Intelligent monitoring and aeration control system for rural sewage based on internet of things

Abstract

The present application relates to the technical field of rural sewage treatment, and discloses a rural sewage intelligent monitoring and aeration regulation system based on the Internet of Things. The system comprises a pollution parameter sensing layer, a pollution index analysis layer, an aeration path generation layer, a process parameter matching layer, a dynamic monitoring focusing layer, a cross-modal mapping layer, an equipment scheduling decision layer and an aeration parameter generation layer. The pollution parameter sensing layer collects operation parameters in real time by using multi-source sensing terminals; the pollution index analysis layer divides the pollution parameter interval and calculates the distribution coefficient; the aeration path generation layer generates an aeration intensity grading path accordingly; the process parameter matching layer outputs a process deviation parameter set; the dynamic monitoring focusing layer adjusts the monitoring point density; the cross-modal mapping layer establishes a space-time correlation mapping of water quality parameters and aeration intensity; the equipment scheduling decision layer sorts the aeration equipment calling sequence; and the aeration parameter generation layer is converted into executable regulation parameters. The system realizes intelligent monitoring and precise aeration regulation of rural sewage.

Description

Technical Field

[0001] This invention relates to the field of rural sewage treatment technology, specifically to an intelligent monitoring and aeration control system for rural sewage based on the Internet of Things. Background Technology

[0002] Rural wastewater treatment is an important component of improving the rural living environment, but its process faces numerous challenges. Currently, rural wastewater treatment facilities are mostly located in remote areas with complex geographical environments and a lack of professional operation and maintenance personnel, resulting in unstable treatment effects. Traditional wastewater treatment monitoring methods rely heavily on manual inspections, which are not only time-consuming and labor-intensive but also suffer from low monitoring frequency and data lag, making it difficult to monitor wastewater quality changes and the operational status of treatment facilities in real time.

[0003] In terms of aeration control, existing systems mostly operate with fixed parameters, making it impossible to dynamically adjust the aeration intensity based on the actual concentration of pollutants in the wastewater. When the concentration of pollutants in the wastewater suddenly increases, the fixed aeration intensity is insufficient to meet the treatment requirements, easily leading to substandard effluent quality; while when the pollutant concentration is low, continuous high-intensity aeration will result in energy waste and increased operating costs.

[0004] The layout of monitoring points for rural wastewater treatment facilities is usually fixed, making it difficult to flexibly adjust the monitoring density according to changes in water quality. In areas with significant water quality fluctuations, fixed monitoring points may fail to detect anomalies in a timely manner, affecting the precise control of the wastewater treatment process; while in areas with stable water quality, too many monitoring points lead to idle resources. These problems hinder the improvement of rural wastewater treatment efficiency and impede the improvement of the rural ecological environment. Summary of the Invention

[0005] The purpose of this invention is to provide an intelligent monitoring and aeration control system for rural sewage based on the Internet of Things, so as to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides an intelligent monitoring and aeration control system for rural sewage based on the Internet of Things, the system comprising:

[0007] The pollution parameter sensing layer collects the operating parameters of the sewage treatment facility in real time through multi-source sensor terminals;

[0008] The pollution index analysis layer obtains the operating parameters of the wastewater treatment facilities, divides the pollution parameter ranges according to the operating parameters, and calculates the pollution index allocation coefficient.

[0009] Aeration path generation layer generates aeration intensity classification paths based on pollution index allocation coefficients.

[0010] The process parameter matching layer compares the current process parameters with the preset process parameter thresholds and outputs a set of process deviation parameters.

[0011] Dynamic monitoring of the focusing layer dynamically adjusts the monitoring point density of the multi-source sensor terminal based on the set of process deviation parameters;

[0012] The cross-modal mapping layer synchronously receives the monitoring point distribution data of the dynamic monitoring focusing layer and the aeration intensity classification path of the aeration path generation layer, and establishes a spatiotemporal correlation mapping between water quality parameters and aeration intensity.

[0013] The equipment scheduling decision-making layer sorts the order of aeration equipment calls according to the spatiotemporal correlation mapping results;

[0014] The aeration parameter generation layer converts the order of aeration equipment calls into executable aeration control parameters.

[0015] Preferably, the system further includes:

[0016] The aeration effect feedback layer is connected to the aeration parameter generation layer. It compares the changes in water quality parameters before and after the aeration control parameters are executed, and dynamically corrects the pollution parameter interval division logic based on the changes in water quality parameters.

[0017] Preferably, the pollution index analysis layer includes:

[0018] Obtain the maximum pollution load range of the wastewater treatment facility and divide the pollution load range into several parameter intervals equally.

[0019] Extract the pollutant type and concentration threshold from the operating parameters, and look up the corresponding pollution characteristic curve in the pollution characteristic comparison table;

[0020] The pollution index allocation coefficient for each parameter interval is obtained through the pollution index allocation coefficient calculation model.

[0021] The number of monitoring points corresponding to each parameter interval is calculated based on the pollution index allocation coefficient.

[0022] A number of key monitoring points are evenly distributed within the corresponding parameter range.

[0023] Preferably, the aeration path generation layer includes:

[0024] The key monitoring point with the highest pollution index allocation coefficient is marked as a heavily polluted monitoring point.

[0025] The key monitoring point with the lowest pollution index allocation coefficient is marked as a light pollution monitoring point;

[0026] Obtain the pollution value of the pollution characteristic curve corresponding to the initial monitoring point;

[0027] Determine whether the difference between the pollution value at a heavily polluted monitoring point and the pollution value at the initial monitoring point is greater than the difference between the pollution value at a lightly polluted monitoring point and the pollution value at the initial monitoring point;

[0028] If true, a first aeration path is generated from the initial monitoring point to the heavily polluted monitoring point, a second aeration path is generated from the heavily polluted monitoring point back to the initial monitoring point, and a third aeration path is generated from the initial monitoring point to the lightly polluted monitoring point.

[0029] If not, a first aeration path is generated from the initial monitoring point to the lightly polluted monitoring point, a second aeration path is generated from the lightly polluted monitoring point back to the initial monitoring point, and a third aeration path is generated from the initial monitoring point to the heavily polluted monitoring point.

[0030] The first aeration path, the second aeration path, and the third aeration path are integrated to form an aeration intensity classification path.

[0031] Preferably, the process parameter matching layer includes:

[0032] Calculate the absolute deviation between the current process parameters and the preset process parameter thresholds;

[0033] Calculate the weighted sum of dissolved oxygen deviation, biochemical oxygen demand deviation, and suspended solids deviation;

[0034] When the weighted sum exceeds the process tolerance threshold, the corresponding parameter range is marked as the process deviation parameter set.

[0035] Preferably, the dynamic monitoring focusing layer includes:

[0036] Identify the key monitoring points covered by the set of process deviation parameters, and upgrade the area where the key monitoring points are located into a dense monitoring area;

[0037] The area covered by the non-process deviation parameter set is downgraded to a sparse monitoring area, the dense monitoring area adopts a high-frequency sampling mode, and the sparse monitoring area adopts a low-frequency sampling mode.

[0038] Preferably, the cross-modal mapping layer includes:

[0039] Establish timestamp alignment between water quality parameter change curves and aeration intensity grading paths in densely monitored areas;

[0040] The water quality parameter fluctuation characteristics corresponding to each node in the aeration intensity grading path are labeled, and a correlation mapping table between water quality parameter fluctuation characteristics and aeration intensity level is generated.

[0041] Preferably, the equipment scheduling decision layer includes:

[0042] Extract nodes that meet the aeration intensity level from the association mapping table, sort the aeration equipment call priority according to the duration of node compliance, and merge consecutively compliant nodes into the efficient operation range of the aeration equipment.

[0043] Preferably, the aeration parameter generation layer includes:

[0044] The efficient operating range of the aeration equipment is converted into a step-by-step instruction for the speed of the aeration blower. A blower start-stop sequence is generated according to the priority of the aeration equipment. The step-by-step instruction for the speed of the aeration blower and the blower start-stop sequence are combined to form executable aeration control parameters.

[0045] Preferably, the aeration effect feedback layer includes:

[0046] Record the baseline water quality parameters at key monitoring points before executing the executable aeration control parameters, collect the real-time water quality parameters at the same key monitoring points after execution, and calculate the absolute change of the real-time water quality parameters relative to the baseline water quality parameters.

[0047] When the absolute change does not reach the expected improvement threshold, increase the number of monitoring points in the corresponding parameter range;

[0048] When the absolute change continues to exceed the expected improvement threshold, the number of monitoring points in the corresponding parameter range will be reduced.

[0049] Update the weighting coefficients of the pollution characteristic curves in the pollution characteristic comparison table.

[0050] Compared with the prior art, the beneficial effects of the present invention are:

[0051] Through the multi-source sensor terminal of the pollution parameter sensing layer, the operating parameters of the wastewater treatment facility can be collected in real time, allowing managers to understand the changes in various indicators during the wastewater treatment process in a timely manner, breaking the limitations of traditional manual monitoring. The pollution index analysis layer divides the pollution parameter ranges based on the operating parameters and calculates the allocation coefficients, providing a scientific basis for subsequent aeration control and making the assessment of the degree of wastewater pollution more accurate.

[0052] The aeration path generation layer generates aeration intensity grading paths based on the pollution index allocation coefficient, changing the previous fixed aeration intensity operation mode. This allows for adjustments to the aeration strategy according to the actual pollutants in the wastewater, making the aeration process more aligned with the actual needs of wastewater treatment. The process parameter matching layer compares the current process parameters with preset thresholds, outputting a set of process deviation parameters. This helps to promptly identify problems in the wastewater treatment process and provides direction for process adjustments.

[0053] The dynamic monitoring focusing layer dynamically adjusts the monitoring point density based on the set of process deviation parameters, increasing monitoring points in areas with large water quality fluctuations and decreasing them in areas with stable water quality. This achieves a rational allocation of monitoring resources, ensuring timely detection of water quality anomalies while avoiding resource waste. The cross-modal mapping layer establishes a spatiotemporal correlation mapping between water quality parameters and aeration intensity, combining monitoring point distribution data with aeration intensity grading paths to clarify the relationship between the two and provide a more comprehensive reference for equipment scheduling.

[0054] The equipment scheduling decision layer sorts the aeration equipment call order based on the spatiotemporal correlation mapping results, which makes the operation of the aeration equipment more orderly and improves the utilization efficiency of the equipment. The aeration parameter generation layer transforms the equipment call order into executable control parameters, ensuring the effective execution of aeration control commands, forming a closed loop in the entire aeration process, and improving the stability and reliability of wastewater treatment. Attached Figure Description

[0055] Figure 1 This is a timing diagram of the IoT-based intelligent monitoring and aeration control system for rural sewage described in this invention.

[0056] Figure 2 A flowchart for pollution index analysis;

[0057] Figure 3 A flowchart generated for the aeration path;

[0058] Figure 4 A flowchart for matching process parameters;

[0059] Figure 5 This is a flowchart of cross-modal mapping. Detailed Implementation

[0060] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0061] Please see Figure 1 This invention provides an intelligent monitoring and aeration control system for rural sewage based on the Internet of Things. The system includes: intelligent operation of sewage treatment facilities through the synergistic effect of a pollution parameter sensing layer, a pollution index analysis layer, an aeration path generation layer, a process parameter matching layer, a dynamic monitoring focusing layer, a cross-modal mapping layer, an equipment scheduling decision layer, and an aeration parameter generation layer.

[0062] The pollution parameter sensing layer collects real-time operating parameters of the wastewater treatment facility through multi-source sensor terminals, including key indicators such as dissolved oxygen concentration, biochemical oxygen demand (BOD), and suspended solids concentration. The pollution index analysis layer divides pollution parameter intervals based on operating parameters and calculates pollution index allocation coefficients, providing a quantitative basis for subsequent aeration control. The aeration path generation layer generates aeration intensity grading paths based on the pollution index allocation coefficients, guiding the operation strategy of aeration equipment. The process parameter matching layer compares current process parameters with preset thresholds, outputting a set of process deviation parameters. The dynamic monitoring focusing layer adjusts the monitoring point density accordingly, optimizing data acquisition efficiency. The cross-modal mapping layer establishes a spatiotemporal correlation mapping between water quality parameters and aeration intensity. The equipment scheduling decision layer sorts the aeration equipment call order based on the mapping results. Finally, the aeration parameter generation layer outputs executable aeration control parameters, completing closed-loop control.

[0063] Example 1: See Figure 2 Before the pollution index analysis layer begins operation, the multi-source sensor terminal has completed parameter collection for the entire wastewater treatment facility. Operating parameters include dynamic data such as dissolved oxygen concentration, biochemical oxygen demand (BOD), chemical oxygen demand (COD), suspended solids (SS) concentration, ammonia nitrogen content, and pH. All data is encrypted and packaged via IoT transmission protocol and transmitted to the central processing unit of the analysis layer. The system's preset maximum pollution load range is set according to the wastewater treatment facility's design capacity, and this range is divided into a fixed number or a dynamic number of parameter intervals. In dynamic division mode, the number of intervals is automatically adjusted based on real-time pollution load fluctuations: the number of intervals increases when the load fluctuation rate exceeds a set threshold, and the baseline number of intervals is maintained when the load is stable.

[0064] The pollution characteristic lookup table is stored in a cloud database and contains a two-dimensional index structure. The first dimension is the pollutant type code, and the second dimension is the concentration threshold classification table. When a compound pollutant is identified in the received operating parameters, the system activates the pollutant combination query mode. In this mode, the lookup table calls the pollutant synergistic effect matrix, which pre-inputs the kinetic characteristics of the interactions between different pollutant combinations at specific concentration ratios. The pollution characteristic curves are characterized by curve equation parameters, including sixteen characteristic values ​​such as the pollutant diffusion decay coefficient, reaction rate constant, and saturation critical point. Each curve corresponds to a unique characteristic curve identifier code.

[0065] The pollution index allocation coefficient calculation model employs a three-tiered architecture. The first layer handles basic parameter normalization, converting operating parameters of different dimensions into standard pollution equivalent values. The second layer performs interval positioning, determining the position of the current pollution equivalent value within the parameter interval based on the maximum total pollution load span and the current parameter interval width. The third layer activates pollution characteristic curve matching, retrieving the corresponding curve equation using the characteristic curve identifier. The core of the calculation model includes a feature value weight allocation module, which incorporates an environmental impact factor evaluation table. The weight coefficients for heavy metal pollutants are higher than those for organic pollutants, and the correction values ​​for the decay coefficients of persistent pollutants are higher than those for degradable pollutants. The pollution index allocation coefficients are obtained by multiplying the characteristic curve equations by the weight coefficients, ultimately outputting a floating-point allocation coefficient value for each parameter interval.

[0066] The number of monitoring points is calculated using a proportional allocation method. The system presets a constant total number of basic monitoring points for the entire region. The number of monitoring points for a specific parameter interval is determined by the percentage of the pollution index allocation coefficient for that interval relative to the sum of allocation coefficients for all intervals. The specific calculation formula is: Number of monitoring points in an interval = Total number of basic monitoring points × (Allocation coefficient for this interval / Sum of allocation coefficients for all intervals). This calculation is automatically triggered after each parameter interval is divided, and the result is rounded down. When the increment of the allocation coefficient for a parameter interval exceeds twice the standard deviation of the historical mean, an emergency monitoring mechanism is triggered, and the number of preset emergency monitoring points is temporarily increased for that interval.

[0067] The deployment of key monitoring points follows the principle of spatial uniformity. In the rectangular processing pool scenario, the system rasterizes the physical region corresponding to each parameter range, with the grid side length adjusted inversely proportionally to the number of monitoring points. A key monitoring point is deployed at the center of each grid. Irregular areas are handled using triangular mesh generation technology, generating a Delaunay triangulation with monitoring points as vertices to ensure spatial uniformity of monitoring point distribution. The coordinate information of the monitoring points is synchronized to the dynamic monitoring focusing layer in real time, with the position offset tolerance controlled within five centimeters.

[0068] The pollution index analysis layer establishes a dual-verification mechanism to ensure data reliability. The allocation coefficients generated in the initial calculation must be verified by comparison with a historical database. When the allocation coefficient for a specific parameter interval deviates from three standard deviations of the historical mean for that interval, a manual review process is triggered. The system generates a 3D visualization report including a scatter plot of pollution parameters, a calculation tree of allocation coefficients, and a heatmap of interval divisions. Operators can manually adjust the parameter interval boundaries through an interactive interface. The confirmed parameter division scheme automatically updates the pollution characteristic comparison table weight library, enhancing the computational adaptability to similar pollution scenarios. Upon completion of the entire analysis process, the system outputs a timestamped pollution index distribution map, which is transmitted to the aeration path generation layer via a high-speed data bus.

[0069] The data flow closed-loop management adopts a two-way verification mode. Multi-source sensor terminals upload a snapshot of the original parameters every 30 seconds. After generating the monitoring point deployment plan, the analysis layer randomly selects 10% of the monitoring point deployment coordinates for reverse verification. During verification, a test command is sent to the specified coordinate point, and the sensor terminal returns the actual monitored value for the current coordinate. When the deviation between the theoretical parameter value corresponding to the deployment coordinate and the actual monitored value exceeds a preset error limit, the system automatically marks the area as an abnormal grid and re-executes the parameter interval division calculation. Abnormal grid data is stored in a separate log file, triggering the offline training process of the deep learning model.

[0070] The system is configured with a three-tiered pollution early warning and response strategy. The Level 1 response is activated when the allocation coefficient in a single parameter range exceeds the safety threshold, automatically notifying on-site management personnel. The Level 2 response is activated when an abnormal increase in the allocation coefficient occurs over three consecutive calculation cycles, forcibly increasing the monitoring frequency of the abnormal area. The Level 3 response is triggered when multiple parameter ranges simultaneously exceed limits, directly linking the aeration parameter generation layer to execute an emergency aeration plan. Each response level corresponds to an independent message notification template and equipment control command set, with the response level priority dynamically increasing according to the pollution index.

[0071] The maintenance cycle is set using an adaptive algorithm. The analysis layer runs a device health assessment program in the background, calculating a system maintenance requirement index based on twelve performance indicators, including data processing latency, peak memory usage, and network packet loss rate. When the index exceeds a critical value, a hardware inspection list is pushed to the operations and maintenance platform, specifying the exact device number requiring maintenance. All operation records are distributed and stored on blockchain nodes, forming an immutable audit trail of the analysis process. After each version upgrade, the analysis layer automatically performs a 48-hour gray-scale calculation, comparing the analysis results of the old and new versions. If the difference rate exceeds the limit, it rolls back to the previous stable version.

[0072] Example 2: See Figure 3 After the pollution index analysis layer completes the parameter range division and pollution index allocation coefficient calculation, the aeration path generation layer begins to construct the aeration intensity classification path. The system first receives the pollution index allocation coefficient set for all key monitoring points from the pollution index analysis layer; this set is stored indexed by the monitoring point's coordinate location. The pollution status of each monitoring point is classified using a three-color labeling system: red indicates a heavily polluted monitoring point with the highest pollution index allocation coefficient, green indicates a lightly polluted monitoring point with the lowest pollution index allocation coefficient, and yellow indicates an intermediate value monitoring point. The initial monitoring point is automatically selected by the system based on the structural characteristics of the wastewater treatment facility, typically located at the midpoint of the line connecting the inlet and the aeration equipment.

[0073] The comparison of pollution value differences uses a relative rate of change algorithm. The pollution value at a heavily polluted monitoring point is denoted as... The pollution value at the light pollution monitoring point is recorded as The pollution value at the initial monitoring point is recorded as The formula for comparing differences is:

[0074]

[0075] in: This is the difference in relative change rates, used to determine the generation order of aeration paths. When When the value is greater than zero, the system determines that the pollution difference between the heavily polluted monitoring point and the initial monitoring point is more significant; when When the value is less than or equal to zero, the difference between the monitoring point for slight pollution and the initial monitoring point is considered more significant. The denominator of this formula is normalized to the maximum value to eliminate the influence of different pollutant concentration dimensions.

[0076] The path generation engine comprises three levels of processing modules. The first level module handles path direction decisions, based on... The positive or negative value prioritizes the endpoint of the path. The second-level module calculates the path turning points. In the two-dimensional plane coordinates of the wastewater treatment facility, a polar coordinate system is established with the initial monitoring point as the origin, decomposing the aeration path into radial and tangential components. The third-level module generates the path intensity curve, the slope of which is proportional to the pollution index allocation coefficient of the endpoint monitoring point. During path generation, physical obstacles within the wastewater treatment facility are automatically avoided; obstacle information is obtained from the facility's three-dimensional model database.

[0077] The aeration intensity is graded using a dynamic interval division method. The system presets a three-level basic aeration intensity: high intensity corresponds to red monitoring points, medium intensity to yellow monitoring points, and low intensity to green monitoring points. During actual grading, adjustments are made based on the specific pollution index values ​​at the monitoring points, with the adjustment range not exceeding 20% ​​of the basic intensity. Changes in aeration intensity along each path segment use a ramp function to avoid mechanical impact on the aeration equipment. The aeration intensity at path turning points is taken as the weighted average of the intensities of adjacent paths, with the weight determined by the turning angle.

[0078] The path integration algorithm employs spatiotemporal constraint optimization. The first aeration path serves as the main path, with its aeration intensity change rate set to a standard value. The second aeration path serves as the return path, with its intensity attenuation coefficient set to 1.5 times that of the first path. The third aeration path serves as the auxiliary path, with its intensity fluctuation range controlled within 60% of that of the main path. In the temporal dimension, the three paths employ a staggered start strategy: the return path starts five seconds after the main path starts, and the auxiliary path starts ten seconds later. Spatially, the minimum distance between any two paths is ensured to be greater than the influence radius of the aeration equipment.

[0079] The aeration equipment control parameter converter transforms path information into execution commands. The path coordinate point sequence is smoothed into a curve using cubic spline interpolation, with the interpolated coordinate points spaced at a fixed interval of ten centimeters. Each interpolation point is associated with three control parameters: aeration fan speed percentage, aeration duration, and delay interval. The speed percentage is determined by the intensity level of the path segment in which the point is located, and stepless speed regulation is achieved using pulse width modulation technology. The base aeration duration is two seconds, dynamically adjusted according to the pollutant degradation rate in the area where the path point is located. The delay interval ensures that the action time of adjacent aeration points does not overlap, with a minimum interval set to 0.5 seconds.

[0080] The path verification mechanism includes real-time feedback correction. During aeration, the three nearest monitoring points form a verification triangle to monitor the dissolved oxygen concentration change rate in real time. When the deviation between the actual and expected change rates exceeds a threshold, the system automatically inserts a correction path point. The aeration intensity at the new path point is adjusted proportionally to the deviation, forming an intensity compensation gradient at the subsequent three path points. Correction records are stored in the path correction log for optimizing subsequent path generation algorithms. After each path execution, an execution report is generated, containing the actual path trajectory, intensity distribution curve, and correction point locations.

[0081] The anomaly handling module is designed with specific strategies for four typical operating conditions. The first is path interruption: when the aeration equipment unexpectedly stops during path execution, the system records the coordinates of the interruption point and activates nearby backup equipment. The second is monitoring point failure: when the data from the monitoring point at the path's end is abnormal, the system automatically switches to a backup monitoring point and recalculates the path. The third is sudden water quality changes: when a sudden surge in pollutant concentration occurs during path execution, the current path is immediately stopped and an emergency aeration mode is activated. The fourth is equipment conflict: when multiple aeration paths may interfere with each other in time and space, the system automatically calculates the optimal avoidance solution.

[0082] The historical path database is stored using a time-series graph structure. Each generated aeration path is encoded as a weighted directed graph, where nodes represent key points on the path, and edges represent path segments and their intensity attributes. The graph is stored with a 12-dimensional feature vector, including features such as total path length, average intensity, and variance of turning angles. The database supports similar operating conditions for retrieval; when the similarity between the current pollution distribution pattern and historical records exceeds a threshold, the best historical path is prioritized. The path optimization engine performs offline evolutionary calculations on all historical paths weekly, eliminating inefficient paths and generating variant path solutions.

[0083] The dynamic load balancing module manages the parallel execution of multiple paths. When a wastewater treatment facility needs to execute multiple aeration paths simultaneously, the system allocates path tasks based on the real-time operating status of the aeration equipment group. The allocation strategy considers three factors: remaining equipment lifespan, current load rate, and energy consumption efficiency, and uses a greedy algorithm to select the optimal equipment combination. A safety buffer is set between parallel paths, and the buffer size is proportional to the product of the path strength. The load balancing status is evaluated every 30 seconds, and when the overall load rate of the equipment group exceeds the warning line, the strength level of non-critical paths is automatically downgraded.

[0084] The aeration path generation layer is deeply integrated with the equipment maintenance system. Before each path execution, the system checks maintenance indicators such as the target aeration equipment's cumulative operating time, recent maintenance records, and performance degradation coefficient. For equipment nearing its maintenance cycle, the intensity requirement of its assigned path is automatically reduced. After path execution, the equipment operating status database is updated, with cumulative running time accurate to the second. When a piece of equipment is assigned a high-intensity path three times consecutively, a preventative maintenance reminder is triggered, suggesting early maintenance. Maintenance records and path generation logs are cross-indexed, forming a complete equipment lifecycle management chain.

[0085] Example 3: See Figure 4 The process parameter matching layer continuously receives the latest operating parameters from the pollution parameter sensing layer, including three core process indicators: dissolved oxygen, biochemical oxygen demand (BOD), and suspended solids concentration. Preset process parameter thresholds are dynamically updated according to wastewater treatment plant design specifications, and each indicator includes a safe operating range consisting of an upper and lower threshold. The absolute deviation between the current process parameter and its corresponding threshold is calculated in real time using the following formula:

[0086]

[0087] in: This represents the weighted sum of process deviations. This is the current measured value of dissolved oxygen concentration. The dissolved oxygen concentration threshold, This is the current measured value of biochemical oxygen demand. This is the threshold value for biochemical oxygen demand. This is the current measured value of suspended solids concentration. This represents the suspended solids concentration threshold. Weighting coefficients. The values ​​1 and 2 correspond to the sensitivity coefficients of the three pollutants to their environmental impact, and are preset in the weight library. The base ratio is automatically adjusted according to seasonal parameters.

[0088] Process tolerance threshold Determined through a two-layer mechanism. Base threshold. Dynamic correction values ​​taken from the design documents of wastewater treatment facilities Adjust proportionally based on the influent flow rate fluctuation rate. When the instantaneous flow rate exceeds 20% of the average flow rate, Increase the base threshold by 15%; when the flow rate is below 30% of the average flow rate, Reduce the base threshold by 10%. Final process tolerance threshold. .when When this happens, the system determines that there is a process deviation in the spatial region corresponding to this set of parameters.

[0089] The process deviation parameter set marker uses bitmap indexing technology. The wastewater treatment facility plane is divided into a 1m × 1m virtual grid, with each grid associated with an independent parameter status register. The high eight bits of the register store the dissolved oxygen status code, the middle eight bits store the biochemical oxygen demand (BOD) status code, and the low eight bits store the suspended solids (SSD) status code. When a parameter is triggered... When conditions are met, the corresponding status code is set to an exception flag. When three exception flags appear simultaneously, the area where the grid is located is marked as the coverage area of ​​the process deviation parameter set. The register status is refreshed every five seconds, and grids that maintain an exception status for three consecutive refresh cycles are confirmed as valid process deviation areas.

[0090] The dynamic monitoring focusing layer includes a monitoring density conversion engine. Key monitoring points are mapped to a virtual grid based on the coordinate distribution generated by the pollution index analysis layer. Each monitoring point carries a density grading identifier: baseline (D0), enhanced (D1), and simplified (D2). When the grid containing a monitoring point is marked as being within the coverage area of ​​the process deviation parameter set, the system performs the following operations: upgrades the point's density identifier to D1; locates all monitoring points within a three-meter radius of the point; and sends a density upgrade command to the sensor terminal of the target monitoring point. The upgrade command triggers a three-layer effect: the sampling frequency is adjusted from once every ten minutes for D0 level to once every three minutes; the data sampling mode is changed from single sampling to averaging of three consecutive samples; and the sensor terminal power supply mode is switched from energy-saving mode to high-performance mode.

[0091] The processing of non-process deviation areas employs a hierarchical dimensionality reduction strategy. Monitoring points not covered by the process deviation parameter set are automatically downgraded to D2 level in terms of density identifier. D2 level monitoring points follow a simplified monitoring procedure: the sampling frequency is extended to once every thirty minutes; the sampling mode is changed to single instantaneous sampling; and only the core sensor module is activated in the sensing terminal. For grid areas where no parameter anomalies have occurred for twelve consecutive cycles, the system initiates a deep sleep program. This program retains the coordinate information of the monitoring points but suspends actual sampling, estimating parameter values ​​only through spatial interpolation using data from adjacent monitoring points. When abnormal fluctuations occur in the surrounding area, the deep sleep point can resume full-function monitoring within 0.5 seconds.

[0092] The management of densely monitored areas employs a clustered collaborative mechanism. All D1-level monitoring points are clustered according to their physical location, forming monitoring clusters with a radius not exceeding five meters. Within each cluster, a master node is elected to coordinate the process. The master node automatically matches the sampling protocol based on the pollution characteristics within the cluster. For clusters primarily polluted by organic matter, the master node instructs member nodes to focus on collecting BOD and COD parameters; for clusters polluted by inorganic matter, the focus is on collecting heavy metal ions and SS parameters. Data transmission within the cluster uses direct device communication technology, establishing a star topology network between nodes. Sampling data is initially fused at the master node before being uploaded to the cloud. This structure reduces network traffic by 60%.

[0093] The sparse monitoring area is optimized using a mobile sensing strategy. In the D2-level monitoring point distribution area, a mobile verification sensor is deployed. This device automatically cruises along a preset inspection route, covering key coordinate points in all sparse areas. When the verification sensor reaches the target area, it wakes up nearby dormant fixed monitoring points to perform synchronous sampling. The sampling results from the fixed monitoring points are cross-validated with the measured values ​​from the mobile sensor; monitoring points with a deviation exceeding 10% are marked as suspicious nodes. Fixed monitoring points that fail three consecutive verifications trigger a position calibration procedure, and equipment maintenance personnel receive a maintenance work order containing GPS offset data.

[0094] The monitoring mode transition process incorporates a state buffer isolation zone. When a region transitions from a non-deviation zone to a process deviation zone, the system generates a two-meter-wide transition zone around that region. Monitoring points within the transition zone maintain a D0-level density, but the sampling frequency is increased to once every five minutes. This buffer design avoids data discontinuity caused by sudden changes in monitoring density. Correspondingly, when the process deviation disappears, the original dense monitoring area retains a six-hour observation period, during which a D1-level monitoring density is maintained, but the cluster coordination mechanism is disabled. After the observation period ends without any abnormal recurrence, the region gradually degrades to D0 level and eventually enters the D2 level state.

[0095] A dynamic strategy database stores monitoring mode configuration parameters. This database contains twelve monitoring scenario templates: a high-nitrogen pollution scenario enhances ammonia nitrogen monitoring frequency, and a high-salinity wastewater scenario adds conductivity monitoring. The scenario identifier analyzes the pollution characteristics of the process deviation parameter set, automatically matching the high-nitrogen scenario template when ammonia nitrogen anomalies exceed 50%. After template application, the monitoring point density grading standard is reconfigured: the ammonia nitrogen collection frequency in D1-level areas is increased to once per minute, while the SS monitoring frequency is reduced. Template switching records are saved to the version history database, and an impact assessment is performed each time a template is updated to avoid system instability caused by frequent switching.

[0096] The resource allocation monitoring module implements dynamic load balancing. The system continuously monitors the proportion of D1-level monitoring points to the total number of points. When this proportion exceeds 30%, a resource optimization program is initiated. The program calculates the optimal transmission compression ratio based on three indicators: network bandwidth utilization, edge computing node load, and cloud platform processing queue depth. Monitoring data is switched from raw transmission to differential compression transmission, with the compression algorithm achieving a compression ratio of up to 10:1 for duplicate data. When the server load continuously exceeds the warning threshold, the system automatically activates a data tiering mechanism: core process parameters are maintained in real-time transmission, while secondary parameters are cached locally and then uploaded in batches.

[0097] Example 4: See Figure 5 The cross-modal mapping layer receives the dense monitoring area distribution matrix output by the dynamic monitoring focusing layer. This matrix identifies area 3 on the east side of a wastewater treatment pond as the current dense monitoring area, with coordinates ranging from X12 to Y18. Simultaneously, it receives the aeration intensity classification path data packet generated by the aeration path generation layer. Path number PATH007 contains twenty-three path nodes. The spatiotemporal correlation engine initiates a timestamp alignment procedure, extracting the dissolved oxygen change curve of monitoring point 12 (coordinates X15-Y16) in area 3 (region 3) from the water quality monitoring database over the past fifteen minutes. Its timestamp sequence is T0 (13:00:00), T1 (13:05:30), and T2 (13:11:15). Path PATH007 contains three key behavioral points within the same time period: aeration device A starts operating at T0, device B joins the collaboration at T1, and device C takes over at T2. The system binds the water quality sampling data at time T1 with the start command of device B as a synchronization event group.

[0098] The water quality parameter fluctuation characteristic analyzer extracted the parameter change pattern of monitoring point 12 within the time window. Dissolved oxygen concentration increased from 1.2 mg / L to 2.4 mg / L during the T0-T1 period, an increase of 0.24 mg / L per minute; biochemical oxygen demand (BOD) decreased from 85 mg / L to 78 mg / L, a decrease rate of 1.4 mg / L / min; suspended solids concentration fluctuated within ±5 mg / L. This characteristic was encoded as a fluctuation characteristic code of type "F013", containing three core attributes: dissolved oxygen rise gradient value, BOD decrease persistence, and suspended solids variation coefficient. Simultaneously, the operating parameters of PATH007 path recording device B were: aeration intensity level V (corresponding to 65% blower speed), single-point aeration duration of 180 seconds, and bubble diameter of 0.8 mm. The system established a mapping relationship between characteristic code F013 and aeration intensity level V, storing it in an association mapping table.

[0099] The equipment scheduling decision layer scanned the correlation mapping table and identified that monitoring point 12 continuously met the aeration intensity standard during the T1-T2 period. This period included four consecutive sampling cycles, with the dissolved oxygen concentration maintained above the 2.0 mg / L threshold in each cycle, for a total compliance time of 625 seconds. The system merged these four consecutive compliance nodes into a single high-efficiency aeration operation zone, labeled EFF_ZONE08. The high-efficiency zone triggered a reordering of equipment scheduling priorities: the currently operating equipment B was promoted to the top priority, and subsequent path nodes were sorted according to compliance time, forming the equipment scheduling sequence DEV_SEQ: B(625s)-C(480s)-A(320s). The 480 seconds for equipment C in the sequence originated from its historical compliance record at the neighboring monitoring point 11.

[0100] The aeration parameter generation layer converts the parameters within the EFF_ZONE08 range. The aeration blower speed command is generated in three stages based on the high-efficiency range characteristics: maintaining 65% speed in the initial stage (first 200 seconds), increasing to 70% in the middle stage (200-500 seconds), and decreasing to 60% in the final stage (last 125 seconds). The blower start / stop sequence is determined according to the DEV_SEQ sorting result: device B is started first and runs for 625 seconds, followed by device C after a 90-second delay and running for 480 seconds; device A is on standby. The final aeration control parameter package contains command pairs.

[0101] Table 1: Aeration control parameters are as follows The parameter execution verification mechanism is activated after the equipment starts. The dissolved oxygen rise slope at monitoring point 12 is monitored in real time. When the measured slope deviates from the F013 characteristic benchmark value by 15%, a dynamic compensation program is triggered. The compensation logic includes a three-level response: Level 1 fine-tunes the rotation speed by ±3%, Level 2 extends the current step duration by 10%, and Level 3 activates backup equipment A for collaboration. At time T1+300 seconds, a 12% decrease in dissolved oxygen increase is detected, and the system automatically triggers Level 1, increasing the rotation speed of equipment B to 68%. After adjustment, the measured data for the 300-400 second period returns to the benchmark range, and the compensation process is recorded in the execution log.

[0102] The aeration equipment collaborative management module handles equipment resource conflicts. Path PATH007 has planned a new path node at coordinates X14-Y17, which requires devices B and C to be active simultaneously. The system detects that device B is already running at X15-Y16, calculates the distance between the two coordinates to be 3.2 meters (greater than the minimum safe distance of 2.5 meters), and determines that parallel operation is possible. When device C starts, it receives a collaborative instruction packet and dynamically adjusts its aeration angle deflection by 15 degrees to avoid mutual airflow interference. In the last 60 seconds before device B stops, the system preheats the fan of device C to standby speed, achieving seamless switching between operating ranges.

[0103] The historical pattern matching engine archives the current scenario. The system extracts the feature vector of the EFF_ZONE08 interval (including sixteen parameters such as influent COD load, water temperature 24℃, and pH value 7.2) and performs similarity matching with the historical case library. When a similar operating condition occurs in the future (similarity > 85%), the system can directly call the CMD_20240718_B001 instruction template, only needing to adjust the runtime volume coefficient according to the real-time flow. The template optimizer re-evaluates the validity period of historical instructions monthly; templates older than three months must be verified through water quality improvement before they can be reused.

[0104] Example 5: The aeration effect retrospective layer initiates process monitoring after the aeration parameter generation layer issues an executable control command. The system locks onto the key area affected by the control command, which covers key monitoring points within a four-meter radius centered on the coordinates of the aeration equipment. Three batches of data are collected within 300 seconds before aeration, with each batch spaced 100 seconds apart. The collected indicators include three core parameters: dissolved oxygen concentration, ammonia nitrogen content, and oxidation-reduction potential. The baseline water quality parameters are calculated as the arithmetic mean of the three samples, timestamped, and stored in a dedicated baseline data area. The baseline water quality parameter database and the real-time dynamic monitoring stream form a dual-channel comparison architecture.

[0105] After executing the aeration control parameters, a countdown observation window is opened, with the total observation time equal to 1.5 times the set operating time of the aeration equipment. Data from the target monitoring point is collected every 40 seconds within the observation window, and real-time water quality parameters are processed using a moving average algorithm. The baseline dissolved oxygen record value at a certain coordinate point X20-Y15 is 2.1 mg / L. After aeration begins, the data for three consecutive cycles are 2.4 mg / L, 2.6 mg / L, and 2.8 mg / L, with a moving average of 2.6 mg / L. The system calculates the absolute change as the difference between the real-time moving average and the baseline value; the absolute change in dissolved oxygen at this point is +0.5 mg / L. The expected improvement threshold is dynamically set according to the improvement coefficient table for the corresponding pollutants in the "Urban Wastewater Treatment Plant Operation Standard," and the current expected dissolved oxygen threshold is +0.7 mg / L.

[0106] Comparator analysis revealed that the absolute change in dissolved oxygen was 0.5 mg / L, which was less than the expected threshold of 0.7 mg / L. The system then activated the monitoring point expansion procedure. The parameter interval code Z09 to which the coordinate point belonged was queried, and an expansion request was sent to the pollution index analysis layer. The expansion operation involved three steps: retrieving the number of existing monitoring points in interval Z09 (the baseline number was six); adding two mobile monitoring points, using a triangulation algorithm to distribute them along the interval edge; and configuring high-precision dissolved oxygen sensors on the new points, increasing the sampling frequency to three times per minute. Simultaneously, the ammonia nitrogen parameter showed a change exceeding the expected threshold by 40%, triggering a monitoring point simplification process. The number of monitoring points in the adjacent interval Z08 was reduced from seven to four, and the activation permissions for edge monitoring points M21, M22, and M25 were revoked.

[0107] The pollution characteristic comparison table is updated using an incremental revision strategy. The pollution characteristic curve identifier CT207 for coordinate point X20-Y15 is extracted from the backtrack layer. This curve describes the correlation model between ammonia nitrogen degradation characteristics and aeration intensity. The system obtains the ammonia nitrogen concentration curve shapes before and after aeration: the curve slope decay rate before aeration is 0.15 mg / L·min, which is optimized to 0.24 mg / L·min after aeration. Based on this, the weight coefficient of curve CT207 is increased by 8% of the original value. Simultaneously, comparing the redox potential change curve in the same area, it is found that the actual improvement is lower than the curve's predicted value; therefore, the weight coefficient of curve CT209 is decreased by 6%. The weight coefficient adjustment adopts a gradient control mechanism, with the maximum value of a single correction limited to 10% of the original weight to avoid excessive oscillations in the system response.

[0108] The pollution parameter interval division logic correction module works in conjunction with the pollution index analysis layer. The retrospective layer outputs a parameter interval adjustment proposal, suggesting three revisions for interval Z09: extending the interval boundary westward by 0.5 meters to include newly added monitoring points; revising the maximum pollution load limit of the interval from 185 mg / L to 195 mg / L; and upgrading the interval pollution level from Class B, Level III to Class B, Level II. Upon receiving the proposal, the analysis layer initiates interval re-division calculations, incorporating the aeration effect coefficient as a new parameter in the new pollution index allocation coefficient. For example, the original allocation coefficient for a certain monitoring point was 0.82; after adding the aeration effect coefficient of 0.93, it was updated to 0.76. The recalculation process covers all key monitoring points, generating a new pollution index distribution map and labeling it with the version number.

[0109] Data reliability verification incorporates a spatiotemporal consistency test. The system randomly selects 20% of monitoring points for backtesting: under the same aeration parameters, the system runs twice, collecting water quality change curves for waveform similarity analysis. Verification is considered successful if the peak position deviation of the dissolved oxygen change curve from three runs at a given point is less than three seconds and the amplitude difference rate remains within 5%. Monitoring points that fail verification trigger the equipment calibration process; the sensor enters standard solution calibration mode, and benchmark parameters are re-collected after calibration. All verification records are digitally signed and stored in a blockchain distributed ledger, forming an immutable chain of evidence for effect traceability.

[0110] The abnormal fluctuation handling mechanism is configured with a four-level response plan. Level 1 handles short-term parameter fluctuations; if dissolved oxygen at a certain point suddenly drops by 0.8 mg / L within three minutes, the system determines this as an equipment malfunction and immediately activates the backup aeration unit. Level 2 addresses persistent deviations; if six consecutive sampling data points fail to reach 80% of the expected threshold, an expert diagnostic request is sent to the control center. Level 3 handles systemic failures; if multiple monitoring points simultaneously deviate from the expected trajectory for more than 30 minutes, the current aeration strategy is forcibly interrupted and the basic operating mode is switched. Level 4 addresses equipment malfunctions; if the aeration fan speed feedback value is lower than 25% of the command value for two consecutive minutes, an equipment maintenance work order is automatically pushed to the maintenance terminal.

[0111] The system maintenance interface is linked to the equipment lifecycle management database. The performance index of the corresponding aeration equipment is updated during each performance review process. For example, the initial performance index of equipment B7 was 92. After three aeration adjustments, its average improvement rate was calculated to be 87%, and the updated index value was 89. When the performance index of a piece of equipment drops by more than 5 percentage points for five consecutive cycles, the system marks it as a yellow warning in the maintenance plan. Cross-analysis of the performance index and equipment maintenance records generates a maintenance priority matrix to guide on-site maintenance operations. During equipment downtime maintenance, relevant monitoring points switch to baseline parameter tracking mode to continuously record baseline water quality changes under natural conditions.

[0112] The retrospective data is ultimately archived in the historical case knowledge base. Each complete retrospective cycle forms an independent portfolio containing four types of data assets: a copy of the aeration control parameter execution package, a water quality change curve dataset, monitoring point adjustment plans, and pollution characteristic curve correction records. The knowledge base uses an index structure based on pollution features, automatically pushing historical case references when a similar combination of water quality parameters is newly detected. The knowledge base performs feature clustering analysis quarterly, merging redundant cases with similarity exceeding 90% to improve system decision-making efficiency. A water quality fingerprint code is added during the archiving process; this code is generated by hashing the feature values ​​of thirteen core parameters, supporting precise full-database retrieval.

[0113] A bidirectional verification mechanism between the backtracking layer and the front-end sensing devices operates routinely. After every ten backtracking cycles, the system issues a self-test command to the multi-source sensing terminal. The terminal activates its built-in verification module: the dissolved oxygen sensor is saturated with standard dissolved oxygen solution, the ammonia nitrogen electrode is immersed in standard ammonium salt solution, and the data transmission module performs a full-channel bit error rate test. The verification results are compared and analyzed with the backtracking data. Devices with error rates exceeding the standard are automatically suspended from sampling and reactivated after on-site calibration. The self-test records and the backtracking reports form a mutual verification chain, constituting a complete data quality assurance system.

[0114] The feedback closed-loop delay control system adjusts the backtracking rhythm. The typical time range for the system's dynamic calculation results is: dissolved oxygen response delay of two to five minutes, and ammonia nitrogen response delay of eight to fifteen minutes. The timing of the backtracking operation is determined based on the current primary monitoring indicators. When dissolved oxygen is the primary monitoring item, the initial backtracking is initiated three minutes after exposure ends; when ammonia nitrogen is dominant, this is extended to ten minutes. The delay control employs a layered buffering strategy to avoid data distortion caused by collecting data too early or too late. The time control parameters are updated monthly based on historical data statistical analysis results to adapt to the seasonal characteristics of water quality changes.

[0115] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0116] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A rural sewage intelligent monitoring and aeration control system based on Internet of Things, characterized in that, The method comprises the following steps: a pollution parameter perception layer, which collects the operation parameters of the sewage treatment facility in real time through a multi-source sensing terminal; a pollution index analysis layer, which obtains the operation parameters of the sewage treatment facility, divides the pollution parameter interval according to the operation parameters, and calculates the pollution index distribution coefficient; an aeration path generation layer, which generates the aeration intensity hierarchical path according to the pollution index distribution coefficient; a process parameter matching layer, which compares the current process parameters with the preset process parameter threshold, and outputs a process deviation parameter set; a dynamic monitoring focusing layer, which dynamically adjusts the monitoring point density of the multi-source sensing terminal according to the process deviation parameter set; a cross-modal mapping layer, which synchronously receives the monitoring point distribution data of the dynamic monitoring focusing layer and the aeration intensity hierarchical path of the aeration path generation layer, and establishes the spatio-temporal correlation mapping of the water quality parameter and the aeration intensity; a device scheduling decision layer, which sorts the aeration device calling sequence according to the spatio-temporal correlation mapping result; an aeration parameter generation layer, which converts the aeration device calling sequence into executable aeration control parameters; The pollution index analysis layer comprises: obtaining the maximum pollution load range of the sewage treatment facility, and equally dividing the pollution load range into a plurality of parameter intervals; extracting the pollution type and concentration threshold in the operation parameter, and querying the corresponding pollution characteristic curve in the pollution characteristic table; obtaining the pollution index distribution coefficient of each parameter interval through a pollution index distribution coefficient calculation model; calculating the number of monitoring points corresponding to each parameter interval based on the pollution index distribution coefficient; uniformly arranging a plurality of key monitoring points in the corresponding parameter interval; The pollution index distribution coefficient calculation model comprises a characteristic value weight distribution module, which is built-in with an environmental impact factor evaluation table, wherein the weight coefficient of heavy metal pollutants is higher than that of organic pollutants, and the pollution index distribution coefficient is obtained by the product operation of the characteristic curve equation and the weight coefficient. Each parameter interval finally outputs a floating-point distribution coefficient value; The aeration path generation layer comprises: marking the key monitoring point with the highest pollution index distribution coefficient as a severe pollution monitoring point; marking the key monitoring point with the lowest pollution index distribution coefficient as a mild pollution monitoring point; obtaining the pollution value of the pollution characteristic curve corresponding to the initial monitoring point; determining whether the difference between the pollution value of the severe pollution monitoring point and the pollution value of the initial monitoring point is greater than the difference between the pollution value of the mild pollution monitoring point and the pollution value of the initial monitoring point; if yes, generating a first aeration path from the initial monitoring point to the severe pollution monitoring point, a second aeration path from the severe pollution monitoring point back to the initial monitoring point, and a third aeration path from the initial monitoring point to the mild pollution monitoring point; if no, generating a first aeration path from the initial monitoring point to the mild pollution monitoring point, a second aeration path from the mild pollution monitoring point back to the initial monitoring point, and a third aeration path from the initial monitoring point to the severe pollution monitoring point; integrating the first aeration path, the second aeration path and the third aeration path to form the aeration intensity hierarchical path.

2. The rural sewage intelligent monitoring and aeration control system based on Internet of Things according to claim 1, characterized in that, Further comprising: an aeration effect backtracking layer, which is connected to the aeration parameter generation layer, compares the water quality parameter change amount before and after the execution of the aeration control parameter, and dynamically corrects the pollution parameter interval division logic according to the water quality parameter change amount. 3.The rural sewage intelligent monitoring and aeration control system based on Internet of Things according to claim 2, characterized in that, The process parameter matching layer comprises: Statistically determining the absolute deviation of the current process parameter from the preset process parameter threshold value; Calculating the weighted sum of the dissolved oxygen deviation, biochemical oxygen demand deviation, and suspended solids deviation; When the weighted sum exceeds the process tolerance threshold value, marking the corresponding parameter interval as the process deviation parameter set.

4. The rural sewage intelligent monitoring and aeration control system based on Internet of Things according to claim 3, characterized in that, The dynamic monitoring focusing layer comprises: Identifying the key monitoring points covered by the process deviation parameter set and upgrading the area where the key monitoring points are located to the intensive monitoring area; The area covered by the non-process deviation parameter set is downgraded to the sparse monitoring area, the intensive monitoring area adopts a high-frequency sampling mode, and the sparse monitoring area adopts a low-frequency sampling mode. 5.The rural sewage intelligent monitoring and aeration control system based on Internet of Things according to claim 4, characterized in that, The cross-modal mapping layer comprises: Establishing timestamp alignment between the water quality parameter change curve of the intensive monitoring area and the aeration intensity classification path; Labeling the water quality parameter fluctuation characteristics corresponding to each node in the aeration intensity classification path to generate an association mapping table of water quality parameter fluctuation characteristics and aeration intensity levels. 6.The rural sewage intelligent monitoring and aeration control system based on Internet of Things according to claim 5, characterized in that, The equipment scheduling decision layer comprises: Extracting the nodes in the association mapping table where the aeration intensity level meets the standard, sorting the aeration equipment call priority according to the node meeting duration, and merging the continuous meeting nodes into the aeration equipment efficient operation interval. 7.The rural sewage intelligent monitoring and aeration control system based on Internet of Things according to claim 6, characterized in that, The aeration parameter generation layer comprises: Converting the aeration equipment efficient operation interval into aeration fan speed ladder instructions, generating a blower start-stop sequence according to the aeration equipment call priority, and combining the aeration fan speed ladder instructions and the blower start-stop sequence to form executable aeration control parameters. 8.The rural sewage intelligent monitoring and aeration control system based on Internet of Things according to claim 7, characterized in that, The aeration effect backtracking layer comprises: Recording the baseline water quality parameters of the key monitoring points before executing the executable aeration control parameters, collecting the real-time water quality parameters of the same key monitoring points after execution, and calculating the absolute change amount of the real-time water quality parameters relative to the baseline water quality parameters; When the absolute change amount does not reach the expected improvement threshold value, increasing the number of monitoring points in the corresponding parameter interval; When the absolute change amount continuously exceeds the expected improvement threshold value, reducing the number of monitoring points in the corresponding parameter interval; Updating the pollution characteristic curve weight coefficient in the pollution characteristic reference table.

Images