Water treatment management method and system based on big data

Abstract

The application discloses a water treatment management method and system based on big data, and relates to the technical field of water treatment data management. The water treatment management method based on big data, in the meteorological prediction integration stage, after the water treatment management platform receives a rainfall warning, in the rainwater collection period, synchronously acquires multi-dimensional meteorological parameters reflecting rainfall changes and rainwater environmental parameters reflecting rainwater characteristics; then, the current water treatment state is synchronously matched, the adaptability is judged, and management response is carried out based on water treatment data; finally, the matching result is compared with the response preparation result, the deviation level of the current treatment state and the expected water quality target is determined, and the corresponding emergency management measures are triggered, so that the accurate regulation and control of water treatment management before the arrival of rainwater based on big data is realized, the water quality change risk can be perceived in advance, and the problem that the corresponding water treatment state and the water treatment data management state do not match in the existing water treatment process is effectively solved.

Description

Technical Field

[0001] The present invention relates to the technical field of water treatment data management, and particularly to a water treatment management method and system based on big data. Background Art

[0002] The water treatment management constructs a full-process closed-loop control system, covering all links from precipitation collection to water storage. Monitoring devices are scientifically arranged at key nodes. The precipitation collection pipeline focuses on capturing the turbidity and suspended solid concentration of the initial water, while the pretreatment pool and the water storage outlet simultaneously monitor multiple water quality indicators, forming a three-dimensional monitoring network.

[0003] A data real-time upload and analysis mechanism is established. After the rainwater is treated by the sedimentation tank and membrane filtration, the relevant water quality data is timely incorporated into the management platform to provide a basis for subsequent treatment. For the sodium hypochlorite generator, the operating state is dynamically adjusted in combination with parameters such as the residual chlorine value and the number of microorganisms before and after treatment. When it is monitored that the rainfall causes a sudden increase in turbidity (such as exceeding 10 NTU), the system automatically retrieves the historical dosing curve and generates a power adjustment suggestion to ensure that the disinfection effect meets the standard.

[0004] Attention is paid to the water quality maintenance in the water storage stage. The change of residual chlorine during the water storage process is tracked by the residual chlorine decay sensor, and the data such as the pH value and residual chlorine content monitored online and the equipment operating parameters are integrated to flexibly switch the working mode of the generator. At the same time, the linkage analysis of the water storage water quality data and the water supply pipe network monitoring data is realized to comprehensively ensure the water quality safety of precipitation utilization, forming a full-chain management closed-loop from collection to storage.

[0005] For example, the Chinese invention patent with the publication number: CN117993689B discloses a water treatment method and system, including: retrieving the wastewater treatment space of a target power plant containing multiple water treatment modules, determining the selection quantity, retrieving the priority strategy and the selection quantity in the power model at the prediction moment, and updating the space for the wastewater treatment by the operation module; obtaining the acquisition device of the treatment equipment in the processing unit for acquiring the regional image in the operation module, and updating the sub-processing unit based on this image to obtain the position display space.

[0006] The above technologies at least have the following technical problems: In existing technologies, water treatment management platforms experience delays in data acquisition, transmission, and analysis, a problem that becomes more pronounced during rainfall. During rainfall, water quality changes rapidly. Initial rainwater carries large amounts of surface pollutants, causing a sharp increase in turbidity, suspended solids concentration, and other indicators. This can lead to network congestion or signal instability during data collection by monitoring equipment, further extending transmission time. Consequently, the management platform struggles to accurately capture these rapid water quality changes in real time. For example, the actual water quality may have deteriorated due to rainfall, but the management platform may not yet reflect this. Operators cannot adjust treatment parameters based on the real-time status, such as increasing coagulant dosage or adjusting filtration speed, thus affecting treatment effectiveness. This results in a mismatch between the actual tap water treatment status and the water treatment data management status. Summary of the Invention

[0007] To address the technical problem of mismatch between the water treatment status and the water treatment data management status in existing technologies, this invention provides a water treatment management method based on big data, the technical solution of which is as follows: On the one hand, a big data-based water treatment management method is provided. This method includes: S1, in the meteorological forecast integration stage, after receiving rainfall warning information, the water treatment management platform synchronously acquires multi-dimensional meteorological parameters and rainfall environmental parameters within the defined rainfall collection time period. The meteorological forecast integration stage represents the preparation stage from when the water treatment management platform receives the rainfall warning information from the meteorological department until water is stored in the tap water storage tank. The multi-dimensional meteorological parameters reflect the changes in the corresponding rainfall process within the rainfall collection time period, and the rainfall environmental parameters reflect the physical and chemical properties of the corresponding rainwater within the rainfall collection time period; S2, the acquired multi-dimensional meteorological parameters and rainfall environmental parameters are synchronized and matched with the current tap water treatment status, and a tap water treatment management response is performed based on the acquired water treatment data. State matching is used to determine the compatibility between multidimensional meteorological parameters, rainwater environmental parameters and the current operating status of the water treatment management platform. Water treatment data is used to reflect the key indicators of the real-time operation of the water treatment management platform. Tap water treatment management response is used to reflect the degree of responsiveness of the water treatment management platform in making decisions in response to the upcoming rainwater characteristics. S3 compares the results of synchronous state matching with the results of tap water treatment response preparation to determine the deviation level between the current tap water treatment status and the expected water quality target. Based on the obtained deviation level, corresponding emergency management measures are triggered. The deviation level is used to determine the degree of deviation between the current tap water treatment status and the expected water quality target. The expected water quality target represents the various water quality indicator standards that should be achieved after tap water treatment. Emergency management measures are used to quickly take corresponding treatment procedures when water quality deviation is detected.

[0008] On the other hand, a big data-based water treatment management system is provided. This system is applied to a big data-based water treatment management method and includes: a multi-dimensional parameter acquisition module before tap water treatment, a synchronous matching management module for tap water treatment status, and an emergency management module for water quality target prediction status. The multi-dimensional parameter acquisition module before tap water treatment is used during the meteorological forecast integration stage. After receiving rainfall warning information, the water treatment management platform synchronously acquires multi-dimensional meteorological parameters and rainfall environmental parameters within the defined rainfall collection time period. The synchronous matching management module for tap water treatment status is used to synchronously match the acquired multi-dimensional meteorological parameters and rainfall environmental parameters with the current tap water treatment status, and simultaneously perform tap water treatment management responses based on the acquired water treatment data. The emergency management module for water quality target prediction status compares the results of the synchronous matching with the results of the tap water treatment response preparation to determine the deviation level between the current tap water treatment status and the expected water quality target, and triggers corresponding emergency management measures based on the acquired deviation level.

[0009] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following: 1. Upon receiving a rainfall warning, the water treatment management platform of this invention simultaneously acquires multi-dimensional meteorological parameters reflecting rainfall changes and rainwater environmental parameters reflecting rainwater characteristics during the rainwater collection period. This provides a data foundation for subsequent treatment, helps to understand rainfall conditions in advance, and enhances response capabilities. The acquired parameters are matched with the current tap water treatment status to determine suitability. Simultaneously, management responses are based on water treatment data, reflecting the degree of decision-making regarding the characteristics of upcoming rainfall. This step achieves a close link between water treatment data management and tap water treatment status. By comparing the synchronous matching results with the response preparation results, the deviation level between the current treatment status and the expected water quality target is determined, triggering corresponding emergency measures. Through this matching and comparison, problems in the treatment process can be identified in a timely manner, deviations can be accurately located, and rapid action can be taken to ensure stable and compliant tap water treatment results, thereby improving the overall level of water treatment management.

[0010] 2. First, water treatment data is input into the platform to prioritize water treatment, quantifying the response levels to different water quality risks and management decisions. During prioritization, the synchronous load of edge nodes is first acquired. If it exceeds a reference value, it is classified as a Level 1 response priority and load balancing is verified. If it does not exceed the reference value, it is classified as a Level 2 response priority, and the current resource allocation is maintained. During load balancing verification, real-time load data is statistically analyzed to calculate the average load balancing deviation. If it does not exceed the reference value, the standard is met, the status is maintained, and a report is generated to visualize load fluctuations. If it exceeds the reference value, the standard is not met, and node migration optimization is performed. The deviation is input into the influent status prediction dataset to obtain the data cache quota adjustment target, alleviating the pressure on high-load nodes. This process accurately responds to water treatment needs, ensures the stable operation of the water treatment management platform, and improves water treatment efficiency and quality.

[0011] 3. First, obtain the ratio of the synchronization status matching time and the tap water treatment response preparation time to the stored reference time, obtain the corresponding score, and sum them to determine the prediction parameter deviation. This deviation level is used to determine the deviation grade. A level 1 deviation indicates that the treatment status matches the expected water quality target, and level 1 management measures are implemented. The deviation is entered into the level 1 management mapping table, and the frequency of influent status collection is increased to promptly grasp the influent situation. A level 2 deviation indicates a mismatch, and in addition to level 1 measures, the deviation is entered into the level 2 management mapping table to prompt manual inspection. During execution, the water treatment management platform automatically generates a restart delivery command, instructing pre-set personnel to check for impurities in the delivery pipeline. After the process is completed, the data is entered into the influent status prediction dataset for storage and updating. Through these steps, the treatment status can be accurately determined, timely measures can be taken to ensure water treatment quality, and the dataset can be continuously optimized to improve subsequent management effectiveness. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 A flowchart illustrating a water treatment management method based on big data, provided as an embodiment of the present invention; Figure 2 The flowchart corresponding to the multi-dimensional parameter acquisition provided in the embodiments of the present invention; Figure 3 The flowchart corresponding to the state matching management provided in the embodiments of the present invention; Figure 4 The flowchart corresponding to the deviation emergency management provided in the embodiments of the present invention; Figure 5 This is a schematic diagram of a water treatment management system based on big data, provided as an embodiment of the present invention. Detailed Implementation

[0014] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0015] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0016] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0017] This invention provides a water treatment management method based on big data, such as... Figure 1 The flowchart shown represents a water treatment management method based on big data. The processing flow of this method may include the following steps: S1, In the meteorological forecast integration stage, after receiving rainfall warning information, the water treatment management platform simultaneously acquires multi-dimensional meteorological parameters and rainwater environmental parameters within the defined rainwater collection time period. The meteorological forecast integration stage refers to the preparation stage from when the water treatment management platform receives rainfall warning information from the meteorological department to before the water is stored in the tap water storage tank. Multi-dimensional meteorological parameters are used to reflect the changes in the corresponding rainfall process within the rainwater collection time period, including but not limited to the rainfall level, duration, temperature, humidity, and wind force transmitted by the meteorological forecast. Rainwater environmental parameters are used to reflect the physical and chemical characteristics of the corresponding rainwater within the rainwater collection time period, including but not limited to the rainfall flow, rainwater turbidity, and initial colony count collected in real time by rainwater sensors.

[0018] S2 synchronizes the acquired multidimensional meteorological parameters and rainwater environmental parameters with the current tap water treatment status. Simultaneously, it performs tap water treatment management response based on the acquired water treatment data. Synchronization status matching is used to determine the compatibility between multidimensional meteorological parameters, rainwater environmental parameters and the current operating status of the water treatment management platform. Water treatment data is used to reflect the key indicators of the real-time operation of the water treatment management platform, such as the influent and effluent flow rate of each treatment unit, turbidity, pH value, residual chlorine content, coagulant and disinfectant dosage, filtration pressure difference, and electrolytic current of disinfection equipment. Tap water treatment management response is used to reflect the degree of responsiveness of the water treatment management platform in making decisions in response to the characteristics of the upcoming rainwater.

[0019] S3 compares the results of the synchronization status matching with the results of the tap water treatment response preparation to determine the deviation level between the current tap water treatment status and the expected water quality target. Based on the obtained deviation level, corresponding emergency management measures are triggered. Water quality indicators include, but are not limited to, residual chlorine value at the water storage inlet, rainwater turbidity, and total bacterial count. The deviation level is used to indicate the degree of deviation between the current tap water treatment status and the expected water quality target, serving as the basis for triggering corresponding emergency management measures. The expected water quality target is used to reflect the water quality deviation. Emergency management measures are used to quickly implement corresponding treatment processes when water quality deviation is detected, such as adjusting the dosage of coagulants and disinfectants, strengthening filtration and disinfection, etc., to ensure water quality safety and prevent the decline in treatment effect or water pollution caused by rainwater input.

[0020] In this embodiment, the water treatment management platform acts as the core hub. During the meteorological forecasting and integration phase, upon receiving rainfall warning information, it simultaneously acquires multi-dimensional meteorological parameters and rainfall environmental parameters within the rainfall collection period to comprehensively understand the rainfall and rainfall situation. Subsequently, the water treatment management platform synchronizes the acquired parameters with the current tap water treatment status. Simultaneously, based on the water treatment data collected by the platform, it initiates tap water treatment management responses, accurately assessing the compatibility of the parameters with the platform's operational status and the degree of response. Next, the platform compares the synchronization status matching results with the tap water treatment response preparation results to determine the deviation level between the current treatment status and the expected water quality target, and triggers corresponding emergency management measures based on the deviation level. Through this series of operations, the water treatment management platform achieves scientific and efficient management, ensuring water quality safety and preventing a decline in treatment effectiveness or water pollution due to rainwater input.

[0021] like Figure 2 The diagram shows a flowchart of the multi-dimensional parameter acquisition process provided in this embodiment of the invention. The process involves obtaining the influent load synchronization duration during the establishment of the influent state prediction dataset. If the influent load synchronization duration matches the first matching relationship, a first-level management strategy is implemented. If the influent load synchronization duration matches the second matching relationship, a second-level management strategy is implemented. If the influent load synchronization duration matches the third matching relationship, a third-level management strategy is implemented.

[0022] Furthermore, the synchronization state matching involves the following steps: The acquired multidimensional meteorological parameters and rainwater environmental parameters are input into the water treatment management platform. Based on the historical influent state dataset (i.e., historical rainwater harvesting and disinfection - tap water treatment process dataset) stored in the water treatment management platform, association rule algorithms from data mining are used to map the data to the multidimensional meteorological parameters and rainwater environmental parameters respectively, establishing an influent state prediction dataset and determining the dynamic mapping relationship. The influent state prediction dataset is used to predict the expected water quality results and the operating status of the water treatment management platform under different water treatment processes at the current rainfall level. The dynamic mapping relationship determination is used to determine the compatibility between the current rainfall and the corresponding management decisions in the tap water treatment process.

[0023] The determination of dynamic mapping relationships specifically includes: obtaining the influent load synchronization duration during the establishment of the influent status prediction dataset. The influent load synchronization duration represents the time interval between the current operating load of the water treatment management platform and the historical influent load data in the water treatment management platform to complete dynamic synchronization. It reflects the efficiency of establishing a correlation between real-time parameters and historical datasets, indirectly reflects the system's response speed to fluctuations in influent load, and provides a quantitative basis for the timeliness and accuracy of dynamic mapping relationships.

[0024] If the influent load synchronization duration meets the first matching relationship, i.e., the obtained influent load synchronization duration is less than the minimum historical influent load synchronization duration, then the first-level management strategy is triggered. The first-level management strategy is used to send an instruction to maintain the current operating state of the sodium hypochlorite generator. If the influent load synchronization duration meets the second matching relationship, i.e., the obtained influent load synchronization duration is within the closed interval between the minimum and maximum historical influent load synchronization duration, then the second-level management strategy is triggered. The second-level management strategy is used to send an instruction to strengthen the filtration process to cope with water quality fluctuations. If the influent load synchronization duration meets the third matching relationship, i.e., the obtained influent load synchronization duration is greater than the maximum historical influent load synchronization duration, then the third-level management strategy is triggered. The third-level management strategy is used to send an instruction to start the sedimentation tank for accelerated settling.

[0025] The first matching relationship, the second matching relationship, and the third matching relationship together constitute the basis for judging the hierarchical control of the water treatment management platform operation status based on the influent load synchronization duration. The first matching relationship, the second matching relationship, and the third matching relationship correspond to different ranges of influent load synchronization duration from low to high.

[0026] In this embodiment, the influent load synchronization duration is obtained through a built-in timer in the water treatment management platform. The historical influent load synchronization duration represents the set of influent load synchronization durations obtained within the historically divided rainwater collection time periods in the database. The closed interval represents the closed interval corresponding to the minimum and maximum values ​​of the influent load synchronization duration stored in the set. By associating the historical rainwater recycling and disinfection-tap water treatment process dataset, an influent status prediction dataset is quickly established, accurately predicting the impact of current rainfall on water quality and treatment processes. This allows decision-making to move away from reliance on experience, improving the intelligent prediction capability and precise resource scheduling efficiency of the water treatment management platform.

[0027] This example uses multi-dimensional meteorological and rainfall environmental parameters as input, combined with historical datasets and association rule algorithms, to build an influent status prediction dataset. This dataset accurately predicts expected water quality and the operational status of the water treatment management platform under different rainfall amounts. The dynamic mapping relationship determination incorporates the influent load synchronization duration, constructing a tiered control basis using three matching relationships. Corresponding management strategies are triggered based on different duration intervals. This allows the water treatment management platform to respond in real-time to influent load fluctuations, adjust treatment processes promptly, ensure stable water quality compliance, improve the system's adaptability to complex operating conditions and treatment efficiency, achieve intelligent and refined management, and reduce operating costs and risks.

[0028] It should be further explained that the influent status dataset stores different water treatment processes corresponding to different rainfall amounts, as well as the corresponding expected water quality results and the current operating status of the water treatment management platform. In the following embodiments, the dataset and mapping set mentioned refer to this influent status dataset. Furthermore, the influent status dataset has a learning function, integrating the Q-learning algorithm from the reinforcement learning model into the influent status dataset. This dataset continuously collects all parameters involved in the adjustment during the water treatment process. After the water treatment process ends, the model performs incremental updates based on the XGBoost algorithm.

[0029] like Figure 3 The diagram shows a flowchart of the state matching management provided in this embodiment of the invention. Priority is assigned based on the acquired water treatment data. The acquired edge node synchronization load is compared with the reference edge node synchronization load. If the load is greater than the reference value, it is classified as a secondary response priority; otherwise, it is classified as a primary response priority. The average load balancing deviation is compared with the reference value. If the deviation is not greater than the reference value, the load balancing meets the standard and a balancing report is generated. If the deviation is greater than the reference value, the data cache quota is adjusted, and it is determined whether the newly acquired average load balancing deviation is greater than the reference value. If it is, a load balancing warning is issued; otherwise, the load balancing meets the standard.

[0030] Furthermore, the specific process of tap water treatment management response is as follows: During the determination of dynamic mapping relationship, water treatment data is acquired and input into the water treatment management platform for water treatment priority classification. Water treatment data includes, but is not limited to, real-time influent flow rate, turbidity, pH value, residual chlorine content, rainfall, water temperature, coagulant dosage, filtration pressure difference, and disinfection equipment operating parameters (such as electrolysis current and sodium chloride concentration). Water treatment priority classification is used to quantify the response level of the water treatment management platform to different water quality risks and the corresponding management decisions in the current tap water treatment process.

[0031] The water treatment priority classification process is as follows: The edge node synchronization load of water treatment data in the water treatment management platform is obtained during the data management process. The edge node synchronization load reflects the data synchronization pressure between various edge sensor nodes in the water treatment management platform, i.e., the urgency of real-time data transmission and processing, indirectly reflecting the intensity of water quality parameter fluctuations. If the obtained edge node synchronization load is greater than the reference edge node synchronization load, it is determined to be a first-level response priority, and load balancing verification is performed. If the obtained edge node synchronization load is not greater than the reference edge node synchronization load, it is determined to be a second-level response priority, and preset personnel are prompted to maintain the current CPU and memory resource allocation status of the water treatment management platform. The first-level response priority is higher than the second-level response priority.

[0032] Load balancing verification specifically involves: collecting real-time load data from all edge sensor nodes in the water treatment management platform; calculating the deviation rate between the load value of each edge node and its corresponding average load value based on the acquired real-time load data; obtaining the deviation rate of each edge sensor node; summing these deviation rates to obtain the average load balancing deviation; and using real-time load data including processor utilization, memory usage, and data transfer rate. If the acquired average load balancing deviation is not greater than the reference average load balancing deviation, the load balancing is deemed satisfactory, and the current resource allocation status is maintained. A load balancing report is also generated to visualize the load fluctuations of each edge sensor node in the water treatment management platform. If the acquired average load balancing deviation is greater than the reference average load balancing deviation, the load balancing is deemed unsatisfactory, and node migration optimization is performed.

[0033] Node migration optimization specifically involves: inputting the acquired average load balancing deviation into the influent status prediction dataset; based on the mapping relationship between the average load balancing deviation stored in the influent status prediction dataset and the increase in data cache quota, obtaining the current data cache quota adjustment target for the water treatment management platform; dynamically adapting to the real-time load requirements of each edge sensor node, alleviating the data processing pressure on high-load nodes, realizing multi-node collaborative processing, reducing overall load deviation, and improving the stability of corresponding data synchronization and processing of the water treatment management platform; after node migration optimization, if the re-acquired average load balancing deviation is greater than the reference average load balancing deviation, a load balancing warning is issued; otherwise, the load balancing is deemed to be up to standard.

[0034] In this embodiment, the edge node synchronous load is obtained through electrical parameter detection sensors. The reference edge node synchronous load is represented by the sum of the historical edge node synchronous loads at the end of the historical water treatment priority division process in the database. The reference average load balance deviation is represented by the sum of the historical average load balance deviations at the end of the historical load balance verification process in the database.

[0035] In the response to water treatment management issues, by acquiring and prioritizing diverse water treatment data, the response levels to different water quality risks are accurately quantified. First- and second-level response priorities are distinguished based on the synchronous load of edge nodes, and targeted measures are taken accordingly. Load balancing verification can promptly identify uneven node loads. Node migration optimization dynamically adjusts data cache quotas using influent status prediction datasets, achieving multi-node collaboration and reducing overall load deviation. The entire process effectively improves the stability of data synchronization and processing in the water treatment management platform, enabling timely responses to water quality fluctuations, ensuring efficient and stable operation of water treatment, and reducing water quality risks caused by data processing problems.

[0036] like Figure 4The flowchart shown is a flowchart of the deviation emergency management provided in the embodiment of the present invention. The obtained response management time is compared with the reference response management time. If it is greater than the reference value, the response management anomaly feedback is performed. If it is not greater than the reference value, the deviation level is determined. The deviation of the obtained prediction parameter is used to determine whether it is a first-level deviation or a second-level deviation, and the corresponding first-level management measures and second-level management measures are selected for correction.

[0037] Furthermore, the water treatment management response also includes: obtaining the current rainfall level and classifying the response management level, which includes Level 1, Level 2, and Level 3 response management. Level 1, Level 2, and Level 3 response management correspond to different levels of risk and handling complexity caused by rainfall levels from low to high, respectively. After classifying the response management level, the average response management time of the water treatment management platform during the response management level classification process is obtained, and response management optimization judgment is performed, that is, the average response management time corresponding to Level 1, Level 2, and Level 3 response management.

[0038] The specific steps for response management optimization judgment are as follows: If the obtained average response management time is not greater than the reference average response management time, the water treatment management platform is judged to have qualified response management, and the deviation level between the current tap water treatment status and the expected water quality target is determined; if the obtained average response management time is greater than the reference average response management time, the water treatment management platform is judged to have unqualified response management, and response management anomaly feedback is provided; response management anomaly feedback is used to prompt the water treatment management platform to verify the data transmission delay peak of water treatment data to determine whether manual calibration is required; the data transmission delay peak is used to reflect the maximum time spent by the water treatment management platform from the acquisition node to the transmission process.

[0039] It should be added that the specific process of manual calibration is as follows: Based on the feedback prompts of response management anomalies, the operation and maintenance personnel retrieve the data transmission latency peak records in the water treatment management platform, locate the specific data acquisition nodes, manually adjust the associated nodes with high latency, and perform manual calibration based on historical data to cover the current anomaly. The dosage of disinfectant and the generation frequency of filter backwash cycle instructions in the water treatment management platform are updated synchronously. The average response management duration is obtained through the timer built into the water treatment management platform. The reference average response management duration is represented by the sum of the historical average response management durations at the end of the historical response management process in the database.

[0040] In this embodiment, response management levels are determined by acquiring the current rainfall level, accurately corresponding to different risks and processing complexities, making management more targeted. Optimization based on average response management time allows for timely detection and feedback of non-compliant response management. Anomaly feedback prompts verification of data transmission latency peaks, and manual calibration when necessary accurately pinpoints problem nodes. Adjustments are made based on historical data, anomalies are covered, and the frequency of key instruction generation is updated synchronously. Overall, this improves the timeliness and accuracy of tap water treatment management response, effectively addressing various situations caused by rainfall, ensuring stable treatment processes, guaranteeing water quality meets expected targets, and enhancing system reliability and adaptability.

[0041] It's important to understand that setting up two response methods for tap water treatment management, compared to existing technologies, is based on the need for comprehensive and precise control. The response based on water treatment data and edge node load focuses on the internal data processing stage of the platform, enabling timely responses to problems caused by data synchronization pressure and ensuring data processing stability. The introduction of rainfall level-based response management, on the other hand, considers external environmental factors such as rainfall, taking into account the risks and processing complexities brought about by different rainfall levels. Combining these two approaches, considering multiple internal and external dimensions, compensates for the shortcomings of a single response method, enabling a more comprehensive and precise response to various complex situations, improving the reliability of tap water treatment management, and ensuring stable water quality compliance.

[0042] Furthermore, the specific process for determining the deviation level is as follows: Obtain the synchronization state matching time and the water treatment response preparation time; simultaneously obtain the stored reference synchronization state matching time and reference water treatment response preparation time from the influent state prediction dataset, and perform ratio processing to obtain the synchronization state matching time score (i.e., the ratio of the obtained synchronization state matching time as the numerator and the reference synchronization state matching time as the denominator) and the water treatment response preparation time score (i.e., the ratio of the obtained water treatment response preparation time as the numerator and the reference water treatment response preparation time as the denominator); calculate the synchronization state matching time score... The predicted parameter deviation is obtained by summing the predicted parameter deviation with the water treatment response preparation time score. When the obtained predicted parameter deviation is a Level 1 deviation (usually set to a certain value), it indicates that the current water treatment status matches the expected water quality target, and Level 1 management measures are implemented. When the obtained predicted parameter deviation is a Level 2 deviation (usually set to a certain value), it indicates that the current water treatment status does not match the expected water quality target, and Level 2 management measures are implemented. The Level 1 deviation and Level 2 deviation correspond to the degree of matching between the water treatment status and the expected water quality target from high to low, respectively. It should be understood that the range settings for Level 1 deviation and Level 2 deviation can be fine-tuned according to the needs of the actual water treatment scenario.

[0043] Based on the acquired deviation level, corresponding emergency management measures are triggered, specifically: Level 1 management measures, the specific steps are: inputting the currently acquired predicted parameter deviation into the mapping table of Level 1 management stored in the influent status prediction dataset to increase the influent status collection frequency of the current water treatment management platform, thereby capturing water quality changes more timely and accurately; Level 2 management measures, the specific steps are: based on the Level 1 management measures, inputting the currently acquired predicted parameter deviation into the mapping table of Level 2 management stored in the influent status prediction dataset to prompt preset personnel to perform manual inspections, such as checking the operating status of water pumps, whether valves are opening and closing normally, and whether filter media is blocked or damaged; during the execution of management measures, the water treatment management platform automatically generates a restart delivery command to prompt preset personnel to check impurities in the tap water delivery pipeline, and after completing a delivery process, inputting the monitored water treatment management data into the influent status prediction dataset for storage and updating.

[0044] In this embodiment, the synchronization state matching time and the tap water treatment response preparation time are both obtained through the built-in timer of the water treatment management platform. The synchronization state matching time and the tap water treatment response preparation time are represented by the sum of the historical synchronization state matching time and the historical tap water treatment response preparation time at the end of the process determined by the historical deviation level in the database.

[0045] It is important to understand that the synchronization state matching time directly affects the water treatment response preparation time. If the synchronization state matching is prolonged due to data surges or calibration delays, it will compress the available window for response preparation, forcing critical operations such as disinfection or filtration to be executed in a compressed manner, increasing the risk of water quality loss of control. Conversely, an excessively long treatment response preparation time will weaken the effectiveness of the matching results, causing the actual water quality to deviate from the predicted range of the matching stage, making the original judgment invalid and requiring the matching process to be retried. The two form an interlocking optimization mechanism through the system closed loop.

[0046] This example calculates the deviation of predicted parameters by synchronizing the state matching time score and the water treatment response preparation time score, thereby achieving intelligent determination of the deviation level. At the same time, the water treatment management platform feeds back the executed water treatment data to the influent state prediction dataset for continuous updating. This enables the water treatment management platform to convert deviations into specific operation instructions, quickly eliminate monitoring blind spots (such as sudden changes in turbidity) under disturbances such as rainstorms, and intercept the risk of equipment failure through a collaborative mechanism (automatic data collection + manual inspection).

[0047] like Figure 5The diagram shows a schematic of a big data-based water treatment management system provided in an embodiment of the present invention. It includes the following modules: a multi-dimensional parameter acquisition module for pre-treatment of tap water, a synchronous matching management module for tap water treatment status, and an emergency management module for water quality target prediction status. The multi-dimensional parameter acquisition module for pre-treatment of tap water is used to synchronously acquire multi-dimensional meteorological parameters and rainwater environmental parameters within a defined rainwater collection period after the water treatment management platform receives rainfall warning information during the meteorological forecast integration phase. The synchronous matching management module for tap water treatment status is used to synchronously match the acquired multi-dimensional meteorological parameters and rainwater environmental parameters with the current tap water treatment status, and simultaneously perform tap water treatment management responses based on the acquired water treatment data. The emergency management module for water quality target prediction status is used to compare the results of the synchronous matching with the results of the tap water treatment response preparation to determine the deviation level between the current tap water treatment status and the expected water quality target, and trigger corresponding emergency management measures based on the acquired deviation level.

[0048] In this embodiment, the multi-dimensional parameter acquisition module before tap water treatment serves as the perception layer, synchronously acquiring meteorological and environmental parameters after a rainfall warning to provide real-time data input for subsequent decision-making; the synchronous matching management module for tap water treatment status serves as the analysis and decision-making layer, dynamically matching the acquired parameters with the current water treatment status and driving the treatment response; the emergency management module for water quality target prediction status serves as the execution optimization layer, triggering adaptive emergency measures by comparing the matching results with the response preparation data.

[0049] The three modules mentioned above work together through standardized data interfaces, dynamic feedback mechanisms, and intelligent algorithms to achieve closed-loop linkage. This closed loop of "perceived input → intelligent decision-making → precise execution → feedback optimization" enables the system to have self-evolution capabilities: the performance improvement of any module will enhance the accuracy and speed of other modules.

[0050] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the flow or function according to the embodiments of the present invention is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. A computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. Available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. Semiconductor media can be solid-state drives.

[0051] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0052] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0053] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0054] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0055] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A water treatment management method based on big data, characterized in that, Includes the following steps: S1, In the meteorological forecast integration stage, after receiving the rainfall warning information, the water treatment management platform synchronously acquires multi-dimensional meteorological parameters and rainwater environmental parameters within the divided rainwater collection time period. The meteorological forecast integration stage refers to the preparation stage from when the water treatment management platform receives the rainfall warning information from the meteorological department to before the water storage tank stores water. The multi-dimensional meteorological parameters are used to reflect the changes in the corresponding rainfall process within the rainwater collection time period, and the rainwater environmental parameters are used to reflect the physical and chemical characteristics of the corresponding rainwater within the rainwater collection time period. S2, the acquired multidimensional meteorological parameters and rainwater environmental parameters are synchronized and matched with the current tap water treatment status, and the tap water treatment management response is performed based on the acquired water treatment data. The synchronized status matching is used to determine the compatibility between the multidimensional meteorological parameters, rainwater environmental parameters and the current operating status of the water treatment management platform. The water treatment data is used to reflect the key indicators of the real-time operation of the water treatment management platform. The tap water treatment management response is used to reflect the degree of responsiveness of the water treatment management platform in making decisions in response to the upcoming rainwater characteristics. S3, compare the result of the synchronization state matching with the result of the tap water treatment response preparation to determine the deviation level between the current tap water treatment state and the expected water quality target, and trigger corresponding emergency management measures according to the obtained deviation level. The deviation level is used to determine the degree of deviation between the current tap water treatment state and the expected water quality target. The expected water quality target represents the various water quality indicators that should be achieved after tap water treatment. The emergency management measures are used to quickly take corresponding treatment procedures when water quality deviation is detected.

2. The water treatment management method based on big data as described in claim 1, characterized in that, The specific steps for the synchronization state matching are as follows: The acquired multidimensional meteorological parameters and rainwater environmental parameters are input into the water treatment management platform. Based on the historical inflow status dataset stored in the water treatment management platform, the data are mapped to the multidimensional meteorological parameters and rainwater environmental parameters respectively to establish an inflow status prediction dataset and determine the dynamic mapping relationship. The influent status prediction dataset is used to predict the expected water quality results and the operating status of the water treatment management platform under different water treatment processes at the current rainfall. The dynamic mapping relationship determination is used to determine the compatibility between the current rainfall and the corresponding management decisions in the tap water treatment process.

3. The water treatment management method based on big data as described in claim 2, characterized in that, The determination of the dynamic mapping relationship specifically includes: The influent load synchronization duration during the establishment of the influent status prediction dataset is obtained. The influent load synchronization duration represents the time interval between the current operating load of the water treatment management platform and the historical influent load data in the water treatment management platform to complete dynamic synchronization. If the influent load synchronization duration meets the first matching relationship, the first-level management strategy is triggered. The first-level management strategy is used to send instructions to maintain the current operating state of the sodium hypochlorite generator. If the influent load synchronization duration matches the second matching relationship, the secondary management strategy is triggered. The secondary management strategy is used to send instructions to strengthen the filtration process in response to water quality fluctuations. If the influent load synchronization duration meets the third matching relationship, the three-level management strategy is triggered, and the three-level management strategy is used to send instructions; The first matching relationship, the second matching relationship, and the third matching relationship together constitute the basis for judging the hierarchical control of the water treatment management platform operation status based on the influent load synchronization duration. The first matching relationship, the second matching relationship, and the third matching relationship correspond to different intervals of influent load synchronization duration from low to high.

4. The water treatment management method based on big data as described in claim 1, characterized in that, The specific process of the water treatment management response is as follows: During the process of determining the dynamic mapping relationship, water treatment data is acquired and input into the water treatment management platform for water treatment priority classification. The water treatment priority classification is used to quantify the response level of the water treatment management platform to different water quality risks and the corresponding management decisions in the current tap water treatment process. The specific process for prioritizing water treatment is as follows: The edge node synchronization load of water treatment data in the water treatment management platform is obtained during the data management process. The edge node synchronization load is used to reflect the data synchronization pressure between various edge sensor nodes in the water treatment management platform. If the obtained edge node synchronization load is greater than the reference edge node synchronization load, it is determined to be a first-level response priority, and load balancing verification is performed. If the obtained edge node synchronization load is not greater than the reference edge node synchronization load, it is determined to be a level 2 response priority, and the preset personnel are prompted to maintain the current CPU and memory resource allocation status of the water treatment management platform. The priority of a Level 1 response is higher than that of a Level 2 response.

5. The water treatment management method based on big data as described in claim 4, characterized in that, The load balancing verification specifically includes: The real-time load data of all edge sensor nodes in the statistical water treatment management platform is collected. Based on the acquired real-time load data, the deviation rate between the load value of each edge node and the corresponding average load value is calculated to obtain the deviation rate of each edge sensor node. The deviation rate is then summed to obtain the average load balancing deviation. The real-time load data includes processor utilization, memory utilization, and data transmission rate. If the obtained average load balancing deviation is not greater than the reference average load balancing deviation, it is determined that the load balancing meets the standard and the current resource allocation status is maintained. At the same time, a load balancing report is generated to visualize the load fluctuation of each edge sensor node in the water treatment management platform. If the obtained average load balancing deviation is greater than the reference average load balancing deviation, it is determined that the load balancing performance is not up to standard and node migration optimization is performed. The node migration optimization specifically includes: The obtained average load balancing deviation is input into the influent state prediction dataset. Based on the mapping relationship between the average load balancing deviation stored in the influent state prediction dataset and the increase in data cache quota, the data cache quota adjustment target of the current water treatment management platform is obtained to dynamically adapt to the real-time load demand of each edge sensor node and alleviate the data processing pressure of high-load nodes. After node migration optimization, if the newly obtained average load balancing deviation is greater than the reference average load balancing deviation, a load balancing warning will be issued; otherwise, the load balancing will be deemed to meet the standard.

6. The water treatment management method based on big data as described in claim 1, characterized in that, The water treatment management response also includes: The current rainfall level is obtained and a response management level is defined. The response management level includes Level 1 response management, Level 2 response management and Level 3 response management. The Level 1 response management, Level 2 response management and Level 3 response management correspond to different risk levels and handling complexities caused by rainfall levels from low to high, respectively. After the response management level is classified, the average response management time of the water treatment management platform during the response management level classification process is obtained, and response management optimization is determined.

7. The water treatment management method based on big data as described in claim 6, characterized in that, The specific steps for the response management optimization determination are as follows: If the average response management time obtained is not greater than the reference average response management time, the response management of the water treatment management platform is deemed qualified and the deviation level between the current tap water treatment status and the expected water quality target is determined. If the average response management time obtained is greater than the reference average response management time, the response management of the water treatment management platform is deemed unqualified and an abnormal response management feedback is issued. The response management anomaly feedback is used to prompt the water treatment management platform to verify the peak data transmission latency of water treatment data in order to determine whether manual calibration is required. The peak data transmission delay is used to reflect the maximum time taken for water treatment data to travel from the acquisition node to the transmission process in the water treatment management platform.

8. The water treatment management method based on big data as described in claim 1, characterized in that, The specific process for determining the deviation level is as follows: Get the synchronization state matching time and the tap water treatment response preparation time. Simultaneously, retrieve the stored reference synchronization state matching time and reference tap water treatment response preparation time from the water inlet state prediction dataset, and perform ratio processing on them respectively to obtain the synchronization state matching time score and the tap water treatment response preparation time score. The summation of the synchronization state matching time score and the tap water treatment response preparation time score yields the prediction parameter deviation. When the deviation of the obtained prediction parameters is a first-level deviation, it indicates that the current tap water treatment status matches the expected water quality target, and first-level management measures should be implemented. When the deviation of the obtained prediction parameters is a secondary deviation, it indicates that the current tap water treatment status does not match the expected water quality target, and secondary management measures should be implemented. The first-level deviation and the second-level deviation correspond to the degree of matching between the tap water treatment status and the expected water quality target, from high to low, respectively.

9. The water treatment management method based on big data as described in claim 8, characterized in that, The specific steps for triggering corresponding emergency management measures based on the obtained deviation level are as follows: The specific steps of the first-level management measures are as follows: based on the currently acquired prediction parameter deviation, input it into the mapping table of the first-level management stored in the water influent status prediction dataset, so as to increase the water influent status collection frequency of the current water treatment management platform. The specific steps of the secondary management measures are as follows: Based on the primary management measures, the currently acquired prediction parameter deviation is input into the mapping table of secondary management stored in the water inflow state prediction dataset to prompt the preset personnel to conduct manual inspection. During the implementation of management measures, the water treatment management platform automatically generates a restart delivery command to prompt the pre-set personnel to check for impurities in the tap water delivery pipeline. After completing a delivery process, the platform inputs the monitored water treatment management data into the influent status prediction dataset for storage and updating.

10. A water treatment management system based on big data, employing the water treatment management method based on big data as described in any one of claims 1-9, characterized in that, include: The system includes a multi-dimensional parameter acquisition module for pre-treatment of tap water, a synchronous matching management module for tap water treatment status, and an emergency management module for predicting water quality targets. The multi-dimensional parameter acquisition module before tap water treatment is used to simultaneously acquire multi-dimensional meteorological parameters and rainwater environmental parameters during the meteorological forecast integration stage, after the water treatment management platform receives rainfall warning information and within the divided rainwater collection time period. The synchronous matching management module for the tap water treatment status is used to synchronously match the acquired multi-dimensional meteorological parameters and rainwater environmental parameters with the current tap water treatment status, and at the same time, to perform tap water treatment management response based on the acquired water treatment data. The emergency management module for the predicted water quality target status is used to compare the results of the synchronization status matching with the results of the tap water treatment response preparation to determine the deviation level between the current tap water treatment status and the expected water quality target, and to trigger corresponding emergency management measures based on the obtained deviation level.

Images