Intelligent monitoring method and system for sewage treatment process based on digital twinning

Abstract

The application provides a sewage treatment process intelligent monitoring method and system based on digital twinning, relates to the technical field of sewage treatment intelligent monitoring, and comprises the following steps: digital twinning model construction, multi-source parameter acquisition, multi-source parameter processing, model dynamic correction, operation state monitoring, hierarchical early warning, optimal process control scheme generation and execution. The application can construct a full-process digital twinning model of sewage treatment which is accurately matched with physical entities in a plant, and can collect multi-source monitoring parameters in real time; then, the multi-source parameters are standardized, input into the twinning model to complete error compensation and dynamic correction, and the virtual and real operation states are synchronized; the operation parameters of each treatment unit are monitored synchronously, the hierarchical early warning threshold is triggered automatically to push fault information and disposal scheme; finally, the optimal process control scheme including aeration intensity and reflux ratio adjustment is generated by combining the measured parameters and the model simulation results, and the instructions are issued to realize the automatic and accurate control of the sewage treatment process.

Description

Technical Field

[0001] This invention relates to the field of intelligent monitoring technology for wastewater treatment, and in particular to an intelligent monitoring method and system for wastewater treatment processes based on digital twins. Background Technology

[0002] In the context of intelligent transformation in the wastewater treatment industry, intelligent monitoring systems are considered a core means to improve treatment efficiency, ensure effluent compliance, and reduce operating costs. However, in actual implementation, they still face multiple technical bottlenecks, failing to achieve the monitoring goals of full-process, high precision, high reliability, and low cost. At the sensing layer, existing water quality sensors have weak anti-interference capabilities and are easily affected by water turbidity, temperature fluctuations, and reagent residues, leading to insufficient accuracy, data drift, and response delays. Furthermore, sensor deployment lacks scientific planning, resulting in monitoring blind spots, inconsistent interfaces, poor compatibility, high maintenance costs, and short lifespans. At the data processing and transmission level, the large volume and time-varying nature of multi-source heterogeneous data make efficient fusion and in-depth analysis difficult with existing technologies. Model generalization capabilities are weak, unable to adapt to complex operating conditions such as fluctuating influent loads. Simultaneously, traditional network transmission poses security risks and data leakage risks; bandwidth and latency issues lead to frequent packet loss and delays; and poor system compatibility creates data silos. In terms of intelligent early warning and control, early warnings are mostly based on simple thresholds, lacking integration of process mechanisms, resulting in serious false alarms and missed alarms. Technologies such as machine vision cannot understand the logic of biochemical reactions, and control is mostly semi-automatic or manual, making it difficult to achieve precise automatic optimization, leading to serious waste of drug and electricity consumption. In terms of system architecture and cost control, the architecture is bloated and functionally redundant, with high computing power costs, excessive hardware investment, high difficulty in system integration and maintenance, and a shortage of professional talents. This results in a lack of unified standards for the construction of monitoring systems for different projects, and poor compatibility and scalability. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a method and system for intelligent monitoring of wastewater treatment processes based on digital twins. This system can construct a digital twin model of the entire wastewater treatment process that accurately matches the physical entity of the plant area, and collect multi-source monitoring parameters in real time. The multi-source parameters are then standardized and input into the twin model to complete error compensation and dynamic correction, ensuring synchronization between virtual and real operating states. The system can simultaneously monitor the operating parameters of each treatment unit, automatically trigger warnings based on graded warning thresholds, and push fault information and disposal plans. Finally, by combining measured parameters and model simulation results, the system can generate an optimal process control scheme that includes aeration intensity and reflux ratio adjustment, and issue commands to achieve automated and precise control of the wastewater treatment process.

[0004] This invention provides an intelligent monitoring method for wastewater treatment processes based on digital twins. The method includes: S101, constructing a digital twin model of the entire wastewater treatment process, with each model corresponding one-to-one with the physical entity of the actual wastewater treatment plant, and collecting multi-source monitoring parameters of the wastewater treatment plant in real time; S102, standardizing the multi-source monitoring parameters of the wastewater treatment plant, inputting the standardized parameters into the digital twin model for error compensation and dynamic correction, ensuring that the operating status of the digital twin model is synchronized with the operating status of the actual wastewater treatment plant; S103, monitoring the operating status parameters of each treatment unit of the wastewater treatment plant in real time, setting different levels of early warning thresholds, automatically triggering corresponding level early warning signals, and pushing specific fault locations, abnormal causes, and handling suggestions; S104, based on the simulation results of the multi-source monitoring parameters and the digital twin model, automatically generating an optimal process control scheme, including aeration intensity adjustment and reflux ratio adjustment, and sending control commands to the actual wastewater treatment equipment in real time to achieve automatic and precise control of process parameters.

[0005] This application also provides an intelligent monitoring system for wastewater treatment processes based on digital twins. This system is applied to an intelligent monitoring method for wastewater treatment processes based on digital twins. The system includes: a digital twin model construction and multi-source parameter acquisition module, a multi-source parameter processing and model dynamic correction module, an operation status monitoring and hierarchical early warning module, and an optimal process control scheme generation and execution module. The digital twin model construction and multi-source parameter acquisition module is used to construct a digital twin model of the entire wastewater treatment process. This digital twin model corresponds one-to-one with the physical entity of the actual wastewater treatment plant, and collects multi-source monitoring parameters of the wastewater treatment plant in real time. The multi-source parameter processing and model dynamic correction module is used to standardize the multi-source monitoring parameters of the wastewater treatment plant and input the processed parameters into... The data is integrated into a digital twin model of the entire wastewater treatment process for error compensation and dynamic correction, ensuring that the operational status of the digital twin model is synchronized with that of the actual wastewater treatment plant. The operational status monitoring and tiered early warning module monitors the operational status parameters of each treatment unit in the wastewater treatment plant in real time, sets different levels of early warning thresholds, automatically triggers corresponding early warning signals, and pushes specific fault locations, abnormal causes, and handling suggestions. The optimal process control scheme generation and execution module automatically generates the optimal process control scheme based on the simulation results of the multi-source monitoring parameters of the wastewater treatment plant and the digital twin model of the entire wastewater treatment process. This includes adjusting aeration intensity and reflux ratio, and the control commands are sent to the actual wastewater treatment equipment in real time, achieving automatic and precise control of process parameters.

[0006] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following: By constructing a digital twin model of the entire wastewater treatment process and combining it with real-time acquisition, standardized processing, error compensation, and dynamic correction of multi-source parameters, this invention effectively avoids data acquisition deviations and equipment operation interference, achieving real-time synchronous mapping between the virtual model and the on-site physical facility operating status, thus improving the accuracy and timeliness of operational simulation. A tiered early warning mechanism is set up based on multi-dimensional operating parameters to accurately identify various operational faults such as abnormal influent temperature, and tiered push notifications of abnormal causes and handling suggestions, proactively mitigating process instability risks and strengthening the plant's operational safety management capabilities. Based on key operating indicators such as pump operating frequency, return pipeline pressure, and aeration equipment operating frequency, combined with various mapping relationships and threshold judgment logic, adaptive dynamic adjustment of valve opening, aeration intensity, and return ratio thresholds is achieved, realizing coordinated and optimized control of the wastewater treatment aeration system and return system. Compared to traditional manual control and fixed threshold management modes, this invention can adaptively match optimal process parameters based on real-time influent load, equipment operating conditions, and pipeline operating status, effectively improving the biochemical reaction environment, stabilizing effluent water quality indicators, and reducing reagent consumption, power consumption, and equipment wear. Based on a modular system architecture, a closed-loop management system is achieved for the entire process of monitoring, early warning, correction, and control. Attached Figure Description

[0007] Figure 1 This is a flowchart of an intelligent monitoring method for wastewater treatment processes based on digital twins, provided in an embodiment of the present invention. Figure 2 This is a schematic diagram of the structure of the intelligent monitoring system for wastewater treatment process based on digital twin provided in an embodiment of the present invention. Detailed Implementation

[0008] This invention provides an intelligent monitoring method for wastewater treatment processes based on digital twins, such as... Figure 1 The flowchart shown is for an intelligent monitoring method for wastewater treatment based on digital twins. The process of this method may include the following steps: S101, construct a digital twin model of the entire wastewater treatment process. The digital twin model of the entire wastewater treatment process corresponds one-to-one with the physical entity of the actual wastewater treatment plant, and collects multi-source monitoring parameters of the wastewater treatment plant in real time.

[0009] It should be understood that a comprehensive on-site survey and parameter mapping of the actual wastewater treatment plant is necessary to obtain the physical structural parameters of each treatment unit (bar screen, grit chamber, biological reaction tank, secondary sedimentation tank, disinfection tank, etc.), including tank dimensions, pipeline layout, equipment models and installation locations, connection methods, etc., to ensure a 1:1 accurate mapping between the digital twin model and the actual physical entity. Simultaneously, the core wastewater treatment process mechanisms (activated sludge reaction, sedimentation, disinfection, etc.) are embedded to build a full-process digital twin model covering the physical, process, and data layers. A multi-source sensing and monitoring network is deployed, with water quality sensors and equipment operation sensors installed at key points in each treatment unit. The system includes sensors, environmental sensors, and various monitoring devices such as flow and pressure sensors. Water quality sensors are used to collect water quality parameters such as COD, SS, and DO. Equipment operation sensors are used to collect parameters such as the operating frequency and current of equipment such as water pumps and aeration blowers. Environmental sensors are used to collect parameters such as plant temperature and humidity. The system activates the linkage mechanism between the monitoring equipment and the digital twin model, setting the acquisition frequency of each sensor to no less than once per minute. Various multi-source monitoring parameters are collected in real time. After preliminary noise reduction processing, the collected data is synchronously transmitted to the data storage module of the digital twin model to ensure that the model can reflect the actual operating status of the wastewater treatment plant in real time.

[0010] S102, standardize the multi-source monitoring parameters of the wastewater treatment plant, input the standardized multi-source monitoring parameters of the wastewater treatment plant into the digital twin model of the entire wastewater treatment process, perform error compensation and dynamic correction, so that the operating status of the digital twin model of the entire wastewater treatment process keeps synchronized with the operating status of the actual wastewater treatment plant.

[0011] It needs to be explained that the specific process for error compensation is as follows: Real-time influent flow rate data at the inlet of the wastewater treatment plant is collected. The instantaneous influent flow rate data is compared with the influent flow rate benchmark value to obtain the flow deviation rate. The flow deviation rate is used to represent the ratio of the absolute value of the difference between the instantaneous influent flow rate data and the influent flow rate benchmark value to the influent flow rate benchmark value. Based on the calculated flow deviation rate, the hydraulic retention time threshold of each treatment unit is dynamically adjusted, specifically as follows: A pre-constructed mapping matrix of flow deviation rate and duration threshold adjustment factor is used to characterize the one-to-one correspondence between flow deviation rate and duration threshold adjustment factor; If the flow deviation rate is less than or equal to the lower limit of the flow deviation reference, the current flow deviation rate is input into the flow deviation rate-duration threshold adjustment factor mapping matrix, and the duration threshold adjustment factor is output. The duration threshold reference value and the duration threshold adjustment factor are multiplied to obtain the target hydraulic residence time threshold. If the flow deviation rate is within the flow deviation reference interval, the current flow deviation rate is input into the flow deviation rate-duration threshold adjustment factor mapping matrix, and the duration threshold adjustment factor is output. The duration threshold base value and the duration threshold adjustment factor are multiplied to obtain the target hydraulic residence time threshold. The flow deviation reference interval represents the open interval formed by the lower limit of the flow deviation reference and the upper limit of the flow deviation reference. If the flow deviation rate is greater than or equal to the upper limit of the flow deviation reference, an early warning signal will be triggered, prompting staff to check the water intake conditions.

[0012] In this embodiment, high-precision flow acquisition equipment deployed at key inlet points of the wastewater treatment plant continuously captures instantaneous influent flow data at the plant's inlet in real time. A time-series smoothing filtering algorithm is used to denoise, remove anomalies, and align the original flow data with the time sequence, eliminating invalid data caused by instantaneous disturbances and signal interference, ensuring the authenticity and continuity of the flow acquisition results. The pre-processed instantaneous influent flow data is then compared with a pre-calibrated influent flow benchmark value based on the plant's designed treatment capacity and conventional influent load conditions. The absolute value of the difference is calculated, and this absolute difference is used as a ratio to the influent flow benchmark value to accurately calculate the real-time flow deviation rate, thereby quantifying the fluctuation range of the actual influent load relative to the standard operating conditions. In advance, considering the tank volume of each wastewater treatment unit, process degradation cycle, microbial reaction characteristics, and water quality tolerance conditions, an offline training and solidification of a flow deviation rate-duration threshold adjustment factor mapping matrix is ​​constructed. This mapping matrix is ​​trained on multi-condition samples using a piecewise fitting algorithm, establishing a one-to-one mapping relationship between flow deviation rates with different fluctuation levels and corresponding duration threshold adjustment factors, achieving precise matching and application of deviation values ​​and control coefficients. During actual operation, the real-time flow deviation rate is interval-based. When the flow deviation rate is less than or equal to the preset lower limit of flow deviation reference, it is determined that the current overall influent load is low, and the degradation rate of pollutants in the water body is slowed down. The real-time calculated flow deviation rate is then imported into the flow deviation rate-duration threshold adjustment factor mapping matrix. Within the time threshold adjustment factor mapping matrix, the corresponding time threshold upward adjustment factor is quickly matched and output. The preset time threshold baseline value for each treatment unit is coupled with this upward adjustment factor and multiplied to calculate and generate a target hydraulic retention time threshold suitable for low-load conditions in real time, extending the effective reaction time of wastewater. When the flow deviation rate is within the open interval formed by the lower and upper limits of the flow deviation reference, it is determined that the influent load is slightly high and the water flow rate is accelerated. Simultaneously, the corresponding time threshold downward adjustment factor within the mapping matrix is ​​retrieved, and the time threshold baseline value is corrected using a multiplier operation to reasonably reduce the hydraulic retention time. The system is designed to prevent water stagnation and accumulation within the tank. When the flow deviation rate is greater than or equal to the preset upper limit of the flow deviation reference, it is determined that the influent load has experienced a severe abnormal fluctuation, exceeding the adaptive adjustment range of the process. The system immediately and automatically triggers a graded operating condition early warning signal, accurately pinpoints the abnormal influent location, and pushes the cause of the abnormal load fluctuation. Simultaneously, it prompts maintenance personnel to promptly conduct influent operating condition investigations, load reduction, and process emergency response. Relying on data calculation, matrix matching, and segmented and graded control logic, the system completes intelligent dynamic correction of the hydraulic retention time threshold, effectively adapting to dynamic changes in the influent load and maintaining the stable operation of the entire wastewater treatment process.

[0013] It should be further explained that the specific process of dynamic correction is as follows: By deploying equipment operation sensors on the water pumps of each sewage treatment unit, the actual operating frequency data of the water pumps is collected in real time. The actual operating frequency data of the water pumps is compared with the standard value of the operating frequency to obtain the frequency deviation value and frequency deviation rate. The frequency deviation value indicates the degree of deviation between the actual operating frequency data of the water pump and the standard operating frequency value, while the frequency deviation rate indicates the result of the analysis of the ratio of the frequency deviation value to the standard operating frequency value. If the frequency deviation rate is less than or equal to the lower limit of the frequency deviation rate reference, the valve opening is increased proportionally based on the absolute value of the frequency deviation rate. The increased valve opening is then compared with the upper limit of the valve opening reference. If the increased valve opening is less than or equal to the upper limit of the valve opening reference, the increased valve opening is used as the target valve opening to ensure that the pipeline flow rate matches the pump output.

[0014] Dynamic correction also includes: If the frequency deviation rate is within the frequency deviation rate reference range, the valve opening is reduced proportionally based on the frequency deviation rate. The reduced valve opening is compared with the lower limit of the valve opening reference. If the reduced valve opening is greater than or equal to the lower limit of the valve opening reference, the reduced valve opening is used as the target valve opening to avoid excessive pipeline pressure that could damage the equipment. The frequency deviation rate reference range represents the opening range formed by the lower limit of the frequency deviation rate reference and the upper limit of the frequency deviation rate reference. If the frequency deviation rate is greater than or equal to the upper limit of the frequency deviation rate reference, the emergency adjustment mode of valve opening will be activated, triggering the equipment operation early warning signal and prompting the staff to check the pump operation status and pipeline condition. The dynamically adjusted valve opening command is sent to the corresponding valve's actuator in real time to control the valve to complete the opening adjustment, and the adjusted valve opening data is fed back to the digital twin model of the entire wastewater treatment process.

[0015] In this embodiment, based on dedicated operating sensors deployed at the pumps in each wastewater treatment unit, the raw data of the pumps' real-time operating frequency is continuously collected around the clock. A sliding window filtering algorithm is used to smooth and reduce noise, eliminate impulse interference, and perform steady-state filtering on the raw data. This effectively eliminates data distortion caused by electromagnetic interference and momentary equipment vibration in industrial settings, ensuring the stability and effectiveness of the pump frequency data. The pre-processed actual pump operating frequency data is then precisely compared with a pre-calibrated standard operating frequency value based on the pump's rated parameters and conventional steady-state operating conditions. Frequency deviation values, used to quantify the degree of equipment operational deviation, and frequency deviation rates, used to characterize the relative magnitude of deviation, are calculated to objectively reflect the difference between the pump's actual output and the standard design conditions. The system performs adaptive dynamic correction and control based on preset frequency deviation rate classification rules. When the real-time frequency deviation rate is less than or equal to the preset lower limit of the frequency deviation rate reference, it indicates that the actual operating output of the water pump is insufficient and the water delivery capacity of the pipeline has decreased. Using the absolute value of the frequency deviation rate as the control base, a linear proportional linkage adjustment algorithm is used to proportionally increase the valve opening of the corresponding return pipeline and water delivery pipeline. After the opening adjustment is completed, the real-time corrected valve opening value is compared with the preset upper limit of the valve opening reference for threshold constraint. Under the premise that the increased valve opening does not exceed the upper limit of the reference, the opening value is determined as the final target valve opening, thereby matching the actual delivery output of the water pump and ensuring a stable and balanced water delivery flow in the pipeline. When the real-time frequency deviation rate is within the range of both the lower and upper limits of the frequency deviation rate reference, it indicates that the actual operating output of the water pump is insufficient and the water delivery capacity of the pipeline has decreased. When the pump operating frequency is within the specified range, the system determines that the pump operating frequency is too high and the pipeline water load is too large. The system synchronously reduces the valve opening amplitude according to the frequency deviation rate change ratio. At the same time, the adjusted valve opening is checked against the lower limit of the valve opening reference to ensure that the adjusted opening is not lower than the lower limit of the reference requirement. This prevents problems such as sudden increase in pipeline pressure, overload of pipe wall, and increased wear and tear on downstream equipment caused by an excessively small pipeline flow cross-section. When the real-time frequency deviation rate is greater than or equal to the upper limit of the frequency deviation rate reference, the system determines that the pump operating condition is seriously abnormal and exceeds the normal adaptive adjustment range. The system immediately activates the emergency valve opening adjustment mode and synchronously triggers a special early warning signal for equipment operation, clearly indicating key information such as abnormal pump operation and pipeline imbalance, guiding on-site maintenance personnel to promptly investigate potential problems such as pump failure, pipeline blockage, and abnormal pressure.Meanwhile, the system sends the target valve opening control command, which has been dynamically calculated and verified in each round, to the valve actuator of the corresponding pipeline in real time, driving the valve to complete the precise opening adjustment action. The adjusted actual valve opening operation data is also transmitted back to the digital twin model of the entire sewage treatment process in real time, completing the synchronous update and dynamic correction of the model's hydraulic parameters and pipeline resistance parameters. This achieves real-time linkage and closed loop between the pump operation status, valve adjustment action and digital twin virtual simulation conditions, further improving the real-time performance, accuracy and overall operational stability of the sewage treatment hydraulic transport system.

[0016] S103 monitors the operating status parameters of each treatment unit in the wastewater treatment plant in real time, sets different levels of early warning thresholds, automatically triggers the corresponding level of early warning signal, and pushes the specific fault location, abnormal cause and handling suggestions.

[0017] It needs to be explained that the specific process for automatically triggering the corresponding level of warning signal is as follows: The system collects influent water temperature parameters at the influent end of the wastewater treatment plant in real time, divides the influent water temperature threshold range into multiple levels, and matches them with Level 1 mild warning, Level 2 moderate warning, and Level 3 severe warning. The influent water temperature parameters are compared and judged in real time with the preset temperature threshold range, specifically as follows: If the influent water temperature parameter is less than or equal to the preset temperature threshold reference lower limit, it is determined to be a Level 1 mild warning, and the monitoring status is maintained without any warning prompts. If the influent water temperature parameter is within the preset temperature threshold range, it is determined to be a level 2 moderate warning, and the cause of the slight abnormality in the influent water temperature is pushed out, as well as basic handling suggestions for continuous monitoring and regular inspection. The preset temperature threshold range means the open interval formed by the preset temperature threshold reference lower limit and the preset temperature threshold reference upper limit. If the influent water temperature parameter is greater than or equal to the preset temperature threshold reference upper limit, it is judged as a level three severe warning. At the same time, the abnormal cause of the severe over-standard influent water temperature is pushed out, as well as emergency handling suggestions for limiting the influent load and on-site personnel intervention to investigate. Early warning information at different levels, the causes of anomalies, and corresponding handling suggestions are simultaneously uploaded to the digital twin model of the entire wastewater treatment process to complete the real-time marking of abnormal temperature conditions.

[0018] In this embodiment, to achieve accurate monitoring and graded early warning of abnormal influent water temperature and ensure stable operation of biochemical reactions, high-precision temperature sensors are deployed at key monitoring points such as the influent channel and in front of the screen at the influent end of the sewage treatment plant. These sensors capture the raw parameters of the influent water temperature in real time. At the same time, a temperature drift compensation algorithm is introduced to dynamically correct the measurement deviation caused by zero-point drift and environmental interference from long-term sensor operation. Combined with the Kalman filter algorithm, the collected raw temperature data is smoothed and denoised to remove invalid data caused by instantaneous temperature fluctuations and signal interference, ensuring the accuracy, continuity and stability of the influent water temperature monitoring data. Subsequently, based on the suitable growth temperature range (15℃-35℃) of microorganisms in the biochemical reaction of wastewater treatment, the actual operating conditions of the plant and the water quality compliance requirements, multiple influent water temperature threshold ranges were pre-divided, and a one-to-one matching relationship between threshold ranges and warning levels was established. The preset lower limit of the temperature threshold was set at 15℃, the preset upper limit of the temperature threshold was set at 35℃, and the preset temperature threshold range was (15℃, 35℃), corresponding to three levels of warning: Level 1 mild warning, Level 2 moderate warning, and Level 3 severe warning. The judgment criteria and handling logic for each level of warning were clarified. The system compares the compensated and filtered influent water temperature parameters in real time with preset temperature threshold ranges for precise judgment. It uses a fuzzy comprehensive evaluation algorithm to quantify the degree of temperature anomaly, improving the scientific rigor and accuracy of early warning judgments: When the influent water temperature parameter is less than or equal to 15℃ (the lower limit of the preset temperature threshold), it is judged as a Level 1 mild warning. At this time, the temperature is low but has not significantly affected microbial activity. The system maintains normal real-time monitoring without initiating any audible, visual, or text warnings, only recording temperature fluctuation data for subsequent trend analysis. When the influent water temperature parameter is within the preset temperature threshold range (15℃, 35℃), it is judged as a Level 2 moderate warning. The system immediately analyzes the cause of the anomaly, identifying it as a small fluctuation in the influent water temperature (such as seasonal changes, changes in upstream water temperature, etc.). Simultaneously, through the plant operation and maintenance platform and mobile terminals, specific explanations of minor anomalies in inlet water temperature are pushed to operation and maintenance personnel, along with basic handling suggestions for continuously increasing the frequency of temperature monitoring and regularly inspecting inlet water temperature sensors and pipeline insulation facilities, guiding operation and maintenance personnel to carry out routine prevention and control. When the inlet water temperature parameter is greater than or equal to 35℃ (the upper limit of the preset temperature threshold reference), it is judged as a level three severe warning. At this time, the excessively high temperature will severely inhibit the activity of microorganisms, resulting in a decrease in biochemical reaction efficiency and difficulty in meeting the effluent water quality standards. The system quickly pushes the abnormal cause of the severely excessive inlet water temperature (such as high temperature weather, abnormal discharge of upstream industrial wastewater, etc.), and at the same time issues emergency handling suggestions for limiting the inlet water load, starting the inlet water cooling facilities, and immediate intervention by on-site operation and maintenance personnel to investigate the upstream water and the operating status of temperature sensors, ensuring timely containment of the deterioration of the operating conditions.Finally, the system will synchronously upload the specific levels of warnings, abnormal temperature values, causes of abnormalities, and corresponding handling suggestions to the digital twin model of the entire wastewater treatment process in real time. The system will complete the real-time marking of abnormal temperature conditions in the model and synchronously update the relevant parameters of biochemical reaction rates within the model. This will provide accurate temperature condition data support for subsequent dynamic model correction and adaptive control of process parameters, and realize closed-loop management of influent water temperature monitoring, graded warnings, handling guidance, and digital twin model linkage, effectively avoiding the adverse effects of abnormal temperatures on the wastewater treatment process.

[0019] S104 automatically generates the optimal process control scheme based on the simulation results of multi-source monitoring parameters of the sewage treatment plant and the digital twin model of the entire sewage treatment process. This includes adjusting the aeration intensity and the return ratio. The control commands are sent to the actual sewage treatment equipment in real time, realizing the automatic and precise control of process parameters.

[0020] It should be further explained that the specific procedure for adjusting the aeration intensity is as follows: Real-time data on the operating frequency of aeration blowers and aeration units in the biological treatment tank is collected. After standardization, the operating frequency data of aeration blowers and aeration units is input into the digital twin model of the entire wastewater treatment process. A pre-constructed correlation mapping relationship between the operating frequency and aeration intensity of aeration equipment is used to characterize the quantitative correspondence between the gain and reduction of air delivery volume corresponding to different actual operating frequencies of aeration equipment, thereby realizing the dynamic adaptive adjustment of aeration intensity. The actual operating frequency of the aeration equipment, collected in real time, is compared and analyzed with the preset rated operating frequency range to determine the current frequency deviation from the range. Specifically: If the actual operating frequency of the aeration equipment is lower than the preset rated operating frequency lower limit, it is determined that the current air supply capacity is insufficient. The current actual operating frequency of the aeration equipment is input into the correlation mapping relationship between the operating frequency of the aeration equipment and the aeration intensity, and the output air delivery gain is output. The air delivery benchmark value and the air delivery gain are coupled to obtain the target air delivery, so as to improve the aeration intensity inside the biological tank and make up for the oxygen supply gap.

[0021] Adjusting the aeration intensity also includes: If the actual operating frequency of the aeration equipment is within the preset rated operating frequency range, the current aeration intensity will be maintained at a constant output to ensure the stable progress of the oxygen biochemical reaction. The preset rated operating frequency range refers to the open interval formed by the lower limit of the preset rated operating frequency and the upper limit of the preset rated operating frequency. If the actual operating frequency of the aeration equipment is higher than the upper limit of the preset rated operating frequency, it is determined that the current aeration output is excessive. The current actual operating frequency of the aeration equipment is input into the correlation mapping relationship between the operating frequency of the aeration equipment and the aeration intensity, and the reduction in the output air delivery volume is output. The difference between the baseline value of the output air delivery volume and the reduction in the output air delivery volume is processed to obtain the target output air delivery volume, so as to weaken the aeration intensity and prevent energy waste and process imbalance caused by over-aeration.

[0022] In this embodiment, a multi-source data acquisition system is established, and monitoring equipment is deployed at key nodes of the aeration system corresponding to the biological treatment tank to collect real-time operating frequency data of aeration blowers and aeration units. At the same time, high-precision gas flow sensors and pressure sensors are used to synchronously collect core parameters such as gas flow rate and air supply pressure during the aeration process. The collected raw data is denoised and anomaly-free through a data preprocessing algorithm (using a sliding window filtering algorithm) to remove invalid data caused by equipment fluctuations and signal interference, ensuring the accuracy and continuity of the collected data. Subsequently, the standardized operating frequency, gas flow rate, air supply pressure and other data are synchronously input into the digital twin model of the entire wastewater treatment process to provide data support for the dynamic adjustment of aeration intensity. A correlation mapping model between the operating frequency and aeration intensity of aeration equipment is pre-constructed. A BP neural network algorithm is introduced to train and optimize the mapping relationship. Through offline training with a large amount of corresponding data on aeration frequency, air supply pressure, aeration intensity, and oxygen diffusion efficiency, the correlation mapping model can accurately output the aeration intensity adjustment parameters under different operating frequencies. At the same time, a genetic algorithm is embedded to iteratively optimize the mapping model, improving the matching accuracy between frequency and aeration intensity. This correlation mapping model is used to clarify the quantitative correspondence between different operating frequencies of aeration equipment and air output and aeration intensity, clearly characterizing the specific values ​​of air output gain and reduction under different operating frequencies, providing a precise basis for the dynamic adjustment of aeration intensity, and realizing adaptive matching of aeration intensity. The actual operating frequency of the aeration equipment is compared and analyzed with the preset rated operating frequency range to accurately determine the current aeration condition: If the actual operating frequency of the aeration equipment is lower than the lower limit of the preset rated operating frequency, it is determined that the current air supply capacity is insufficient. At this time, the actual operating frequency is input into the pre-trained correlation mapping model, and the model automatically outputs the corresponding air delivery gain. The air delivery benchmark value is coupled with the gain to obtain the target air delivery volume, and then the operating power of the aeration blower is adjusted to increase the aeration intensity, make up for the oxygen supply gap, and ensure the amount of oxygen required for microbial metabolism in the biological tank. If the actual operating frequency of the aeration equipment is within the preset rated operating frequency range, the current aeration intensity is maintained unchanged to ensure the stable progress of the biochemical reaction and avoid insufficient or excessive aeration. If the actual operating frequency of the aeration equipment is higher than the upper limit of the preset rated operating frequency, it is determined that the aeration output is excessive. The actual operating frequency is input into the correlation mapping model, and the corresponding air delivery volume reduction is output. Combined with the dissolved oxygen concentration data in the biological tank, the aeration intensity is reasonably reduced to reduce power consumption and energy waste, while avoiding the adverse effects of excessive aeration on microbial activity.The adjusted aeration intensity parameters are fed back to the digital twin model in real time. The model's built-in error correction algorithm verifies the accuracy of the aeration intensity adjustment, ensuring that the adjusted aeration intensity matches the metabolic needs of microorganisms and the degradation needs of wastewater pollutants in the biological treatment tank. This achieves synchronous linkage between the aeration system and the digital twin model. At the same time, the adjusted aeration parameters and operating status are recorded synchronously, forming a closed-loop control for dynamic adjustment of aeration intensity. This ensures the oxygen supply required for the biochemical reaction and achieves efficient energy utilization, thereby improving the intelligence level and process stability of wastewater treatment.

[0023] It should be further explained that the specific process for adjusting the reflux ratio is as follows: Pressure sensors deployed in the return pipeline collect the actual effective pressure in the return pipeline in real time. The return pipeline includes the internal return pipeline, the external return pipeline, and the sludge return pipeline. The actual effective pressure of the return pipeline is compared with the preset management pressure reference range to obtain the pressure deviation value and the pressure deviation rate. The pressure deviation value indicates the degree of deviation between the actual effective pressure of the return pipeline and the lower limit of the preset management pressure reference, and the pressure deviation rate indicates the proportion between the pressure deviation value and the lower limit of the preset management pressure reference. If the actual effective pressure of the return pipeline is less than or equal to the preset lower limit of the management pressure benchmark, it is determined that there is insufficient flow in the pipeline. Based on the absolute value of the pressure deviation rate, the return ratio threshold of the corresponding return pipeline is increased proportionally. It is then determined whether the adjusted return ratio threshold is less than or equal to the upper limit of the return ratio threshold reference. If so, the adjusted return ratio threshold is used as the target return ratio threshold. If not, the upper limit of the return ratio threshold reference is used as the target return ratio threshold.

[0024] Reflux ratio adjustment also includes: If the actual effective pressure of the return pipeline is within the preset management pressure reference range, the pipeline flow status is judged to be normal, and the current return ratio threshold is maintained. The preset management pressure reference range represents the open interval formed by the lower limit of the preset management pressure reference and the upper limit of the preset management pressure reference. If the actual effective pressure of the return pipeline is greater than or equal to the upper limit of the preset management pressure benchmark, it is determined that there is a blockage in the pipeline. Based on the pressure deviation rate, the return ratio threshold of the corresponding return pipeline is reduced accordingly. It is then determined whether the adjusted return ratio threshold is greater than or equal to the lower limit of the return ratio threshold reference. If so, the adjusted return ratio threshold is used as the target return ratio threshold. If not, the lower limit of the return ratio threshold reference is used as the target return ratio threshold.

[0025] In this embodiment, high-precision pressure sensors are deployed on all return-related pipelines in the wastewater treatment system, including the internal return pipeline, external return pipeline, and sludge return pipeline. These sensors collect real-time actual effective pressure data (i.e., the actual effective pressure of the return pipeline), covering pressure monitoring of the internal, external, and sludge return pipelines. This ensures that the collected data accurately reflects the actual operating status of each return pipeline. Simultaneously, a Kalman filter algorithm is used to reduce noise in the collected pressure data, eliminating abnormal data caused by signal interference and equipment fluctuations, ensuring the accuracy and stability of the pressure monitoring data. A preset management pressure benchmark range (including a preset lower and upper limit) is established for the return pipelines. Simultaneously, a reference upper and lower limit for the return ratio threshold are calibrated, constructing a correlation model between pressure and return ratio adjustment. A particle swarm optimization algorithm is introduced to optimize the adjustment parameters, ensuring the accuracy and rationality of the return ratio adjustment. Subsequently, the actual effective pressure of the return pipeline collected by the sensor is compared with the preset management pressure benchmark range to calculate the pressure deviation value and pressure deviation rate. The pressure deviation value is the difference between the actual effective pressure of the return pipeline and the lower limit of the preset management pressure benchmark, and the pressure deviation rate is the ratio of the pressure deviation value to the lower limit of the preset management pressure benchmark, thus quantifying the degree of pressure deviation. If the actual effective pressure of the return pipeline is less than or equal to the lower limit of the preset management pressure benchmark, it is determined that there is an insufficient flow problem in the current pipeline. At this time, based on the absolute value of the pressure deviation rate, the return ratio threshold of the corresponding return pipeline is increased according to the principle of proportional linkage. After the adjustment, it is determined whether the adjusted return ratio threshold is less than or equal to the preset upper limit of the return ratio threshold reference. If it is satisfied, the adjusted return ratio threshold is used as the target return ratio threshold. If the adjusted return ratio threshold exceeds the upper limit of the return ratio threshold reference, the upper limit of the return ratio threshold reference is directly used as the target return ratio threshold to ensure that the return flow can match the current pipeline pressure state and make up for the insufficient flow problem. If the actual effective pressure of the return pipeline is within the preset management pressure reference range (i.e., the open interval between the preset management pressure reference lower limit and the preset management pressure reference upper limit), the pipeline flow is considered normal, and the current return ratio threshold is maintained unchanged to ensure the stable operation of the return system and guarantee the normal water circulation and pollutant degradation. If the actual effective pressure of the return pipeline is greater than or equal to the preset management pressure reference upper limit, the pipeline is considered to have abnormal conditions such as blockage. In this case, the return ratio threshold of the corresponding return pipeline is reduced proportionally based on the pressure deviation rate. At the same time, it is determined whether the adjusted return ratio threshold is greater than or equal to the preset return ratio threshold reference lower limit. If it is satisfied, the adjusted return ratio threshold is used as the target return ratio threshold. If the adjusted return ratio threshold is lower than the return ratio threshold reference lower limit, the return ratio threshold reference lower limit is used as the target return ratio threshold to avoid further increase in pipeline pressure due to excessive return flow.The determined target reflux ratio threshold is synchronized to the digital twin model to dynamically update the reflux system parameters within the model. This ensures that the reflux ratio parameters in the digital twin model are consistent with the actual operating state. Simultaneously, the control commands corresponding to the target reflux ratio threshold are sent to actuators such as reflux pumps and pipeline valves to achieve automatic adjustment of the reflux ratio. The adjustment response speed is optimized through particle swarm optimization algorithm, effectively solving problems such as flow imbalance and pipeline blockage caused by abnormal reflux pipeline pressure. This ensures the stable operation of the reflux system and improves the intelligent control level of the wastewater treatment process.

[0026] like Figure 2 This is a schematic diagram of the intelligent monitoring system for wastewater treatment processes based on digital twins provided in this embodiment of the invention. The system includes: a digital twin model construction and multi-source parameter acquisition module, a multi-source parameter processing and model dynamic correction module, an operation status monitoring and hierarchical early warning module, and an optimal process control scheme generation and execution module. The digital twin model construction and multi-source parameter acquisition module is used to construct a digital twin model of the entire wastewater treatment process. The digital twin model of the entire wastewater treatment process corresponds one-to-one with the physical entity of the actual wastewater treatment plant, and collects multi-source monitoring parameters of the wastewater treatment plant in real time. The multi-source parameter processing and model dynamic correction module is used to standardize the multi-source monitoring parameters of the wastewater treatment plant and input the processed multi-source monitoring parameters into the intelligent monitoring system for the entire wastewater treatment process. In the digital twin model, error compensation and dynamic correction are performed to keep the operating status of the digital twin model of the entire wastewater treatment process synchronized with the operating status of the actual wastewater treatment plant. The operation status monitoring and hierarchical early warning module is used to monitor the operating status parameters of each treatment unit of the wastewater treatment plant in real time, set different levels of early warning thresholds, automatically trigger the corresponding level of early warning signal, and push specific fault location, abnormal cause and disposal suggestions. The optimal process control scheme generation and execution module is used to automatically generate the optimal process control scheme based on the simulation results of the multi-source monitoring parameters of the wastewater treatment plant and the digital twin model of the entire wastewater treatment process, including aeration intensity adjustment and reflux ratio adjustment. The control instructions are sent to the actual wastewater treatment equipment in real time to realize automatic and precise control of process parameters.

[0027] In this embodiment, to achieve accurate monitoring and tiered early warning of influent temperature and improve the stability and intelligence of the wastewater treatment process, a high-precision temperature sensor is used to collect real-time water temperature data at the influent of the wastewater treatment plant. A Kalman filter algorithm is used to denoise the collected temperature data, effectively eliminating transient interference and measurement errors to ensure the accuracy and continuity of the monitoring data. Simultaneously, a temperature drift compensation algorithm is introduced to dynamically correct the sensor's measurement deviation, further improving the accuracy of temperature monitoring. The system pre-divides multiple temperature threshold ranges according to the wastewater treatment process requirements, matching corresponding early warning levels. These include a normal temperature range suitable for microbial growth, a slightly abnormal range below normal temperature, and a severely abnormal range above process requirements, each corresponding to a different level of early warning mechanism. In practice, the temperature sensor captures the water temperature data at the inlet in real time. After being filtered by a sliding window, the data is transmitted to the system processing module. The system automatically compares and analyzes the difference between the inlet water temperature and the preset threshold: when the inlet water temperature is lower than the preset lower limit and is in a slightly abnormal range suitable for microbial growth, it is determined to be a mild warning. The system maintains normal monitoring and does not activate the warning prompt, only continuously collecting temperature data. When the inlet water temperature is in the preset slightly abnormal range (i.e., between the preset lower limit and the normal temperature range), it is determined to be a moderate warning. The system automatically pushes a prompt indicating abnormal inlet water temperature and records temperature fluctuation data, reminding staff to strengthen inspections and regularly observe the water condition. When the inlet water temperature exceeds the normal temperature range and reaches the severe abnormality standard, it is determined to be a severe warning. The system simultaneously pushes a detailed analysis of the cause of the abnormality and emergency response suggestions, guiding staff to intervene and investigate. At the same time, the abnormal temperature condition is marked in real time, completing the accurate identification of the abnormal state. Furthermore, the system compares and analyzes the deviation between temperature monitoring data and preset thresholds in real time, using a linear regression algorithm to dynamically correct temperature parameters and ensure the accuracy of the monitoring data. Simultaneously, it synchronizes temperature anomaly-related data to the digital twin model, marking abnormal conditions and updating parameters. Combined with machine learning algorithms, it dynamically optimizes temperature warning thresholds, enabling intelligent adjustment of warning levels. Through these operations, the system can accurately capture changes in influent temperature, promptly push corresponding treatment suggestions, and synchronously update temperature-related parameters in the digital twin model. This ensures a stable biochemical reaction environment, avoids process imbalances caused by temperature anomalies, and further improves the intelligent management and control level of wastewater treatment. It achieves closed-loop management of temperature monitoring, early warning, and process control, ensuring a normal growth environment for microorganisms while achieving precise control of temperature anomalies, effectively improving the efficiency and stability of wastewater treatment.

Claims

1. A method for intelligent monitoring of wastewater treatment processes based on digital twins, characterized in that, The method includes: S101, Construct a digital twin model of the entire wastewater treatment process. The digital twin model of the entire wastewater treatment process corresponds one-to-one with the physical entity of the actual wastewater treatment plant, and collects multi-source monitoring parameters of the wastewater treatment plant in real time. S102, standardize the multi-source monitoring parameters of the sewage treatment plant, input the processed multi-source monitoring parameters of the sewage treatment plant into the digital twin model of the entire sewage treatment process, perform error compensation and dynamic correction, so that the operating status of the digital twin model of the entire sewage treatment process keeps synchronized with the operating status of the actual sewage treatment plant. S103 monitors the operating status parameters of each treatment unit in the wastewater treatment plant in real time, sets different levels of early warning thresholds, automatically triggers the corresponding level of early warning signal, and pushes the specific fault location, abnormal cause and handling suggestions. S104 automatically generates the optimal process control scheme based on the simulation results of multi-source monitoring parameters of the sewage treatment plant and the digital twin model of the entire sewage treatment process. This includes adjusting the aeration intensity and the return ratio. The control commands are sent to the actual sewage treatment equipment in real time, realizing the automatic and precise control of process parameters.

2. The intelligent monitoring method for wastewater treatment processes based on digital twins as described in claim 1, characterized in that, The specific process for error compensation is as follows: Real-time influent flow rate data at the inlet of the wastewater treatment plant is collected. The instantaneous influent flow rate data is compared with the influent flow rate benchmark value to obtain the flow deviation rate. The flow deviation rate is used to represent the ratio of the absolute value of the difference between the instantaneous influent flow rate data and the influent flow rate benchmark value to the influent flow rate benchmark value. Based on the calculated flow deviation rate, the hydraulic retention time threshold of each treatment unit is dynamically adjusted, specifically as follows: A pre-constructed mapping matrix of flow deviation rate and duration threshold adjustment factor is used to characterize the one-to-one correspondence between flow deviation rate and duration threshold adjustment factor; If the flow deviation rate is less than or equal to the lower limit of the flow deviation reference, the current flow deviation rate is input into the flow deviation rate-duration threshold adjustment factor mapping matrix, and the duration threshold adjustment factor is output. The duration threshold reference value and the duration threshold adjustment factor are multiplied to obtain the target hydraulic residence time threshold. If the flow deviation rate is within the flow deviation reference interval, the current flow deviation rate is input into the flow deviation rate-duration threshold adjustment factor mapping matrix, and the duration threshold adjustment factor is output. The duration threshold benchmark value and the duration threshold adjustment factor are multiplied to obtain the target hydraulic residence time threshold. The flow deviation reference interval represents the open interval formed by the lower limit of the flow deviation reference and the upper limit of the flow deviation reference. If the flow deviation rate is greater than or equal to the upper limit of the flow deviation reference, an early warning signal will be triggered, prompting staff to check the water intake conditions.

3. The intelligent monitoring method for wastewater treatment processes based on digital twins as described in claim 1, characterized in that, The specific process of the dynamic correction is as follows: By deploying equipment operation sensors on the water pumps of each sewage treatment unit, the actual operating frequency data of the water pumps is collected in real time. The actual operating frequency data of the water pumps is compared with the standard value of the operating frequency to obtain the frequency deviation value and frequency deviation rate. The frequency deviation value represents the degree of deviation between the actual operating frequency data of the water pump and the standard operating frequency value, and the frequency deviation rate represents the result of the analysis of the ratio of the frequency deviation value to the standard operating frequency value. If the frequency deviation rate is less than or equal to the lower limit of the frequency deviation rate reference, the valve opening is increased proportionally based on the absolute value of the frequency deviation rate. The increased valve opening is then compared with the upper limit of the valve opening reference. If the increased valve opening is less than or equal to the upper limit of the valve opening reference, the increased valve opening is used as the target valve opening to ensure that the pipeline flow rate matches the pump output.

4. The intelligent monitoring method for wastewater treatment processes based on digital twins as described in claim 3, characterized in that, The dynamic correction also includes: If the frequency deviation rate is within the frequency deviation rate reference range, the valve opening is reduced proportionally based on the frequency deviation rate. The reduced valve opening is compared with the lower limit of the valve opening reference. If the reduced valve opening is greater than or equal to the lower limit of the valve opening reference, the reduced valve opening is used as the target valve opening to avoid excessive pipeline pressure that could damage the equipment. The frequency deviation rate reference range refers to the opening range formed by the lower limit of the frequency deviation rate reference and the upper limit of the frequency deviation rate reference. If the frequency deviation rate is greater than or equal to the upper limit of the frequency deviation rate reference, the emergency adjustment mode of valve opening will be activated, triggering the equipment operation early warning signal and prompting the staff to check the pump operation status and pipeline condition. The dynamically adjusted valve opening command is sent to the corresponding valve's actuator in real time to control the valve to complete the opening adjustment, and the adjusted valve opening data is fed back to the digital twin model of the entire wastewater treatment process.

5. The intelligent monitoring method for wastewater treatment processes based on digital twins as described in claim 1, characterized in that, The specific process for automatically triggering the corresponding level of warning signal is as follows: Real-time collection of influent water temperature parameters at the influent end of the sewage treatment plant, division of multiple influent water temperature threshold ranges, and corresponding matching of Level 1 mild warning, Level 2 moderate warning, and Level 3 severe warning; The influent water temperature parameters are compared and judged in real time with the preset temperature threshold range, specifically as follows: If the influent water temperature parameter is less than or equal to the preset temperature threshold reference lower limit, it is determined to be a Level 1 mild warning, and the monitoring status is maintained without any warning prompts. If the influent water temperature parameter is within the preset temperature threshold range, it is determined to be a level 2 moderate warning, and the cause of the slight abnormality in the influent water temperature is pushed, as well as basic handling suggestions for continuous monitoring and regular inspection. The preset temperature threshold range refers to the open interval formed by the preset temperature threshold reference lower limit and the preset temperature threshold reference upper limit. If the influent water temperature parameter is greater than or equal to the preset temperature threshold reference upper limit, it is judged as a level three severe warning. At the same time, the abnormal cause of the severe over-standard influent water temperature is pushed out, as well as emergency handling suggestions for limiting the influent load and on-site personnel intervention to investigate. Early warning information at different levels, the causes of anomalies, and corresponding handling suggestions are simultaneously uploaded to the digital twin model of the entire wastewater treatment process to complete the real-time marking of abnormal temperature conditions.

6. The intelligent monitoring method for wastewater treatment processes based on digital twins as described in claim 1, characterized in that, The specific procedure for adjusting the aeration intensity is as follows: Real-time data on the operating frequency of aeration blowers and aeration units in the biological treatment tank is collected. After standardization, the operating frequency data of aeration blowers and aeration units is input into the digital twin model of the entire wastewater treatment process. A pre-constructed correlation mapping relationship between the operating frequency and aeration intensity of the aeration equipment is used to characterize the quantitative correspondence between the gain and reduction of the air delivery volume corresponding to different actual operating frequencies of the aeration equipment, thereby realizing the dynamic adaptive adjustment of the aeration intensity. The actual operating frequency of the aeration equipment, collected in real time, is compared and analyzed with the preset rated operating frequency range to determine the current frequency deviation from the range. Specifically: If the actual operating frequency of the aeration equipment is lower than the preset rated operating frequency lower limit, it is determined that the current air supply capacity is insufficient. The current actual operating frequency of the aeration equipment is input into the correlation mapping relationship between the operating frequency of the aeration equipment and the aeration intensity, and the output air delivery gain is output. The air delivery benchmark value and the air delivery gain are coupled to obtain the target air delivery, so as to improve the aeration intensity inside the biological tank and make up for the oxygen supply gap.

7. The intelligent monitoring method for wastewater treatment processes based on digital twins as described in claim 6, characterized in that, The aeration intensity adjustment also includes: If the actual operating frequency of the aeration equipment is within the preset rated operating frequency range, the current aeration intensity will be maintained at a constant output to ensure the stable progress of the oxygen biochemical reaction. The preset rated operating frequency range refers to the open interval formed by the lower limit of the preset rated operating frequency and the upper limit of the preset rated operating frequency. If the actual operating frequency of the aeration equipment is higher than the upper limit of the preset rated operating frequency, it is determined that the current aeration output is excessive. The current actual operating frequency of the aeration equipment is input into the correlation mapping relationship between the operating frequency of the aeration equipment and the aeration intensity, and the reduction in the output air delivery volume is output. The difference between the baseline value of the output air delivery volume and the reduction in the output air delivery volume is processed to obtain the target output air delivery volume, so as to weaken the aeration intensity and prevent energy waste and process imbalance caused by over-aeration.

8. The intelligent monitoring method for wastewater treatment processes based on digital twins as described in claim 1, characterized in that, The specific process for adjusting the reflux ratio is as follows: Pressure sensors deployed in the return pipeline collect the actual effective pressure of the return pipeline in real time. The return pipeline includes an internal return pipeline, an external return pipeline, and a sludge return pipeline. The actual effective pressure of the return pipeline is compared with the preset management pressure reference range to obtain the pressure deviation value and the pressure deviation rate. The pressure deviation value represents the degree of deviation between the actual effective pressure of the return pipeline and the lower limit of the preset management pressure reference, and the pressure deviation rate represents the proportion between the pressure deviation value and the lower limit of the preset management pressure reference. If the actual effective pressure of the return pipeline is less than or equal to the preset lower limit of the management pressure benchmark, it is determined that there is insufficient flow in the pipeline. Based on the absolute value of the pressure deviation rate, the return ratio threshold of the corresponding return pipeline is increased proportionally. It is then determined whether the adjusted return ratio threshold is less than or equal to the upper limit of the return ratio threshold reference. If so, the adjusted return ratio threshold is used as the target return ratio threshold. If not, the upper limit of the return ratio threshold reference is used as the target return ratio threshold.

9. The intelligent monitoring method for wastewater treatment processes based on digital twins as described in claim 8, characterized in that, The reflux ratio adjustment also includes: If the actual effective pressure of the return pipeline is within the preset management pressure reference range, the pipeline flow status is judged to be normal, and the current return ratio threshold is maintained. The preset management pressure reference range refers to the open interval formed by the lower limit of the preset management pressure reference and the upper limit of the preset management pressure reference. If the actual effective pressure of the return pipeline is greater than or equal to the upper limit of the preset management pressure benchmark, it is determined that there is a blockage in the pipeline. Based on the pressure deviation rate, the return ratio threshold of the corresponding return pipeline is reduced accordingly. It is then determined whether the adjusted return ratio threshold is greater than or equal to the lower limit of the return ratio threshold reference. If so, the adjusted return ratio threshold is used as the target return ratio threshold. If not, the lower limit of the return ratio threshold reference is used as the target return ratio threshold.

10. A digital twin-based intelligent monitoring system for wastewater treatment processes, wherein the digital twin-based intelligent monitoring system for wastewater treatment processes is used to implement the digital twin-based intelligent monitoring method for wastewater treatment processes as described in any one of claims 1-9, characterized in that, The system includes: a digital twin model construction and multi-source parameter acquisition module, a multi-source parameter processing and model dynamic correction module, an operation status monitoring and hierarchical early warning module, and an optimal process control scheme generation and execution module; The digital twin model construction and multi-source parameter acquisition module is used to construct a digital twin model of the entire wastewater treatment process. The digital twin model of the entire wastewater treatment process corresponds one-to-one with the physical entity of the actual wastewater treatment plant and collects multi-source monitoring parameters of the wastewater treatment plant in real time. The multi-source parameter processing and model dynamic correction module is used to standardize the multi-source monitoring parameters of the sewage treatment plant, and input the processed multi-source monitoring parameters of the sewage treatment plant into the digital twin model of the entire sewage treatment process for error compensation and dynamic correction, so that the operating status of the digital twin model of the entire sewage treatment process keeps synchronized with the operating status of the actual sewage treatment plant. The operation status monitoring and hierarchical early warning module is used to monitor the operation status parameters of each treatment unit of the sewage treatment plant in real time, set early warning thresholds of different levels, automatically trigger early warning signals of the corresponding level, and push specific fault locations, abnormal causes and handling suggestions. The optimal process control scheme generation and execution module is used to automatically generate the optimal process control scheme based on the simulation results of the multi-source monitoring parameters of the sewage treatment plant and the digital twin model of the entire sewage treatment process. This includes adjusting the aeration intensity and the reflux ratio. The control commands are sent to the actual sewage treatment equipment in real time to achieve automatic and precise control of process parameters.

Images