device.

[0075] In the embodiment of the present application, each of the above modules in the water pollution composite treatment system based on real-time water pollution monitoring can be independently implemented and called by other modules. Here, calling can be understood as connecting a module to multiple modules of another type and providing corresponding services to the connected multiple modules. For example, the instruction processing output module can call the same information collection module to obtain the information collected by the information collection module. Based on the above characteristics, the water pollution composite treatment system based on real-time water pollution monitoring provided in the embodiment of the present application can adjust the application scope of the water pollution composite treatment system based on real-time water pollution monitoring architecture by adding modules and directly calling without modifying program codes, realize cluster-level expansion, and thus achieve the purpose of quickly and flexibly expanding the water pollution composite treatment system based on real-time water pollution monitoring. In practical applications, the above modules can be set in the same device or different devices, or can be set in a virtual device, such as a service instance in a cloud server. Embodiment 1

[0076] Please refer to Figure 1 Fig. 1 shows a water pollution composite treatment system based on real-time water pollution monitoring according to the present application, which includes:

[0077] The multi-source data fusion processing module is used to collect raw data based on a sensor network in real time and pre-process the raw data to obtain a raw processed data set.

[0078] Further, the step of collecting raw data based on a sensor network in real time and pre-processing the raw data includes:

[0079] S1.1: Based on a preset collection time window, and according to real-time collection of original data by a sensor network, an original data set is obtained, the sensor network includes a water quality sensor, a hydrological sensor, a weather release platform, and a pollution source sensor, and the original data includes:

[0080] It needs to be explained that the preset collection time window is manually set and input into the system, for example, the preset collection time window is 10 seconds;

[0081] The sensor ID collected by the water quality sensor, the three-dimensional coordinates of the collection site, the collection timestamp, and the measurement value;

[0082] It needs to be explained that the measurement value includes but is not limited to pH value, chemical oxygen demand, ammonia nitrogen value, and dissolved oxygen value;

[0083] The hydrological station ID collected by the hydrological sensor, the collection timestamp, the flow rate data, the flow data, and the water level data;

[0084] The weather area ID collected by the weather release platform, the collection timestamp, the weather forecast period, the rainfall, the wind speed, and the wind direction;

[0085] The pollution source sensor collects the discharge outlet ID, the collection timestamp, the three-dimensional coordinates of the collection site, the discharge type, and the allowable discharge amount;

[0086] S1.2: The original data set is subjected to validity verification processing to obtain an original verification data set, and the validity verification refers to eliminating data items that exceed the physical range;

[0087] It needs to be explained that exceeding the physical range means, for example, the data item of the pH value measurement value collected by a certain water quality sensor is 15;

[0088] S1.3: Based on a unified system clock and a fixed time length, all data items in the original verification data set are aligned within the same time period to obtain an original alignment data set, wherein when there is no data item at the time point within the same time period, a linear interpolation method is used to fill in;

[0089] It needs to be explained that the fixed time length is manually set and input into the system, for example, the fixed time length is five minutes;

[0090] S1.4: Based on a database to retrieve a monitoring section and a pollution source association rule table, the data items in the original alignment data set are fused to obtain an original processing data set;

[0091] It needs to be explained that fusion means, for example, the water quality type data of the downstream section S001 of the region, the hydrological type data of the upstream hydrological station H001, and all pollution source type data in the water body intersection region are fused into the same data set;

[0092] S1.5: output the original processed data set to the water quality digital twin prediction module;

[0093] The water quality digital twin prediction module is configured to update a water body simulation model based on the original processed data set, and predict water pollution based on the updated water body simulation model to obtain a water quality spatiotemporal matrix;

[0094] Further, the step of updating the water body simulation model based on the original processed data set and predicting water pollution based on the updated water body simulation model comprises:

[0095] S2.1: based on the database, call a preset water body simulation model, input the original processed data set into the water body simulation model, and adjust all state variables of the water body simulation model using a data assimilation algorithm to obtain an updated water body simulation model;

[0096] It should be explained that the state variables refer to, for example, chemical oxygen demand, ammonia nitrogen value and flow rate data, etc.

[0097] S2.2: take the current state of the updated water body simulation model as an initial condition, and predict a future time period according to a control equation to obtain a water quality spatiotemporal matrix, and the specific expression of the control equation is: ;

[0098] wherein, is the concentration of a certain pollutant in the water body, is a time point, is a velocity vector field of the water flow, is a gradient operator, is a pollutant diffusion coefficient, is an external source-sink term, is a chemical reaction term;

[0099] It should be explained that the velocity vector field of the water flow is provided by a water dynamic model; the pollutant diffusion coefficient refers to the ability of the pollutant to diffuse outward due to water flow turbulence; the external source-sink term refers to the input or output from external sources such as sewage outlets or tributaries; and the chemical reaction term refers to biochemical processes such as degradation and transformation of the pollutant itself, for example, degradation of chemical oxygen demand and nitrification of ammonia nitrogen, etc.

[0100] It should be explained that the water quality spatiotemporal matrix refers to the pollutant concentration distribution at each time and each location point in the future obtained by solving the control equation using the finite volume method;

[0101] S2.3: output the water quality spatiotemporal matrix to the pollution responsibility tracing and identification module and the multi-scenario risk early warning simulation module;

[0102] The pollution responsibility tracing identification module is configured to trigger an abnormal event based on the original processing data set, and perform reverse tracing based on the water quality space-time matrix and the water body simulation model to obtain a pollution source analysis report.

[0103] Further, the step of triggering an abnormal event based on the original processing data set and performing reverse tracing based on the water quality space-time matrix and the water body simulation model comprises:

[0104] S3.1: Real-time monitoring is performed on all data items in the original processing data set, and when at least one data item exceeds a corresponding preset threshold, an abnormal data report is generated, and step S3.2 is entered.

[0105] S3.2: The updated water body simulation model in step S2.1 is called, the abnormal data item in the abnormal data report is taken as an end condition, and reverse tracing is performed along the time stamp in the updated water body simulation model to obtain a pollution source analysis report.

[0106] The pollution source analysis report includes a description of the abnormal data item, the most likely pollution source ID, and the responsibility probability.

[0107] S3.3: The pollution source analysis report is output to a staff receiving end.

[0108] The multi-scenario risk early warning simulation module is configured to perform risk prediction based on the water quality space-time matrix, and perform simulation prediction based on future meteorological data obtained from the sensor network to obtain an active early warning report.

[0109] Further, the step of performing risk prediction based on the water quality space-time matrix and performing simulation prediction based on future meteorological data obtained from the sensor network comprises:

[0110] S4.1: Risk prediction is performed on the water quality space-time matrix based on a preset reading time to obtain a risk prediction report, the risk prediction comprising traversing all space-time units in the water quality space-time matrix and comparing the predicted pollutant concentration with a corresponding early warning threshold.

[0111] It should be explained that the preset reading time is manually set and input into the system, for example, the preset reading time is every hour.

[0112] The risk prediction report includes a predicted occurrence time stamp, three-dimensional coordinates of a collection location, a predicted pollutant concentration, and a risk level.

[0113] S4.2: Future meteorological data is obtained from a meteorological publishing platform in the sensor network to obtain a future meteorological data set.

[0114] Based on the updated water body simulation model, a multi-target simulation scenario is created, and the multi-target simulation scenario is run according to the updated water body simulation model to obtain a simulated water quality spatiotemporal matrix set;

[0115] It needs to be explained that the multi-target simulation scenario refers to the change of the meteorological type data in the future meteorological data set, thereby creating, for example, a simulated water quality spatiotemporal matrix based on the current time meteorological condition or a simulated water quality spatiotemporal matrix based on the simulated heavy rainfall meteorological condition;

[0116] S4.3: Based on the risk prediction report and the simulated water quality spatiotemporal matrix set, an active early warning report is generated;

[0117] The active early warning report includes a warning ID, a warning level, an impact range area, a risk data value, a risk start time, a risk peak time, a risk end time, and a recommended use strategy ID;

[0118] S4.4: The active early warning report is output to the comprehensive management strategy intelligent generation module;

[0119] The comprehensive management strategy intelligent generation module is configured to process the active early warning report to obtain a comprehensive management strategy report;

[0120] Further, the step of processing the active early warning report includes:

[0121] S5.1: Based on the database, a management strategy rule library is retrieved, and a standard management template is obtained by searching according to the active early warning report;

[0122] It needs to be explained that the rule form of the management strategy rule library is that the early warning condition corresponds to the management operation, and the early warning condition includes the warning level, the impact range area, and the recommended use strategy ID;

[0123] S5.2: Based on the detailed parameters in the active early warning report, the standard management template is adjusted to obtain a comprehensive management strategy report, and the detailed parameters include the risk start time, the risk peak time, and the risk end time;

[0124] It needs to be explained that the adjustment in step S5.2 refers to, for example, adjusting the management intensity and the management duration of the management operation according to the area and the flow rate data of the impact range area;

[0125] It needs to be explained that the comprehensive management strategy report is a series of strategy schemes generated based on the active early warning report, for example, the comprehensive management strategy report includes a warning ID: ***-001, a management means type: microorganism injection, a management implementation area: **-001 upstream, a management intensity: 0.75, a management duration: 90 minutes, a microorganism injection type: nitrifying bacteria, and an injection rate: level 1;

[0126] S5.3: output the comprehensive management strategy report to the instruction processing output module;

[0127] The instruction processing output module is configured to process the comprehensive management strategy report to obtain a device control instruction set and output the device control instruction set.

[0128] Further, the step of processing the comprehensive management strategy report to obtain a device control instruction set and output the device control instruction set comprises:

[0129] S6.1: based on the comprehensive management strategy report, perform strategy step decomposition, and convert the decomposed strategy into an execution instruction to obtain a strategy execution instruction set;

[0130] S6.2: perform execution sequence dependency checking on all execution instructions in the strategy execution instruction set, and when there is at least one execution sequence dependency between the execution instructions, perform execution sequence adjustment on the execution instructions in the strategy execution instruction set to obtain a device control instruction set.

[0131] It should be explained that the execution sequence dependency checking refers to, for example, that the microorganism needs to be put into the water flow guide first.

[0132] S6.3: output the device notification instruction set to the corresponding intelligent controller.

[0133] The management effect evaluation optimization module is configured to comprehensively evaluate the water quality after management, and generate a management optimization report according to the evaluation result.

[0134] Further, the step of comprehensively evaluating the water quality after management and generating a management optimization report according to the evaluation result comprises:

[0135] S7.1: continuously obtain the original processing data set in step S1.4 to obtain a real-time original data set, associate the execution-end comprehensive management strategy report with the real-time original data set according to the early warning ID, and enter step S7.2.

[0136] S7.2: based on a water quality improvement evaluation window, calculate the pollutant removal rate and the improvement rate respectively to obtain removal evaluation values and improvement evaluation values, and the specific formula group for calculation is: ;

[0137] The removal evaluation values are obtained respectively as and the improvement evaluation values are obtained respectively as , wherein, is the average concentration of the target pollutant in the target area before execution of the device control instruction set, is the average concentration of the target pollutant in the target area after execution of the device control instruction set, is the management duration.

[0138] It needs to be explained that the water quality improvement evaluation window is artificially set and input into the system, for example, the water quality improvement evaluation window is two hours after the execution of the device control instruction set;

[0139] S7.3: Compare the removal evaluation value and the improvement evaluation value with the expected target respectively, and generate a governance optimization report;

[0140] It needs to be explained that the expected target is artificially set and input into the system;

[0141] The governance optimization report includes strategy execution and recommended parameter adjustment;

[0142] It needs to be explained that, for example, the governance optimization report includes an explanation that the early warning ID: ***-001 in actual use, the removal rate of organic matter is only 40%, lower than the expected target of 60%, and it is recommended to increase the governance intensity parameter from 0.75 to 0.85;

[0143] S7.4: Output the governance optimization report to the comprehensive governance strategy intelligent generation module for updating the governance strategy rule library. Embodiment 2

[0144] Please refer to Figure 2 The part not described in detail in this embodiment can be seen from the description of embodiment 1. The water pollution composite governance method based on real-time monitoring of water pollution is provided, which comprises: S1: based on the sensor network, real-time acquisition of original data and preprocessing to obtain an original processing data set;

[0145] S2: updating the water body simulation model based on the original processing data set, and predicting water pollution based on the updated water body simulation model to obtain a water quality spatio-temporal matrix;

[0146] S3: based on the original processing data set, triggering an abnormal event, and performing reverse tracing according to the water quality spatio-temporal matrix and the water body simulation model to obtain a pollution source analysis report;

[0147] S4: based on the water quality spatio-temporal matrix, risk prediction is performed, and simulation prediction is performed according to the future meteorological data obtained by the sensor network to obtain an active early warning report;

[0148] S5: based on the active early warning report, processing is performed to obtain a comprehensive governance strategy report;

[0149] S6: processing the comprehensive governance strategy report to obtain a device control instruction set and outputting;

[0150] S7: comprehensively evaluating the water quality after governance, and generating a governance optimization report according to the evaluation result.

[0151] The foregoing merely illustrates some exemplary embodiments of the application, and it will be appreciated that those skilled in the art will be able to devise various modifications without departing from the spirit and scope of the application. The described embodiments are to be considered in all respects as illustrative only and not restrictive in character, and the scope of the application is indicated not by the foregoing description but by the claims that follow.

Claims

1. A water pollution composite treatment system based on real-time monitoring of water quality pollution, characterized in that, The system comprises a pollution responsibility tracing identification module, a multi-scenario risk early warning simulation module, an integrated management strategy intelligent generation module, an instruction processing output module and a management effect evaluation optimization module, wherein: The pollution responsibility tracing identification module is configured to trigger an abnormal event based on the original processed data set, and perform reverse tracing based on the water quality space-time matrix and the water body simulation model to obtain a pollution source analysis report. The step of triggering an abnormal event based on the original processed data set and performing reverse tracing based on the water quality space-time matrix and the water body simulation model comprises: S3.1: Real-time monitoring is performed on all data items in the original processed data set, and when at least one data item exceeds the corresponding preset threshold, an abnormal data report is generated, and step S3.2 is entered; S3.2: The updated water body simulation model in step S2.1 is called, the abnormal data item in the abnormal data report is taken as an end condition, and reverse tracing is performed along the time stamp in the updated water body simulation model to obtain a pollution source analysis report; The pollution source analysis report comprises a description of the abnormal data item, the most likely pollution source ID and the responsibility probability; S3.3: The pollution source analysis report is output to a staff receiving end; The multi-scenario risk early warning simulation module is configured to perform risk prediction based on the water quality space-time matrix, and perform simulation prediction based on future meteorological data obtained from a sensor network to obtain an active early warning report. The step of performing risk prediction based on the water quality space-time matrix and performing simulation prediction based on future meteorological data obtained from a sensor network comprises: S4.1: Risk prediction is performed on the water quality space-time matrix based on a preset reading time to obtain a risk prediction report, and the risk prediction comprises traversing all space-time units in the water quality space-time matrix and comparing the predicted pollutant concentration with the corresponding early warning threshold; The risk prediction report comprises a predicted occurrence time stamp, a three-dimensional coordinate of a collection location, a predicted pollutant concentration and a risk level; S4.2: Future meteorological type data is obtained based on a meteorological publishing platform in the sensor network to obtain a future meteorological data set; Based on the updated water body simulation model, a multi-target simulation scenario is created, and the multi-target simulation scenario is run based on the updated water body simulation model to obtain a simulated water quality space-time matrix set; S4.3: An active early warning report is generated based on the risk prediction report and the simulated water quality space-time matrix set; The active early warning report comprises an early warning ID, an early warning level, an impact range area, a risk data value, a risk start time, a risk peak time, a risk end time and a recommended use strategy ID; S4.4: The active early warning report is output to the integrated management strategy intelligent generation module; The integrated management strategy intelligent generation module is configured to process the active early warning report to obtain an integrated management strategy report; The instruction processing output module is configured to process the integrated management strategy report to obtain a device control instruction set and output the device control instruction set; The management effect evaluation optimization module is configured to comprehensively evaluate the water quality after management, and generate a management optimization report based on the evaluation result. The system further comprises a multi-source data fusion processing module and a water quality digital twin prediction module, wherein: The multi-source data fusion processing module is configured to collect raw data in real time based on a sensor network, and perform preprocessing to obtain a raw processed data set; The water quality digital twin prediction module is configured to update a water body simulation model based on the raw processed data set, and predict water quality pollution based on the updated water body simulation model to obtain a water quality spatiotemporal matrix.

2. The water pollution composite treatment system based on real-time monitoring of water quality pollution according to claim 1, characterized in that, The step of collecting raw data in real time based on a sensor network and performing preprocessing includes: S1.1: Collecting raw data in real time based on a preset collection time window and a sensor network to obtain a raw data set, the sensor network including a water quality sensor, a hydrological sensor, a weather release platform, and a pollution source sensor, the raw data including: sensor ID, three-dimensional coordinates of the collection location, collection timestamp, and measurement value collected by the water quality sensor; hydrological station ID, collection timestamp, flow rate data, flow data, and water level data collected by the hydrological sensor; weather area ID, collection timestamp, weather forecast period, rainfall, wind speed, and wind direction collected by the weather release platform; discharge outlet ID, collection timestamp, three-dimensional coordinates of the collection location, discharge type, and allowable discharge amount collected by the pollution source sensor; S1.2: Performing validity check processing on the raw data set to obtain a raw check data set, the validity check being to eliminate data items that exceed the physical range; S1.3: Aligning all data items in the raw check data set in the same time period based on a unified system clock and a fixed time length, to obtain a raw alignment data set, wherein when there is no data item at a time point in the same time period, linear interpolation is used to fill in the missing data; S1.4: Based on a database, retrieving a monitoring section and a pollution source association rule table, and fusing the data items in the raw alignment data set to obtain a raw processed data set; S1.5: Outputting the raw processed data set to the water quality digital twin prediction module.

3. The water pollution composite treatment system based on real-time monitoring of water quality pollution according to claim 2, characterized in that, The step of updating a water body simulation model based on a raw processed data set, and predicting water quality pollution based on the updated water body simulation model includes: S2.1: Based on a database, retrieving a preset water body simulation model, inputting the raw processed data set into the water body simulation model, and adjusting all state variables of the water body simulation model using a data assimilation algorithm to obtain an updated water body simulation model; S2.2: Taking the current state of the updated water body simulation model as an initial condition, and predicting a future time period based on a control equation to obtain a water quality spatiotemporal matrix; S2.3: Outputting the water quality spatiotemporal matrix to a pollution responsibility tracing identification module and a multi-scenario risk early warning simulation module.

4. The water pollution composite treatment system based on real-time monitoring of water quality pollution according to claim 2, characterized in that, The step of processing based on the active early warning report includes: S5.1: Based on a database, retrieving a governance strategy rule library, and searching based on the active early warning report to obtain a standard governance template; S5.2: Adjusting the standard governance template based on detailed parameters in the active early warning report to obtain a comprehensive governance strategy report, the detailed parameters including risk start time, risk peak time, and risk end time; S5.3: Outputting the comprehensive governance strategy report to the instruction processing output module.

5. The water pollution composite treatment system based on real-time monitoring of water quality pollution according to claim 4, characterized in that, The step of processing the comprehensive treatment strategy report to obtain the device control instruction set and outputting the device control instruction set comprises: S6.1: decomposing the strategy step based on the comprehensive treatment strategy report, and converting the decomposed strategy into an execution instruction to obtain a strategy execution instruction set; S6.2: performing execution sequence dependency checking on all execution instructions in the strategy execution instruction set, and when there is at least one execution sequence dependency between the execution instructions, adjusting the execution sequence of the execution instructions in the strategy execution instruction set to obtain a device control instruction set; S6.3: outputting the device notification instruction set to the corresponding intelligent controller.

6. The water pollution composite treatment system based on real-time monitoring of water quality pollution according to claim 2, characterized in that, The step of comprehensively evaluating the treated water quality and generating a treatment optimization report based on the evaluation result comprises: S7.1: continuously obtaining the real-time original data set from the original processing data set in step S1.4, associating the execution-end comprehensive treatment strategy report with the real-time original data set according to the early warning ID, and entering step S7.2; S7.2: calculating the removal rate and the improvement rate based on the water quality improvement evaluation window to obtain removal evaluation values and improvement evaluation values; S7.3: comparing the removal evaluation values and the improvement evaluation values with the expected target to generate a treatment optimization report; The treatment optimization report includes the strategy execution situation and the recommended parameter adjustment; S7.4: outputting the treatment optimization report to the comprehensive treatment strategy intelligent generation module for updating the treatment strategy rule library.

7. The water pollution composite treatment method based on real-time monitoring of water quality pollution, according to the water pollution composite treatment system based on real-time monitoring of water quality pollution of any one of claims 1-6, characterized in that, The following working steps are included: S1: based on the sensor network, real-time acquisition of original data and pre-processing to obtain an original processing data set; S2: updating the water body simulation model based on the original processing data set, and predicting water pollution based on the updated water body simulation model to obtain a water quality spatio-temporal matrix; S3: triggering an abnormal event based on the original processing data set, and performing reverse tracing based on the water quality spatio-temporal matrix and the water body simulation model to obtain a pollution source analysis report; S4: risk prediction based on the water quality spatio-temporal matrix, and simulation prediction based on future meteorological data obtained from the sensor network to obtain a proactive early warning report; S5: processing the proactive early warning report to obtain a comprehensive treatment strategy report; S6: processing the comprehensive treatment strategy report to obtain a device control instruction set, and outputting the device control instruction set; S7: comprehensively evaluating the treated water quality, and generating a treatment optimization report based on the evaluation result.

Images